Determination Device, Determination Method, and Program

Abstract

An assessment device according to an embodiment includes an acquisition unit, a determination unit, an assessment unit, and an update unit. The acquisition unit acquires data of a sentence comprising at least two words. The determination unit determines a verb and an object from words included in the data. The assessment unit refers to group label information indicating whether a word included in a label describing a sentence that is representative of a group that includes one or more sentences having the same meaning is a verb or an object, and assesses to which label a synonym of the determined verb and a synonym of the determined object correspond. When it can be assessed to which label the synonym of the verb and the synonym of the object corresponds, the update unit updates the group label information by associating the sentence and the assessed label.

Description

Technical Field

[0001] Embodiments relate to a determination device, a determination method, and a program.

Background Art

[0002] Generally, information about an event is registered in a sentence, and later, it may be desired to access the event via the sentence in order to understand the content of the event. When a large number of sentences and events are registered in this way, since access to the event is made using the sentence as a key, it is desirable that the registered information and the event match.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, there may be a notation variation in the sentence which is the registered information, and it may not be possible to access the desired event via the sentence.

[0005] Embodiments provide a determination device, a determination method, and a program that can be interpreted as the same sentence even when a plurality of sentences having the same meaning are registered.

Means for Solving the Problems

[0006] The determination device according to the embodiment includes an acquisition unit, a determination unit, a determination section, and an update unit. The acquisition unit acquires data of a sentence consisting of at least two words. The determination unit determines a verb and an object from among the words included in this data. The determination section refers to group label information indicating whether the words included in the label representing the representative sentence of a group including one or more sentences having the same meaning are either a verb or an object, and determines which label the synonym of the determined verb and the synonym of the determined object correspond to. The update unit updates the group label information by associating the sentence with the determined label when it is possible to determine which label the synonym of the verb and the synonym of the object correspond to.

Advantages of the Invention

[0007] The embodiment enables different multiple sentences having the same meaning to be interpretable as the same sentence even when they are registered.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

BEST MODE FOR CARRYING OUT THE INVENTION

[0009] Hereinafter, the determination device, determination method, and program according to the embodiment will be described with reference to the drawings. (Overview) There is a technique for extracting a unique combination of failure events for each failure case from a database in which failure cases of a network are registered so as not to overlap with the registered failure cases, and automatically creating and modifying rules capable of determining a failure factor location as a characteristic failure event.

[0010] In an already operating network, it is necessary to register failure information from past failure history information in order to generate this rule. The failure history information includes, for example, the failure location, the cause of the failure, and the countermeasure method for the failure.

[0011] Even when the same operation is performed for a failure, the sentence expressing the countermeasure method may include writing variations due to differences in the registrants, etc.

[0012] In the present embodiment, as an example of a case where information is registered for an event associated with a sentence and the event may be accessed via the sentence later to understand the content of the event, the countermeasure method included in the network failure history information will be described.

[0013] The following embodiments will detail a method in the case where writing variations occur in a sentence explaining the countermeasure method included in the failure history information as an example. However, the following embodiments are merely examples, and the present application is not applicable only to the countermeasure method included in the network failure history information. The present application is widely applicable to cases where information is registered in association with a sentence for an event and the event is accessed via the sentence later to understand the content of the event.

[0014] (First Embodiment) (Hardware Configuration) An example of the hardware configuration of the similarity determination device (also simply referred to as the determination device) of the present embodiment will be described with reference to FIG. 1.

[0015] The similarity determination device 100 of the present embodiment includes a processor 101, a ROM 102, a RAM 103, an interface 104, a display 105, and a storage 106.

[0016] The processor 101 is a processing device that controls the entire similarity determination device 100. The processor 101 is, for example, a CPU (Central Processing Unit). The processor 101 is not limited to a CPU. Also, an ASIC (Application Specific IC) or the like may be used instead of the CPU. Further, the processor 101 may be not one but two or more.

[0017] The ROM 102 is a read-only storage device. The ROM 102 stores the firmware and various programs necessary for the operation of the similarity determination device 100.

[0018] The RAM 103 is a storage device that can be written to arbitrarily. The RAM 103 is used as a working area for the processor 101 and temporarily stores the firmware and the like stored in the ROM 102.

[0019] The interface 104 is a device for exchanging information with an external device. The interface 104 receives, for example, text data. Also, the interface 104 transmits information to an external server or the like.

[0020] The display 105 is a display device that displays various screens. The display 105 may be a liquid crystal display, an organic EL display, or the like. Also, the display 105 may be provided with a touch panel.

[0021] The storage 106 is a storage device such as a hard disk. The storage 106 stores, for example, various applications executed by the processor 101, data input to the applications, and data obtained by executing the applications.

[0022] (Functional configuration) Next, an example of the functions of the similarity determination device 100 of the present embodiment will be described with reference to FIG. 2. The similarity determination device 100 of this embodiment includes, as functional blocks, a data acquisition unit 201, a part-of-speech determination unit 202, a verb determination unit 203, a synonym frequency DB (hereinafter, the database is abbreviated as DB) 204, an object language determination unit 205, a similarity determination unit 206, a group label DB 207, and an update unit 208. The data acquisition unit 201 is realized by, for example, the interface 104. The part-of-speech determination unit 202, the verb determination unit 203, the object language determination unit 205, the similarity determination unit 206, and the update unit 208 are realized by, for example, the processor 101, the ROM 102, the RAM 103, and the storage 106. The synonym frequency DB 204 and the group label DB 207 are realized by, for example, the storage 106.

