Electronic apparatus that support dictation practice through repetitive learning and the operating method thereof

Abstract

The present invention relates to an electronic device and a method of operation that supports repetitive learning in a manner in which a predetermined practice sentence is synthesized into speech and output through a speaker, the user is asked to transcribe the sentence, and if the sentence transcribed by the user differs from the practice sentence, the corresponding practice sentence is output again as speech so that the user is asked to transcribe the sentence again.

Description

Technology Field

[0001] The present invention relates to an electronic device that supports dictation practice through repetitive learning and a method of operation thereof. Background Technology

[0002] Spelling is important when writing, and dictation is commonly used as one method to improve spelling skills.

[0003] Here, dictation refers to the act of transcribing exactly what is said or read by others while listening to them.

[0004] In this regard, to support the improvement of users' spelling skills, the introduction of technology that enables dictation on electronic devices can be considered. In particular, with the recent advancement of speech synthesis technology that converts text into speech, it is possible to introduce a dictation practice technology that configures predetermined practice sentences and then synthesizes and outputs these sentences as speech.

[0005] In addition, to increase learning efficiency through dictation practice, the introduction of technology that enables dictation practice using repetitive learning can be considered.

[0006] Specifically, one may consider introducing a technology that can increase the efficiency of a user's dictation learning by performing repetitive learning in a manner where a predetermined practice sentence is synthesized into speech and output through a speaker, the user is asked to transcribe the sentence, and if the sentence transcribed by the user differs from the practice sentence, the corresponding practice sentence is output again as speech so that the user is asked to transcribe the sentence again.

[0007] In addition, through this repetitive learning, the introduction of technology can be considered to support users in perfectly mastering the spelling of the characters they frequently misspell by identifying the characters they frequently misspell and creating various learning sentences based on those characters to provide to the user. The problem to be solved

[0008] The present invention aims to support a user in performing dictation learning more efficiently by presenting an electronic device and a method of operation that support repetitive learning in a manner in which a predetermined practice sentence is synthesized into speech and output through a speaker, the user is asked to transcribe the sentence, and if the sentence transcribed by the user differs from the practice sentence, the corresponding practice sentence is output again as speech so that the user is asked to transcribe the sentence again. means of solving the problem

[0009] An electronic device supporting dictation practice through repetitive learning according to an embodiment of the present invention comprises: a sentence database in which a plurality of pre-produced sentences are stored; a problem generation unit that, when a command to generate a problem for dictation practice is granted from a user of the electronic device, designates a first sentence, which is one of the plurality of sentences stored in the sentence database, as a problem, and then generates a first synthesized voice by applying the first sentence as input to a pre-constructed speech synthesis model to perform speech synthesis, and outputs the first synthesized voice through a speaker mounted on the electronic device at a preset speech output speed; a first re-output unit that, when a first input sentence is input from the user as a dictation answer sentence corresponding to the first synthesized voice, checks whether the string constituting the first input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, increases the speech output speed by a value multiplied by a preset first value and re-outputs the first synthesized voice through the speaker; and the first synthesized voice re-outputted from the user through the first re-output unit A second re-output unit that, when a second input sentence is re-entered as a dictation answer sentence corresponding to the voice, checks whether the string constituting the second input sentence and the string constituting the first sentence are identical, and if it is confirmed that they are not identical, increases the voice output speed by a value obtained by multiplying it by a preset second value—the second value being greater than the first value—and re-outputs the first synthesized voice through the speaker; and when a third input sentence is re-entered from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the second re-output unit, checks whether the string constituting the third input sentence and the string constituting the first sentence are identical, and if it is confirmed that they are not identical, increases the voice output speed.It includes a third re-output unit that increases the first synthesized voice through the speaker by a value multiplied by a preset third value—the third value being greater than the second value—and a fourth re-output unit that, when a fourth input sentence is re-input from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the third re-output unit, checks whether the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, re-outputs the first synthesized voice through the speaker at the same speed as the voice output speed and then displays the first sentence on the screen.

[0010] In addition, a method of operation of an electronic device that supports dictation practice through repetitive learning according to an embodiment of the present invention comprises: maintaining a sentence database in which a plurality of pre-produced sentences are stored; when a command to generate a problem for dictation practice is granted from a user of the electronic device, a first sentence, which is one of the plurality of sentences stored in the sentence database, is designated as a problem, and then the first sentence is applied as input to a pre-constructed speech synthesis model to perform speech synthesis, thereby generating a first synthesized voice, and outputting the first synthesized voice through a speaker mounted on the electronic device at a preset voice output speed; when a first input sentence is input from the user as a dictation answer sentence corresponding to the first synthesized voice, checking whether the string constituting the first input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, increasing the voice output speed by a value multiplied by a preset first value, and re-outputting the first synthesized voice through the speaker; and the re-outputted from the user through the first re-output step A second re-output step in which, when a second input sentence is re-input as a dictation answer sentence corresponding to the first synthesized voice, the string constituting the second input sentence and the string constituting the first sentence are checked to see if they are identical, and if they are not identical, the voice output speed is increased by a value obtained by multiplying by a preset second value—the second value being greater than the first value—to re-output the first synthesized voice through the speaker; and when a third input sentence is re-input from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the second re-output step, the string constituting the third input sentence and the string constituting the first sentence are checked to see if they are identical, and if they are not identical,The method includes a third re-output step of increasing the voice output speed by a value obtained by multiplying the voice output speed by a preset third value—the third value being greater than the second value—and re-outputting the first synthesized voice through the speaker; and a fourth re-output step in which, when a fourth input sentence is re-input from the user as a dictation answer sentence corresponding to the first synthesized voice re-outputted through the third re-output step, the method checks whether the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, the method re-outputs the first synthesized voice through the speaker at the same speed as the voice output speed, and then displays the first sentence on the screen. Effects of the invention

