Knowledge generation assistance device, knowledge generation assistance method, and knowledge generation assistance program

Abstract

The purpose of the present invention is to assist confirmation work required to generate knowledge from text data.　A knowledge generation assistance device 1100 for assisting generation of knowledge related to business comprises: a storage unit 17 for storing information related to a plurality of confirmers of knowledge; an input unit 12 for receiving text data related to the business; a text mining unit 142 for analyzing the text data; a graph 144 generation unit for generating a graph, which is one example of the knowledge, on the basis of the result of the analysis of the text mining unit 142; and a confirmer identification unit 147 for identifying a confirmer of the generated knowledge on the basis of the analyzed text data and the stored information related to the confirmer of the knowledge.

Description

Knowledge creation support device, knowledge creation support method, and knowledge creation support program

[0001] The present invention relates to knowledge generation in information processing, and in particular to a technique for supporting knowledge generation using text mining.

[0002] Recent trends in IT (Information Technology) include the spread of cloud environments that allow for the inexpensive storage of large amounts of data, improvements in computer processing performance, and improvements in data processing technologies such as AI (Artificial Intelligence). With regard to data processing technologies, natural language processing technology, especially generative AI, has recently been rapidly developing and becoming widespread.

[0003] The momentum for data utilization among medium-sized companies is growing more than ever, and data utilization is also advancing in various areas of the manufacturing industry. In response to this trend, as mentioned above, with the development and widespread adoption of natural language processing technology in recent years, there has been a trend toward analyzing and utilizing unstructured data, such as free text in documents. This trend can be seen, for example, in quality assurance and related tasks, where there are attempts to analyze quality information such as product defect reports to extract knowledge and provide feedback to processes such as design, manufacturing, and maintenance. In this specification, feedback refers to the transmission of defect and countermeasure information to product design, process design, etc., with the aim of preventing the defect from recurring.

[0004] Regarding the analysis of data containing free text, a method for extracting knowledge using text mining technology has been devised. In Patent Document 1, text mining is used to mechanically extract information from written reports of product failures. In addition, a dictionary is used to extract fault events so that the method can be used to deal with text in which general semantic information alone cannot sufficiently narrow down the causative component.

[0005] Regarding feedback of extracted knowledge, a method has been devised in which keywords are automatically extracted from the document the user is creating, as in Patent Document 2, and then the method compares the keywords with a list of issues that lists issues and their related words to find issues for each design situation, and then classifies and displays information according to the issues.

[0006] When analyzing quality information such as defect reports to generate knowledge and provide feedback to processes such as design, manufacturing, and maintenance in actual business operations, the following problems can arise. Note that while the following explanation focuses on defect reports as a specific example of quality information, the present invention can also be applied to quality information other than product defects, such as violations of laws and regulations.

[0007] A defect report contains information such as the target product, target part, report author, and defect details. While the target product, target part, and report author may be structured data, the defect details, such as the defect events and their causal relationships, are generally unstructured data written in free text format. Users read the information from the unstructured free text and then concisely combine the target product, target part, defect events, and their causal relationships to create knowledge. Simply extracting knowledge from a single report is expected to incur a burden, and if there are multiple reports of the same defect, the burden will be compounded. Furthermore, it is conceivable that the same defect may be reported multiple times. Users must read and interpret each defect report individually to determine whether they are identical, and aggregating identical defects also incurs a burden. In this invention, an identical defect refers to a defect that has the same target product, target part, defect events, defect causal relationships, the process causing the defect, and the tasks in the process causing the defect.

[0008] JP 2023-163427 A JP 2011-108067 A

[0009] Patent Document 1 discloses a causal component identification device and a technology that uses the device to support the identification of the causal component, and Patent Document 1 can support the generation and utilization of knowledge. However, Patent Document 1 requires a person to manually confirm the accuracy of the extracted knowledge. Furthermore, when confirming the accuracy, it is necessary to identify an appropriate person to confirm and request the person to confirm, but if for some reason the creator or other information cannot be read from the defect report, it is necessary to identify the person to confirm by another method. These tasks are also thought to be burdensome, but Patent Document 1 does not address them.

[0010] Patent Document 2 discloses a technology that supports feedback of quality information through the distribution of knowledge. However, Patent Document 2 does not address identifying a person who will verify the generated knowledge. Therefore, the present invention aims to support the generation of knowledge from text data, and in particular, to support the work of verifying knowledge.

[0011] To this end, the present invention identifies reviewers of knowledge and / or the text data used to generate that knowledge.

[0012] More specifically, the knowledge generation support device supports the generation of business-related knowledge and includes: a memory unit that stores information about multiple knowledge reviewers; an input unit that accepts text data about the business; a text mining unit that analyzes the text data; a knowledge generation unit that generates the knowledge based on the analysis results by the text mining unit; and a reviewer identification unit that identifies the reviewer of the generated knowledge based on the analyzed text data and the stored information about the reviewer of the knowledge.

[0013] Furthermore, the present invention also includes a knowledge creation support method executed by the knowledge creation support device, a knowledge creation support program for causing the knowledge creation support device to function as a computer, and a storage medium storing the same.

[0014] According to the present invention, it is possible to support the confirmation work when generating knowledge, and to support more efficient generation of knowledge.

[0015] 1 is a functional block diagram of a knowledge creation support system including a knowledge creation support device 1100 according to one embodiment of the present invention. FIG. 2 is a diagram illustrating the hardware configuration of the knowledge creation support device 1100 according to one embodiment of the present invention. FIG. 3 is a diagram illustrating text mining according to one embodiment of the present invention. FIG. 4 is a diagram illustrating knowledge basis generation according to one embodiment of the present invention. FIG. 5 is a diagram schematically illustrating a graph according to one embodiment of the present invention. FIG. 6 is a diagram illustrating an excerpt from a table of work record data in a product development project managed by a product development project management system 1800 according to one embodiment of the present invention. FIG. 7 is a diagram illustrating a user dictionary 1470 according to one embodiment of the present invention. FIG. 8 is a diagram illustrating WF creation instruction data according to one embodiment of the present invention. FIG. 9 is a diagram illustrating the contents of a knowledge confirmation request email according to one embodiment of the present invention. FIG. 10 is a flowchart illustrating an overall flow from obtaining a defect report to storing a final version of knowledge according to one embodiment of the present invention. FIG. 11 is a flowchart illustrating an example of a processing flow including identification of a confirmer according to one embodiment of the present invention. FIG. 12 is a diagram illustrating a confirmation screen according to one embodiment of the present invention. FIG. 13 is a flowchart illustrating a case where confirmation processing is executed by serial processing according to one embodiment of the present invention. FIG. 14 is a flowchart illustrating a case where confirmation processing is executed by parallel processing according to one embodiment of the present invention.

