KR102675867B1 - Electronic terminal apparatus that automatically generates a query sentence through language analysis of the plain text sentence included in the electronic document and operating method thereof - Google Patents

Abstract

An electronic terminal device that automatically generates query sentences through linguistic analysis of descriptive sentences included in electronic documents and a method of operating the same are disclosed. The present invention provides an electronic terminal device that can automatically generate a question sentence through linguistic analysis of the sentence when an automatic question generation command for a specific sentence in the form of a descriptive sentence written in Korean included in an electronic document is authorized by the user, and the same. By presenting an operation method, we aim to help users utilize the present invention for text-based artificial intelligence learning or quiz questions for education.

Description

Electronic terminal device and method of operation for automatically generating query sentences through linguistic analysis of descriptive sentences included in electronic documents AND OPERATING METHOD THEREOF}

The present invention relates to an electronic terminal device and a method of operating the same that automatically generate query sentences through linguistic analysis of descriptive sentences included in electronic documents.

Recently, learning programs utilizing the Internet have been developed, and accordingly, the user's educational environment is also rapidly developing.

In particular, the development of various educational media has enabled users to select and use a wider range of learning methods.

Meanwhile, various functions that can be learned using electronic documents are also emerging.

In this regard, devices exist that enable users to solve problems in electronic documents.

Although various functions that enable learning using electronic documents are emerging, a product that automatically generates query sentences using sentences included in electronic documents has not yet been released.

Therefore, when a command to generate a query sentence for a specific sentence included in an electronic document is granted by the user, the query sentence is automatically generated through linguistic analysis of the specific sentence, thereby creating a quiz for text-based artificial intelligence learning or education. Research is needed on technologies that can be used for exam preparation, etc.

The present invention provides an electronic terminal device that can automatically generate a question sentence through linguistic analysis of the sentence when an automatic question generation command for a specific sentence in the form of a descriptive sentence written in Korean included in an electronic document is authorized by the user, and the same. By presenting an operation method, we aim to help users utilize the present invention for text-based artificial intelligence learning or quiz questions for education.

According to an embodiment of the present invention, an electronic terminal device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document is provided by a user among a plurality of descriptive sentence-type sentences written in Korean included in an electronic document. When an automatic problem generation command based on a first sentence is applied, within the first sentence, a first text corresponding to the subject, a second text corresponding to the object, a third text referring to time information, and place information are generated. an extraction unit for extracting a fourth text that refers to A first query sentence generator that generates a first query sentence in the form of an interrogative sentence by checking an existing predicate and changing the predicate to an interrogative form, replacing the second text with a preset second query text for querying the object. While doing so, a second question sentence is generated by deleting the particle coupled to the second text, checking the predicate existing in the first sentence, and changing the predicate to an interrogative form, thereby generating a second question sentence in the form of an interrogative sentence. Part, replacing the third text with a preset third query text for querying the time information, deleting the particle associated with the third text, and checking the predicate present in the first sentence to A third query sentence generator that generates a third query sentence in the form of an interrogative sentence by changing the predicate to an interrogative form, replacing the fourth text with a preset fourth query text for querying the location information, and the fourth text A fourth question sentence generator that generates a fourth question sentence in the form of an interrogative sentence by deleting the particle coupled to the first sentence, checking the predicate present in the first sentence, and changing the predicate to an interrogative form, and the first sentence. When the query sentence, the second query sentence, the third query sentence, and the fourth query sentence are generated, each of the first text, the second text, the third text, and the fourth text is converted into the first query sentence. , an answer table generator that generates an answer table recorded with answer text corresponding to each of the second question sentence, the third question sentence, and the fourth question sentence.