[0011] The present invention provides an electronic device and a method of operation that support repetitive learning by synthesizing a predetermined practice sentence into speech and outputting it through a speaker, having the user transcribe the sentence, and if the sentence transcribed by the user differs from the practice sentence, outputting the corresponding practice sentence again into speech and having the user transcribe the sentence again, thereby increasing the efficiency of the user's dictation learning. Brief explanation of the drawing

[0012] FIG. 1 is a diagram illustrating the structure of an electronic device that supports dictation practice through repetitive learning according to an embodiment of the present invention. FIG. 2 is a flowchart illustrating the operation method of an electronic device that supports dictation practice through repetitive learning according to an embodiment of the present invention. Specific details for implementing the invention

[0013] Embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. This description is not intended to limit the present invention to specific embodiments and should be understood to include all modifications, equivalents, and substitutions that fall within the spirit and scope of the present invention. Similar reference numerals have been used for similar components in describing each drawing, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, have the same meaning as generally understood by a person skilled in the art to which the present invention pertains.

[0014] In this document, when a part is described as "including" a component, it means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, in various embodiments of the present invention, each component, functional block, or means may be composed of one or more sub-components, and the electrical, electronic, or mechanical functions performed by each component may be implemented by various known devices or mechanical elements, such as electronic circuits, integrated circuits, and ASICs (Application Specific Integrated Circuits), and may be implemented separately or two or more may be integrated into one.

[0015] Meanwhile, the blocks in the attached block diagram or the steps in the flowchart may be interpreted as computer program instructions that perform designated functions by being loaded into the processor or memory of data-processing equipment, such as general-purpose computers, specialized computers, portable notebook computers, and network computers. Since these computer program instructions may be stored in memory provided in a computer device or in memory readable by a computer, the functions described in the blocks in the block diagram or the steps in the flowchart may be produced as manufactured products containing means of instruction to perform them. Furthermore, each block or each step may represent a module, segment, or part of code containing one or more executable instructions for executing a specific logical function(s). Also, it should be noted that in some alternative embodiments, the functions mentioned in the blocks or steps may be executed in a different order than the prescribed 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.

[0016] FIG. 1 is a diagram illustrating the structure of an electronic device that supports dictation practice through repetitive learning according to an embodiment of the present invention.

[0017] Referring to FIG. 1, the electronic device (110) according to the present invention includes a sentence database (111), a question generation unit (112), a first re-output unit (113), a second re-output unit (114), a third re-output unit (115), and a fourth re-output unit (116).

[0018] First, the electronic device (110) of the present invention refers to a device equipped with a microprocessor, such as a desktop computer, smartphone, tablet computer, or laptop, and the electronic device (110) of the present invention is equipped with a predetermined speaker (10) capable of outputting sound.

[0019] The sentence database (111) stores multiple pre-made sentences.

[0020] For example, if the above multiple sentences are assumed to be 'Sentence 1, Sentence 2, Sentence 3, ..., Sentence 100', the sentence database (111) may store the above multiple sentences, 'Sentence 1, Sentence 2, Sentence 3, ..., Sentence 100'.

[0021] When a command to generate a problem for dictation practice is issued by a user of the electronic device (110), the problem generation unit (112) designates a first sentence, which is one of the plurality of sentences stored in the sentence database (111), as a problem, and then generates a first synthesized voice by applying the first sentence as input to a pre-built speech synthesis model to perform speech synthesis, and outputs the first synthesized voice through a speaker (10) mounted on the electronic device (110) at a preset speech output speed.

[0022] For example, let us assume that a command to generate questions for dictation practice is authorized from the user of the electronic device (110).

[0023] Then, the question generation unit (112) can designate any one of the plurality of sentences stored in the sentence database (111), namely 'sentence 1, sentence 2, sentence 3, ..., sentence 100', as a question.

[0024] At this time, the question generation unit (112) can randomly select a sentence to be designated as a question among the plurality of sentences above. If 'Sentence 3' is selected among 'Sentence 1, Sentence 2, Sentence 3, ..., Sentence 100', the question generation unit (112) can generate a first synthesized speech by applying 'Sentence 3' as input to a pre-built speech synthesis model and performing speech synthesis.

[0025] Then, the question generation unit (112) can output the first synthesized voice through the speaker (10) at a preset voice output speed. For example, if the voice output speed is 'a speed at which 3 characters are output per second', the question generation unit (112) can output the first synthesized voice through the speaker (10) at 'a speed at which 3 characters are output per second'.

[0026] Thus, when the first synthesized voice is output through the speaker (10), the user can listen to the first synthesized voice output through the speaker (10) and input a dictation answer sentence corresponding to the first synthesized voice on the electronic device (110) through a keyboard or touch input connected to the electronic device (110).

[0027] At this time, when a first input sentence is input to the electronic device (110) as a dictation answer sentence corresponding to the first synthesized voice from the user, the first re-output unit (113) checks whether the string constituting the first input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, the voice output speed is increased by a value multiplied by a preset first value, and the first synthesized voice can be re-output through the speaker (10).

