JP6974751B2 - Visualizers, visualization methods, and programs - Google Patents

Description

The present invention relates to a visualization device, a visualization method, and a program.

Conventionally, when the classification to which a document (text) belongs is multi-valued (three or more types), it is estimated which classification the document belongs to (estimation of N-value classification), and one of the most probable classification results is displayed. The classification determination method is known. For example, when a document describing a failure status of a personal computer is classified into a failure type, when the classification is "power supply", "HDD (Hard Disc Drive)", "display", and "fan", for example, " When the document "Nothing is displayed on the screen even when the power is turned on" is input, the input document is acquired as shown in FIG. 17 (step S51). When the document is acquired in step S51, it is estimated that the document belongs to the classification "display" from the above-mentioned plurality of classifications by the estimation of the N value classification (step S52). When the N value classification is estimated in step S52, the result information including the classification result "display" is stored (step S53) and displayed on a display or the like (step S54). As a classifier used for estimating N-value classification, it is known that SVM (Support Vector Machine) has extremely high classification performance (see, for example, Non-Patent Document 1). There is also a method of assigning a reliability of the classification result and displaying one or a plurality of classification results together with the reliability.

Daiya Takamura, "Introduction to Machine Learning for Language Processing", Corona Publishing Co., Ltd., August 10, 2010, P.M. 117-127

However, when the user tries to determine the classification with reference to the classification result displayed by the conventional technique as described above, if only one classification result is displayed, the reliability of the classification result is unknown. It may be difficult for the user to decide whether to adopt the classification result. Also, even if the classification result is displayed together with the reliability, the reliability of the displayed classification result can be known, but the judgment criteria for adopting the classification result (for example, what percentage of reliability can be adopted). It can be difficult to decide. Furthermore, when a document contains a plurality of sentences, it may not be possible to determine which sentence contributes to the determination of classification.

Therefore, an object of the present invention made in view of such a point is to visualize the user's judgment criteria for the classification result of the input document.

In order to solve the above problems, the visualization device according to the present invention defines in advance a document acquisition unit for acquiring a document, a division unit for dividing the document into a plurality of sentences, and each of the document and the plurality of sentences. A classification estimation unit that estimates the classification results for all of the plurality of classifications, and a display unit that simultaneously displays the document, the plurality of sentences, and the classification results for the document and each of the plurality of sentences. It is characterized by being prepared.
The visualization apparatus according to the present invention includes: a document acquisition unit that acquires a document, a dividing unit for dividing the document into a plurality of sentences, the document and for each of the plurality of statements, multiple classification all predetermined A classification estimation unit that estimates the classification result for the document, a display unit that simultaneously displays the document, the plurality of sentences included in the document, and the classification result for each of the document and the plurality of sentences in association with each other. , It is characterized by having.
The plurality of predetermined classifications may be common to the document and the plurality of sentences.
The document acquisition unit may further acquire the manual assignment classification for the document, and the display unit may further display the document, the classification result, and the classification result by the manual assignment classification in association with each other.

Further, the visualization method according to the present invention includes a step of acquiring a document, a step of dividing the document into a plurality of sentences, and a classification result for all of a plurality of predetermined classifications of the document and the plurality of sentences. It is characterized by including a step of estimating the document, a plurality of sentences, and a step of simultaneously displaying the classification result for each of the document and the plurality of sentences.

Further, the program according to the present invention is a program for making a computer function as the above-mentioned visualization device.

According to the present invention, it is possible to visualize the user's judgment criteria for the classification result of the input document.

It is a block diagram which shows the structural example of the visualization apparatus which concerns on 1st Embodiment. It is a figure which shows the display example of the display part in 2nd Embodiment. It is a figure which shows an example of the result information of 1st Embodiment. It is a flowchart which shows an example of the visualization method which concerns on 1st Embodiment. It is a block diagram which shows the structural example of the visualization apparatus which concerns on 2nd Embodiment. It is a figure which shows the display example of the display part in 2nd Embodiment. It is a figure which shows an example of the result information of the 2nd Embodiment. It is a flowchart which shows an example of the visualization method which concerns on 2nd Embodiment. It is a figure which shows the display example of the display part in 3rd Embodiment. It is a figure which shows an example of the result information of the 3rd Embodiment. It is a flowchart which shows an example of the visualization method which concerns on 3rd Embodiment. It is a figure which shows the display example of the display part of 4th Embodiment. It is a figure which shows an example of the result information in 4th Embodiment. It is a flowchart which shows an example of the visualization method which concerns on 4th Embodiment. It is a figure which shows an example of the 5th Embodiment result information. It is a block diagram which shows the structural example of the visualization apparatus which concerns on the modification of 1st Embodiment. It is a flowchart which shows an example of the classification determination method in the prior art.