In addition, a method of operating an electronic terminal device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document according to an embodiment of the present invention is a method of operating a plurality of descriptive sentences written in Korean included in an electronic document from the user. When an automatic problem generation command based on a first sentence, which is one of the sentences in the form, is applied, within the first sentence, a first text corresponding to the subject, a second text corresponding to the object, and a third text referring to time information Extracting a fourth text referring to text and location information, replacing the first text with a preset first query text for querying the subject, while deleting a particle associated with the first text, Generating a first query sentence in the form of an interrogative sentence by checking the predicate existing in the first sentence and changing the predicate to an interrogative form, replacing the second text with a preset second query text for querying the object. , generating a second interrogative sentence in the form of an interrogative sentence by deleting the particle coupled to the second text, checking the predicate existing in the first sentence and changing the predicate to an interrogative form, the third text by replacing with a preset third query text for querying the time information, deleting the particle coupled to the third text, and checking the predicate present in the first sentence and changing the predicate to an interrogative form. , generating a third query sentence in the form of an interrogative sentence, replacing the fourth text with a preset fourth query text for querying the location information, while deleting a particle coupled to the fourth text, and Generating a fourth question sentence in the form of an interrogative sentence by checking the predicate existing in one sentence and changing the predicate to an interrogative form, and the first question sentence, the second question sentence, the third question sentence, and the first question sentence. 4 When a query sentence is generated, the first text, the second text, the third text, and the fourth text are respectively converted into the first query sentence, the second query sentence, the third query sentence, and the fourth query. It includes the step of creating a table of correct answers recorded with the correct answer text corresponding to each sentence.

The present invention provides an electronic terminal device that can automatically generate a question sentence through linguistic analysis of the sentence when an automatic question generation command for a specific sentence in the form of a descriptive sentence written in Korean included in an electronic document is authorized by the user, and the same. By presenting an operation method, it is possible to support users in utilizing the present invention for text-based artificial intelligence learning or quiz questions for education.

Figure 1 is a diagram illustrating the structure of an electronic terminal device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document according to an embodiment of the present invention.
Figure 2 is a flowchart showing a method of operating an electronic terminal device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings. This description is not intended to limit the present invention to specific embodiments, but should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention. In describing each drawing, similar reference numerals are used for similar components, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, are within the scope of common knowledge in the technical field to which the present invention pertains. It has the same meaning as generally understood by those who have it.

In this document, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary. Additionally, in various embodiments of the present invention, each component, functional block, or means may be composed of one or more subcomponents, and the electrical, electronic, and mechanical functions performed by each component may be electronic. It may be implemented with various known elements or mechanical elements such as circuits, integrated circuits, and ASICs (Application Specific Integrated Circuits), and may be implemented separately or by integrating two or more into one.

Meanwhile, the blocks in the attached block diagram or the steps in the flow chart are computer program instructions that are mounted on the processor or memory of equipment capable of data processing, such as general-purpose computers, special-purpose computers, portable laptop computers, and network computers, and perform designated functions. It can be interpreted to mean. Because these computer program instructions can be stored in a memory provided in a computer device or in a computer-readable memory, the functions described in the blocks of a block diagram or the steps of a flow diagram can be produced as a manufactured product containing instruction means to perform them. It could be. In addition, each block or each step may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). Additionally, it should be noted that in some alternative embodiments, it is possible for functions mentioned in blocks or steps to be executed in a different order. For example, two blocks or steps shown in succession may be performed substantially simultaneously or in reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram showing the structure of an electronic terminal device according to an embodiment of the present invention.

Referring to Figure 1, the electronic terminal device 110 according to the present invention is a device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document, and includes an extractor 111, a first query sentence It includes a generator 112, a second query sentence generator 113, a third query sentence generator 114, a fourth query sentence generator 115, and an answer table generator 116.

When an automatic problem generation command based on a first sentence, which is one of a plurality of sentences in the form of a Korean language included in an electronic document, is applied from the user 150, the extraction unit 111 selects the subject within the first sentence. A first text corresponding to , a second text corresponding to the target word, a third text indicating time information, and a fourth text indicating place information are extracted.

At this time, according to an embodiment of the present invention, the extraction unit 111 includes a time information regular expression storage unit 117, a location information regular expression storage unit 118, a first text extraction unit 119, and a second text extraction unit. It may include a unit 120, a third text extraction unit 121, and a fourth text extraction unit 122.

The time information regular expression storage unit 117 stores a plurality of different first regular expressions that are preset to correspond to the notation format of the time information.

Here, regular expression refers to a formal language used to express a set of strings with specific rules, such as '111-2222-3333' or '123456-4567890'.

For example, the time information regular expression storage unit 117 may store a plurality of different preset first regular expressions, as shown in Table 1 below.