[0028] For example, the first value may be '1.25'. That is, if the first input sentence entered by the user does not match the first sentence, it is a situation where the user has made a mistake in dictation, so the first re-output unit (113) can adjust the voice output speed to be '1.25' times faster and re-output the first synthesized voice through the speaker (10). In this way, when the first synthesized voice is re-output, the user can listen to the first synthesized voice output at '1.25 times' faster speed again and input the dictation answer sentence corresponding to the first synthesized voice once again on the electronic device (110) through a keyboard or touch input connected to the electronic device (110).

[0029] At this time, according to one embodiment of the present invention, if the first re-output unit (113) confirms that the string constituting the first input sentence and the string constituting the first sentence are identical to each other, the first sentence can be displayed on the screen along with a message indicating that the first input sentence is the correct answer, without re-outputting the first synthesized speech.

[0030] That is, unlike the example described above, if the user listens to the first synthesized voice and inputs an accurate dictation answer, the first re-output unit (113) can display the original correct sentence, the first sentence, on the screen along with a message indicating that the first input sentence entered by the user is the correct answer, without re-outputting the first synthesized voice, because the user has performed the dictation correctly. Through this, the user can confirm that they have entered an accurate dictation answer sentence.

[0031] Additionally, according to one embodiment of the present invention, if the first re-output unit (113) confirms that the string constituting the first input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the first input sentence and the string constituting the first sentence with each other, selects a character among the characters recorded on a pre-specified character table that is confirmed to have one or more typos through the first input sentence, records it on a first typo information table, and then increases the voice output speed by the value multiplied by the first value, and can re-output the first synthesized voice through the speaker (10).

[0032] Here, the character table refers to a table in which characters appearing one or more times in the plurality of sentences are recorded. For example, the character table may be configured as shown in Table 1 below.

[0034] Multiple characters go me all la mind ... crab dog Pig become life my re her ...

[0036] The characters recorded in the character table as shown in Table 1 above are characters that appear one or more times in multiple sentences stored in the sentence database (111).

[0037] In this regard, if it is confirmed that the first input sentence entered by the user is different from the first sentence, the first re-output unit (113) can increase the voice output speed by the value multiplied by the first value and re-output the first synthesized voice. Before re-outputting the first synthesized voice, the first re-output unit (113) can find a character different from the first sentence in the first input sentence, i.e., a typo, and perform the operation of recording the character corresponding to this typo on the first typo information table.

[0038] Specifically, when the first re-output unit (113) confirms that the string constituting the first input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the first input sentence and the string constituting the first sentence with each other, selects the characters among the characters recorded on the character table such as Table 1 that are confirmed to have one or more typos through the first input sentence, and records the selected characters on the first typo information table as shown in Table 2 below.

[0040] Characters with typos crab Pig ...

[0042] Then, the first re-output unit (113) can increase the voice output speed by the value multiplied by the first value and re-output the first synthesized voice through the speaker (10).

[0043] Thus, when the first synthesized voice is re-output through the first re-output unit (113) via the speaker (10), the user can listen to the first synthesized voice being re-output through the speaker (10) and re-input a dictation answer sentence corresponding to the first synthesized voice on the electronic device (110) via a keyboard or touch input connected to the electronic device (110).

[0044] At this time, when a second input sentence is re-entered into the electronic device (110) from the user as a dictation answer sentence corresponding to the first synthesized voice, the second re-output unit (114) checks whether the string constituting the second input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, the voice output speed is increased by a value obtained by multiplying by a preset second value (the second value is a value greater than the first value), and the first synthesized voice can be re-output through the speaker (10).

[0045] For example, the second value may be '1.5'. That is, if the second input sentence entered by the user does not match the first sentence, it is a situation where the user has made a mistake in dictation, so the second re-output unit (114) can adjust the voice output speed to be '1.5' times faster and re-output the first synthesized voice through the speaker (10). In this way, when the first synthesized voice is re-output, the user can listen to the first synthesized voice output at '1.5' times faster again and input the dictation answer sentence corresponding to the first synthesized voice once again on the electronic device (110) through a keyboard or touch input connected to the electronic device (110).

[0046] At this time, according to one embodiment of the present invention, if the second re-output unit (114) confirms that the string constituting the second input sentence and the string constituting the first sentence are identical to each other, the first sentence can be displayed on the screen along with a message indicating that the second input sentence is the correct answer, without re-outputting the first synthesized speech.

[0047] That is, unlike the example described above, if the user listens to the first synthesized voice and inputs an accurate dictation answer, the second re-output unit (114) can display the original correct answer sentence, the first sentence, on the screen along with a message indicating that the second input sentence entered by the user is the correct answer, without re-outputting the first synthesized voice, because the user has performed the dictation correctly. Through this, the user can confirm that they have entered an accurate dictation answer sentence.

[0048] Additionally, according to one embodiment of the present invention, if the second re-output unit (114) confirms that the string constituting the second input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the second input sentence and the string constituting the first sentence with each other, selects a character among the characters recorded on the character table that is confirmed to have one or more typos through the second input sentence, records it on the second typo information table, and then increases the voice output speed by the value multiplied by the second value, thereby re-outputting the first synthesized voice through the speaker (10).

[0049] In this regard, if it is confirmed that the second input sentence entered by the user is different from the first sentence, the second re-output unit (114) can increase the voice output speed by the value multiplied by the second value and re-output the first synthesized voice. Before re-outputting the first synthesized voice, the second re-output unit (114) can find a character in the second input sentence that is different from the first sentence, i.e., a typo, and perform the operation of recording the character corresponding to this typo on the second typo information table.