[First Embodiment]
First, the functional configuration of the first embodiment of the present invention will be described with reference to FIG. FIG. 1 is a functional configuration diagram of the visualization device 1 according to the first embodiment.

As shown in FIG. 1, the visualization device 1 includes a document acquisition unit 11, a binary classification estimation unit 12, a storage unit 13, and a display unit 14.

The document acquisition unit 11 acquires a document based on the operation of the user. The document acquired by the document acquisition unit 11 is arbitrary, but in the present embodiment, as an example, the user uses a Web application to display a screen as shown in FIG. 2A “even if the power is turned on”. Enter the document "Nothing is displayed on the screen." And press the send button. In this case, the document acquisition unit 11 acquires the input document.

The binary classification estimation unit 12 estimates whether or not the document acquired by the document acquisition unit 11 belongs to each of the plurality of classifications by a known machine estimation method based on the learning data. The classification may be arbitrary, but in the present embodiment, examples of the classification will be described as "power supply", "HDD", "display", and "fan".

In this case, the binary classification estimation unit 12 estimates based on the learning data whether or not the document acquired by the document acquisition unit 11 belongs to the “power supply”, “HDD”, “display”, and “fan”, respectively. .. When the document is "Nothing is displayed on the screen even when the power is turned on", the binary classification estimation unit 12 estimates that the document belongs to the classification "power" (○) based on the learning data. It is estimated that it does not belong to the classification of "HDD" (x), it is estimated that it belongs to the classification of "display" (○), and it is estimated that it does not belong to the classification of "fan" (x).

The storage unit 13 stores the result information. As shown in FIG. 3, the result information includes an ID (Identification) for uniquely identifying the document, the document, and the classification result. The classification result is information indicating whether or not the document belongs to each classification (◯) or not (x), which is estimated by the binary classification estimation unit 12 as described above. For example, the storage unit 13 corresponds to the document "Nothing is displayed on the screen even when the power is turned on" of the ID "A", the power supply "○", the HDD "×", the display "○", and the fan "○". × ”is stored as the classification result.

The display unit 14 displays the result information stored in the storage unit 13. Specifically, the display unit 14 displays the document and the classification result on a display or the like. For example, the display unit 14 displays the classification results estimated by the binary classification estimation unit 12 as belonging to the classifications of "power supply" and "display" as shown in FIG. 2B. The display unit 14 may transmit the result information to another information processing device via the communication network.

Subsequently, the visualization method of the visualization device 1 in the first embodiment will be described with reference to the sequence diagram shown in FIG.

First, the document acquisition unit 11 acquires a document based on the user's operation (step S11). In the present embodiment, the document acquisition unit 11 acquires, for example, a document that "nothing is displayed on the screen even when the power is turned on."

When the document is acquired in step S11, the binary classification estimation unit 12 estimates the binary classification of the document (step S12). Specifically, the binary classification estimation unit 12 estimates whether or not the document belongs to each of the predetermined classifications. In the present embodiment, for example, the binary classification estimation unit 12 estimates whether or not the document belongs to the classification of "power source".

When the binary classification is estimated in step S12, the binary classification estimation unit 12 determines whether or not all the classifications have been estimated (step S13). In the example of the present embodiment, the binary classification estimation unit 12 determines whether or not the binary classification is estimated for all the classifications of "power supply", "HDD", "display", and "fan".

If not all classifications have been estimated in step S13, returning to step S12, the binary classification estimation unit 12 estimates whether the document belongs to a classification that has not yet been estimated. If all the classifications have been estimated in step S13, the storage unit 13 stores the result information including the classification result (step S14).

When the result information is stored in step S14, the display unit 14 displays the result information on a display or the like (step S15).