[0023] The data acquisition unit 201 receives text data. The text data includes data of a sentence indicating a certain content (hereinafter, the "data of the sentence" may be abbreviated as "sentence"), and includes, for example, a sentence explaining a coping method. The sentence is composed of at least two words and includes a verb and an object.

[0024] The part-of-speech determination unit 202 determines the part of speech of the words included in the sentence acquired by the data acquisition unit 201. The part-of-speech determination unit 202 performs syntactic analysis (for example, morphological analysis) on the sentence. The part-of-speech determination unit 202 decomposes the sentence into the smallest meaningful words by morphological analysis. The part-of-speech determination unit 202 determines whether each word is a noun or not. Note that the part-of-speech determination unit 202 may determine whether each word is a verb or not, or may determine whether each word is a verb, a noun, or another part of speech (for example, an adjective or a particle).

[0025] The synonym frequency DB 204 includes synonym frequency information indicating the frequency of use for each synonym. The synonym frequency DB 204 includes, as the synonym frequency information, for example, a synonym of a verb, a synonym of an object, a first frequency assigned to each synonym, and a second frequency. The first frequency includes the frequency of a certain synonym used as a verb and the frequency of the same synonym used as an object. The second frequency is the sum of the first frequencies of the synonyms included in a group of one or more words that form a synonym (referred to as a synonym group) for each synonym group. The second frequency includes the sum of the first frequencies of the verbs when the synonym is used as a verb (also referred to as the second frequency of the verb) and the sum of the first frequencies of the objects when the synonym is used as an object (also referred to as the second frequency of the object). The synonym frequency DB 204 may be prepared in advance, or may be one that has been modified by the method described in the second embodiment for a pre-prepared one. Also, the synonym frequency DB 204 may initially have nothing registered and may be registered by the method described in the second embodiment.

[0026] The verb determination unit 203 determines a verb from among the words included in a sentence. When there is only one word determined to be a verb by morphological analysis by the part-of-speech determination unit 202, the verb determination unit 203 determines this word as the verb. When all words are determined not to be verbs by syntactic analysis by the part-of-speech determination unit 202, or when two or more words are determined to be verbs, the verb determination unit 203 determines a verb as follows. The verb determination unit 203 refers to the synonym frequency DB 204 and calculates the second frequency of the synonym group to which each word belongs for each word. Then, the verb determination unit 203 determines the word with the largest second frequency among these second frequencies, which is the second frequency of the verb, as the verb.

[0027] The object determination unit 205 determines an object from among the words included in a sentence. When a certain word is determined to be a verb by the part-of-speech determination unit 202, the object determination unit 205 performs syntactic analysis on the sentence and determines the word that becomes the object from the remaining words.

[0028] When it is determined by morphological analysis by the verb determination unit 203 that one word is a verb and it is determined by the part-of-speech determination unit 202 that two or more words are nouns, the object determination unit 205 may determine the object as follows. The object determination unit 205 refers to the synonym frequency DB 204 and calculates the second frequency of the synonym group to which each word belongs for each word. Then, the object determination unit 205 determines that the word with the largest second frequency among these second frequencies is the object.

[0029] The group label DB 207 includes group label information that associates a label representing a sentence (referred to as a sentence group) including one or more sentences having the same meaning with one or more sentences having the same meaning. The group label DB 207 includes, as group label information, for example, this label, an object label that is the object included in this label, a verb label that is the verb included in this label, one or more sentences having the same meaning included in the sentence group of this label, the verb included in this sentence, and the object included in this sentence. One or more sentences having the same meaning included in the sentence group are one or more sentences included in the one or more text data acquired by the data acquisition unit 201.

[0030] The similarity determination unit 206 determines which label included in the group label DB 207 the synonym of the verb determined by the verb determination unit 203 corresponds to. Further, the similarity determination unit 206 determines which label included in the group label DB 207 the synonym of the object determined by the object determination unit 205 corresponds to. The similarity determination unit 206 selects the number of verb labels that match the verb label included in the group label DB 207 that the synonym of the verb determined by the verb determination unit 203 matches. Then, the similarity determination unit 206 selects the number of object labels that match the object label included in the group label DB 207 that the synonym of the object determined by the object determination unit 205 matches.

[0031] After that, the similarity determination unit 206 refers to the verb label selected as a match and the object label selected as a match, and searches for the verb label and the object label associated with the same label. The similarity determination unit 206 extracts by associating the verb label and the object label associated with the same label, this label, the sentence acquired by the data acquisition unit 201, the object of the sentence, and the verb of the sentence. This same label is not necessarily one, and there may be a plurality of them, but the similarity determination unit 206 extracts all the same labels. Also, when there is no same label, the similarity determination unit 206 may perform processing to indicate that fact (details are described in the second embodiment).

[0032] The update unit 208 associates the sentence included in the text data acquired by the data acquisition unit 201 with the label determined by the similarity determination unit 206, and updates the group label DB 207. For example, the update unit 208 associates a sentence, the verb determined by the verb determination unit 203, the object determined by the object determination unit 205, and the label determined by the similarity determination unit 206 to correspond to the synonyms of these verbs and the synonyms of the objects. When the associated information is not included in the group label DB 207, the update unit 208 adds the associated information to the group label DB 207. Note that the update unit 208 may update the group label DB 207 including not only the label but also the verb label and the object label. Furthermore, when the update unit 208 newly adds the sentence included in the text data acquired by the data acquisition unit 201 to the group label DB 207, since the words (verbs and objects) included in this sentence are in the word list of the synonym frequency DB 204, the update unit 208 increments the appearance count of those words by that amount and updates the synonym frequency DB 204.