[0050] Specifically, when the second re-output unit (114) confirms that the string constituting the second input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the second input sentence and the string constituting the first sentence with each other, selects the characters among the characters recorded on the character table such as Table 1 that are confirmed to have one or more typos through the second input sentence, and records the selected characters on the second typo information table as shown in Table 3 below.

[0052] Characters with typos life her ...

[0054] Then, the second re-output unit (114) can increase the voice output speed by the value multiplied by the second value, and re-output the first synthesized voice through the speaker (10).

[0055] Thus, when the first synthesized voice is re-output through the speaker (10) via the second re-output unit (114), the user can listen to the first synthesized voice being re-output through the speaker (10) and re-input a dictation answer sentence corresponding to the first synthesized voice on the electronic device (110) via a keyboard or touch input connected to the electronic device (110).

[0056] At this time, when a third input sentence is re-entered into the electronic device (110) from the user as a dictation answer sentence corresponding to the first synthesized voice, the third re-output unit (115) checks whether the string constituting the third input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, the voice output speed is increased by a value obtained by multiplying by a preset third value (the third value is a value greater than the second value), and the first synthesized voice can be re-output through the speaker (10).

[0057] For example, the third value may be '1.75'. That is, if the third input sentence entered by the user does not match the first sentence, it is a situation where the user has made a mistake in dictation, so the third re-output unit (115) can adjust the voice output speed to be '1.75' times faster and re-output the first synthesized voice through the speaker (10). In this way, when the first synthesized voice is re-output, the user can listen to the first synthesized voice output at '1.75' times faster again and input the dictation answer sentence corresponding to the first synthesized voice once again on the electronic device (110) through a keyboard or touch input connected to the electronic device (110).

[0058] At this time, according to one embodiment of the present invention, if the third re-output unit (115) confirms that the string constituting the third input sentence and the string constituting the first sentence are identical to each other, the first sentence can be displayed on the screen along with a message indicating that the third input sentence is the correct answer, without re-outputting the first synthesized speech.

[0059] That is, unlike the example described above, if the user listens to the first synthesized voice and inputs an accurate dictation answer, the third re-output unit (115) can display the original correct answer sentence, the first sentence, on the screen along with a message indicating that the third input sentence entered by the user is the correct answer, without re-outputting the first synthesized voice, because the user has performed the dictation correctly. Through this, the user can confirm that they have entered an accurate dictation answer sentence.

[0060] In addition, according to one embodiment of the present invention, if the third re-output unit (115) confirms that the string constituting the third input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the third input sentence and the string constituting the first sentence with each other, selects a character among the characters recorded on the character table that is confirmed to have one or more typos through the third input sentence, records it on the third typo information table, and then increases the voice output speed by the value multiplied by the third value, thereby re-outputting the first synthesized voice through the speaker (10).

[0061] In this regard, if it is confirmed that the third input sentence entered by the user is different from the first sentence, the third re-output unit (115) can increase the voice output speed by the value multiplied by the third value and re-output the first synthesized voice. Before re-outputting the first synthesized voice, the third re-output unit (115) can find a character in the third input sentence that is different from the first sentence, i.e., a typo, and perform the operation of recording the character corresponding to this typo on the third typo information table.

[0062] Specifically, when the third re-output unit (115) confirms that the string constituting the third input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the third input sentence and the string constituting the first sentence with each other, selects the characters among the characters recorded on a character table such as Table 1 that are confirmed to have one or more typos through the third input sentence, and records the selected characters on the third typo information table as shown in Table 4 below.

[0064] Characters with typos mind Pig ...

[0066] Then, the third re-output unit (115) can increase the voice output speed by the value multiplied by the third value, and re-output the first synthesized voice through the speaker (10).

[0067] Thus, when the first synthesized voice is re-output through the speaker (10) via the third re-output unit (115), the user can listen to the first synthesized voice being re-output through the speaker (10) and re-input a dictation answer sentence corresponding to the first synthesized voice on the electronic device (110) via a keyboard or touch input connected to the electronic device (110).

[0068] At this time, when a fourth input sentence is re-entered into the electronic device (110) from the user as a dictation answer sentence corresponding to the first synthesized voice, the fourth re-output unit (116) checks whether the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other, and if it is confirmed that they are not identical, it re-outputs the first synthesized voice through the speaker (10) at the same speed as the voice output speed, and then displays the first sentence on the screen.

[0069] In this regard, the fourth re-output unit (116) is configured to provide the first synthesized voice to the user as a final output. That is, if the fourth input sentence entered by the user does not match the first sentence, the fourth re-output unit (116) can re-output the first synthesized voice through the speaker (10) because the user has made a mistake in dictation. The first synthesized voice can be re-output at the same speed as the initial voice output speed. In addition, the fourth re-output unit (116) can display the first sentence, which is the correct answer, on the screen. Through this, the user can verify what the final correct answer is for the first synthesized voice.

[0070] At this time, according to one embodiment of the present invention, if the fourth re-output unit (116) confirms that the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other, the first sentence can be displayed on the screen along with a message indicating that the fourth input sentence is the correct answer, without re-outputting the first synthesized speech.

[0071] That is, unlike the example described above, if the user listens to the first synthesized voice and inputs an accurate dictation answer, the fourth re-output unit (116) can display the original correct answer sentence, the first sentence, on the screen along with a message indicating that the fourth input sentence entered by the user is the correct answer, without re-outputting the first synthesized voice, because the user has performed the dictation correctly. Through this, the user can confirm that they have entered an accurate dictation answer sentence.