As described above, according to the first embodiment, the classification results for all the classifications are stored and displayed for the input document. If a document belongs to more than one classification, it means that either classification is possible, and conversely, if it does not belong to any classification, it means that it lacks a decisive factor. For example, in the case of the classification result shown in FIG. 3, the document "Nothing is displayed on the screen even when the power is turned on" indicates that it may belong to both the classifications of "power" and "display". As a result, it is possible to determine the classification by considering the excess or deficiency information in the input document, deleting unnecessary information, and supplementing the insufficient information. For example, in the case of the classification result shown in FIG. 3, the classification can be determined as "power supply" by supplementing "the power lamp of the personal computer body does not light" as insufficient information.

[Second Embodiment]
Subsequently, the second embodiment of the present invention will be described with reference to the drawings.

As shown in FIG. 5, the visualization device 2 according to the second embodiment has the same as the visualization device 1 according to the first embodiment, the document acquisition unit 11, the binary classification estimation unit 12, the storage unit 13, and the storage unit 13. A display unit 14 is provided, and a division unit 15 is further provided. The same reference numerals as those of the visualization device 1 in the first embodiment are designated by the same reference numerals, and the description thereof will be omitted as appropriate.

The division unit 15 divides the document acquired by the document acquisition unit 11. The division unit 15 extracts, for example, sentences included in a document one by one. For example, the division unit 15 can search for the phrase "." And extract the character string before the first phrase as one sentence from the first character of the document. Further, the division unit 15 can extract the character string before the next phrase from the characters after the phrase as one sentence. Further, when the document has a line break, the division unit 15 may divide the document before and after the line break.

As an example, the user inputs a document "The operation is very slow and there is no fan noise. It may not start up" on the screen as shown in FIG. 6A by using the Web application. Press the submit button. In this case, the document acquisition unit 11 acquires the input document. Then, the division unit 15 divides the document acquired by the document acquisition unit 11 into a sentence "the operation is very slow and there is no fan noise" and a sentence "may not stand up."

The binary classification estimation unit 12 estimates the binary classification of each sentence divided by the division unit 15 by a known machine estimation method based on the learning data. As described above, when the division unit 15 divides the operation into the sentence "the operation is very slow and the fan does not make a noise" and the sentence "may not start up", the binary classification estimation unit 12 , It is estimated whether or not the sentence divided by the division unit 15 belongs to the "power supply", the "HDD", the "display", and the "fan", respectively.

Specifically, the binary classification estimation unit 12 says that the sentence "the operation is very slow and there is no fan noise" is "power supply" as shown in FIG. 7 based on the learning data. It is estimated that it does not belong to the classification (x), it is estimated that it does not belong to the classification "HDD" (x), it is estimated that it does not belong to the classification "display" (x), and it belongs to the classification "fan" (○). ).

In addition, the binary classification estimation unit 12 estimates that the sentence "may not start up" belongs to the category "power supply" (○) based on the learning data, and classifies it as "HDD". It is estimated that it does not belong (x), it is estimated that it does not belong to the classification of "display" (x), and it is estimated that it does not belong to the classification of "fan" (x).

Further, the binary classification estimation unit 12 classifies the document as "power supply" based on the learning data for the entire document "the operation is very slow and the fan does not make a noise. It may not start up." Estimated as (○), presumed not to belong to the classification of "HDD" (x), presumed to not belong to the classification of "display" (x), and presumed to belong to the classification of "fan" (○) And.

The storage unit 13 stores the result information. As shown in FIG. 7, the result information includes an ID, a document, each divided sentence, and a classification result estimated by the binary classification estimation unit 12 to indicate whether or not each sentence belongs to each classification. , And classification results indicating whether the entire document belongs to each classification.

The display unit 14 displays the result information stored in the storage unit 13. Specifically, the display unit 14 displays a document, each sentence, and a classification result on a display or the like. For example, the display unit 14 classifies the classification results estimated by the binary classification estimation unit 12 into the classifications of "fan" and "power supply" in the entire document as shown in FIG. 6 (b). The sentence "It's very slow and there is no fan noise" belongs to the category "Fan", and the sentence "Sometimes it doesn't start up" indicates that it belongs to the category "Power supply". The display unit 14 may transmit the result information to another information processing device via the communication network.

Subsequently, the visualization method of the visualization device 2 in the second embodiment will be described with reference to the sequence diagram shown in FIG.