Notation formats for time information Multiple first regular expressions 2021-03-01 ^\d{4}\-\d{2}\-\d{2}$ 2021.03.01 ^\d{4}\.\d{2}\.\d{2}$ 01.03.2021 ^\d{2}\.\d{2}\.\d{4}$ ... ...

The location information regular expression storage unit 118 stores a plurality of different second regular expressions that are preset to correspond to the notation format of the location information.

For example, the location information regular expression storage unit 118 may store a plurality of different preset second regular expressions, as shown in Table 2 below.

Notation formats for location information Multiple second regular expressions Yeongdeungpo-gu, Seoul ^\S{2,8}\Si\S{2,8}\District$ Yeouido-dong, Yeongdeungpo-gu ^\S{2,8}\district \S{2,8}\dong$ ... ...

The first text extraction unit 119 extracts, as the first text, a text that is combined with one of at least one preset nominative particle within the first sentence.

The second text extractor 120 extracts a text combined with one of at least one preset accusative particle within the first sentence as the second text.

The third text extraction unit 121 extracts a string having a notation format corresponding to one of the plurality of first regular expressions as the third text within the first sentence.

The fourth text extraction unit 122 extracts a character string having a notation format corresponding to one of the plurality of second regular expressions as the fourth text within the first sentence.

Hereinafter, the operations of the first text extraction unit 119, the second text extraction unit 120, the third text extraction unit 121, and the fourth text extraction unit 122 will be described in detail using examples. .

For example, among the plurality of sentences in the form of descriptive sentences written in Korean included in the electronic document from the user 150, an automatic message is sent based on the first sentence: 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.' Assume that the problem creation command is approved.

Then, the first text extraction unit 119 extracts a text that is combined with one of at least one preset nominative particle within the first sentence, 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.' can be extracted as the first text.

In relation to this, when the at least one nominative particle is 'eun, eun, i, a', the first text extraction unit 119 outputs 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.' Within the first sentence, the text 'Cheolsu', which is combined with the nominative particle 'eun', can be extracted as the first text.

And, the second text extraction unit 120 extracts a text that is combined with one of at least one preset accusative particle within the first sentence, 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.' can be extracted as the second text.

In relation to this, when the at least one accusative particle is called 'eul, eul', the second text extractor 120 extracts the first sentence 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.' Within the text, 'chocolate', which is a text combined with the accusative particle 'eul', can be extracted as the second text.

And, the third text extraction unit 121 refers to the time information regular expression storage unit 117 as shown in Table 1 above, and the first text reads 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.' Within the sentence, '2021-03-01', a string with a notation format corresponding to one of the plurality of first regular expressions, can be extracted as the third text.

And, the fourth text extractor 122 refers to the place information regular expression storage unit 118 as shown in Table 2 above, and the first text reads 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.' Within the sentence, 'Yeongdeungpo-gu, Seoul', which is a string having a notation format corresponding to one of the plurality of second regular expressions, can be extracted as the fourth text.

In this way, the extraction unit 111 selects 'Cheolsu' as the first text corresponding to the subject within the first sentence 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.', and 'Cheolsu' as the object. 'Chocolate' can be extracted as the second text, '2021-03-01' as the third text indicating the time information, and 'Yeongdeungpo-gu, Seoul' as the fourth text indicating the place information.

The first query sentence generator 112 replaces the first text with a preset first query text for querying the subject, deletes the particle coupled to the first text, and replaces the first text with a preset first query text for querying the subject. By checking the existing predicate and changing the predicate to an interrogative form, a first question sentence in the form of an interrogative sentence is generated.

The second query sentence generator 113 replaces the second text with a preset second query text for querying the target word, deletes the particle associated with the second text, and replaces the second text with a preset second query text for querying the object. By checking the existing predicate and changing the predicate to an interrogative form, a second query sentence in the form of an interrogative sentence is generated.

The third query sentence generator 114 replaces the third text with a preset third query text for querying the time information, deletes the postposition coupled to the third text, and replaces the third text with a preset third query text for querying the time information. By checking the predicate existing in the predicate and changing the predicate to an interrogative form, a third question sentence in the form of an interrogative sentence is generated.