[0072] Additionally, according to one embodiment of the present invention, if the fourth re-output unit (116) confirms that the string constituting the fourth input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the fourth input sentence and the string constituting the first sentence with each other, selects a character among the characters recorded on the character table that is confirmed to have one or more typos through the fourth input sentence, records it on the fourth typo information table, and then re-outputs the first synthesized voice through the speaker (10) at the same speed as the voice output speed, and then displays the first sentence on the screen.

[0073] In this regard, if it is confirmed that the fourth input sentence entered by the user is different from the first sentence, the fourth re-output unit (116) can re-output the first synthesized speech at the original speech output speed. Before re-outputting the first synthesized speech, the fourth re-output unit (116) can find a character in the fourth input sentence that is different from the first sentence, i.e., a typo, and perform the operation of recording the character corresponding to this typo on the fourth typo information table.

[0074] Specifically, when the fourth re-output unit (116) confirms that the string constituting the fourth input sentence and the string constituting the first sentence are not identical to each other, it compares the string constituting the fourth input sentence and the string constituting the first sentence with each other, selects the characters among the characters recorded on the character table such as Table 1 that are confirmed to have one or more typos through the fourth input sentence, and records the selected characters on the fourth typo information table as shown in Table 5 below.

[0076] Characters with typos life Pig ...

[0078] Then, the fourth re-output unit (116) can re-output the first synthesized voice through the speaker (10) at the same speed as the voice output speed, and then display the first sentence on the screen.

[0079] At this time, according to one embodiment of the present invention, the electronic device (110) may further include a verification unit (117), a selection unit (118), and a message display unit (119).

[0080] When the verification unit (117) receives a sentence learning request command based on characters recorded on the typo information table from the user, it verifies the characters recorded on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table, respectively.

[0081] The selection unit (118) selects, among the plurality of sentences, sentences that contain one or more characters recorded on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table within the sentence as learning sentences.

[0082] The message display unit (119) displays the learning sentences on the screen and displays an instruction message on the screen instructing to transcribe the learning sentences.

[0083] For example, if the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table are as shown in Tables 2 to 5, the verification unit (117) can verify ‘ge, dae, sal, heo, ma’ using the characters recorded on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table, respectively.

[0084] Then, the selection unit (118) can select sentences that contain one or more of the characters ‘ge, dae, sal, heo, ma’ from among the plurality of sentences stored in the sentence database (111) such as Table 1 above as learning sentences.

[0085] After that, the message display unit (119) can display the learning sentences on the screen and display an instruction message on the screen instructing to transcribe the learning sentences.

[0086] Then, the user can learn the characters ‘ge, dae, sal, heo, ma’ by looking at the learning sentences and instruction messages displayed on the screen and transcribing the learning sentences using a keyboard or touch input connected to the electronic device (110).

[0087] At this time, according to one embodiment of the present invention, when the selection unit (118) completes the selection of the learning sentences, it checks whether there is a character that is recorded in duplicate at least once on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table. If it is confirmed that there is at least one first character among the characters recorded in duplicate, it can obtain additional learning sentences by inputting a prompt to a preset sentence generation model instructing it to generate a sentence in which each of the at least one first character appears at least once.

[0088] Here, the sentence generation model refers to a generative artificial intelligence model that receives a prompt and automatically generates a sentence corresponding to the input prompt based on a pre-built Large Language Model (LM), and a Transformer-based language model may be utilized.

[0089] In this regard, as in the example described above, if it is confirmed that ‘ge, dae, sal, heo, ma’ is recorded in the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table through the verification unit (117), the selection unit (118) can select sentences containing one or more of the characters ‘ge, dae, sal, heo, ma’ from among the plurality of sentences stored in the sentence database (111) such as Table 1 as learning sentences.

[0090] After that, the selection unit (118) can check whether there are any characters recorded one or more times in duplicate on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table among ‘ge, dae, sal, heo, ma’.

[0091] In this regard, among ‘ge, dae, sal, heo, ma’, the characters that are recorded one or more times in the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table are ‘dae’ and ‘sal’, so the selection unit (118) generates a prompt instructing to generate a sentence in which ‘dae’ and ‘sal’ each appear one or more times, and by applying the prompt as input to the sentence generation model, additional learning sentences can be obtained from the sentence generation model.

[0092] Thus, when the learning sentences are selected through the selection unit (118) and the additional learning sentence is obtained at the same time, the message display unit (119) can display the learning sentences and the additional learning sentence on the screen, and display an instruction message on the screen instructing to transcribe the learning sentences and the additional learning sentence.

[0093] Then, the user can learn the characters ‘ge, dae, sal, heo, ma’ by transcribing the learning sentences using a keyboard or touch input connected to the electronic device (110), and at the same time, by transcribing the additional learning sentences, can also intensively learn the characters ‘dae’ and ‘sal’, which the user frequently gets wrong.

[0094] FIG. 2 is a flowchart illustrating the operation method of an electronic device that supports dictation practice through repetitive learning according to an embodiment of the present invention.

[0095] In step (S210), a sentence database containing multiple pre-generated sentences is maintained.