[0016] An embodiment of the present invention will be described below with reference to the accompanying drawings. In this embodiment, a reviewer of knowledge and / or text data used to generate the knowledge is identified. Here, the knowledge in this embodiment refers to business-related knowledge, particularly knowledge related to product manufacturing.

[0017] The text data is data related to manufacturing, which is an example of a business, and includes reports (e.g., defect reports), specifications, design documents, etc. Note that the text data in this embodiment may include control codes other than character strings. Knowledge generation refers to identifying knowledge, and is a concept that also includes knowledge extraction. Furthermore, the checker is a person involved in the business, for example, manufacturing, and includes a designer, a quality assurance officer, a manufacturing worker, etc.

[0018] <Schematic Configuration of the Present Embodiment> A schematic configuration of the present embodiment will be described with reference to FIGS. 1A and 1B.

[0019] 1A is a functional block diagram of a knowledge creation support system including a knowledge creation support device 1100 (hereinafter, also referred to as the device 1100) according to this embodiment. The knowledge creation support device 1100 is connected to an input / output device 1600, a defect management system 1700, a product development project management system 1800, and a Workflow (WF) system 1900 via a network 1000 to form the knowledge creation support system. The device 1100 then executes processing to identify the reviewer of the knowledge and / or the text data used to generate the knowledge. To this end, the knowledge creation support device 1100 includes a communication unit 11, an input unit 12, an output unit 13, a knowledge generation processing unit 14, a knowledge reviewer information identification unit 146, a Workflow creation instruction unit 15, a knowledge distribution unit 16, and a storage unit 17.

[0020] First, the communication unit 11 connects to other devices and systems via the network 1000. The input unit 12 accepts operations from a user. Then, the communication unit 11 and the input unit 12 accept text data such as a defect report. The output unit 13 outputs, for example, displays, processing results of the knowledge creation support device 1100. The input unit 12 and the output unit 13 may be configured as an integrated unit, such as a touch panel. Furthermore, if the knowledge creation support device 1100 is realized as a server or the like, the input unit 12 and the output unit 13 can be omitted.

[0021] The knowledge generation processing unit 14 also executes processing for generating knowledge related to manufacturing operations based on text data. To this end, the knowledge generation processing unit 14 includes a quality information acquisition unit 141, a text mining unit 142, a mining basis generation unit 143, a graph generation unit 144, and an identical quality information aggregation unit 145.

[0022] The quality information acquisition unit 141 acquires defect report data stored in the defect management system 1700 via the communication device 1500. The text mining unit 142 analyzes the text data, i.e., executes text mining processing. As a result, the text mining unit 142 extracts knowledge grounds that can become knowledge. Note that this knowledge ground itself may be treated as knowledge.

[0023] Here, the text mining unit 142 analyzes, for example, a manufacturing defect report as text data, and extracts analysis items such as knowledge basis candidates from the data.

[0024] Furthermore, the mining basis generation unit 143 generates knowledge basis that serves as the basis for generating knowledge in accordance with the text mining process performed by the text mining unit 142. To this end, the mining basis generation unit 143 identifies partial text of the text data that is extracted as the knowledge basis. It is desirable that such knowledge basis be displayed on the output unit 13.

[0025] The graph generation unit 144 is an example of a knowledge generation unit that generates knowledge based on the analysis results of text data. The knowledge generation unit generates knowledge from the knowledge basis as the analysis result. The knowledge generation unit may use the knowledge basis itself as knowledge, or may generate knowledge from the knowledge basis. Here, the graph generation unit 144 generates a graph, which is a graph structure, as knowledge from the knowledge basis.

[0026] Furthermore, the identical quality information aggregating unit 145 aggregates related text data, such as identical text data, for multiple pieces of text data processed by the text mining unit 142. More preferably, the identical quality information aggregating unit 145 aggregates multiple pieces of knowledge based on related text data. Note that the aggregation of knowledge may be performed by a knowledge generating unit such as the graph generating unit 144.

[0027] In this embodiment, defect reports are used as text data. In this case, the identical quality information aggregating unit 145 determines whether there are defect reports about the same defect among multiple defect reports, and aggregates the identical reports into one knowledge.

[0028] Furthermore, the knowledge checker information identification unit 146 identifies the checker who checks the generated knowledge, or in the above example, the graph. At this time, it is desirable to also identify information about the checker. For this purpose, the knowledge checker information identification unit 146 has a checker identification unit 147 and a user ID matching unit 148.

[0029] First, the checker identification unit 147 identifies relevant parties in the work who could be checkers from the text data. In this embodiment, a defect report is used as the text data. To this end, the checker identification unit 147 identifies the work records in the development project for the product using the product, parts, target process, and tasks in the target process that are the subject of the defect report as keys, and identifies the person in charge. Furthermore, the user ID matching unit 148 uses a user dictionary 1470 that indicates information about the checker to identify the user ID that identifies the identified person in charge.

[0030] Furthermore, the WF creation instruction unit 15 creates WF creation instruction data for creating a workflow for having the checker identified by the checker identification unit 147 check the knowledge. Furthermore, the knowledge distribution unit 16 distributes knowledge such as a graph generated by the graph generation unit 144 to persons involved in the work via the communication unit 11. Preferably, the knowledge distribution unit 16 distributes the knowledge confirmed by the checker.

[0031] The storage unit 17 also stores a product configuration dictionary 1450, a project process / task dictionary 1460, a user dictionary 1470, and a database 1480. First, the product configuration dictionary 1450 indicates configuration data of a product to be manufactured. This is an example of data on the object of a business operation.