The fourth query sentence generator 115 replaces the fourth text with a preset fourth query text for querying the location information, deletes the postposition coupled to the fourth text, and replaces the fourth text with a preset fourth query text for querying the location information. By checking the predicate existing in the predicate and changing the predicate to an interrogative form, a fourth question sentence in the form of an interrogative sentence is generated.

When the first query sentence, the second query sentence, the third query sentence, and the fourth query sentence are generated, the answer table generator 116 generates the first text, the second text, the third text, and A correct answer table is generated in which each of the fourth texts is recorded as the correct answer text corresponding to each of the first query sentence, the second query sentence, the third query sentence, and the fourth query sentence.

At this time, according to one embodiment of the present invention, the first query text is “who”, the second query text is “what”, the third query text is “when”, and the fourth query text is “what”. can be “where”.

Hereinafter, the first query sentence generator 112, the second query sentence generator 113, the third query sentence generator 114, the fourth query sentence generator 115, and the answer table generator 116. The operation will be explained in detail using an example.

For example, as in the above-mentioned example, the first sentence is 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.', and from the extraction unit 111, 'Cheolsu' and the first text are Assume that 'Chocolate' is extracted as text 2, '2021-03-01' as the third text, and 'Yeongdeungpo-gu, Seoul' as the fourth text.

Then, the first query sentence generator 112 replaces the first text 'Cheolsu' with the first query text 'who' and deletes the particle 'eun' linked to 'Cheolsu', In the first sentence above, 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.', by changing the predicate 'bought.' to the interrogative form 'Did you buy it?', 'Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?' The first query sentence can be generated in the form of an interrogative question such as 'Did you buy chocolate at ?'

In addition, the second query sentence generator 113 replaces the second text, ‘chocolate,’ with the second query text, ‘what,’ and deletes the particle ‘eul’ that is combined with ‘chocolate.’ , the first sentence above, ‘Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.’ By changing the predicate 'bought.' to the interrogative form 'Did you buy it?', the second question sentence can be created in the interrogative form 'What did Cheolsu buy in Yeongdeungpo-gu, Seoul on 2021-03-01?'

In addition, the third query sentence generator 114 replaces the third text, '2021-03-01', with the third query text, 'when', and adds '2021-03-01' to '2021-03-01'. By deleting the particle 'E' and changing the predicate 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01' in the first sentence above, 'Cheolsu bought' to the interrogative 'Did you buy it?', 'Cheolsu bought chocolate' 'When did you buy chocolate in Yeongdeungpo-gu, Seoul?' can generate the third question sentence in the form of an interrogative.

In addition, the fourth query sentence generator 115 replaces the fourth text, 'Yeongdeungpo-gu, Seoul' with the fourth query text, 'where', and replaces the fourth text 'Yeongdeungpo-gu, Seoul' with the particle 'from' combined with 'Yeongdeungpo-gu, Seoul.' By deleting the first sentence above, ‘Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.’, by changing the predicate ‘bought.’ to the interrogative form ‘Did you buy it?’, ‘Cheolsu bought chocolate on 2021-03-01.’ The fourth query sentence can be created in the form of an interrogative question, 'Where did you buy chocolate on 01?'

In this way, the first question sentence, ‘Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?’, and the second question sentence, ‘What did Cheolsu buy in Yeongdeungpo-gu, Seoul on 2021-03-01?’, above. The third question sentence, 'When did Cheolsu buy chocolate in Yeongdeungpo-gu, Seoul?' And when the fourth query sentence 'Where did Cheolsu buy chocolate on 2021-03-01?' is generated, the answer table generator 116 generates the first text 'Cheolsu' and the second text ' Chocolate', the third text '2021-03-01', and the fourth text 'Yeongdeungpo-gu, Seoul', respectively, are combined with the first query sentence 'Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?', The second question sentence, ‘What did Cheolsu buy in Yeongdeungpo-gu, Seoul on 2021-03-01?’, and the third question sentence, ‘When did Cheolsu buy chocolate in Yeongdeungpo-gu, Seoul?’ And the fourth question sentence above, 'Where did Cheolsu buy chocolate on 2021-03-01?' You can create a table of correct answers recorded with the correct answer text corresponding to each.