[0096] In step (S220), when a command to generate a problem for dictation practice is issued from the user of the electronic device, a first sentence, which is one of the plurality of sentences stored in the sentence database, is designated as a problem, and the first sentence is input to a pre-built speech synthesis model to perform speech synthesis, thereby generating a first synthesized speech, and the first synthesized speech is output through a speaker mounted on the electronic device at a preset speech output speed.

[0097] In step (S230), when a first input sentence is input from the user as a dictation answer sentence corresponding to the first synthesized voice, it is checked whether the string constituting the first input sentence and the string constituting the first sentence are identical to each other; if it is confirmed that they are not identical, the voice output speed is increased by a value multiplied by a preset first value, and the first synthesized voice is re-output through the speaker.

[0098] In step (S240), when a second input sentence is re-entered from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through step (S230), the string constituting the second input sentence and the string constituting the first sentence are checked to see if they are identical. If it is confirmed that they are not identical, the voice output speed is increased by a value obtained by multiplying by a preset second value—the second value is greater than the first value—and the first synthesized voice is re-output through the speaker.

[0099] In step (S250), when a third input sentence is re-entered from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through step (S240), the string constituting the third input sentence and the string constituting the first sentence are checked to see if they are identical. If it is confirmed that they are not identical, the voice output speed is increased by a value obtained by multiplying by a preset third value—the third value is greater than the second value—and the first synthesized voice is re-output through the speaker.

[0100] In step (S260), when a fourth input sentence is re-entered from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through step (S250), it is checked whether the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other; if it is confirmed that they are not identical, the first synthesized voice is re-output through the speaker at the same speed as the voice output speed, and then the first sentence is displayed on the screen.

[0101] At this time, according to one embodiment of the present invention, in step (S230), if it is confirmed that the string constituting the first input sentence and the string constituting the first sentence are identical to each other, the first sentence is displayed on the screen along with a message indicating that the first input sentence is the correct answer without re-outputting the first synthesized voice; in step (S240), if it is confirmed that the string constituting the second input sentence and the string constituting the first sentence are identical to each other, the first sentence is displayed on the screen along with a message indicating that the second input sentence is the correct answer without re-outputting the first synthesized voice; in step (S250), if it is confirmed that the string constituting the third input sentence and the string constituting the first sentence are identical to each other, the first sentence is displayed on the screen along with a message indicating that the third input sentence is the correct answer without re-outputting the first synthesized voice; and in step (S260), if it is confirmed that the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other, the Without re-outputting the first synthesized speech, the first sentence can be displayed on the screen along with a message indicating that the fourth input sentence is the correct answer.

[0102] Additionally, according to one embodiment of the present invention, in step (S230), if it is confirmed that the string constituting the first input sentence and the string constituting the first sentence are not identical to each other, the string constituting the first input sentence and the string constituting the first sentence are compared with each other, and among the characters recorded on a pre-specified character table (the character table is a table in which characters appearing one or more times in the plurality of sentences are recorded), a character confirmed to have occurred one or more times through the first input sentence is selected and recorded on a first typo information table, and then the voice output speed is increased by the value multiplied by the first value, and the first synthesized voice is re-output through the speaker, and in step (S240), if it is confirmed that the string constituting the second input sentence and the string constituting the first sentence are not identical to each other, the string constituting the second input sentence and the string constituting the first sentence are compared with each other, and among the characters recorded on the character table, a character confirmed to have occurred one or more times through the second input sentence Select and record on the second typo information table, then increase the voice output speed by the value multiplied by the second value, and re-output the first synthesized voice through the speaker; in step (S250), if it is confirmed that the string constituting the third input sentence and the string constituting the first sentence are not identical to each other, compare the string constituting the third input sentence and the string constituting the first sentence with each other, select a character among the characters recorded on the character table that is confirmed to have one or more typos through the third input sentence, record it on the third typo information table, then increase the voice output speed by the value multiplied by the third value, and re-output the first synthesized voice through the speaker; and in step (S260),If it is confirmed that the string constituting the fourth input sentence and the string constituting the first sentence are not identical to each other, the string constituting the fourth input sentence and the string constituting the first sentence are compared with each other, and among the characters recorded on the character table, a character confirmed to have occurred one or more times through the fourth input sentence is selected and recorded on the fourth typo information table, and then the first synthesized speech is re-output through the speaker at the same speed as the voice output speed, and the first sentence can be displayed on the screen.

[0103] At this time, according to one embodiment of the present invention, the method of operation of the electronic device may further include, when a sentence learning request command based on characters recorded on a typo information table is received from the user, the step of checking the characters recorded on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table, respectively; the step of selecting, among the plurality of sentences, sentences containing one or more characters recorded on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table as learning sentences; and the step of displaying the learning sentences on a screen and displaying an instruction message on a screen instructing to transcribe the learning sentences.

[0104] At this time, according to one embodiment of the present invention, the selection step is performed by checking whether there is a character recorded in duplicate at least once on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table once or more, and if it is confirmed that there is at least one first character among the characters recorded in duplicate, then inputting a prompt instructing a pre-set sentence generation model (the sentence generation model is a generative artificial intelligence model that receives a prompt and automatically generates a sentence corresponding to the input prompt based on a pre-built LLM (Large Language Model)) to generate a sentence in which each of the at least one first character appears at least once, thereby obtaining additional training sentences.

[0105] At this time, the above-mentioned displaying step may display the above-mentioned learning sentences and the above-mentioned additional learning sentences on the screen, and display an instruction message on the screen instructing to transcribe the above-mentioned learning sentences and the above-mentioned additional learning sentences.