[0032] Furthermore, the project process / task dictionary 1460 indicates process data for a manufacturing project. This is an example of data related to procedures and steps in a business. Furthermore, the user dictionary 1470 is data such as the names and IDs of users, including checkers. As mentioned above, the user dictionary 1470 is an example of data related to checkers. Furthermore, the database 1480 indicates various data such as generated knowledge, knowledge grounds, and text data.

[0033] The input / output device 1600 includes a keyboard, a mouse, a display, etc., through which the user inputs data and displays the processing results, and can be realized by a computer such as a PC, a tablet, or other terminal device. Note that if the knowledge creation support device 1100 is provided with the input unit 12 and the output unit 13, the input / output device 1600 can be omitted.

[0034] Furthermore, the defect management system 1700 creates and stores defect reports, which are an example of text data. Furthermore, the product development project management system 1800 creates and stores work records for a product development project, which is an example of a business operation, and is the target of manufacturing. The WF system 1900 executes a workflow that allows a checker to check knowledge. This concludes the explanation of the functional blocks in this embodiment. Next, an implementation example for realizing each of these functions will be explained.

[0035] <Implementation Example (Hardware Configuration)> Fig. 1B is a diagram illustrating the hardware configuration of a knowledge creation support device 1100 according to this embodiment. The knowledge creation support device 1100 can be realized by a computer such as a cloud server. Therefore, in Fig. 1B, the knowledge creation support device 1100 includes a computing device 1200, a main memory device 1300, an auxiliary memory device 1400, and a communication device 1500, which are connected to each other via communication paths. The knowledge creation support device 1100 is connected via a network 1000 to a terminal device 1601, which is an example of an input / output device 1600, a defect management system 1700, a product development project management system 1800, and a WF system 1900.

[0036] First, the arithmetic unit 1200 can be realized by a processor such as a CPU, and executes calculations in accordance with a knowledge generation processing program 1410 and a knowledge checker information identification program 1420 stored in an auxiliary storage device 1400, which will be described later. These programs will be described later.

[0037] The communication device 22 corresponds to the communication unit 205 in FIG. 7, and is connected to the network 40 to communicate with other devices.

[0038] 1A . The main memory device 1300 and the auxiliary memory device 1400 deploy the knowledge generation processing program 1410 and the knowledge checker information identification program 1420 stored in the auxiliary memory device 1400, as well as information used for processing by the arithmetic unit 1200. The auxiliary memory device 1400 can be realized as a so-called storage, and stores the knowledge generation processing program 1410, the knowledge checker information identification program 1420, the WF creation instruction program 1430, the knowledge distribution program 1440, the product configuration dictionary 1450, the project process / task dictionary 1460, the user dictionary 1470, and the database 1480.

[0039] In addition, the auxiliary storage device 1400 may be realized by various storage media such as an external HDD (Hard Disk Drive), SSD (Solid State Drive), or memory card, or may be realized as a device separate from the knowledge creation support device 1100, such as a file server.

[0040] Here, the knowledge generation processing program 1410 is composed of a quality information acquisition subprogram 1411, a text mining subprogram 1412, a mining basis generation subprogram 1413, a graph generation subprogram 1414, and an identical quality information aggregation subprogram 1415. Also, the knowledge checker information identification program 1420 is composed of a checker identification subprogram 1421 and a user ID matching subprogram 1422.

[0041] Each of the above subprograms may be realized as an individual program or a partial combination, or may be configured as a so-called module.

[0042] 1A, which executes the same functions as each program or submodule, is as follows: Knowledge generation processing program 1410: knowledge generation processing unit 14 Quality information acquisition subprogram 1411: quality information acquisition unit 141 Text mining subprogram 1412: text mining unit 142 Mining basis generation subprogram 1413: mining basis generation unit 143 Graph generation subprogram 1414: graph generation unit 144 Identical quality information aggregation subprogram 1415: Identical quality information aggregation unit 145 Knowledge checker information identification program 1420: knowledge checker information identification unit 146 Checker identification subprogram 1421: checker identification unit 147 User ID matching subprogram 1422: user ID matching unit 148 WF creation instruction program 1430: WF creation instruction unit 15 Knowledge distribution program 1440: knowledge distribution unit 16 Therefore, the computing device 1200 executes the processing of the knowledge generation processing unit 14, the knowledge confirmer information identification unit 146, the WF creation instruction unit 15, the knowledge distribution unit 16, and each of the units that constitute these, in accordance with the knowledge generation processing program 1410, the knowledge confirmer information identification program 1420, the WF creation instruction program 1430, the knowledge distribution program 1440, and the subprograms that constitute these.

[0043] <Function Details> Next, the functions of each program and subprogram in this embodiment will be described in detail. These functions are realized in the arithmetic device 1200 by each program and its constituent subprograms. Each function is executed by the above-mentioned programs and subprograms and the units shown in FIG. 1A.

[0044] First, the knowledge generation processing program 1410 executes processing for analyzing quality information and generating information such as events and causes as knowledge. This processing for generating knowledge includes the generation of knowledge itself. The knowledge confirmer information identification program 1420 identifies the confirmer of the created knowledge. The WF creation instruction program 1430 creates creation instruction data for a knowledge confirmation WF based on the identified confirmer. The knowledge distribution program 1440 distributes the confirmed knowledge to the user. Next, the knowledge generation processing program 1410 analyzes the defect report as text data and generates knowledge. At this time, the knowledge generation processing program 1410 identifies the knowledge basis, which is the basis for generating the knowledge. Here, the subprograms that make up the knowledge generation processing program 1410 will be described.

[0045] First, the quality information acquisition subprogram 1411 acquires a defect report from the defect management system 1700, which is an external system. The defect report may also be acquired from the terminal device 1601 or the product development project management system 1800. The quality information acquisition subprogram 1411 may also acquire quality information on the quality of the product, such as specifications other than the defect report, as text data.

[0046] The acquired defect report is analyzed, that is, text mined, by the text mining subprogram 1412. Here, the acquired defect report is text mined by the text mining subprogram 1412, and the target product, target part, defect phenomenon, defect causal relationship, cause of the defect, task in the cause of the defect, affiliation of the person who checked the knowledge, and name of the person who checked the knowledge are extracted as analysis items.