In relation to this, the answer table generator 116 may generate the answer table in which information such as Table 3 below is recorded.

query sentence Correct answer text Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01? withdrawal What did Cheolsu buy in Yeongdeungpo-gu, Seoul on 2021-03-01? chocolate When did Cheolsu buy chocolate in Yeongdeungpo-gu, Seoul? 2021-03-01 Where did Cheolsu buy chocolate on 2021-03-01? Yeongdeungpo-gu, Seoul

According to one embodiment of the present invention, the electronic terminal device 110 may further include a query sentence selection unit 123 and a correct answer text extraction unit 124.

After the answer table is created, when a command to pose a question is applied from the user 150, the question sentence selection unit 123 selects the first question sentence, the second question sentence, the third question sentence, and the fourth question. After randomly selecting one of the sentences, the selected query sentence is displayed on the screen.

For example, assume that after the answer table shown in Table 3 above is created, a command to pose a question is approved by the user 150.

Then, the query sentence selection unit 123 selects 'Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?', which is the first query sentence, and 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?', which is the second query sentence. 'What did you buy in Yeongdeungpo-gu?', the third question sentence above, 'When did Cheolsu buy chocolate in Yeongdeungpo-gu, Seoul?' And the fourth question sentence above, 'Where did Cheolsu buy chocolate on 2021-03-01?' After randomly selecting one of the query sentences, the selected query sentence can be displayed on the screen.

After the selected query sentence is displayed on the screen, the correct answer text extractor 124 receives a command to display the correct answer for the selected query sentence from the user 150, and generates the first answer text corresponding to the selected query sentence from the correct answer table. After extracting the correct answer text, the first correct answer text is displayed on the screen.

For example, the first query sentence 'Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?' is randomly selected by the query sentence selection unit 123, and the selected query sentence 'Who bought 2021-03' Let's assume that after 'Did you buy chocolate in Yeongdeungpo-gu, Seoul on -01?' displayed on the screen, a command to display the correct answer to 'Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?' is authorized by the user 150.

Then, the correct answer text extraction unit 124 extracts 'Cheolsu' as the first correct answer text for 'Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?' from the correct answer table shown in Table 3 above, and then 1 The correct answer text, ‘Cheolsu’, can be displayed on the screen.

According to one embodiment of the present invention, the electronic terminal device 110 may further include a table update unit 125 and a sentence update unit 126.

After the first correct answer text is displayed on the screen, the table updating unit 125 provides an answer replacement command that instructs the user 150 to replace the first correct answer text corresponding to the selected query sentence with a first replacement text. When this is approved, the answer table is updated by changing the first answer text recorded in the answer table to the first replacement text.

When the correct answer table is updated, the sentence update unit 126 changes the first correct answer text existing in the first sentence included in the electronic document to the first alternative text, thereby changing the first correct answer text included in the electronic document. Update the first sentence above.

Hereinafter, the operations of the table update unit 125 and the sentence update unit 126 will be described in detail using an example.

For example, as in the above-mentioned example, the selected query sentence is 'Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01?', and the first correct answer text 'Cheolsu' is selected by the correct answer text extraction unit 124. After is displayed on the screen, it is assumed that a command to replace the correct answer is applied to the electronic terminal device 110 from the user 150, instructing to replace the first correct text, 'Cheolsu', with a first alternative text called 'Younghee'. let's do it.

Then, the table update unit 125 changes the first correct answer text, 'Cheolsu', recorded in the correct answer table as shown in Table 3, to the first alternative text, 'Younghee,' as shown in Table 4 below. The answer table can be updated.

query sentence Correct answer text Who bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01? Younghee What did Cheolsu buy in Yeongdeungpo-gu, Seoul on 2021-03-01? chocolate When did Cheolsu buy chocolate in Yeongdeungpo-gu, Seoul? 2021-03-01 Where did Cheolsu buy chocolate on 2021-03-01? Yeongdeungpo-gu, Seoul

In this way, when the correct answer table is updated, the sentence update unit 126 changes the first correct answer text existing in the first sentence included in the electronic document to the first alternative text, thereby included in the electronic document. The first sentence can be updated.

