Information extraction device, information extraction method, and information extraction program

Abstract

To provide an information extraction device, information extraction method and information extraction program, which allow for extracting, from a report or the like, information for presenting effective countermeasure candidates that can quickly cope with similar troubles.SOLUTION: An information extraction device disclosed herein comprises a trouble event extraction unit, a countermeasure candidate extraction unit, and an effect determination unit. The trouble event extraction unit extracts description of a trouble event from text data. The a countermeasure candidate extraction unit extracts description of countermeasure candidates for coping with the trouble event from text data. The effect determination unit determines the effect of the countermeasures for the trouble event.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information extraction device, an information extraction method, and an information extraction program. [Background technology]

[0002] A technology has been proposed to assist design when a design change is made, such as changing the material used to manufacture equipment, by storing the improvements and side effects of the design change in a database and presenting the improvements and side effects of the design change to the designer based on this database. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-095377 Summary of the Invention [Problem to be solved by the invention]

[0004] In order to quickly address problems that occur in the manufacturing or operation of equipment, it is important to identify effective solutions. Therefore, a system that collects potential solutions for problems from texts, such as reports on past problems, and presents them to the engineers is crucial. The solutions described in the texts, such as reports, often contain both "ineffective solutions" that were actually tried but were ineffective against the problem, and "effective solutions" that were actually effective against the problem. While it may seem sufficient to collect only "effective solutions," these "ineffective solutions" may not necessarily be ineffective against new, similar problems. This is because similar problems may not necessarily have the same causes. Therefore, when an engineer identifies a potential solution for a certain problem, it is likely to be a useful solution.

[0005] The present disclosure aims to provide an information extraction device, an information extraction method, and an information extraction program that can extract information from text to present effective countermeasure candidates that can quickly respond to similar problems. [Means for solving the problem]

[0006] An information extraction device according to one aspect includes a trouble event extraction unit, a candidate countermeasure extraction unit, and an effectiveness determination unit. The trouble event extraction unit extracts descriptions of trouble events from text data. The candidate countermeasure extraction unit extracts descriptions of candidate countermeasures for dealing with the trouble events from the text data. The effectiveness determination unit determines the effectiveness of the candidate countermeasures for dealing with the trouble events. When a plurality of candidate measures are combined to deal with a trouble event, the candidate measure extracting unit extracts the combination of the plurality of candidate measures as one candidate measure. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a block diagram showing an example of an information extraction device according to the first embodiment. [Figure 2] FIG. 2 is a diagram showing an example of text data of a document. [Figure 3] FIG. 3 is a diagram illustrating an example of the extraction result data. [Figure 4] FIG. 4 is a diagram illustrating an example of a hardware configuration of the information extraction device. [Figure 5] FIG. 5 is a flowchart showing the processing of the information extraction program of the information extraction device. [Figure 6] FIG. 6 is a diagram showing an example of a display of possible solutions to a trouble event. [Figure 7] FIG. 7 is a diagram showing an example of a display of possible solutions to a trouble event. [Figure 8] FIG. 8 is a diagram showing an example of a display of possible solutions to a trouble event. [Figure 9] FIG. 9 is a block diagram showing an example of an information extraction device according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments will be described with reference to the drawings. [First embodiment] First, a first embodiment will be described. Fig. 1 is a block diagram showing an example of an information extraction device according to the first embodiment. The information extraction device 1 includes a text database (DB) 11, a trouble event extraction unit 12, a countermeasure candidate extraction unit 13, an effect determination unit 14, an extraction result database (DB) 15, and a display unit 16.

[0009] The text DB 11 stores text data of multiple documents, such as reports and daily reports, that describe trouble events. FIG. 2 is a diagram illustrating an example of the text data of a document. In each embodiment, a document includes at least a description of a “trouble event” and a description of a “potential countermeasure,” and may also include a description of an “effect.” The “trouble event” is a description that describes the details of the trouble event that should be addressed in the corresponding document. The “potential countermeasure” is a description that describes potential countermeasures for the trouble event. The potential countermeasures may be countermeasures that have actually been implemented, countermeasures that are planned for implementation, or countermeasures that have not been implemented but are considered possible. The “effect” is a description that indicates whether or not each countermeasure has had an effect on the trouble event as a result of being implemented. It is preferable that the documents in each embodiment be written in a way that allows the chronological order of the contents to be identified. For example, as shown in FIG. 2, it is preferable that the contents are written with dates or that each content is written in chronological order. By writing each content in chronological order, it becomes easier to extract the order of the potential countermeasures.