[0033] (Similarity determination process) Next, the processing steps for the similarity determination device 100 to determine similarity will be described with reference to FIG. 3.

[0034] In step S301, the data acquisition unit 201 acquires text data including a sentence.

[0035] In step S302, the part-of-speech determination unit 202 performs morphological analysis on the sentence.

[0036] In step S303, the part-of-speech determination unit 202 determines whether there is one verb among the words included in the sentence. If the part-of-speech determination unit 202 determines that there is one verb included in the text data, the process proceeds to step S305. If the part-of-speech determination unit 202 determines that there is not one verb included in the text data, the process proceeds to step S304.

[0037] In step S304, the verb determination unit 203 determines the verb included in the sentence. If the verb determination unit 203 determines that no verb is included in the sentence, it may stop the similarity determination process and accept other text data. The verb determination unit 203 may also determine the verb by referring to the synonym frequency DB204.

[0038] In step S305, the object determination unit 205 determines the object from among the words other than the verb included in the sentence. The object determination unit 205 may also determine the verb by referring to the synonym frequency DB204.

[0039] In step S306, the similarity determination unit 206 extracts synonyms of the verb determined by the verb determination unit 203 from the synonym frequency DB204, and determines whether any of the extracted synonyms match any of the verb labels included in the group label DB207.

[0040] In step S307, the similarity determination unit 206 extracts synonyms of the object determined by the object determination unit 205 from the synonym frequency DB204, and determines whether any of the extracted synonyms match any of the object labels included in the group label DB207. Note that since the results obtained are the same regardless of whether step S306 or step S307 is executed first, either step can be executed first.

[0041] In step S308, the similarity determination unit 206 determines whether there is a set in which the synonym of the verb matches the verb label and a set in which the synonym of the object matches the object label in steps S306 and S307. If there is a matching set for the verb and the object, the similarity determination unit 206 proceeds to step S309; if there is no matching set for the verb or the object, the similarity determination unit 206 proceeds to step S310.

[0042] In step S309, the update unit 208 associates (determines as existing labels) the sentences included in the text data acquired by the data acquisition unit 201 with the existing verb label, the existing object label, and the existing labels including these labels. The update unit 208 may also associate the verb and the object with the labels together with the sentences included in the text data.

[0043] In step S310, since there is no verb label or object label (or both labels) that can be associated with the sentences included in the text data, the update unit 208 determines it as a new label and records the information of the sentences included in the text data. An example of a variation of the operation prior to this step is described in the second embodiment.

[0044] In step S311, when proceeding from step S309, the update unit 208 records, in the group label DB 207 (countermeasure method DB), the information in which the sentences included in the text data acquired by the data acquisition unit 201 are associated with the existing labels, and updates the group label DB 207.

[0045] In step S311, when proceeding from step S310, the update unit 208 records, in the group label DB 207, as new information, the information of the sentences included in the text data acquired by the data acquisition unit 201, and updates the group label DB 207. In step S311, when the group label DB207 is updated, the update unit 208 newly adds the sentences included in the text data acquired by the data acquisition unit 201 to the group label DB207. Since the words (verbs and objects) included in these sentences are in the word list of the synonym frequency DB204, the update unit 208 increments the synonym frequency DB204 by the number of occurrences of those words. For example, when a verb in the synonym frequency DB204 newly appears once, the update unit 208 increments the occurrence count of this verb by one. As a result, in the synonym frequency DB204, the total number of occurrences of the synonym group to which this word belongs is incremented by the incremented number. In the synonym frequency DB204, the total number of occurrences of the verb or the object is incremented according to whether the word is a verb or an object, respectively.

[0046] (Group label DB207) An example of the information included in the group label DB207 will be described with reference to FIG. 4. Three types are illustrated, including "device replacement" as a label. In this example, the label indicates a method for dealing with network failures. For each label, one object label (displayed as label O) and one verb label (displayed as label V) are associated. For each label, one sentence (original text) included in the text data is associated. Since the sentence may include variations, multiple sentences can be associated with the same label. In the example of FIG. 4, for one type of "card replacement" as a label, two types, namely the original text "card replacement" and the original text "card exchange", are associated. In this example, although they have the same meaning, it shows that there are variations in the two notations of "card replacement" and "card exchange". In other words, either "card replacement" or "card exchange" can be converted into the same expression of "card replacement". That is, if the group label DB207 is used, the variation in notation can be absorbed.

[0047] (Synonym frequency DB204) An example of the information included in the synonym frequency DB 204 will be described with reference to FIG. 5.

[0048] In the synonym frequency DB 204, a list of words that are synonyms is grouped. In FIG. 5, the words that are grouped synonyms are described in the same column. For each word that is a synonym, the frequency indicating whether this word was used as a verb and the frequency indicating whether it was used as an object are described. In the example of FIG. 5, as the frequency, the number of times the word appeared as a verb and the number of times the word appeared as an object in a certain period are adopted. For example, "replacement: 1: 0" (VO appearance count) in FIG. 5 indicates that "replacement" appeared 1 time as a verb and 0 times as an object. Note that this frequency (the first frequency) may be a numerical value corresponding to the probability that the word is used as a verb or an object, and is not limited to the number of appearances.

[0049] For each group of one or more words that are synonyms, the frequency indicating whether the words included in the group were used as a verb and the frequency indicating whether they were used as an object are described. In the example of FIG. 5, as the frequency, the total number of times the words included in the group appeared as a verb and the total number of times the words included in the group appeared as an object are adopted. For example, "3,0" (total VO appearance count) in the second row and second column of FIG. 5 indicates that the group including the words "replacement", "substitute", and "exchange" that are synonyms appeared 3 times as a verb and 0 times as an object. Note that this frequency (the second frequency) may be a numerical value corresponding to the probability that any of the words included in the group is used, and is not limited to the total number of appearances of the words included in the group.