[0106] Hereinafter, a method of operation of an electronic device according to an embodiment of the present invention has been described with reference to FIG. 2. Here, since the method of operation of an electronic device according to an embodiment of the present invention may correspond to the configuration of the operation of the electronic device (110) described using FIG. 1, a more detailed description thereof will be omitted.

[0107] A method of operation of an electronic device according to one embodiment of the present invention can be implemented as a computer program stored in a storage medium for execution through combination with a computer.

[0108] In addition, a method of operation of an electronic device according to an embodiment of the present invention may be implemented in the form of computer program instructions for execution through combination with a computer and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present invention, or they may be those known and available to 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 recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0109] As described above, the present invention has been explained by specific details such as specific components, limited embodiments, and drawings; however, this is provided merely to aid in a more comprehensive understanding of the invention, and the invention is not limited to the above embodiments. A person skilled in the art can make various modifications and variations from this description.

[0110] Accordingly, the scope of the present invention is not limited to the described embodiments, and all things equivalent to or having equivalent variations to the claims set forth below, as well as the claims set forth below, shall be considered to fall within the scope of the concept of the present invention. Explanation of the symbols

[0111] 110: Electronic device 111: Sentence Database 112: Question Generation Section 113: 1st re-output unit 114: 2nd re-output unit 115: 3rd re-output unit 116: 4th re-output unit 117: Verification Department 118: Sorting Department 119: Message display 10: Speaker