[0010] The trouble event extraction unit 12 extracts a description of a trouble event from the text data of a document stored in the text DB 11. For example, when the text data in the example of Fig. 2 is input, the trouble event extraction unit 12 extracts "current drops" as a description of the trouble event. Methods for extracting the description of the trouble event include a method of extraction based on manual input by a user who has checked the document, and a method of extraction by inputting text data into an extraction model that has undergone machine learning such as sequence labeling.

[0011] The candidate countermeasure extraction unit 13 extracts descriptions of candidate countermeasures for the trouble events extracted by the trouble event extraction unit 12 from the text data stored in the text DB 11. For example, when the text data shown in FIG. 2 is input, the candidate countermeasure extraction unit 13 extracts "Replace A," "Fix looseness in cable C," and "Replace D" as candidate countermeasure descriptions for the trouble event "Current drops." Examples of methods for extracting candidate countermeasure descriptions include a method of extracting based on manual input by a user who checks the document, and a method of extracting by inputting text data into an extraction model that has undergone machine learning such as sequence labeling. Furthermore, the candidate countermeasure extraction unit 13 may extract descriptions of candidate countermeasures that include data on the trouble events. For example, the candidate countermeasure extraction unit 13 may receive input of data on the trouble events extracted by the trouble event extraction unit 12 and extract candidate countermeasures for the data on the trouble events extracted by the trouble event extraction unit 12.

[0012] The effect determination unit 14 determines the effect of each candidate countermeasure extracted by the candidate countermeasure extraction unit 13 on the trouble event extracted by the trouble event extraction unit 12. The effect determination unit 14 then associates the extracted trouble event, the candidate countermeasure, and the effect, and stores them in the extraction result DB 15. For example, in FIG. 2, the result of the candidate countermeasure "Replace A" is described as "No change," so the effect determination unit 14 determines the effect of the candidate countermeasure "Replace A" as "No effect." Similarly, in FIG. 2, "Repair of loose cable C" is described as "Report of recurrence" the day after "Replacement of cable C," so the effect determination unit 14 determines the effect of the candidate countermeasure "Repair of loose cable C" as "No effect." Also, in FIG. 2, "No recurrence thereafter" is described the day after "Replacement of cable D." This can be interpreted as meaning that the candidate countermeasure "Replacement of cable D" was effective on the trouble event. Therefore, the effect determination unit 14 determines the effect of the candidate countermeasure "Replacement of cable D" as "Effective." Examples of methods for determining effectiveness include a method of determining effectiveness based on manual input by a user who has checked the document, and a method of determining effectiveness by inputting text data, trouble event data, and candidate countermeasure data into a discrimination model that has undergone machine learning such as series labeling. Furthermore, the effectiveness determination unit 14 may determine effectiveness based on both the trouble event data and the candidate countermeasure data. For example, the effectiveness determination unit 14 may receive input of the trouble event data extracted by the trouble event extraction unit 12 and the candidate countermeasure data extracted by the candidate countermeasure extraction unit 13, and determine the effectiveness of each candidate countermeasure extracted by the candidate countermeasure extraction unit 13 on the trouble event data extracted by the trouble event extraction unit 12.

[0013] Here, the effectiveness of a single measure is not necessarily sufficient. Therefore, the effect determining unit 14 may be able to associate an effect with a combination of two or more candidate measures. For example, if a document states, "After fixing the looseness of cable C and replacing cable D, the problem was resolved," it is likely that the problem was resolved only after "fixing the looseness of cable C" and "replacing cable D" were simultaneously implemented. In such a case, the effect determining unit 14 may determine that the effect of the combination of candidate measures "fixing the looseness of cable C" and candidate measures "replacing cable D" is "effective." This determination may also be made using a method that uses manual input or a method that uses a machine learning model. In the example shown here, the combination is determined to be "effective," but it goes without saying that the combination may also be determined to be "ineffective."