Relatedly, as in the above-described example, when the first sentence is 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01.', the sentence update unit 126 updates the answer table as shown in Table 4 above. When this is updated, the first correct answer text 'Cheolsu' existing in the first sentence 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01' included in the electronic document is replaced with the first. By changing the text 'Younghee', the first sentence included in the electronic document, 'Cheolsu bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01', to 'Younghee bought chocolate in Yeongdeungpo-gu, Seoul on 2021-03-01. It can be updated to 'I bought chocolate from.'

Figure 2 is a flowchart showing a method of operating an electronic terminal device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document according to an embodiment of the present invention.

In step S210, when an automatic problem generation command based on a first sentence, which is one of a plurality of descriptive sentences written in Korean included in an electronic document, is applied by the user, a question corresponding to the subject in the first sentence is applied. 1 text, a second text corresponding to the target word, a third text indicating time information, and a fourth text indicating location information are extracted.

In step S220, the first text is replaced with a preset first query text for querying the subject, the particle coupled to the first text is deleted, and the predicate present in the first sentence is confirmed. By changing the predicate into an interrogative form, a first question sentence in the form of an interrogative sentence is generated.

In step S230, the second text is replaced with a preset second query text for querying the object, the particle associated with the second text is deleted, and the predicate present in the first sentence is confirmed. By changing the predicate to an interrogative form, a second question sentence in the form of an interrogative sentence is generated.

In step S240, the third text is replaced with a preset third query text for querying the time information, the postposition coupled to the third text is deleted, and the predicate existing in the first sentence is replaced with a preset third query text for querying the time information. By confirming and changing the predicate to an interrogative form, a third question sentence in the form of an interrogative sentence is generated.

In step S250, the fourth text is replaced with a preset fourth query text for querying the location information, the postposition coupled to the fourth text is deleted, and the predicate present in the first sentence is replaced. By confirming and changing the predicate to an interrogative form, a fourth question sentence in the form of an interrogative sentence is generated.

In step S260, when the first query sentence, the second query sentence, the third query sentence, and the fourth query sentence are generated, the first text, the second text, the third text, and the fourth query sentence are generated. A correct answer table is created in which each text is recorded as the correct answer text corresponding to each of the first query sentence, the second query sentence, the third query sentence, and the fourth query sentence.

At this time, according to one embodiment of the present invention, in step S210, maintaining a time information regular expression storage unit in which a plurality of different first regular expressions preset to correspond to the notation format of the time information are stored, Maintaining a place information regular expression storage unit storing a plurality of different second regular expressions preset to correspond to the notation format of the place information, wherein, within the first sentence, one of at least one preset nominative particle extracting a text that is combined with the first text, within the first sentence, extracting a text that is combined with one of at least one preset accusative particle into the second text, the first sentence extracting, within the third text, a string having a notation format corresponding to one of the plurality of first regular expressions, and within the first sentence, corresponding to one of the plurality of second regular expressions. It may include extracting a string having a notation format as the fourth text.

At this time, according to one embodiment of the present invention, the first query text is “who”, the second query text is “what”, the third query text is “when”, and the fourth query text is “what”. can be “where”.

In addition, according to an embodiment of the present invention, the method of operating the electronic terminal device is such that, after the answer table is created, when a command to pose a question is applied from the user, the first question sentence, the second question sentence, the After randomly selecting any one of the third query sentence and the fourth query sentence, displaying the selected query sentence on the screen, and after the selected query sentence is displayed on the screen, the selected query sentence from the user When a command to display the correct answer to a sentence is applied, the step of extracting the first correct answer text corresponding to the selected question sentence from the correct answer table and then displaying the first correct answer text on the screen may be further included.

At this time, according to one embodiment of the present invention, the method of operating the electronic terminal device is to replace the first answer text corresponding to the question sentence selected by the user with a first answer text after the first answer text is displayed on the screen. When an answer replacement command instructing to replace text is applied, updating the answer table by changing the first answer text recorded in the answer table to the first replacement text; and when the answer table is updated, , It may further include the step of updating the first sentence included in the electronic document by changing the first correct text present in the first sentence included in the electronic document to the first alternative text. there is.

Above, a method of operating an electronic terminal device according to an embodiment of the present invention has been described with reference to FIG. 2. Here, the operation method of the electronic terminal device according to an embodiment of the present invention may correspond to the configuration of the operation of the electronic terminal device 110 described using FIG. 1, so a more detailed description thereof will be omitted. .