Claims

Claim 1 In an electronic device supporting dictation practice through repetitive learning, the device comprises: a sentence database in which a plurality of pre-generated sentences are stored; a problem generation unit that, upon receiving a command to generate a problem for dictation practice from a user of the electronic device, designates a first sentence, which is one of the plurality of sentences stored in the sentence database, as a problem, applies the first sentence as input to a pre-constructed speech synthesis model to perform speech synthesis, thereby generating a first synthesized voice, and outputs the first synthesized voice through a speaker mounted on the electronic device at a preset voice output speed; and, upon receiving a first input sentence from the user as a dictation answer sentence corresponding to the first synthesized voice, checks whether the string constituting the first input sentence is identical to the string constituting the first sentence, and if it is confirmed that they are not identical, compares the string constituting the first input sentence with the string constituting the first sentence, and among the characters recorded on a preset character table—the character table is a table in which characters appearing one or more times in the plurality of sentences are recorded—through the first input sentence A first re-output unit that selects a character confirmed to have one or more typos, records it on a first typo information table, and then increases the voice output speed by a value multiplied by a preset first value, and re-outputs the first synthesized voice through the speaker;A second re-output unit that, when a second input sentence is re-input from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the first re-output unit, checks whether the string constituting the second input sentence and the string constituting the first sentence are identical to each other; if it is confirmed that they are not identical, compares the string constituting the second input sentence and the string constituting the first sentence with each other, selects a character among the characters recorded on the character table that is confirmed to have one or more typos through the second input sentence, records it on the second typo information table, and then increases the voice output speed by a value obtained by multiplying it by a preset second value—the second value is a value greater than the first value—and re-outputs the first synthesized voice through the speaker; and, when a third input sentence is re-input from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the second re-output unit, checks whether the string constituting the third input sentence and the string constituting the first sentence are identical to each other Subsequently, if it is confirmed that they are not identical, a third re-output unit compares the string constituting the third input sentence with the string constituting the first sentence, selects a character among the characters recorded on the character table that is confirmed to have one or more typos through the third input sentence, records it on the third typo information table, and then increases the voice output speed by a value obtained by multiplying it by a preset third value—the third value is a value greater than the second value—and re-outputs the first synthesized voice through the speaker;A fourth re-output unit that, when a fourth input sentence is re-input by the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the third re-output unit, checks whether the string constituting the fourth input sentence and the string constituting the first sentence are identical, and if it is confirmed that they are not identical, compares the string constituting the fourth input sentence and the string constituting the first sentence, selects a character among the characters recorded on the character table that is confirmed to have an error one or more times through the fourth input sentence, records it on the fourth error information table, then re-outputs the first synthesized voice through the speaker at the same speed as the voice output speed, and then displays the first sentence on the screen; and a confirmation unit that, when a sentence learning request command based on the characters recorded on the error information table is received from the user, checks the characters recorded on the first error information table, the second error information table, the third error information table, and the fourth error information table, respectively.Among the plurality of sentences above, sentences containing one or more characters recorded in the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table within the sentence are selected as training sentences; and when the selection of the training sentences is completed, after checking whether there exists a character recorded duplicately one or more times in the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table, if it is confirmed that at least one first character exists as a duplicate character, a selection unit obtains additional training sentences by inputting a prompt instructing a preset sentence generation model—the sentence generation model is a generative artificial intelligence model that receives a prompt and automatically generates a sentence corresponding to the input prompt based on a pre-built LLM (Large Language Model)—to generate a sentence in which each of the at least one first character appears one or more times; An electronic device comprising a message display unit that displays the above-mentioned learning sentences and the above-mentioned additional learning sentences on a screen, and displays an instruction message on a screen instructing to transcribe the above-mentioned learning sentences and the above-mentioned additional learning sentences. Claim 2 In claim 1, if the first re-output unit confirms that the string constituting the first input sentence and the string constituting the first sentence are identical to each other, the first sentence is displayed on the screen along with a message indicating that the first input sentence is the correct answer without re-outputting the first synthesized voice; if the second re-output unit confirms that the string constituting the second input sentence and the string constituting the first sentence are identical to each other, the first sentence is displayed on the screen along with a message indicating that the second input sentence is the correct answer without re-outputting the first synthesized voice; if the third re-output unit confirms that the string constituting the third input sentence and the string constituting the first sentence are identical to each other, the first sentence is displayed on the screen along with a message indicating that the third input sentence is the correct answer without re-outputting the first synthesized voice; and if the fourth re-output unit confirms that the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other, the fourth input sentence is the correct answer without re-outputting the first synthesized voice An electronic device characterized by displaying the first sentence on a screen along with a directing message. Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 A method of operation for an electronic device that supports dictation practice through repetitive learning, comprising: a step of maintaining a sentence database in which a plurality of pre-generated sentences are stored; a step in which, when a command to generate a problem for dictation practice is granted from a user of the electronic device, a first sentence, which is one of the plurality of sentences stored in the sentence database, is designated as a problem, and the first sentence is input to a pre-constructed speech synthesis model to perform speech synthesis, thereby generating a first synthesized voice, and outputting the first synthesized voice through a speaker mounted on the electronic device at a preset voice output speed; and when a first input sentence is input from the user as a dictation answer sentence corresponding to the first synthesized voice, a check is made whether the string constituting the first input sentence and the string constituting the first sentence are identical, and if it is confirmed that they are not identical, the string constituting the first input sentence and the string constituting the first sentence are compared with each other, and among the characters recorded on a preset character table—the character table is a table in which characters appearing one or more times in the plurality of sentences are recorded—the first input A first re-output step of selecting a character confirmed to have one or more typos through a sentence, recording it on a first typo information table, and then increasing the voice output speed by a value multiplied by a preset first value to re-output the first synthesized voice through the speaker;A second re-output step in which, when a second input sentence is re-input from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the first re-output step, the string constituting the second input sentence and the string constituting the first sentence are compared with each other, and among the characters recorded on the character table, a character confirmed to have occurred at least once through the second input sentence is selected and recorded on the second typo information table, and then the voice output speed is increased by a value obtained by multiplying by a preset second value - the second value is a value greater than the first value - and the first synthesized voice is re-output through the speaker; and when a third input sentence is re-input from the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the second re-output step, the string constituting the third input sentence and the string constituting the first sentence are checked to see if they are identical, and if they are not identical, the string constituting the third input sentence and the string constituting the first sentence are compared with each other, and the A third re-output step of selecting a character among the characters recorded on a character table that is confirmed to have one or more typos through the third input sentence, recording it on a third typo information table, and then increasing the voice output speed by a value obtained by multiplying it by a preset third value—the third value being greater than the second value—and re-outputting the first synthesized voice through the speaker;A fourth re-output step, wherein when a fourth input sentence is re-input by the user as a dictation answer sentence corresponding to the first synthesized voice re-output through the third re-output step, the string constituting the fourth input sentence and the string constituting the first sentence are checked to see if they are identical; if they are not identical, the string constituting the fourth input sentence and the string constituting the first sentence are compared to each other, and among the characters recorded on the character table, a character confirmed to have occurred at least once through the fourth input sentence is selected and recorded on the fourth typo information table, and then the first synthesized voice is re-output through the speaker at the same speed as the voice output speed, and the first sentence is displayed on the screen; and when a sentence learning request command based on the characters recorded on the typo information table is received from the user, the characters recorded on the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table, respectively are checked.Among the plurality of sentences above, sentences containing one or more characters recorded in the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table within the sentence are selected as training sentences; and when the selection of training sentences is completed, after checking whether there is a character recorded duplicately one or more times in the first typo information table, the second typo information table, the third typo information table, and the fourth typo information table, if it is confirmed that at least one first character exists as a duplicate character, a pre-configured sentence generation model—the sentence generation model is a generative artificial intelligence model that receives a prompt and automatically generates a sentence corresponding to the input prompt based on a pre-constructed LLM (Large Language Model)—is input with a prompt instructing to generate a sentence in which each of the at least one first character appears one or more times, thereby obtaining an additional training sentence; A method of operating an electronic device comprising the step of displaying the above-mentioned learning sentences and the above-mentioned additional learning sentences on a screen, and displaying an instruction message on a screen instructing to transcribe the above-mentioned learning sentences and the above-mentioned additional learning sentences. Claim 7 In claim 6, the first re-output step displays the first sentence on the screen with a message indicating that the first input sentence is the correct answer without re-outputting the first synthesized voice when it is confirmed that the string constituting the first input sentence and the string constituting the first sentence are identical to each other; the second re-output step displays the first sentence on the screen with a message indicating that the second input sentence is the correct answer without re-outputting the first synthesized voice when it is confirmed that the string constituting the second input sentence and the string constituting the first sentence are identical to each other; the third re-output step displays the first sentence on the screen with a message indicating that the third input sentence is the correct answer without re-outputting the first synthesized voice when it is confirmed that the string constituting the fourth input sentence and the string constituting the first sentence are identical to each other; and the fourth re-output step indicates that the fourth input sentence is the correct answer without re-outputting the first synthesized voice A method of operation of an electronic device characterized by displaying the first sentence on a screen along with a directing message. Claim 8 delete Claim 9 delete Claim 10 delete Claim 11 A computer-readable recording medium having a computer program for executing the method of either paragraph 6 or 7 through combination with a computer. Claim 12 A computer program stored on a storage medium for executing the method of either paragraph 6 or 7 through combination with a computer.

Images