[0014] Furthermore, there may be cases where a solution is only effective when two or more proposed solutions are implemented in a specific order. For example, if a document states, "After restarting C, I replaced B, but the problem was not resolved. However, after replacing B and restarting C, the problem was resolved," it is likely that the problem was resolved by implementing the two proposed solutions in the order of "replace B" to "restart C." In such a case, the effect determining unit 14 may determine that the effect of the combination, including the order of proposed solution "replace B" to proposed solution "restart C," is "effective." This determination can also be made using a method using manual input or a method using a machine learning model. Furthermore, in the example shown here, the combination, including the order, is determined to be "effective," but it goes without saying that the combination may also be determined to be "ineffective."

[0015] Hereinafter, a plurality of candidate countermeasures for a trouble event in a certain document will be referred to as a candidate countermeasure set for this trouble event. A candidate countermeasure set may be a plurality of separate candidate countermeasures for a certain trouble event, a combination of a plurality of candidate countermeasures for a certain trouble event, or a combination including the order of a plurality of candidate countermeasures for a certain trouble event.

[0016] The extraction result DB 15 stores, as extraction result data, data on trouble events, data on one or more candidate countermeasures, and data on their effects, which are associated by the effect determination unit 14. FIG. 3 illustrates an example of the extraction result data. The extraction result data is managed, for example, by a document ID. The document ID is, for example, an ID number uniquely assigned to each document. The document ID is associated with data on trouble events, data on candidate countermeasures, and data on their effects. Extraction result data assigned the same document ID indicates that the data was extracted from the same document. The effect data may be expressed as a binary value, either "yes" or "no." The effect data may also be expressed as a probability value indicating the presence or absence of an effect. The probability value may be, for example, the confidence level of the extraction process using machine learning, or may be assigned manually. The extraction result data may further include a cost value indicating the cost required to implement each candidate countermeasure. The cost value may be calculated from the price of the replacement part, the labor hours, etc., or may be assigned manually. To determine the display order taking into account the effect and cost, as described later, the cost value may be normalized to a range from 0 to 1, similar to the probability value of the effect.

[0017] The display unit 16 displays on a display device potential solutions to the trouble event designated by the user based on the extraction result data stored in the extraction result DB 15 .

[0018] 4 is a diagram showing an example of the hardware configuration of the information extraction device 1. The information extraction device 1 is a computer, and has, for example, a processor 101, a memory 102, an input device 103, a display device 104, a communication device 105, and a storage 106 as hardware. The processor 101, the memory 102, the input device 103, the display device 104, the communication device 105, and the storage 106 are connected to a bus 107.

[0019] The processor 101 is a processor that controls the overall operation of the information extraction device 1. The processor 101 operates as a trouble event extraction unit 12, a countermeasure candidate extraction unit 13, an effect determination unit 14, and a display unit 16 by executing a program stored in, for example, the storage 106. The processor 101 is, for example, a CPU. The processor 101 may be an MPU, a GPU, an ASIC, an FPGA, or the like. The processor 101 may be a single CPU or the like, or may be multiple CPUs or the like.

[0020] The memory 102 includes a ROM and a RAM. The ROM is a non-volatile memory. The ROM stores a startup program for the information extraction device 1 and the like. The RAM is a volatile memory. The RAM is used as a working memory during processing in the processor 101, for example.

[0021] The input device 103 is an input device such as a touch panel, keyboard, or mouse. When the input device 103 is operated, a signal corresponding to the operation is input to the processor 101 via the bus 107. The processor 101 performs various processes in response to this signal. The input device 103 is used, for example, for input by the user when extracting the above-mentioned trouble phenomenon, extracting potential countermeasures, and determining the effectiveness of the countermeasures.

[0022] The display device 104 is a display device such as a liquid crystal display or an organic EL display.

[0023] The communication device 105 is a communication device that enables the information extraction device 1 to communicate with external devices. The communication device 105 may be a communication device for wired communication or a communication device for wireless communication.