[0047] Here, text mining will be explained using FIG. 2. In FIG. 2, the extracted analysis items are indicated by bold lines in a defect report, which is an example of text data. Specifically, the signature field 2100 in FIG. 2 is extracted as a candidate checker. This signature field 2100 reveals the affiliation and name of the creator, checker, and approver of the defect report. These people are appropriate checkers of the correctness of the knowledge. When a defect report has a signature field like this, it is easy to identify the checker of the knowledge. Cases where the checker cannot be identified from the defect report due to reasons such as the absence of a signature field will be explained later. Note that analysis items are items (words, etc.) extracted from text data by text mining, and include knowledge basis candidates and checker candidates.

[0048] Next, regarding the content of the status column, "In the fuel piping of the fuel hose / pipe (model number: P-aaaa)" 2200 and "excessive load" 2500 are written in one sentence, and the following sentence states, "As a result, if continued use is carried out, the piping in question will break and fuel will leak" 2600. From this, it can be seen that the "fuel hose / pipe (model number: P-aaaa)" is the target part, and "excessive load" and "the piping in question will break and fuel will leak" are malfunction events. In other words, these can be extracted as knowledge basis candidates by text mining.

[0049] Additionally, "inappropriate structure" 2300 and "excessive load" 2500 are connected by the expression "because" 2400. From this, it can be seen that "inappropriate structure" is the cause and "excessive load" is the effect. Furthermore, it can be inferred that "Therefore, if continued use is as is, the pipe in question may break and fuel may leak" 2600 is a continuation of "excessive load" 2500. Therefore, it can be seen that there is a causal relationship with "inappropriate structure." And from the statement "The vehicle model equipped with this device is BBBB (model number: I-bbbb)" 2700, it can be seen that this is the affected product. Furthermore, from the statement "inappropriate structure" 2300, it can be inferred that the causal process is design, and the task within that process is structural design. As a result, the above statements are extracted as candidate knowledge grounds using text mining.

[0050] As a mechanism for improving the accuracy of text mining, the following dictionaries, items 1 to 4, can be mentioned: (item 1) Preparing a dictionary of defect events (item 2) Preparing a dictionary of causal relationships (item 3) Preparing a dictionary for identifying relationships between products and parts (item 4) Preparing a dictionary for identifying processes and tasks Each of these dictionaries can be stored in the memory unit 17, and it is desirable to store at least one of them.

[0051] Furthermore, while items 1 and 2 above can be expressed using general terms, items 3 and 4 are likely to have wording and structures specific to each customer or product. Therefore, one way to improve the accuracy of text mining is to use the product configuration dictionary 1450 and project process / task dictionary 1460 in Figure 1 as dictionaries.

[0052] Furthermore, the mining basis generation subprogram 1413 generates analysis items that serve as the basis for extraction from the text data that has been subjected to text mining.

[0053] Furthermore, the graph generation subprogram 1414 creates a graph from the knowledge candidates extracted by text mining as an example of knowledge, which is structured data. The graph created by the graph generation subprogram 1414 is then stored in the database 1480 of the storage unit 17.

[0054] Furthermore, when multiple defect reports are text-mined as related knowledge, the same quality information aggregation subprogram 1415 aggregates the related knowledge into one piece of knowledge for the same defect. Note that the number of aggregated pieces is not limited to one, as long as it is less than the number before aggregation.

[0055] Furthermore, the quality information acquisition subprogram 1411 acquires the data of the defect report stored in the defect management system 1700 via the communication unit 11 .

[0056] Furthermore, the above-mentioned knowledge basis is generated by the mining basis generation subprogram 1413. Details of this will be explained below with reference to FIG. 3. FIG. 3 is a diagram for explaining the generation of knowledge basis in this embodiment. Expressions extracted from the defect report as analysis items that are knowledge candidates or confirmer candidates are highlighted in FIG. 3.

[0057] Here, text mining is performed by the text mining unit 142 (text mining subprogram 1412), but the accuracy cannot be guaranteed. It is desirable for the user to check the accuracy of the text mining results, and it is considered that when checking the accuracy, the user may read the report of the original data.

[0058] However, it is thought that it would be a burden for users to read through all of the long text to confirm the knowledge. However, by referring to the knowledge basis, users can easily see where the knowledge is written, such as the target product, target part, defect phenomenon, defect causal relationship, defect cause process, and task in the defect cause process. Then, by reading the defect report focusing on the context of these, it is possible to efficiently confirm the knowledge basis.

[0059] Therefore, in this embodiment, the mining basis generation subprogram 1413 generates a knowledge basis generation screen as shown in Fig. 3 and causes this to be displayed on the terminal device 1601. In other words, the mining basis generation unit 143 generates a knowledge basis generation screen and causes this to be displayed on the output unit 13 and / or on the input / output device 1600 via the communication unit 11.

[0060] In Figure 3, the highlights are expressed in grayscale, but at the time of implementation, classifications such as product and target part names, defects, etc. may be established and highlight colors may be set for each classification. In this case, it is believed that the knowledge basis can be more easily visualized.

[0061] Furthermore, the graph generation subprogram 1414 structures the extracted knowledge candidates to generate a graph, which is an example of knowledge. The graph generation subprogram 1414 then stores this in the database 1480. Here, the structure of graph data will be explained using FIG. 4. FIG. 4 is a diagram schematically showing a graph in this embodiment. In this embodiment, knowledge is handled as graph-structured data. Here, the graph structure is made up of nodes that store data such as objects and events, and edges that define the relationships between the nodes.

[0062] In addition, in Figure 4, the relationship details are written near the edges. That is, in Figure 4, nodes are represented by ellipses and edges by solid lines. The target product, target part, defect event, defect causal process, and task in the defect causal process are nodes. Meanwhile, the relationship between products and parts and the causal relationship of defects are edges. In this way, the generated knowledge can be used not only for feedback to processes such as design, manufacturing, and maintenance, but also for users to confirm the accuracy of the knowledge. For example, while knowledge stored in a relational database is displayed in a table format, a graph illustrates relationships such as the relationship between products and parts and the causal relationship of defects. This allows users to intuitively understand the causal relationship of defects. Therefore, in this embodiment, it is desirable for the graph generation subprogram 1414 to display the graph shown in Figure 4 on the terminal device 1601. In other words, the graph generation unit 144 displays the graph on the input / output device 1600 via the output unit 13 and / or the communication unit 11.