First, the document acquisition unit 11 acquires a document based on the user's operation (step S21). For example, the document acquisition unit 11 uses a Web application to display a screen as shown in FIG. 6A, "The operation is very slow and there is no fan noise. It may not start up." Enter the document and press the send button to get the entered document.

When the document is acquired in step S21, the dividing unit 15 divides the document (step S22). For example, the division unit 15 changes the document "the operation is very slow and the fan does not make a sound. It may not start up" to the sentence "the operation is very slow and the fan does not make a sound." And "does not start up." It may be divided into the sentence "Sometimes."

When the document is divided in step S22, the binary classification estimation unit 12 estimates the binary classification of the divided sentence (step S23). Specifically, the binary classification estimation unit 12 estimates whether or not the divided sentence belongs to a predetermined classification. In the present embodiment, for example, the binary classification estimation unit 12 estimates whether or not the sentence "the operation is very slow and there is no fan noise" contained in the document belongs to the classification "power supply".

When the binary classification is estimated in step S23, the binary classification estimation unit 12 determines whether or not all the classifications have been estimated (step S24). In the example of the present embodiment, the binary classification estimation unit 12 determines whether or not the document belongs to or is estimated for all the classifications of "power supply", "HDD", "display", and "fan".

If the sentence is not estimated for all the classifications in step S24, returning to step S23, the binary classification estimation unit 12 estimates whether the sentence belongs to the classification that has not been estimated yet. When sentences are estimated for all the classifications in step S24, the binary classification estimation unit 12 determines whether or not the sentences are estimated for all the divided sentences (step S25). In the present embodiment, it is determined whether or not both the divided sentences "the operation is very slow and there is no fan noise" and the sentence "may not start up" are estimated.

When the determination is made for all the sentences in step S25, the storage unit 13 stores the result information including the classification result (step S26). If all the sentences have not been determined in step S25, the process returns to step S23 to determine whether or not the sentence that has not yet been estimated belongs to each classification.

When the result information is stored in step S26, the display unit 14 displays the result information on a display or the like (step S27). For example, the display unit 14 classifies the classification results estimated by the binary classification estimation unit 12 into the categories of "fan" and "power supply" in the entire document as shown in FIG. 6 (b), and "operates". The sentence "is very slow and there is no fan noise" belongs to the category "fan", and the sentence "may not start up" indicates that it belongs to the category "power supply".

As described above, according to the second embodiment, the division unit 15 divides the document into a plurality of sentences. Then, the binary classification estimation unit 12 estimates whether or not each of the plurality of sentences corresponds to each classification. Therefore, if the input document contains a plurality of sentences, the classification result is stored and displayed for each sentence. This makes it possible to reconsider the classification with reference to the classification results estimated for each sentence, even if the classification cannot be determined for the entire document.

[Third Embodiment]
Subsequently, a third embodiment of the present invention will be described with reference to the drawings.

As shown in FIG. 1, the visualization device 1 according to the third embodiment includes a document acquisition unit 11, a binary classification estimation unit 12, a storage unit 13, and a display unit 14, as in the first embodiment. .. Since the constituent blocks are the same as those in the first embodiment, the description of the constituent blocks will be omitted.

In the third embodiment, the document acquisition unit 11 acquires a document and acquires a classification (manually assigned classification) corresponding to the document based on the operation of the user. As an example, the user inputs a document "bad start-up" on the screen as shown in FIG. 9A using a Web application, and inputs "HDD" in the failure classification as a manual assignment classification. .. Then, the user presses the send button. In this case, the document acquisition unit 11 acquires the document "bad start-up" and acquires the failure classification "HDD" as the manual assignment classification.

The binary classification estimation unit 12 estimates whether or not the acquired document belongs to each classification by a known machine estimation method based on the learning data. For example, the binary classification estimation unit 12 estimates that the document "bad rise" does not belong to the classification "power supply" (x) as shown in FIG. 10 based on the learning data. It is assumed that it belongs to the classification of "HDD" (○), does not belong to the classification of "display" (x), and does not belong to the classification of "fan" (x).