[0024] The storage 106 is, for example, a storage such as a hard disk drive or a solid state drive, and stores various programs executed by the processor 101, such as an information extraction program 1061.

[0025] The storage 106 may also store a trouble event extraction model 1062, a countermeasure candidate extraction model 1063, and an effectiveness assessment model 1064. The trouble event extraction model 1062 is a trained model that has undergone machine learning such as sequence labeling to extract descriptions related to trouble events from the text data of an input document. The countermeasure candidate extraction model 1063 is a trained model that has undergone machine learning such as sequence labeling to extract descriptions related to countermeasure candidates for trouble events from the text data of an input document. The effectiveness assessment model 1064 is a trained model that has undergone machine learning such as sequence labeling to assess the effectiveness of each countermeasure candidate from the text data of an input document. As described above, the extraction of trouble events, the extraction of countermeasure candidates, and the assessment of effectiveness can also be performed by manual input by a user. If the extraction of trouble events, the extraction of countermeasure candidates, and the assessment of effectiveness are also performed by manual input by a user, the trouble event extraction model 1062, the countermeasure candidate extraction model 1063, and the effectiveness assessment model 1064 may not be required. Furthermore, the trouble event extraction model 1062, the countermeasure candidate extraction model 1063, and the effect determination model 1064 do not necessarily have to be stored in the storage 106. For example, the trouble event extraction model 1062, the countermeasure candidate extraction model 1063, and the effect determination model 1064 may be stored in a server or the like that can communicate with the information extraction device 1.

[0026] Furthermore, the storage 106 may store a text database (DB) 1065 and an extraction result database (DB) 1066. The text DB 1065 corresponds to the text DB 14. Furthermore, the extraction result DB 1066 corresponds to the extraction result DB 15. Here, the text DB 1065 and the extraction result DB 1066 do not necessarily have to be stored in the storage 106. For example, the text DB 1065 and the extraction result DB 1066 may be stored in a server or the like that can communicate with the information extraction device 1.

[0027] The bus 107 is a data transfer path for exchanging data between the processor 101, the memory 102, the input device 103, the display device 104, the communication device 105, and the storage 106.

[0028] Next, a description will be given of the operation of the information extraction device 1. Fig. 5 is a flowchart showing the processing of the information extraction program 1061 of the information extraction device 1. The processing of Fig. 5 is executed by the processor 101.

[0029] In step S1, processor 101 determines whether or not to extract extraction result data from the text data of a document. For example, when text data of a new document is input to information extraction device 1 or when a user operates input device 103 to instruct extraction of extraction result data, it is determined that extraction result data is to be extracted from the text data of the document. If it is determined in step S1 that extraction result data is to be extracted from the text data of the document, the process proceeds to step S2. If it is determined in step S1 that extraction result data is not to be extracted from the text data of the document, the process proceeds to step S8.

[0030] In step S2, processor 101 selects text data. When text data of a new document is input, processor 101 selects the text data. On the other hand, when the user instructs extraction of extraction result data, processor 101 selects text data from text DB 1065 based on the user's operation of input device 103. After the text data is selected, the process proceeds to step S3.

[0031] In step S3, the processor 101 extracts a description of the trouble event from the selected text data. The processor 101 extracts the description of the trouble event by inputting the text data into the trouble event extraction model 1062. Alternatively, the processor 101 displays the text of the document on the display device 104. The processor 101 then extracts, from the text displayed on the display device 104, a description portion designated by the user through operation of the input device 103, as the description of the trouble event. After the description of the trouble event is extracted, the process proceeds to step S4.

[0032] In step S4, processor 101 extracts the description of the candidate measures extracted in step S3 from the selected text data. Processor 101 extracts the description of the candidate measures by inputting the text data to candidate measure extraction model 1063. Alternatively, processor 101 displays the text of the document on display device 104. Processor 101 then extracts, as a candidate measure, a description portion specified by the user's operation of input device 103 from the text displayed on display device 104. After the candidate measures are extracted, the process proceeds to step S5.