[0063] Here, this graph is created through the execution of code. In this embodiment, it is assumed that the graph generation subprogram 1414 is implemented by a generation AI, thereby eliminating the burden of the user having to manually write code. Furthermore, by employing a generation AI instead of a conventional AI, it is possible to generate graphs without detailed engineering according to the graph pattern. This also reduces the burden of graph generation. However, the extracted knowledge candidates and graphs, which are examples of generated knowledge, are not necessarily correct. For this reason, human confirmation, such as by a user, is desirable. In particular, there is a risk of hallucination occurring in the output of the generation AI, making human confirmation all the more important.

[0064] In this embodiment, it is assumed that the quality information acquisition subprogram 1411 can acquire multiple defect reports in one process, and in this case, multiple pieces of knowledge are also generated at once. It is conceivable that multiple defect reports with the same content will be acquired and knowledge extracted, and the processing in this case will be explained later.

[0065] Furthermore, when the text mining subprogram 1412 performs text mining on multiple defect reports in a single process, if defect reports for the same defect exist, the same quality information aggregation subprogram 1415 aggregates these into one knowledge. To this end, the same quality information aggregation subprogram 1415 determines whether defect reports for the same defect exist. At this time, in addition to the same defect, related defects (defects in the same location or defects of the same type) may also be aggregated.

[0066] Here, the aggregation process in the identical quality information aggregation subprogram 1415 will be explained using Figure 4. As mentioned above, Figure 4 shows a graph that is an example of knowledge generated by the graph generation subprogram 1414. Here, we will take as an example a case where there are two defect reports, defect report 1 and defect report 2, and the defect is the same. First, the "Defect Report 1" node 4100 and the "Defect Report 2" node 4200 are both connected to the "Fuel Hose / Pipe" node. Similarly, they are also connected to the "Damaged, Fuel Leak" node. By using this graph structure, the identical quality information aggregation subprogram 1415 can aggregate multiple identical defect reports into a single piece of knowledge.

[0067] It is believed that among the defect reports held by a company, there are multiple identical cases. If knowledge is generated for each of the same defect, multiple copies of the same knowledge will be created, which makes it difficult for users to check and utilize the knowledge. Therefore, by consolidating the knowledge into one knowledge as in this embodiment, the burden of checking on the user can be reduced.

[0068] Furthermore, an appropriate checker for the generated graph is identified by the knowledge checker information identification program 1420. To this end, the knowledge checker information identification program 1420 has the following subprograms.

[0069] First, the checker identification subprogram 1421 identifies the work record in the development project of the product in question using the product, part, target process, and task in the target process that are the subject of the defect report as keys, and identifies the person in charge. Then, the user ID matching subprogram 1422 matches the identified user name with a user dictionary, and uniquely identifies the user ID.

[0070] As mentioned above, the user must verify the accuracy of the knowledge generated by the AI-based knowledge generation processing program 1410. When the knowledge generation processing program 1410 performs text mining on defect reports, it can also mine the names of reviewers from signature fields, etc. However, if the names of the reviewers are not listed in the defect report, the reviewers must be identified by other means, which places a burden on the user. In this case, the use of the reviewer identification subprogram 1421 can reduce the workload.

[0071] Next, the details of each of these subprograms will be described. The checker identification subprogram 1421 identifies work records for the product development project from the product development project management system 1800 using the product, part, target process, and tasks in the target process that have been text mined by the knowledge generation processing program 1410 as keys. The checker identification subprogram 1421 then identifies the designer and quality assurance personnel. Here, the data structure of work records for a product development project and the search logic for work records for the product will be described using FIG. 5 . FIG. 5 shows an excerpt from a table of work record data for a product development project managed by the product development project management system 1800 in this embodiment. In FIG. 5 , the work record data is assumed to be composed of columns such as a product ID column 5100, a product name column 5200, a part ID column 5300, a part name column 5400, a process name column 5500, a task name column 5600, a designer column 5700, and a quality assurance personnel column 5800. Therefore, the checker identification subprogram 1421 can search the work records using the above-mentioned data (task) as a key to identify the target work record. Then, the checker identification subprogram 1421 can identify the person who checked the knowledge by referencing the data stored in the design engineer column 5700 and the quality assurance engineer column 5800 in the identified work record.

[0072] Furthermore, the user ID matching subprogram 1422 matches the checker name identified by the checker identification subprogram 1421 with the user dictionary 1470 to uniquely identify the checker's user ID. Here, the identification of the user ID will be described with reference to FIG. 6 . FIG. 6 is a diagram showing the user dictionary 1470 in this embodiment. In FIG. 6 , the user dictionary 1470 is assumed to be composed of columns such as a user ID column 6100, a name column 6200, and an affiliation column 6300. The checker identification subprogram 1421 searches the user dictionary 1470 using the identified checker name as a key and references the data stored in the user ID column 6100, thereby uniquely identifying the checker of the knowledge. Note that if there are multiple users with the same name, the checker identification subprogram 1421 performs a second search using affiliation information as a key to narrow down the user IDs. This reduces the search burden on the user when the checker of the knowledge cannot be easily identified.

[0073] Furthermore, the WF creation instruction program 1430 creates WF creation instruction data for knowledge confirmation and transmits it to the WF system 1900 via the communication device 1500. The contents of the WF creation instruction data will now be described with reference to FIG. 7 . FIG. 7 is a diagram illustrating an excerpt from a table of the WF creation instruction data in this embodiment. In FIG. 7 , the WF creation instruction data is assumed to be composed of columns such as an email subject column 7100, a defect report name column 7200, a checker 1_ID column 7300, a checker 2_ID column 7400, a link column 7500 to the target defect report, a link column 7600 to knowledge, a link column 7700 to knowledge basis, and a confirmation request email body 7800. The email subject column 7100 stores data output by the generation AI as the subject of the confirmation WF based on the defect report name. The defect report name column 7200 stores the defect report name, which is the name of the defect report, which is text data mined by the knowledge generation processing program 1410. The checker 1_ID column 7300 and the checker 2_ID column 7400 store user ID data identified by the knowledge generation processing program 1410 or the knowledge checker information identification program 1420, respectively. Note that while Figure 7 illustrates an example of two checkers, the number may be other (e.g., three or more). The confirmation request email body 7800 stores the knowledge confirmation request email body generated by the generation AI. Note that in Figure 7, the WF creation instruction data is described in table format, but the data structure may be determined during implementation to match the specifications of the destination WF system.