[0050] Also, the data whose frequency is determined according to the content of the target text data may be changed. The content of the synonym frequency DB 204 may be changed according to the content of the target text data. For example, the content of the synonym frequency DB 204 may be changed depending on the type of network.

[0051] Next, three sentences included in the text data acquired by the data acquisition unit 201 are shown, and examples are specifically described for each sentence. Note that each sentence indicates a method for dealing with network failures.

[0052] <Example 1> Example 1 is the case where the data acquisition unit 201 acquires a sentence indicating a coping method of "device replacement".

[0053] In step S302, the part-of-speech determination unit 202 performs morphological analysis on "device replacement" and determines that "device" is a noun and "replacement" is a noun. In this example, it is unclear whether "device" and "replacement" are verbs, and it is also unclear whether there is one verb, so the process proceeds to step S304.

[0054] In step S304, the verb determination unit 203 refers to the synonym frequency DB204. The synonym frequency DB204 of Example 1 is shown in FIG. 6. The verb determination unit 203 refers to the synonym frequency DB204 in FIG. 6 and confirms that the synonym group to which "device" belongs has a verb frequency (the second frequency) of 0, and the synonym group to which "replacement" belongs has a verb frequency of 2. As a result, the verb determination unit 203 determines that the "replacement" with a higher frequency is a verb.

[0055] In step S305, the object determination unit 205 determines the object for "replacement" that has already been determined as a verb. In this example, the object determination unit 205 confirms that there is only "device" among the words other than "replacement", and determines that "device" is the object through syntactic analysis.

[0056] In step S306, the similarity determination unit 206 selects, from among the words ("replacement", "substitution", "exchange") included in the synonym group to which the "exchange" determined as a verb belongs, those that match the verb label in the group label DB207 shown in FIG. 7. In this example, the similarity determination unit 206 determines that the "substitution" and "replacement" shown in the thick frame in FIG. 7 are the words that match the verb label.

[0057] In step S307, the similarity determination unit 206 selects, from among the words ("device", "apparatus") included in the synonym group to which the determined target word "device" belongs, the one that matches the target word label in the group label DB207 shown in FIG. 7. In this example, the similarity determination unit 206 determines that the "device" shown in the thick frame in FIG. 7 is the word that matches the target word label.

[0058] In step S308, the similarity determination unit 206 searches the group label DB207 for a label in which "replacement" and "replace" are verb labels and "device" is the target word label. In this example, since the label "device replacement" shown in FIG. 7 has the target word label "device" and the verb label "replacement", the similarity determination unit 206 determines that "device replacement" is the label for the countermeasure method "device exchange". In this example, since there is a matching pair for the verb and the target word, the process proceeds to step S309.

[0059] In step S309, the update unit 208 associates (determined as an existing label) the existing verb label "replacement", the existing target word label "device", and the existing label "device replacement" including these labels with the sentence "device exchange" included in the text data acquired by the data acquisition unit 201.

[0060] In step S311, the update unit 208 adds to the group label DB207 the information associating the label "device replacement", the label O "device", the label V "replacement", and the sentence (original text) "device exchange" in this example in step S309, as described by the underlined and bold text in the bottom row of FIG. 8. Note that based on this meaning, the group label DB207 is also referred to as the countermeasure method DB. Furthermore, in step S311, the update unit 208 reflects the object word "device" and the verb "replace" included in "device replacement" of the sentence (original text) added to the group label DB 207 in the synonym frequency DB 204. The update unit 208 increments the number of occurrences of each of the object word "device" and the verb "replace" by one. The update unit 208 increments the number of occurrences and the total number of occurrences as shown by the underlined and bold numbers in FIG. 9. That is, as shown in FIG. 9, the VO occurrence number is incremented from the VO occurrence numbers shown in FIG. 6 as "replacement: 1:0", "device 0:2", and the total number of VO occurrences is incremented from the total number of VO occurrences shown in FIG. 6 as "3,0", "0,4".

[0061] <Example 2> Example 2 is a case where the data acquisition unit 201 acquires a sentence indicating a countermeasure method of "device replacement".

[0062] In step S302, the part-of-speech determination unit 202 performs morphological analysis on "device replacement" and determines that "device" is a noun and "replacement" is a noun. In this example, it is unclear whether "device" and "replacement" are verbs, and it is unclear whether there is one verb, so the process proceeds to step S304.

[0063] In step S304, the verb determination unit 203 refers to the synonym frequency DB 204. The synonym frequency DB 204 of Example 2 is shown in FIG. 10. The verb determination unit 203 refers to the synonym frequency DB 204 in FIG. 10 and confirms that there is no synonym group to which "device" belongs, and the frequency of the synonym group to which "replacement" belongs is 2. As a result, the verb determination unit 203 determines that "replacement" with an existing frequency is a verb.

[0064] In step S305, the object word determination unit 205 determines the object word for "replacement" that has already been determined as a verb. In this example, the object word determination unit 205 confirms that the only word other than "replacement" is "device", and determines that "device" is the object word through syntactic analysis.

[0065] In step S306, the similarity determination unit 206 selects, from among the words ("replacement", "substitute", "exchange") included in the synonym group to which the verb "exchange" determined to belong, those that match the verb label in the group label DB207 shown in FIG. 11. In this example, the similarity determination unit 206 determines that "substitute" and "replacement" shown in the thick frame in FIG. 11 are the words that match the verb label.