[0033] In step S5, the processor 101 determines the effectiveness of the candidate measures extracted in step S4 on the corresponding trouble event from the selected text data. The processor 101 determines the effectiveness by inputting the text data into the effectiveness determination model 1064. Alternatively, the processor 101 displays the text of the document on the display device 104. The processor 101 then extracts a portion of the text displayed on the display device 104 designated by the user through operation of the input device 103 as a description of the effectiveness, and determines the effectiveness from the extracted description. Alternatively, the processor 101 determines the effectiveness of the candidate measures based on the user's operation of the input device 103. For example, the user designates either "effective" or "ineffective" for each candidate measure. Alternatively, the user designates a probability value representing the effectiveness for each candidate measure. When the user designates the effectiveness or the probability value, the text does not necessarily need to be displayed. Alternatively, for example, the user may determine the effectiveness based on their own expertise, experience, etc. Various statistical information may be used to determine the effectiveness. The determination of the effect using the statistical information may be performed by the processor 101 or by the user. After the effect is determined, the process proceeds to step S6.

[0034] In step S6, the processor 101 generates extraction result data including the trouble event, potential countermeasures, and effects. Then, the processor 101 assigns a document ID to the extraction result data. Thereafter, the processor 101 stores the extraction result data with the assigned document ID in the extraction result DB 1066.

[0035] In step S7, processor 101 determines whether extraction is complete. For example, processor 101 displays a confirmation screen for determining whether extraction is complete. If the user selects completion of extraction on this confirmation screen, it is determined that extraction is complete. If it is determined in step S7 that extraction is complete, the process proceeds to step S8. If it is determined in step S7 that extraction is not complete, the process returns to step S2. In this case, the process after selection of the next text data is performed.

[0036] In step S8, the processor 101 determines whether or not to display candidate countermeasures for the trouble event. For example, if the user operates the input device 103 to instruct the display of candidate countermeasures, it is determined that candidate countermeasures for the trouble event are to be displayed. If it is determined in step S8 that candidate countermeasures for the trouble event are to be displayed, the process proceeds to step S9. If it is determined in step S8 that candidate countermeasures for the trouble event are not to be displayed, the process proceeds to step S13.

[0037] In step S9, the processor 101 selects at least one trouble event from among the trouble events stored in the extraction result DB 1066. For example, the processor 101 displays a list of documents such as reports or a list of trouble events on the display device 104. The user selects a document or trouble event from the list, including the trouble event for which the user wants to know how to deal with it. In response to this, the processor 101 selects the trouble event. Alternatively, the user inputs keywords related to the trouble event or details of the trouble event that occurred. Based on the details input by the user, the processor 101 selects a trouble event. For example, if the user inputs "current drops" as the trouble event that occurred, the processor 101 searches the extraction result DB 1066 for similar trouble events, such as "current drop," "current decline," or "current decreases." Methods for searching for similar trouble events include, for example, a method that considers synonyms and similar words, or a method that uses machine learning to determine semantic similarity. Here, it is easy to imagine that the same or similar trouble event has occurred multiple times in the past. In this case, multiple trouble events may be selected for the trouble event specified by the user.

[0038] In step S10, the processor 101 displays candidate countermeasures for the selected trouble event on the display device 104 based on the extraction result data. Fig. 6 is an example of a display of candidate countermeasures for a trouble event. Fig. 6 shows an example of a display when the trouble event "voltage is unstable" is selected. In Fig. 3, the trouble event "voltage is unstable" is a trouble event in document id1, so in Fig. 6 the display is based on the extraction result data of document id1.

[0039] As shown in Fig. 6, the display of candidate countermeasures for a trouble event displays the selected trouble event 104a, and a list of candidate countermeasures for the trouble event 104a is displayed. In Fig. 6, three candidate countermeasures 104b, 104c, and 104d are displayed for the trouble event "voltage is unstable." A "effective" indicator 104e is displayed for a candidate countermeasure among the candidate countermeasures 104b, 104c, and 104d that was found to be effective. In Fig. 6, "replace D," which is one of the candidate countermeasures 104b for the trouble event 104a "voltage is unstable," is displayed as a "effective" indicator 104e. When the effect is recorded as a probability value rather than as a binary value of "effective" or "ineffective," the probability value may be displayed in the "effective" indicator 104e.