[0074] The contents of the knowledge confirmation request email will be explained below with reference to Figure 8. In Figure 8, the body of the knowledge confirmation request email is assumed to consist of items such as a request 8100, a link to the defect report 8200, a link to the knowledge 8300, and a link to the knowledge basis 8400. By having a generation AI generate the email body, it is possible to reduce the burden of creating email bodies according to patterns such as the number of defect reports.

[0075] By using the WF creation instruction data and knowledge confirmation request email shown in Figures 7 and 8 above, it is possible to reduce the load of building a knowledge confirmation flow and starting the flow, and it is also possible to reduce the load of identifying reference information by using links to the extraction basis, etc.

[0076] Furthermore, the knowledge distribution program 1440 distributes the knowledge accumulated in the database 1480 via the communication device 1500 to the terminal device 1601 used by the user who is responsible for tasks such as product and part design, production line startup, and product maintenance. Here, the knowledge in this embodiment is stored as a graph, with the target product, target part, defect event, defect cause, defect occurrence process, and defect occurrence task being held as nodes. Meanwhile, the relationship between the product and part and the causal relationship of the defect are held as edges. When data such as the product, part, and process for which the user is responsible is input to the knowledge generation support device 1100 from the terminal device 1601 or the like, the knowledge extracted from the database 1480 is distributed to the terminal device 1601. This allows past knowledge to be checked without omission, and by using it like a checklist for one's own tasks, it is expected that recurrence of defects will be prevented.

[0077] As explained in the knowledge generation processing program 1410, the knowledge in this embodiment has a graph structure that illustrates relationships between products and parts, and the causal relationships of defects. This allows users to intuitively understand the causal relationships of defects from the delivered knowledge without having to devise a display format. It is also conceivable that users would like to check not only the structured knowledge but also the original defect report and the description that served as the basis for extracting the knowledge. In this case, the knowledge basis generated by the mining basis generation subprogram 1413 can be used as auxiliary information. In this case, the knowledge basis generated by the mining basis generation subprogram 1413 can be notified to the terminal device 1601 via the communication device 1500. This allows users to confirm the burden of searching for original information and the burden of searching for important information from the original information, thereby reducing these burdens.

[0078] This concludes the description of the configuration of this embodiment. The network 1000 of this embodiment shown in FIGS. 1A and 2B can utilize the following communications. It is possible to use a general public line network, whether wired or wireless, such as a fifth-generation mobile communication system (5G), which enables multiple simultaneous connections and ultra-low latency. Furthermore, by utilizing the features of new mobile phone systems beyond 5G, it is possible to distribute various data, including knowledge. Furthermore, even if the functions of the knowledge generation support device 1100 are distributed across the network 1000 or more, it is possible to minimize processing delays in the linkages between them.

[0079] The knowledge creation support system of this embodiment may be implemented as an in-house system, or may be implemented as a so-called cloud system that can be used by multiple organizations (e.g., companies). In the latter case, the input / output device 1600 (e.g., terminal device 1601) is used by each of the multiple organizations.

[0080] <Processing Flow> <Overall Flow> Next, the processing flow in this embodiment will be described. To this end, first, the overall flow from acquiring a defect report to storing the final version of knowledge in this embodiment will be described using Fig. 9. In this regard, the subject of each process will be described using the configuration in Fig. 1A.

[0081] First, the quality information acquisition unit 141 acquires text data of a defect report from the defect management system 1700 via the communication unit 11 (step S9100).

[0082] The text mining unit 142 then performs text mining on the acquired defect report to extract analysis items such as the name of the target product or component, the causal relationship of the defect, the process that caused the defect, the tasks in the process that caused the defect, the name of the quality assurance officer who reported the defect, and the name of the designer (step S9200). In other words, analysis items that are knowledge candidates or confirming personnel candidates are extracted. The mining basis generation unit 143 then generates mining basis for the defect report, which is text data mined based on the analysis items (step S9300). The mining basis here includes data highlighting the defect report (FIG. 3) and the highlighted portions themselves.

[0083] Furthermore, when multiple defect reports are text mined, the identical quality information aggregating unit 145 determines whether identical defect reports exist, and if so, aggregates them into a single knowledge (step S9400). Here, in step S9400, the identical quality information aggregating unit 145 aggregates, for example, defect reports with the same status and countermeasures but different defect report management numbers. Here, the identical defect (same defect) refers to a defect with the same or similar results in text mining. Similarity can be used to refer to a defect having a predetermined relationship. Furthermore, defect reports with the same device but different defect report management numbers may be aggregated.

[0084] Furthermore, the graph generating unit 144 structures the extracted knowledge candidates and generates a graph that is an example of knowledge (step S9500). Then, the graph generating unit 144 stores this graph in the storage unit 17.

[0085] Furthermore, the knowledge checker information identification unit 146 identifies a checker for the graph, which is the generated knowledge, and the WF creation instruction unit 15 creates WF creation instruction data (step S9600). Then, the WF creation instruction unit 15 notifies the WF system 1900 via the communication unit 11 of the WF creation instruction data including deployment to the identified checker. As a result, the WF system 1900 creates a WF for the checker to check the graph in accordance with the WF creation instruction data. As a result, a confirmation process for the graph (step S9700) is executed in accordance with the WF.

[0086] First, the WF is deployed to the terminal device 1601 of the relevant checker. In this case, the input / output device 1600 performs a confirmation process so that the user can check the graph (step S9701). That is, the input / output device 1600 displays a confirmation screen. This confirmation screen includes at least one of the graph (FIG. 4) that is the generated knowledge, the knowledge basis generation screen (FIG. 3), the defect report (FIG. 2), and the knowledge confirmation request email. As another display example, a display such as that shown in FIG. 11 may be used. In FIG. 11, the display screen 110 is composed of a defect report area 111 and a knowledge confirmation request email area 112.