The storage unit 13 stores the result information. As shown in FIG. 10, the result information includes an ID, a document, a classification result of machine estimation estimated by the binary classification estimation unit 12, and a manual assignment classification. For example, as shown in FIG. 10, the storage unit 13 stores a manual assignment classification of "HDD" corresponding to a document of "bad rise" of ID "C". Further, the storage unit 13 stores the power supply “×”, the HDD “◯”, the display “×”, and the fan “×” as the classification result of the machine estimation.

The display unit 14 displays the result information stored in the storage unit 13. Specifically, the display unit 14 displays a document, a classification result of machine estimation estimated by the binary classification estimation unit 12, and a manual assignment classification on a display or the like. For example, the display unit 14 indicates that the classification result estimated by the binary classification estimation unit 12 belongs to the classification of "HDD" as shown in FIG. 9B, and the input failure classification (manual). It is displayed that the grant classification) is "HDD". The display unit 14 may transmit the result information to another information processing device via the communication network.

Subsequently, the visualization method of the visualization device 3 in the third embodiment will be described with reference to the sequence diagram shown in FIG.

First, the document acquisition unit 11 acquires the document and the manual assignment classification based on the user's operation (step S31). For example, as shown in FIG. 9A, when a document "bad start-up" and a manual grant classification "HDD" are input by the user's operation, the input document and the manual grant classification are input. To get.

The processing of steps S32 and S33 of the visualization method performed by the visualization device 3 in the present embodiment is the same as the processing of steps S12 and S13 of the first embodiment.

When documents are estimated for all classifications in step S33, the storage unit 13 stores the result information (step S34). The result information in the third embodiment includes the manual grant classification in addition to the classification result in the first embodiment. For example, as shown in FIG. 10, the storage unit 13 includes result information including a classification result of a power supply “×”, an HDD “○”, a display “×”, and a fan “×”, and a manual classification of “HDD”. To store.

When the result information is stored in step S34, the display unit 14 displays the result information on a display or the like (step S35). For example, as shown in FIG. 9B, the display unit 14 is determined by machine learning to have a high possibility of belonging to the classification of "HDD", and the input failure classification (manually assigned classification). Displays that is "HDD".

As described above, according to the third embodiment, the document acquisition unit 11 further acquires the manual assignment classification of the document based on the operation of the user. Then, the display unit 14 displays the classification result estimated by the binary classification estimation unit 12 and the manually assigned classification as the result information. Therefore, the user can recognize the classification result estimated based on the learning data, and finally determine the classification of the document in consideration of the hand-assigned classification indicating the judgment of the user who acquired the document. can.

[Fourth Embodiment]
Subsequently, a fourth embodiment of the present invention will be described with reference to the drawings.

As shown in FIG. 5, the visualization device 2 according to the fourth embodiment has the document acquisition unit 11, the binary classification estimation unit 12, the storage unit 13, the display unit 14, and the division, as in the second embodiment. A unit 15 is provided. Since the constituent blocks are the same as those in the second embodiment, the description of the constituent blocks will be omitted.

In the fourth embodiment, the document acquisition unit 11 acquires a document based on the operation of the user, and also acquires a manual grant classification corresponding to the document. As an example, the user inputs a document "The startup is poor. It is the same even if the power is turned off and started up" on the screen as shown in FIG. 12A by using the Web application, and as a manual assignment classification. Enter "HDD" in the failure classification of. Then, the user presses the send button. In this case, the document acquisition unit 11 acquires a document stating, "The startup is poor. It is the same even if the power is turned off and restarted." Further, "HDD" is acquired as a manual grant classification.

Then, the division unit 15 divides the document acquired by the document acquisition unit 11 into a sentence "a poor start-up" and a sentence "even if the power is turned off and restarted."

Further, the binary classification estimation unit 12 estimates whether or not each sentence divided by the division unit 15 belongs to each classification by a known machine estimation method based on the learning data. For example, as shown in FIG. 13, the binary classification estimation unit 12 estimates that the sentence "the rise is bad" does not belong to the classification "power supply" (x) based on the learning data. It is estimated that it belongs to the classification of "HDD" (○), it is estimated that it does not belong to the classification of "display" (x), and it is estimated that it does not belong to the classification of "fan" (x).