[0040] Furthermore, the candidate measures may be displayed in order of effectiveness, cost, or both. For example, FIG. 6 illustrates an example in which both effectiveness and cost are taken into consideration. As illustrated in FIG. 3, candidate measure 104b, “Replace D,” is costly but effective. On the other hand, candidate measure 104c, “Replace A,” and candidate measure 104d, “Repair loose cable C,” are less costly than “Replace D,” but are significantly less effective. Therefore, processor 101 displays candidate measure 104b at the top of the list. Furthermore, between candidate measure 104c and candidate measure 104d, candidate measure 104c is less costly and more effective. Therefore, processor 101 displays candidate measures 104b, 104c, and 104d in that order. The weighting of whether to prioritize effectiveness or cost during display may be a preset fixed weighting or may be set by the user.

[0041] As described above, multiple trouble events may be selected for a user-specified trouble event. In this case, it is desirable to display a single set of candidate countermeasures for the multiple trouble events. One possible method for grouping the candidate countermeasures is to treat similar candidate countermeasures as the same and take their union. The processor 101 then determines the display order of the candidate countermeasures, taking into consideration factors such as the effectiveness and cost of each candidate countermeasure, including the combination and order, and the frequency of occurrence of similar candidate countermeasures in similar trouble events. The processor 101 may determine the display order based on a certainty factor calculated from these factors using a specific formula, or may estimate the display order based on a certainty factor calculated by machine learning. Similar candidate countermeasures may be identified using a method that considers synonyms and similar words, as in the search for similar trouble events, or a method that uses machine learning to determine semantic similarity.

[0042] Furthermore, the display of the candidate measures may be performed by a method other than simply displaying a list of candidate measures as shown in FIG.

[0043] For example, the processor 101 may display a hierarchical structure showing the configuration of devices, as shown in Fig. 7, and display candidate countermeasures in response to a user's specification in the hierarchical structure. For example, in Fig. 7, a list 104f of device names is displayed, and a list 104g of names of parts constituting each device is displayed below the device names 104f. The processor 101 may display this list 104g of part names and display candidate countermeasures while illustrating in list 104g which part should be addressed for the specified trouble event. Furthermore, when one of the part names displayed in list 104g is selected, the processor 101 may display candidate countermeasures for the specified trouble event and whether or not they are effective.

[0044] The processor 101 may also display a structural diagram 104h of the facility or equipment as shown in FIG. 8, and display candidate countermeasures while illustrating in the structure 104h which parts of the structure 104h should be addressed for a specified trouble event. Possible methods for displaying candidate countermeasures in this case include displaying the effectiveness of the candidate countermeasures at their locations on the structural diagram 104h, or coloring the candidate countermeasures at their locations on the structural diagram 104h. Furthermore, in addition to the effectiveness, the cost or the confidence level may also be displayed. While FIG. 8 is a structural diagram, various other drawings, such as blueprints, that allow the user to identify the locations of candidate countermeasures may also be used for display.

[0045] Now, returning to the explanation of Fig. 5, in step S11 after displaying potential countermeasures for the trouble event, the processor 101 determines whether or not to end the display. For example, if the user operates the input device 103 to instruct the end of the display, it is determined that the display should be ended. If it is determined in step S11 that the display should not be ended, the processing proceeds to step S12. If it is determined in step S11 that the display should be ended, the processing proceeds to step S13.

[0046] In step S12, the processor 101 determines whether or not to change the trouble event. For example, if the user operates the input device 103 to instruct a change of the trouble event, it is determined that the trouble event is to be changed. If it is determined in step S12 that the trouble event is not to be changed, the process returns to step S10. In this case, the display of potential countermeasures for the trouble event continues. If it is determined in step S12 that the trouble event is to be changed, the process returns to step S9. In this case, the processor 101 selects a trouble event again.