[0087] These are shown in Figures 2 and 8, respectively, and may be displayed as follows. For example, both of these may be displayed from the beginning, or the knowledge confirmation request email area 112 may be displayed first. In the latter case, when the user specifies a link to a defect report in the knowledge confirmation request email area 112, the corresponding defect report is displayed in the defect report area 111. Note that when the defect report area 111 is displayed, the input / output device 1600 preferably also displays the corresponding graph. This graph may be displayed in response to a user instruction or automatically. As a result of the above, the user can confirm the generated knowledge and knowledge basis.

[0088] The input / output device 1600 also receives confirmation from the user regarding the graph using the confirmation screen in step S9701, and determines whether approval for the graph is possible (step S9702). If approval is possible (YES), the input / output device 1600 notifies the knowledge generation support device 1100 that city approval is possible, and the process proceeds to step S9800. If approval is not possible (NO), the process proceeds to step S9703.

[0089] Furthermore, if approval for the graph is not possible (NO in S9702), the input / output device 1600 executes a return process (step S9703). To this end, the input / output device 1600 transmits a message to the knowledge creation support device 1100 indicating that approval for the graph is not possible. Then, the process proceeds to one of steps S9200 and thereafter in the knowledge creation support device 1100. As a result, the knowledge creation support device 1100 executes one of steps S9200 by changing conditions such as parameters.

[0090] Furthermore, when the graph generation unit 144 of the knowledge creation support device 1100 receives through the communication unit 11 that approval of the graph is possible, the approved graph is stored in the storage unit 17 (step S9800).

[0091] If approval is possible, the input / output device 1600 may accept a manual instruction to modify the graph from the user. In this case, in step S9800, the input / output device 1600 transmits the modification instruction or a graph modified in accordance with the modification instruction to the knowledge generation support device 1100. In response to this, the graph generation unit 144 may update the graph.

[0092] As a result of the above, in step S9800, the knowledge that has been confirmed by the confirmer and the confirmation record are recorded in DB 1480 of knowledge generation support device 1100.

[0093] <Example of flow for identifying a confirmer> Next, an example of a processing flow including the identification of a confirmer in this embodiment will be described. That is, with reference to Fig. 10, a detailed flow will be described in which the knowledge generation support device 1100 identifies a confirmer of knowledge, creates a WF creation instruction, and the user confirms and finalizes the knowledge.

[0094] First, the text mining unit 142 determines whether the checker name has been identified (step S10100). If it has been identified (YES), the process proceeds to step S10400, and if it has not been identified (NO), the process proceeds to step S10200.

[0095] Furthermore, if the name of the checker has not been identified, the checker identification unit 147 identifies the work record in the development project of the product using the product, part, target process, and task in the target process that are the subject of the defect report as keys (step S10200).

[0096] The checker identification unit 147 then identifies the checker name from the work record for the identified development project (step S10300). The user ID matching unit 148 then searches the user dictionary 1470 using the identified checker name and affiliation as keys to uniquely identify the user ID for the checker name identified in step S10300 (step S10400). These steps S10100 to S10400 correspond to the identification of the checker by the knowledge checker information identification unit 146 in step S9600 in FIG. 9.

[0097] 9. The WF creation instruction unit 15 also creates WF creation instruction data for knowledge confirmation (step S10500). This step S10500 corresponds to the creation of WF creation instruction data by the WF creation instruction unit 15 in step S9600 of FIG.

[0098] Then, similarly to step S9600 in FIG. 9, the WF creation instruction unit 15 notifies the WF system 1900 of the WF creation instruction data via the communication unit 11.

[0099] Furthermore, the WF system 1900 creates a WF for the checker to check the graph in accordance with the WF creation instruction data (step S10700), and then the WF system 1900 deploys the created WF to the checker's input / output device 1600.

[0100] In response to this, the input / output device 1600 executes a knowledge confirmation process similar to step S9700 in Fig. 9 (step S10800). Note that the confirmation processes of steps S9700 and S10800 are processed by the WF system 1900 in response to user (checker) input to the input / output device 1600. However, in this application, these processes are described as processes performed by the input / output device 1600. The confirmation results are managed by the WF system 1900, which then transmits the user's confirmation results to the knowledge creation support device 1100 via the input / output device 1600 (step S10900). As a result, similar to step S9800 in Fig. 9, the knowledge that has been confirmed by the user and the confirmation record are recorded in the storage unit 17 by the knowledge creation support device 1100 (step S10600).

[0101] <Detailed Flow of Confirmation Processing> Next, two confirmation processes (steps S9700 and S10800) when multiple confirmers are identified will be described. First, as a first example, serial processing will be described. Fig. 12A is a flowchart of the confirmation processing in this embodiment when it is executed as serial processing.

[0102] First, the WF system 1900 executes the following steps S10701 to S10703 as the WF creation process of step S10700 shown in FIG. 10 . Note that at least one of these steps may be executed by the WF creation instruction unit 15 or the input / output device 1600. The WF system 1900 specifies the confirmation order for the multiple checkers specified in steps S10100 to S10400 (step S10701). To do this, the WF system 1900 uses, for example, the roles and affiliations of the specified checkers. In these cases, the confirmation order may be the creation order of defect reports (e.g., creation-confirmation-approval), or a priority order may be determined for each affiliation, and the confirmation order may correspond to that priority.

[0103] The WF system 1900 also extracts the checker with the highest confirmation order from the multiple checkers (step S10702), and then creates a confirmation request for the extracted checker with the highest confirmation order and notifies the corresponding input / output device 1600 (step S10703).

[0104] Next, the input / output device 1600 executes steps S10801 to S10804 as step S10800. First, the input / output device 1600 performs a confirmation process similar to step S9701 (step S10801). Then, the input / output device 1600 determines whether approval of the graph is possible (step S10802), similar to step S9702. If the result of this determination is that approval is possible (YES), the process proceeds to step S10803.