Further, the binary classification estimation unit 12 estimates that the sentence "it is the same even if the power is turned off and restarted" is not classified as "power" (x) based on the learning data, and ". It is estimated that it does not belong to "HDD" (x), it is estimated that it does not belong to "display" (x), and it is estimated that it does not belong to "fan" (x). In addition, the binary classification estimation unit 12 does not belong to the classification of "power supply" based on the learning data for the entire document "The startup is bad. It is the same even if the power is turned off and restarted." ), It is estimated that it belongs to "HDD" (○), it is estimated that it does not belong to "display" (x), and it is estimated that it does not belong to "fan" (x).

The storage unit 13 stores the result information. As shown in FIG. 13, the result information includes an ID, a document, each divided sentence, and a classification result estimated by the binary classification estimation unit 12 indicating whether or not each sentence belongs to each classification. And the classification result showing whether or not the whole document belongs to each classification, and the manual grant classification are included.

As described above, the document acquisition unit 11 acquires the document "The startup is poor. It is the same even if the power is turned off and restarted." And the manually assigned classification "HDD" is acquired by the binary classification estimation unit 12. The result information stored in the storage unit 13 when it is estimated will be described. As shown in FIG. 13, the storage unit 13 corresponds to the document "The startup is poor. It is the same even if the power is turned off and restarted." Power supply "x", HDD "○", display "x", and fan "x", which are the classification results by machine estimation.
To store. Further, the storage unit 13 stores the power supply “x”, the HDD “◯”, the display “x”, and the fan “x” in response to the divided sentence “slow rise”. Further, the storage unit 13 corresponds to the divided sentence "It is the same even if the power is turned off and restarted", and the power supply "x", the HDD "x", the display "x", and the fan "x" are used. Store.

The display unit 14 displays the result information stored in the storage unit 13. Specifically, the display unit 14 includes a document, each sentence, a classification result indicating whether or not each sentence belongs to each category, a classification result indicating whether or not a document including each sentence belongs to each category, and a manual operation. The grant classification is displayed on a display or the like.

For example, as shown in FIG. 12B, the display unit 14 determines that the entire document is likely to belong to the classification of "HDD" by the judgment by machine learning, and the input failure classification (manual). It is displayed that the grant classification) is "HDD". Further, on the display unit 14, it is determined that the divided sentence "poor start-up" is likely to belong to the category "HDD", and the sentence "even if the power is turned off and started up" is either. Displays that it is highly likely that it does not belong to the classification. The display unit 14 may transmit the result information to another information processing device via the communication network.

Subsequently, the visualization method of the visualization device 4 in the fourth embodiment will be described with reference to the sequence diagram shown in FIG.

First, the document acquisition unit 11 acquires the document and the manual assignment classification based on the user's operation (step S41). For example, as shown in FIG. 12A, a document "The startup is poor. It is the same even if the power is turned off and started up" and a manual assignment classification "HDD" are input by the user's operation. If so, the entered document and manual grant classification are acquired.

The processing of steps S42 to S45 of the visualization method performed by the visualization device 3 in the present embodiment is the same as the processing of steps S22 to S25 of the second embodiment.

If all the statements are estimated in step S45, the storage unit 13 stores the result information (step S46). The result information in the fourth embodiment includes the manual grant classification in addition to the classification result in the second embodiment. For example, the storage unit 13 corresponds to the document of ID "D", "The startup is poor. It is the same even if the power is turned off and restarted." As shown in FIG. "HDD", a power supply "x" which is a classification result by machine estimation, an HDD "○", a display "x", and a fan "x" are stored. Further, the storage unit 13 corresponds to the divided sentence "bad start-up" and displays the power supply "x", the HDD "○", the display "x", and the fan "x", which are the classification results by machine estimation. Store. Further, the storage unit 13 corresponds to the divided sentence "It is the same even if the power is turned off and restarted", and the power supply "x", the HDD "x", and the display "x", which are the classification results by machine estimation. "
, Stores the fan "x".

When the result information is stored in step S34, the display unit 14 displays the result information on a display or the like (step S47). For example, as shown in FIG. 12B, the display unit 14 determines that the entire document is likely to belong to the classification of "HDD" by the judgment by machine learning, and the input failure classification ( It is displayed that the manual assignment classification) is "HDD". Further, on the display unit 14, it is determined that the divided sentence "poor start-up" is likely to belong to the category "HDD", and the sentence "even if the power is turned off and started up" is either. Displays that it is highly likely that it does not belong to the classification.