[0047] In step S13, processor 101 determines whether or not to terminate the processing of information extraction program 1061. For example, if the user operates input device 103 to instruct termination, it is determined that the processing of information extraction program 1061 is to be terminated. If it is determined in step S13 that the processing of information extraction program 1061 is not to be terminated, the processing returns to step S1. If it is determined in step S13 that the processing of information extraction program 1061 is to be terminated, processor 101 terminates the processing of FIG. 5.

[0048] As described above, according to the first embodiment, trouble events and candidate countermeasures are extracted from the text data of a document. Furthermore, the effect of each candidate countermeasure for the trouble event is determined. Then, the trouble event, candidate countermeasure, and effect are associated and stored in a database. Furthermore, the candidate countermeasure and effect associated with the specified trouble event are displayed.

[0049] That is, in the first embodiment, not only candidate countermeasures effective for a certain trouble event but also candidate countermeasures that are only planned to be implemented, candidate countermeasures that have not been implemented but have been raised as possibilities, and the effects of each candidate countermeasure on the trouble event can be displayed. A countermeasure raised by an engineer or the like as a candidate countermeasure for a certain trouble event may not be effective for that trouble event, but may be effective for another trouble event. In the embodiment, the user can know not only countermeasures that are effective at the time but also countermeasures that are effective at other times, and it is expected that the user will be able to quickly respond to the trouble event that has occurred.

[0050] [Second embodiment] Next, a second embodiment will be described. Fig. 9 is a block diagram showing an example of an information extraction device according to the second embodiment. The information extraction device 1 includes a text database (DB) 11, a trouble event extraction unit 12, a countermeasure candidate extraction unit 13, an effect determination unit 14, an extraction result database (DB) 15, a display unit 16, and a cluster generation unit 17.

[0051] The cluster generation unit 17 clusters the trouble events stored in the extraction result DB 15 based on the similarity of the candidate countermeasure sets. The similarity of the candidate countermeasure sets can be determined based on a measure that takes into account the extent to which similar candidate countermeasure sets are included, the extent to which the effects of the candidate countermeasure sets are the same, the extent to which the combinations or orders of effective candidate countermeasures are the same, etc. Clustering can be performed using, for example, the k-means method, hierarchical clustering method, etc.

[0052] For example, suppose that multiple sets of candidate countermeasures for similar trouble events, such as "current drops," "current drop," and "current has dropped," are divided into two clusters. This indicates that, although the trouble events are similar, there are two different types of candidate countermeasures. Therefore, it is considered that this potentially indicates that the root causes of the trouble events in these different clusters are different. Using such cluster information, the processor 101 may display candidate countermeasures for each cluster when presenting candidate countermeasures for similar trouble events, or may add more detailed information about the trouble events for each cluster in advance. For example, if there are two clusters for the trouble event "current drops" and the difference between the clusters is "whether function A is activated," the processor 101 may display "current drops when function A is activated" when displaying the trouble event.

[0053] [Variations] In the above-described embodiment, it is assumed that "trouble events," "potential countermeasures," and "effects" are associated with each other. In contrast, trouble events described in reports, etc., require a countermeasure and can be considered to correspond to the "purpose" for which the report, etc. is described. Similarly, "potential countermeasures" can be considered to correspond to "action items" that are implemented to achieve that purpose. Considered in this way, the technology of the embodiment is not limited to cases in which "trouble events," "potential countermeasures," and "effects" extracted from text data such as reports are associated and stored in a database, but can also be applied to cases in which "purposes," "action items," and "effects" extracted from arbitrary text data are associated and stored in a database.

[0054] Furthermore, the instructions shown in the processing procedures described in the above-described embodiments can be executed based on a software program. A general-purpose computer system can store this program in advance and, by loading this program, achieve effects similar to those achieved by the data log processing device described above. The instructions described in the above-described embodiments are recorded as a computer-executable program on a magnetic disk (flexible disk, hard disk, etc.), an optical disk (CD-ROM, CD-R, CD-RW, DVD-ROM, DVD±R, DVD±RW, Blu-ray (registered trademark) Disc, etc.), semiconductor memory, or similar recording medium. The recording medium may take any storage format as long as it is readable by a computer or embedded system. A computer can achieve operations similar to those of the data log processing device described in the above-described embodiments by loading the program from the recording medium and having the CPU execute the instructions described in the program based on the program. Of course, the computer may acquire or load the program via a network. In addition, an OS (operating system), database management software, network middleware, etc. running on a computer may execute some of the processes required to realize this embodiment based on instructions from a program installed on the computer or embedded system from a recording medium. Furthermore, the recording medium in this embodiment is not limited to a medium independent of a computer or an embedded system, but also includes a recording medium that stores or temporarily stores a program downloaded via a LAN, the Internet, or the like. Furthermore, the number of recording media is not limited to one, and cases where the processing in this embodiment is executed from multiple media are also included in the recording media in this embodiment, and the media may have any configuration.