The method of operating an electronic terminal device according to an embodiment of the present invention may be implemented as a computer program stored in a storage medium to be executed through combination with a computer.

Additionally, the method of operating an electronic terminal device according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and constructed for the present invention or may be known and usable by those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

As described above, the present invention has been described with specific details such as specific components and limited embodiments and drawings, but this is only provided to facilitate a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , those skilled in the art can make various modifications and variations from this description.

Accordingly, the spirit of the present invention should not be limited to the described embodiments, and the scope of the patent claims described later as well as all things that are equivalent or equivalent to the scope of this patent claim shall fall within the scope of the spirit of the present invention. .

110: Electronic terminal device
111: extraction unit 112: first query sentence generation unit
113: Second query sentence generator 114: Third query sentence generator
115: Fourth question sentence generation unit 116: Answer table generation unit
117: Time information regular expression storage unit 118: Place information regular expression storage unit
119: first text extraction unit 120: second text extraction unit
121: Third text extraction unit 122: Fourth text extraction unit
123: Question sentence selection unit 124: Correct answer text extraction unit
125: table update unit 126: sentence update unit

Claims (12)

In an electronic terminal device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document,
When an automatic problem generation command based on a first sentence, which is one of a plurality of descriptive sentences written in Korean included in an electronic document, is granted by the user, the first text corresponding to the subject and the object within the first sentence are an extraction unit that extracts the corresponding second text, a third text referring to time information, and a fourth text referring to place information;
Replacing the first text with a preset first query text for querying the subject, deleting the particle bound to the first text, checking the predicate existing in the first sentence, and converting the predicate into an interrogative form a first question sentence generator that generates a first question sentence in the form of a question by changing it;
Replacing the second text with a preset second query text for querying the object, deleting the particle associated with the second text, checking the predicate present in the first sentence, and converting the predicate into an interrogative form a second question sentence generator that generates a second question sentence in the form of an interrogative sentence;
Replacing the third text with a preset third query text for querying the time information, deleting the particle associated with the third text, and checking the predicate present in the first sentence to replace the predicate a third question sentence generator that generates a third question sentence in the form of an interrogative sentence by changing it to an interrogative form;
Replacing the fourth text with a preset fourth query text for querying the location information, deleting the particle associated with the fourth text, and checking the predicate present in the first sentence to replace the predicate a fourth question sentence generator that generates a fourth question sentence in the form of an interrogative sentence by changing it to an interrogative form;
When the first query sentence, the second query sentence, the third query sentence, and the fourth query sentence are generated, each of the first text, the second text, the third text, and the fourth text is converted into the first query sentence. an answer table generator that generates a answer table recorded with answer text corresponding to each of the first question sentence, the second question sentence, the third question sentence, and the fourth question sentence;
After the answer table is created, when a command to pose a question is issued by the user, one of the first question sentence, the second question sentence, the third question sentence, and the fourth question sentence is randomly selected. a query sentence selection unit that, after selection, displays the selected query sentence on the screen;
After the selected query sentence is displayed on the screen, if a command to display the correct answer for the selected query sentence is received from the user, the first correct answer text corresponding to the selected question sentence is extracted from the correct answer table, and then the first correct answer text is extracted from the correct answer table. A correct answer text extraction unit that displays text on the screen;
After the first correct answer text is displayed on the screen, if a correct answer replacement command instructing to replace the first correct answer text corresponding to the selected query sentence with a first replacement text is applied from the user, it is recorded in the correct answer table. a table updating unit that updates the correct answer table by changing the first correct answer text to the first replacement text; and
When the answer table is updated, the first answer text present in the first sentence included in the electronic document is changed to the first alternative text, thereby updating the first sentence included in the electronic document. Sentence update section
Including,
The extraction unit
a time information regular expression storage unit storing a plurality of different first regular expressions that are preset to correspond to the notation format of the time information;
a location information regular expression storage unit storing a plurality of different second regular expressions preset to correspond to the notation format of the location information;
a first text extraction unit that extracts, within the first sentence, a text combined with one of at least one preset nominative particle as the first text;