As described above, according to the fourth embodiment, the division unit 15 divides the document into a plurality of sentences as in the second embodiment. Then, the binary classification estimation unit 12 estimates whether or not each of the plurality of sentences corresponds to each classification. Therefore, the user can recognize whether each sentence contained in the document corresponds to each classification. Further, according to the fourth embodiment, as in the third embodiment, the document acquisition unit 11 further acquires the manual assignment classification of the document based on the operation of the user. Then, the display unit 14 displays the classification estimated by the binary classification estimation unit 12 and the manually assigned classification as result information. Therefore, the user can recognize the classification estimated based on the learning data and the manually assigned classification indicating the judgment of the user who acquired the document. Therefore, when the user finally decides the classification to which the document belongs, it is possible to make a comprehensive decision in consideration of both the classification result for each sentence and the manual assignment classification.

[Fifth Embodiment]
Subsequently, the fifth embodiment of the present invention will be described with reference to the drawings.

As shown in FIG. 5, the visualization device 2 according to the fifth embodiment has the document acquisition unit 11, the binary classification estimation unit 12, the storage unit 13, the display unit 14, and the division, as in the fourth embodiment. A unit 15 is provided. Since the constituent blocks are the same as those in the fourth embodiment, the description of the constituent blocks will be omitted.

In the fifth embodiment, the document acquisition unit 11 acquires a plurality of documents and acquires the manual assignment classification corresponding to each document based on the operation of the user. For example, the document acquisition unit 11 acquires a document that "nothing is displayed on the screen even when the power is turned on" and a manual assignment classification of "display". In addition, the document acquisition unit 11 acquires a document that "the operation is very slow and the fan does not make a noise. It may not start up." And a manual assignment classification of "fan". Further, the document acquisition unit 11 acquires a document "The startup is poor. It is the same even if the power is turned off and restarted." And a manual assignment classification "HDD".

In this case, the binary classification estimation unit 12 and the storage unit 13 perform the same processing as in the third embodiment for the document "Nothing is displayed on the screen even when the power is turned on." Further, the division unit 15, the binary classification estimation unit 12, and the storage unit 13 have a document saying "The operation is very slow and there is no fan noise. It may not start up." And "The power is turned off. The same process is performed for the document "It is the same even if it is restarted."

The display unit 14 displays the result information of each document stored by the storage unit 13 on a display or the like. The display unit 14 may combine the result information for each document and transmit it to another information processing device via the communication network.

The visualization method of the visualization device 2 in the fifth embodiment is a combination of the visualization method of the third embodiment and the visualization method of the fourth embodiment. Specifically, the document acquisition unit 11 acquires a plurality of documents and classifications corresponding to the respective documents. When the document contains only one sentence, the visualization device 5 performs the processes of steps S32 to S34 of the third embodiment. Further, when the document contains a plurality of sentences, the visualization device 2 performs the processes of steps S42 to S46 of the fourth embodiment. Then, as shown in FIG. 15, the storage unit 13 stores the result information stored in step S34 and the result information stored in step S46 together.

As described above, according to the fifth embodiment, the document acquisition unit 11 acquires a plurality of documents and the manual grant classification corresponding to each document. Therefore, the user can recognize the classification estimated based on the learning data and the manual assignment classification for each of the plurality of documents. Therefore, when the user finally decides the classification to which a plurality of documents belong, it is possible to make a comprehensive decision in consideration of the classification result of each document and the sentences included in each document and the manual assignment classification.

Further, in the above-described embodiment, each function of the visualization devices 1, 2, 3, 4, and 5 stores a program describing the processing contents for realizing these functions in the storage unit of the computer, and the computer is used. It may be realized by reading and executing this program by the CPU. In addition, the program may be recorded on a recording medium or provided through a network.

Further, in the first embodiment, as shown in FIG. 16, the visualization device 1 may further include a voice recognition unit 16. The voice recognition unit 16 performs voice recognition processing on the voice emitted by the user and converts it into a document. Then, the document acquisition unit 11 acquires the document converted by the voice recognition unit 16 and performs the same processing as described above. This makes it possible to estimate the classification of information represented by voice. The same applies to the second to fifth embodiments.