[0055] The computer or embedded system in this embodiment is for executing each process in this embodiment based on a program stored on a recording medium, and may be configured as either a device consisting of a single device such as a personal computer or a microcomputer, or a system in which multiple devices are connected to a network. Furthermore, the computer in this embodiment is not limited to a personal computer, but also includes an arithmetic processing unit, a microcomputer, etc. included in information processing equipment, and is a general term for equipment or devices that can realize the functions in this embodiment by a program.

[0056] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0057] 1 Information extraction device, 11 Text database (DB), 12 Trouble event extraction unit, 13 Countermeasure candidate extraction unit, 14 Effectiveness determination unit, 15 Extraction result database (DB), 16 Display unit, 17 Cluster generation unit, 101 Processor, 102 Memory, 103 Input device, 104 Display device, 105 Communication device, 106 Storage, 107 Bus, 1061 Information extraction program, 1062 Trouble event extraction model, 1063 Countermeasure candidate extraction model, 1064 Effectiveness determination model, 1065 Text database (DB), 1066 Extraction result database (DB).

Claims

1. a trouble event extraction unit that extracts a description of a trouble event from the text data; a candidate solution extraction unit that extracts a description of candidate solutions for dealing with the trouble event from the text data; an effect determining unit that determines the effect of the candidate measures on the trouble event; Equipped with when a plurality of candidate measures are combined to deal with the trouble event, the candidate measure extraction unit extracts the combination of the plurality of candidate measures as one candidate measure; Information extraction device.

2. 2. The information extraction device according to claim 1, further comprising a database that stores the trouble events, the candidate countermeasures, and the effects.

3. 3. The information extraction device according to claim 2, further comprising a display unit that displays on a display device candidate countermeasures for a specified trouble event based on the trouble event, the candidate countermeasures, and the effects stored in the database.

4. The candidate measures include a plurality of candidate measures, The information extraction device according to claim 3 , wherein the display unit determines a display order of the plurality of candidate measures according to the effect associated with each of the plurality of candidate measures.

5. The candidate measures include a plurality of candidate measures, The information extraction device according to claim 3 , wherein the display unit determines a display order of the plurality of candidate measures according to a cost required for implementing each of the plurality of candidate measures.

6. The information extraction device according to claim 1 , wherein the effect determining unit determines the effect from the text data.

7. 7. The information extraction device according to claim 6, wherein when there is an order among the plurality of candidate measures, the candidate measure extraction unit extracts a combination of the plurality of candidate measures including the order as one candidate measure.

8. 8. The information extraction device according to claim 1, further comprising a cluster generation unit that clusters the trouble events based on similarities between the candidate countermeasures.

9. Extracting a description of a trouble event from text data by an information extraction device; extracting, from the text data, descriptions of candidate countermeasures for dealing with the trouble event by the information extraction device; determining the effectiveness of the candidate measures for the trouble event by the information extraction device; Equipped with extracting the description of the candidate measures includes, when a plurality of candidate measures are combined to deal with the trouble event, extracting the combination of the plurality of candidate measures as one candidate measure; Information extraction method.

10. Extracting a description of a trouble event from the text data; extracting from the text data a description of a countermeasure candidate for dealing with the trouble event; determining the effectiveness of the candidate measures for the trouble event; An information extraction program for causing a computer to execute the above, extracting the description of the candidate measures includes, when a plurality of candidate measures are combined to deal with the trouble event, extracting the combination of the plurality of candidate measures as one candidate measure; Information extraction program.

Images