[0066] In step S307, the similarity determination unit 206 confirms that there is no synonym group to which the object "device" determined to belong belongs.

[0067] In step S308, the similarity determination unit 206 searches the group label DB207 for a label in which "substitute" and "replacement" are verb labels and "device" is an object label. In this example, since there is no synonym group to which the object "device" determined to belong belongs, for "device replacement" acquired by the data acquisition unit 201, there is no matching pair with respect to the verb and the object, so the process proceeds to step S310.

[0068] In step S310, since there is no label that can be associated with the sentence included in the text data, the update unit 208 determines it as a new label and records the information of the sentence included in the text data. Note that the operations prior to this step are described in the second embodiment.

[0069] <Example 3> Example 3 is a case where the data acquisition unit 201 acquires a sentence indicating a countermeasure method of "replaced the device and confirmed the recovery".

[0070] In step S302, the part-of-speech determination unit 202 performs morphological analysis on "replaced the device and confirmed the recovery" and determines that "device" is a noun, "replacement" is a verb, "recovery" is a noun, and "confirmed" is a verb. In this example, since there are two verbs, the process proceeds to step S304.

[0071] In step S304, the verb determination unit 203 refers to the synonym frequency DB204. The synonym frequency DB204 of the third embodiment is shown in FIG. 12. The verb determination unit 203 refers to the synonym frequency DB204 in FIG. 12 and confirms that the synonym group to which "replacement" belongs has a verb frequency (second frequency) of 2, and that the synonym group to which "confirmed" belongs does not exist. As a result, the verb determination unit 203 determines that the frequent "replacement" is a verb.

[0072] In step S305, the object determination unit 205 determines the object for "replacement" that has already been determined as a verb. In this example, the object determination unit 205 determines by syntactic analysis that the object of "replacement" is "device".

[0073] In step S306, the similarity determination unit 206 selects, from among the words ("replacement", "substitute", "exchange") included in the synonym group to which the verb "replacement" belongs, those that match the verb label in the group label DB207 shown in FIG. 13. In this example, the similarity determination unit 206 determines that the words "substitute" and "replacement" shown in the thick frame in FIG. 13 are the words that match the verb label.

[0074] In step S307, the similarity determination unit 206 selects, from among the words ("device", "equipment") included in the synonym group to which the object "device" belongs, those that match the object label in the group label DB207 shown in FIG. 13. In this example, the similarity determination unit 206 determines that the word "device" shown in the thick frame in FIG. 13 is the word that matches the object label.

[0075] In step S308, the similarity determination unit 206 searches the group label DB207 for a label where "replacement" or "replace" is a verb label and "device" is an object label. In this example, since the label "device replacement" shown in FIG. 13 has an object label of "device" and a verb label of "replacement", the similarity determination unit 206 determines that "device replacement" is a label for the countermeasure method of "replaced the device and confirmed the recovery". In this example, since there is a matching pair for the verb and the object, the process proceeds to step S309.

[0076] In step S309, the update unit 208 associates the existing verb label "replacement", the existing object label "device", and the existing label "device replacement" that includes these labels with the sentence "replaced the device and confirmed the recovery" included in the text data acquired by the data acquisition unit 201 (determined as an existing label).

[0077] In step S311, the update unit 208 adds to the group label DB207 the information associating the label "device replacement", the label O "device", the label V "replacement", and the sentence (original text) "replaced the device and confirmed the recovery" in this example in step S309, as described in the underlined and bold text in the bottom row of FIG. 14. Furthermore, in step S311, the update unit 208 reflects the object "device" and the verb "replacement" included in the sentence (original text) "replaced the device and confirmed the recovery" added to the group label DB207 in the synonym frequency DB204. The update unit 208 increments the number of occurrences of each of the object "device" and the verb "replacement" by one. The update unit 208 increments the number of occurrences and the total number of occurrences as shown by the underlined and bold numbers in FIG. 15. That is, as shown in FIG. 15, the VO occurrence numbers of "replacement: 2:0" and "device 0:2" are incremented from the VO occurrence numbers shown in FIG. 12, and the total VO occurrence numbers of each are incremented from the total VO occurrence numbers shown in FIG. 12, which are "3,0" and "0,4".

[0078] The similarity determination device according to the first embodiment described above can extract the label corresponding to a sentence and interpret it as the same sentence corresponding to the label based on the synonym frequency information and the group label information using the verb and the object included in the sentence as keys, even if there are a plurality of different sentences having the same meaning, and can access accurate information. Further, according to the present embodiment, by determining the label corresponding to a sentence, it is possible to automatically update the group label information and the synonym frequency information, and improve the database including the group label information and the synonym frequency information to increase the accuracy.

[0079] According to the present embodiment, for example, even if there are variations in the notation in a sentence describing a coping method recorded when coping with a failure, it is possible to convert this sentence into the same sentence. Therefore, according to the present embodiment, even if there are variations in the notation in a sentence describing a coping method, it is possible to access the desired information regarding the coping method. As a result, according to the present embodiment, it is possible to eliminate the variations in the notation and automatically update the database describing the coping method (and the synonym frequency information) to improve the accuracy of the coping method.

[0080] (Second Embodiment) (Functional Configuration) An example of the functional configuration of the similarity determination device 1600 according to the second embodiment will be described with reference to FIG. 16. Note that the hardware configuration of the similarity determination device 1600 is the same as that of the similarity determination device 100 of the first embodiment, and thus the description thereof is omitted.