Although the above embodiments have been described as representative examples, it will be apparent to those skilled in the art that many modifications and substitutions can be made within the spirit and scope of the invention. Therefore, the present invention should not be construed as being limited by the above-described embodiments, and various modifications and modifications can be made without departing from the scope of claims.

1, 2, 3, 4, 5 Visualization device 11 Document acquisition unit 12 2 Value classification estimation unit 13 Storage unit 14 Display unit 15 Division unit 16 Speech recognition unit

Claims (9)

The document acquisition department that acquires documents, and
A division part that divides the document into a plurality of sentences,
A classification estimation unit that estimates the classification results for all of the plurality of predetermined classifications for each of the document and the plurality of sentences.
A display unit that simultaneously displays the document, the plurality of sentences, and the classification result for each of the document and the plurality of sentences.
A visualization device characterized by being equipped with. The document acquisition department that acquires documents, and
A division part that divides the document into a plurality of sentences,
A classification estimation unit that estimates the classification results for all of the plurality of predetermined classifications for each of the document and the plurality of sentences.
A display unit that simultaneously displays the document, the plurality of sentences included in the document, and the classification result for each of the document and the plurality of sentences in association with each other.
A visualization device characterized by being equipped with. The document acquisition department that acquires documents, and
A division part that divides the document into a plurality of sentences,
A classification estimation unit that estimates the classification results for all of the plurality of predetermined classifications for each of the document and the plurality of sentences.
A display unit that simultaneously displays the document, the plurality of sentences, and the classification result for each of the document and the plurality of sentences.
Equipped with
A visualization device, characterized in that the plurality of predetermined classifications are common to the document and the plurality of sentences. The document acquisition department that acquires documents, and
A division part that divides the document into a plurality of sentences,
A classification estimation unit that estimates the classification results for all of the plurality of predetermined classifications for each of the document and the plurality of sentences.
A display unit that simultaneously displays the document, the plurality of sentences included in the document, and the classification result for each of the document and the plurality of sentences in association with each other.
Equipped with
A visualization device, characterized in that the plurality of predetermined classifications are common to the document and the plurality of sentences. The document acquisition department that acquires documents, and
A division part that divides the document into a plurality of sentences,
A classification estimation unit that estimates the classification results for all of the plurality of predetermined classifications for each of the document and the plurality of sentences.
A display unit that simultaneously displays the document, the plurality of sentences, and the classification result for each of the document and the plurality of sentences.
Equipped with
The document acquisition unit further acquires the manual assignment classification for the document, and obtains the manual classification.
The display unit is a visualization device characterized in that the document, the classification result, and the classification result by the manual addition classification are further displayed in association with each other. The document acquisition department that acquires documents, and
A division part that divides the document into a plurality of sentences,
A classification estimation unit that estimates the classification results for all of the plurality of predetermined classifications for each of the document and the plurality of sentences.
A display unit that simultaneously displays the document, the plurality of sentences, and the classification result for each of the document and the plurality of sentences.
Equipped with
The plurality of predetermined classifications are common to the document and the plurality of sentences.
The document acquisition unit further acquires the manual assignment classification for the document, and obtains the manual classification.
The display unit is a visualization device characterized in that the document, the classification result, and the classification result by the manual addition classification are further displayed in association with each other. The document acquisition department that acquires documents, and
A division part that divides the document into a plurality of sentences,
A classification estimation unit that estimates the classification results for all of the plurality of predetermined classifications for each of the document and the plurality of sentences.
A display unit that simultaneously displays the document, the plurality of sentences included in the document, and the classification result for each of the document and the plurality of sentences in association with each other.
Equipped with
The plurality of predetermined classifications are common to the document and the plurality of sentences.
The document acquisition unit further acquires the manual assignment classification for the document, and obtains the manual classification.
The display unit is a visualization device characterized in that the document, the classification result, and the classification result by the manual addition classification are further displayed in association with each other. A visualization method performed by a visualization device that estimates the classification of documents.
Steps to get the document and
The step of dividing the document into multiple sentences,
For each of the document and the plurality of sentences, a step of estimating the classification result for all the plurality of predetermined classifications, and
A step of simultaneously displaying the document, the plurality of sentences, and the classification result for each of the document and the plurality of sentences.
A visualization method characterized by including. A program for operating a computer as the visualization device according to any one of claims 1 to 7.

Images