a second text extraction unit that extracts, as the second text, a text that is combined with one of at least one preset accusative particle in the first sentence;
a third text extraction unit that extracts, from the first sentence, a string having a notation format corresponding to one of the plurality of first regular expressions as the third text; and
A fourth text extraction unit that extracts, within the first sentence, a string having a notation format corresponding to one of the plurality of second regular expressions as the fourth text.
Electronic terminal device including. delete According to paragraph 1,
wherein the first query text is “who”, the second query text is “what”, the third query text is “when”, and the fourth query text is “where”. terminal device. delete delete A method of operating an electronic terminal device that automatically generates a query sentence through linguistic analysis of a descriptive sentence included in an electronic document, comprising:
When an automatic problem generation command based on a first sentence, which is one of a plurality of descriptive sentences written in Korean included in an electronic document, is granted by the user, the first text corresponding to the subject and the object within the first sentence are extracting a corresponding second text, a third text referring to time information, and a fourth text referring to place information;
Replacing the first text with a preset first query text for querying the subject, deleting the particle bound to the first text, checking the predicate existing in the first sentence, and converting the predicate into an interrogative form generating a first question sentence in the form of an interrogative sentence by modifying it;
Replacing the second text with a preset second query text for querying the object, deleting the particle associated with the second text, checking the predicate present in the first sentence, and converting the predicate into an interrogative form generating a second question sentence in the form of an interrogative sentence by changing to;
Replacing the third text with a preset third query text for querying the time information, deleting the particle associated with the third text, and checking the predicate present in the first sentence to replace the predicate generating a third question sentence in the form of an interrogative sentence by changing it to an interrogative form;
Replacing the fourth text with a preset fourth query text for querying the location information, deleting the particle associated with the fourth text, and checking the predicate present in the first sentence to replace the predicate generating a fourth question sentence in the form of an interrogative sentence by changing it to an interrogative form;
When the first query sentence, the second query sentence, the third query sentence, and the fourth query sentence are generated, each of the first text, the second text, the third text, and the fourth text is converted into the first query sentence. generating a correct answer table recorded with correct answer text corresponding to each of the first question sentence, the second question sentence, the third question sentence, and the fourth question sentence;
After the answer table is created, when a command to pose a question is issued by the user, one of the first question sentence, the second question sentence, the third question sentence, and the fourth question sentence is randomly selected. After selection, displaying the selected query sentence on the screen;
After the selected query sentence is displayed on the screen, if a command to display the correct answer for the selected query sentence is received from the user, the first correct answer text corresponding to the selected question sentence is extracted from the correct answer table, and then the first correct answer text is extracted from the correct answer table. displaying text on a screen;
After the first correct answer text is displayed on the screen, if a correct answer replacement command instructing to replace the first correct answer text corresponding to the selected query sentence with a first replacement text is applied from the user, it is recorded in the correct answer table. updating the correct answer table by changing the first correct answer text to the first alternative text; and
When the answer table is updated, the first answer text present in the first sentence included in the electronic document is changed to the first alternative text, thereby updating the first sentence included in the electronic document. step
Including,
The extraction step is
maintaining a time information regular expression storage unit in which a plurality of different first regular expressions preset to correspond to the notation format of the time information are stored;
maintaining a location information regular expression storage unit in which a plurality of different second regular expressions preset to correspond to the notation format of the location information are stored;
extracting, within the first sentence, a text that is combined with one of at least one preset nominative particle as the first text;
extracting, within the first sentence, a text that is combined with one of at least one preset accusative particle as the second text;
extracting, within the first sentence, a string having a notation format corresponding to one of the plurality of first regular expressions as the third text; and
Within the first sentence, extracting a string having a notation format corresponding to one of the plurality of second regular expressions as the fourth text.
A method of operating an electronic terminal device comprising: delete According to clause 6,
wherein the first query text is “who”, the second query text is “what”, the third query text is “when”, and the fourth query text is “where”. How a terminal device operates. delete delete A computer-readable recording medium recording a computer program for executing the method of any one of claims 6 or 8 through combination with a computer. A computer program stored in a storage medium for executing the method of any one of paragraphs 6 or 8 through combination with a computer.

Images