[0081] The similarity determination device 1600 of the present embodiment further includes, as functional blocks, a determination result presentation unit 1602 and an update input unit 1603 in addition to the similarity determination device 100 of the first embodiment. However, the update unit 208 of the first embodiment is changed to an update unit 1601. Among the other blocks, the blocks assigned the same numbers as the blocks in the first embodiment are basically described as having the same configuration and operation, and thus the description thereof is omitted.

[0082] The update unit 1601 is realized by, for example, the processor 101, the ROM 102, the RAM 103, and the storage 106. The determination result presentation unit 1602 is realized by, for example, the processor 101 and the display 105. The update input unit 1603 is realized by, for example, the interface 104.

[0083] In addition to the operations of the update unit 208 in the first embodiment, the update unit 1601 includes the following functions. The update unit 1601 sends the information of the updated group label DB 207 and new information not included in the group label DB 207 (for example, a sentence corresponding to a new countermeasure method) to the determination result presentation unit 1602. Further, the update unit 1601 sends the existing label determined by the similarity determination unit 206 in which the verb label and the object label are associated with the same label, and the sentence acquired by the data acquisition unit 201, to the determination result presentation unit 1602.

[0084] Based on the content presented by the determination result presentation unit 1602, the update unit 1601 accepts the provision of determination information from outside the device (for example, a user or a recognition device), or other information from outside the device. The update unit 1601 acquires these determination information, etc. (determination information and other information), and based on these information, etc., associates the sentence acquired by the data acquisition unit 201 with the label registered in the group label DB 207 and registers it in the group label DB 207. The determination information, etc. includes information on whether the known label determined by the similarity determination unit 206 matches the sentence acquired by the data acquisition unit 201. Further, when the known label does not match this sentence, the determination information, etc. includes information specifying the label that matches this sentence. The case where the known label does not match this sentence is the case where the similarity determination unit 206 determines that the object label or verb label corresponding to at least one synonym of the object or verb included in the sentence is not in the group label DB 207.

[0085] Furthermore, when the verb or object contained in the sentence is not registered in the synonym frequency DB 204 based on the determination information or the like, the update unit 1601 adds this verb or object to the corresponding synonym group and updates the synonym frequency DB 204. In this case, the determination information or the like includes information specifying the label included in the group label DB 207 corresponding to the sentence acquired by the data acquisition unit 201. Separately from this, when there is no label corresponding to the sentence acquired by the data acquisition unit 201 in the labels included in the group label DB 207, the determination information or the like includes information indicating that the label is not registered and information specifying the label to be newly registered. Furthermore, the update unit 1601 adds a verb or object that is not registered in the synonym frequency DB 204 included in the sentence corresponding to the specified label to the synonym group and updates the synonym frequency DB 204.

[0086] The update unit 1601 sets the first frequency (VO appearance count) corresponding to the added verb or object to a predetermined value (for example, 1), and increments the second frequency (total VO appearance count) corresponding to the added verb or object by a predetermined value (for example, 1).

[0087] The determination result presentation unit 1602 presents the information received from the update unit 1601 to the outside of the similarity determination device 1600 (for example, a user or a recognition device). This recognition device is a device capable of recognizing the information presented by the determination result presentation unit 1602.

[0088] The update input unit 1603 receives the information presented by the determination result presentation unit 1602, and an external device or the like (for example, a user, or a recognition device and a determination device) makes a determination, accepts new information to be registered in the synonym frequency DB 204 or the group label DB 207, and sends this new information to the update unit 1601. This determination device is a device capable of determining the information to be sent to the update input unit 1603 based on the information recognized by the recognition device. Also, when the update input unit 1603 receives the information presented by the determination result presentation unit 1602 and an external device or the like determines that this information remains unchanged, since there is no new information, the update input unit 1603 sends the information indicating no change to the update unit 1601.

[0089] (Similarity determination process) Next, the processing steps for the similarity determination device 1600 to determine similarity will be described with reference to FIG. 17. Note that, among the steps, the steps with the same numbers as those in the first embodiment are basically the same in operation, and thus the description thereof will be omitted.

[0090] In step S1701, when proceeding from step S309, the determination result presentation unit 1602 presents information associating the sentences included in the text data acquired by the data acquisition unit 201 with the existing verb label, the existing object label, and the existing labels including these labels.

[0091] In step S1701, when proceeding from step S310, the determination result presentation unit 1602 presents the information of the sentence included in the text data acquired by the data acquisition unit 201, the information indicating that this sentence corresponds to a new label, and the information included in the group label DB207.

[0092] In step S1702, the update input unit 1603 receives the content judged by an external device or the like or the information based on the judgment based on the information presented by the judgment result presentation unit 1602. In step S1702, when passing through step S309 and the information received by the update input unit 1603 indicates that the information associating the existing label and the sentence is correct, the update unit 1601 determines that the existing label and the sentence "match" and proceeds to step S1704. When the information indicates that this associated information is incorrect, it determines that they "do not match" and proceeds to step S1703. Further, in step S1702, when the information received by the update input unit 1603 is such that the sentence corresponds to a new label (when passing through step S310), the update unit 1601 determines that they "do not match" and proceeds to step S1703. Note that when passing through step S310, it is possible that the label corresponding to the sentence exists in the group label DB207 or does not exist.

[0093] In step S1703, the update unit 1601 adds at least one of the verbs or objects of synonyms that are not registered in the synonym frequency DB 204 and are included in the sentence corresponding to the designated label received from the update input unit 1603 to the synonym group of the synonym frequency DB 204.

[0094] In step S1704, when only step S1702 is passed through, the update unit 1601 registers, in the group label DB 207 (countermeasure method DB), information associating the sentences included in the text data acquired by the data acquisition unit 201 with the existing verb label, the existing object label, and the existing labels including these labels, and updates the group label DB 207.