[0105] The input / output device 1600 also determines whether there is a checker next in rank to the identified highest-ranking checker. If there is a checker (YES), the process proceeds to step S10702, where the WF system 1900 extracts the next-highest-ranking checker. If there is no checker (NO), the input / output device 1600 notifies the WF system 1900 that approval has been completed, and the process proceeds to step S10900. The input / output device 1600 also executes a return process (step S10804), similar to step S9703. Through the above process, confirmation processing can be executed serially for multiple checkers.

[0106] Next, as a second example, an example in which confirmation processing is executed by parallel processing will be described. FIG. 12B is a flowchart for executing confirmation processing in parallel processing in this embodiment. The WF system 1900 creates confirmation requests for multiple confirmers as the WF creation processing in step S10700 shown in FIG. 10 and broadcasts the confirmation requests to the input / output devices 1600 of each confirmer. Then, in step S10800, the input / output devices 1600 of each confirmer each execute knowledge confirmation processing similar to steps S9700 and S10801 (step S10805). Then, each input / output device 1600 notifies the WF system 1900 of the confirmation results.

[0107] The WF system 1900 also collects confirmation results from each input / output device 1600 (step S11001). The WF system 1900 then determines whether all confirmers can approve the confirmation results from each input / output device 1600 (step S11002). If all confirmers are able to approve (YES), the process proceeds to step S10600. If there are any confirmers who cannot approve (NO), the process proceeds to step S1103, where the WF system 1900 executes a return process similar to steps S9703 and S10804 (step S11003). Note that step S11001 may be determined as YES if a predetermined number or percentage, such as half, of all confirmers approve. The above process allows parallel confirmation processing for multiple confirmers.

[0108] This concludes the description of this embodiment, but various modifications and applications of this embodiment are possible. For example, this embodiment can be applied to business operations other than product manufacturing, such as logistics, sales, and service provision. Furthermore, this embodiment can reduce task load and provide rapid feedback on quality information. In particular, it can generate defect-related knowledge from a large amount of past defect information. Furthermore, it can appropriately identify a person who will verify the accuracy of the generated defect-related knowledge, establish a verification process, and perform the verification work. Furthermore, organizations that use this embodiment can contribute to reducing defect response costs, improving product quality, and ultimately maintaining their brand image. Furthermore, this embodiment can provide factory equipment and factory line configuration services for improving product quality.

[0109] 1100: Knowledge generation support device 1200: Computing device 1300: Main memory device 1400: Auxiliary memory device 1410: Knowledge generation processing program 1411: Quality information acquisition subprogram 1412: Text mining subprogram 1413: Mining basis generation subprogram 1414: Graph generation subprogram 1415: Identical quality information aggregation subprogram 1420: Knowledge checker information identification program 1421: Checker identification subprogram 1422: User ID matching subprogram 1430: WF creation instruction program 1440: Knowledge distribution program 1450: Product configuration dictionary 1460: Project process / task dictionary 1470: User dictionary 1480: Database 1500: Communication device 1600: Input / output device 1700: Defect management system 1800: Product development project management system 1900: WF system

Claims

1. A knowledge generation support device that supports the generation of knowledge related to a business, comprising: a memory unit that stores information regarding multiple knowledge reviewers; an input unit that accepts text data related to the business; a text mining unit that analyzes the text data; a knowledge generation unit that generates the knowledge based on the analysis results by the text mining unit; and a reviewer identification unit that identifies the reviewer of the generated knowledge based on the analyzed text data and the stored information regarding the reviewer of the knowledge.

2. The knowledge creation support device according to claim 1, further comprising an identical quality information aggregation unit that aggregates a plurality of pieces of knowledge based on related text data.

3. A knowledge creation support device according to claim 1, further comprising: a mining basis generation unit that generates knowledge basis that serves as a basis for generating said knowledge; and an output unit that outputs said knowledge basis.

4. A knowledge creation support device according to claim 1, wherein a generation AI is implemented in the knowledge creation unit, and the knowledge is generated by the generation AI.

5. A knowledge creation support device according to claim 1, wherein the knowledge creation unit is a graph creation unit that creates a graph having a graph structure as the knowledge.

6. A knowledge generation support method executed by a knowledge generation support device that supports the generation of knowledge related to a business, wherein a memory unit stores information about multiple knowledge reviewers, an input unit receives text data related to the business, a text mining unit analyzes the text data, a knowledge generation unit generates the knowledge based on the analysis results by the text mining unit, and a reviewer identification unit identifies a reviewer of the generated knowledge based on the analyzed text data and the stored information about the reviewer of the knowledge.

7. A knowledge creation support method according to claim 6, wherein the same quality information aggregation unit further aggregates a plurality of pieces of knowledge based on related text data.

8. A knowledge creation support method according to claim 6, further comprising: a mining basis generation unit generating knowledge basis that serves as a basis for generating said knowledge; and an output unit outputting said knowledge basis.

9. A knowledge creation support method according to claim 6, wherein a generation AI is implemented in the knowledge creation unit, and the knowledge is generated by the generation AI.

10. A knowledge creation support method according to claim 6, wherein the knowledge creation unit is a graph creation unit that creates a graph having a graph structure as the knowledge.

11. A knowledge generation support program that causes a knowledge generation support device that supports the generation of knowledge related to a certain business process by a computer to function as: a memory unit that stores information regarding multiple knowledge reviewers; an input unit that accepts text data related to the business process; a text mining unit that analyzes the text data; a knowledge generation unit that generates the knowledge based on the analysis results by the text mining unit; and a reviewer identification unit that identifies the reviewer of the generated knowledge based on the analyzed text data and the stored information regarding the reviewer of the knowledge.

12. A knowledge creation support program according to claim 11, wherein the knowledge creation support device further functions as an identical quality information aggregation unit that aggregates multiple pieces of knowledge based on related text data.

13. A knowledge creation support program as claimed in claim 11, wherein the knowledge creation support device further comprises a mining basis generation unit that generates knowledge basis that serves as the basis for generating the knowledge, and functions as an output unit that outputs the knowledge basis.

14. A knowledge generation support program according to claim 11, wherein the knowledge generation unit is equipped with a generation AI, and the knowledge is generated by the generation AI.

15. A knowledge creation support program according to claim 11, wherein the knowledge creation unit is a graph creation unit that creates a graph having a graph structure as the knowledge.

Images