[0095] In step S1704, when step S1703 is passed through, the update unit 1601 registers, in the group label DB 207 (countermeasure method DB), information associating the new label, the verb label and object label included in this new label, and the sentences included in the text data acquired by the data acquisition unit 201, and updates the group label DB 207. Note that in step S1704, when the group label DB 207 is updated, the update unit 1601 newly adds the sentences included in the text data acquired by the data acquisition unit 201 to the group label DB 207. Since the words (verbs and objects) included in these sentences are in the word list of the synonym frequency DB 204, the update unit 1601 increments the synonym frequency DB 204 by the number of occurrences of those words. For example, when a verb existing in the synonym frequency DB 204 newly appears once, the update unit 1601 increments the number of occurrences of this verb by one. As a result, in the synonym frequency DB 204, the total number of occurrences of the synonym group to which this word belongs is also incremented by the incremented number. In the synonym frequency DB 204, the total number of occurrences of the verb or object is incremented according to whether the word is a verb or an object.

[0096] <Example 2> The continuation of Example 2 described in the first embodiment will be described below in accordance with the description of the second embodiment described above. Example 2 is a case where the data acquisition unit 201 acquires a sentence indicating a coping method of "device replacement".

[0097] In step S1701, the determination result presentation unit 1602 presents information indicating that there is no label (target language label) corresponding to the sentence "device replacement" acquired by the data acquisition unit 201 in the group label DB207 which is a coping method DB, (new coping method), and the current information included in the group label DB207.

[0098] In step S1702, the update input unit 1603 receives information corresponding to the existing label "device replacement" registered in the group label DB207. Also in step S1702, since the sentence corresponds to a new label (when passing through step S310), the update unit 1601 determines that the information received by the update input unit 1603 does not "match" and proceeds to step S1703.

[0099] In step S1703, as shown in the synonym frequency DB204 of FIG. 18, the update unit 1601 adds the target language of the synonym not registered in the synonym frequency DB204 included in the sentence corresponding to the designated label "device replacement" received from the update input unit 1603 to the synonym group and updates the synonym frequency DB204. Further, the update unit 1601 sets the first frequency (VO appearance times) corresponding to the added target language "device" to 1 which is a predetermined value, and increments the second frequency (total number of VO appearances) corresponding to the added target language by 1 which is a predetermined value. As a result, as shown in FIG. 18, "device:0:1" (the bold underlined part in FIG. 18) is added, the "total number of VO appearances" is changed to "0,2", and the synonym frequency DB204 is updated.

[0100] In step S1704, as shown in the bold underlined part of FIG. 19, the update unit 1601 registers, in the group label DB207 (countermeasure method DB), information associating the label “device replacement” to be newly registered, the object label “device” and the verb label “replacement” included in this label, and the sentence “device exchange” included in the text data acquired by the data acquisition unit 201, and updates the group label DB207.

[0101] The similarity determination device according to the second embodiment described above has the same effects as the first embodiment. Further, even when the determination cannot be made by the determination device of the first embodiment, the verb or object included in the sentence is registered in the synonym frequency DB as a synonym of the verb label or object label of the label corresponding to the sentence, and by adding a new label to the group label information, it becomes possible to extract the label corresponding to the sentence and interpret it as the same sentence corresponding to the label, and to access accurate information. Also, according to the present embodiment, even when the determination cannot be made by the determination device of the first embodiment, it becomes possible to determine the label corresponding to the sentence, and it becomes possible to automatically update the group label information and improve the database including the group label information to increase the accuracy.

[0102] (Modification example) <Verb determination, object determination> After the object determination unit 205 determines the object, the verb determination unit 203 may determine the verb. The object determination unit 205 determines the object from among the words included in the sentence. When the part-of-speech determination unit 202 determines that a certain word is a verb and there is only one remaining word, the object determination unit 205 determines this word as the object. When the part-of-speech determination unit 202 determines that two or more words are nouns by morphological analysis by the part-of-speech determination unit 202, the object determination unit 205 determines the object as follows. The object determination unit 205 refers to the synonym frequency DB204 and calculates the second frequency of the synonym group to which each word belongs for each word. Then, the object determination unit 205 determines, as the object, the word with the largest second frequency among these second frequencies.

[0103] After that, the verb determination unit 203 determines a verb from among the words included in the sentence. When there is only one word determined by the morphological analysis by the part-of-speech determination unit 202 not to be a noun, the verb determination unit 203 determines this word as the verb. Further, when a certain word is determined to be an object by the part-of-speech determination unit 202, the verb determination unit 203 may perform syntactic analysis on the sentence and determine a verb word from the remaining words.

[0104] <Label addition> The update input unit 1603 may receive a label that can be included in the group label DB 207, and the update unit 1601 may add this label to the group label DB 207. For example, when neither the verb label nor the object label corresponding to the sentence acquired by the data acquisition unit 201 is in the group label DB 207, the update unit 1601 may add the new label received by the update input unit 1603 to the group label DB 207. <Label modification> The determination result presentation unit 1602 may present the content of the group label DB 207, the update input unit 1603 may receive a modification to this content, and the update unit 1601 may be able to modify the content of the group label DB 207.

[0105] <Syntactic analysis> The syntactic analysis used by the part-of-speech determination unit 202 or the object determination unit 205 includes, but is not limited to, morphological analysis. The syntactic analysis may use a structural grammar or a lexical functional grammar. Further, the syntactic analysis may use a statistical method. The statistical method is used for syntactic analysis, for example, using training data specialized for a specific term field. The same syntactic analysis as this is also used when the verb determination unit 203 performs syntactic analysis.

[0106] <Synonym frequency DB 204> The failure may be classified into a plurality of categories, and there may be a synonym frequency DB specific to each category for each category.

[0107] <Synonym frequency DB 204, group label DB 207> At least one of the synonym frequency DB 204 or the group label DB 207 may not be included in the similarity determination devices 100 and 1600 and may be external to this device. For example, at least one of the synonym frequency DB 204 or the group label DB 207 may be included in an external server or the like. In this case, the similarity determination devices 100 and 1600 exchange information with at least one of the synonym frequency DB 204 or the group label DB 207 via the interface 104.

[0108] The devices of the embodiment can also be realized by a computer and a program, and it is also possible to record the program on a recording medium (or storage medium) or provide it via a network. In addition, each of the above devices and their device parts can be implemented in any of a hardware configuration or a combination configuration of hardware resources and software. As the software of the combination configuration, it is installed in a computer in advance from a network or a computer-readable recording medium (or storage medium) and executed by the processor of the computer, and a program for realizing the operations (or functions) of each device in the computer is used.

[0109] Note that the present invention is not limited to the above embodiments, and various modifications can be made without departing from the gist thereof at the implementation stage. Also, the respective embodiments may be implemented in appropriate combination, and in that case, the combined effects can be obtained. Furthermore, the above embodiments include various inventions, and various inventions can be extracted by combinations selected from a plurality of disclosed constituent elements. For example, even if some constituent elements are deleted from all the constituent elements shown in the embodiments, if the problem can be solved and the effects can be obtained, the configuration from which these constituent elements are deleted can be extracted as an invention.

Explanation of Reference Numerals

[0110] 100... Similarity determination device 101... Processor 102... ROM 103…RAM 104…Interface 105…Display 106…Storage 201…Data acquisition unit 202…Part-of-speech determination unit 203…Verb determination unit 204…Synonym frequency DB 205…Object determination unit 206…Similarity determination unit 207…Group label DB 208…Update unit 1600…Similarity determination device 1601…Update unit 1602…Judgment result presentation unit 1603…Update input unit

Claims

1. An acquisition unit that acquires data of a sentence consisting of at least two words; A determination unit that determines a verb and an object from among the words included in the data; A determination unit that refers to group label information indicating whether a word included in a label representing a sentence that is a representative of a group including one or more sentences having the same meaning is either a verb or an object, and determines which label the synonym of the determined verb and the synonym of the determined object correspond to; An update unit that, when it is possible to determine which label the synonym of the verb and the synonym of the object correspond to, associates the sentence and the determined label and updates the group label information; Comprising: The determination unit refers to synonym frequency information including a first frequency of a verb indicating the frequency of use of a word as a verb for each synonym, a first frequency of an object indicating the frequency of use of a word as an object for each synonym, a second frequency of a verb indicating the sum of the first frequencies of the verb for each group of one or more words that are synonyms, and a second frequency of an object indicating the sum of the first frequencies of the object for each group of the words, and determines the verb and the object from among the words included in the data based on either one or more of the second frequency of the verb or the second frequency of the object. A determination device.

2. A presentation unit that presents the sentence data and the group label information when it is not possible to determine which label at least one of the synonyms of the verb or the synonyms of the object corresponds to; An input unit that accepts a label that matches the sentence when the label that matches the sentence is in the group label information, and accepts a new label that matches the sentence when the label that matches the sentence is not in the group label information; Further comprising: The update unit registers the verb or the object corresponding to the label that matches the sentence as a synonym of the verb or the object of the label that matches the sentence, and newly registers the matching label, the sentence, the verb, and the object in the group label information in association with each other. The determination device according to claim 1.

3. The determination unit according to claim 1, wherein when a word included in the data is included in the group, the determination unit determines which of the two words is a verb or an object by comparing the second frequency of the verb and the second frequency of the object of each of the two words. The determination device described.

4. The determination unit refers to the group label information including the two words, the verb included in the two words, the object included in the two words, the label associated with the two words, the verb label that is the verb included in the label, and the object label that is the object included in the label, and determines which verb label and which object label included in the group label information the synonyms of the words included in the synonym frequency information corresponding to the determined verb and the synonyms of the words included in the synonym frequency information corresponding to the determined object correspond to. The determination device according to claim 1 or 3.

5. When the update unit can determine which label the verb and the object correspond to, the update unit associates the determined verb with the verb label determined to correspond, associates the determined object with the object label determined to correspond, and associates the label including the determined verb label and the determined object label with the sentence. The determination device according to claim 4.

6. The acquisition unit acquires data of a sentence consisting of at least two words, the determination unit determines a verb and an object from among the words included in the data, the determination unit refers to group label information indicating whether the words included in the label representing the representative sentence of a group including one or more sentences having the same meaning are either a verb or an object, and determines which label the synonyms of the determined verb and the synonyms of the determined object correspond to, when the update unit can determine which label the synonyms of the verb and the object correspond to, the update unit associates the sentence and the determined label and updates the group label information, comprising The determination unit refers to synonym frequency information including the first frequency of the verb indicating the frequency of use of the word as a verb for each synonym, the first frequency of the object indicating the frequency of use of the word as an object for each synonym, the second frequency of the verb indicating the sum of the first frequencies of the verb for each group of one or more words that are synonyms, and the second frequency of the object indicating the sum of the first frequencies of the object for each group of the words, and determines the verb and the object from among the words included in the data based on either one or more of the second frequency of the verb or the second frequency of the object. A determination method.

7. A program for causing a computer to function as each part of the determination device according to any one of claims 1 to 5.

Images