KR102375508B1 - Electronic device that enables speech recognition of editing commands frequently used in document editing programs and operating method thereof - Google Patents

Abstract

Disclosed are an electronic device that enables voice recognition of an editing command frequently used in a document creation program, and an operating method thereof. An electronic device and an operating method thereof according to the present invention select editing commands frequently used in a document creation program, perform voice synthesis based on a corpus corresponding to the selected editing commands, and generate a synthesized voice, After creating a voice recognition module through machine learning using a synthesized voice for editing commands and a corpus, by recognizing the user's voice command through the voice recognition module, the user can use the voice to edit the frequently used editing commands when writing documents. We can support you for easy approval.

Description

ELECTRONIC DEVICE THAT ENABLES SPEECH RECOGNITION OF EDITING COMMANDS FREQUENTLY USED IN DOCUMENT EDITING PROGRAMS AND OPERATING METHOD THEREOF

The present invention relates to an electronic device that enables voice recognition for an editing command frequently used in a document creation program, and an operating method thereof.

In recent years, as computers, smart phones, or tablet PCs have become widespread, various types of document creation programs have been released that allow users to read, write, and edit electronic documents using such electronic devices.

These document creation programs include a word processor supporting basic document creation and editing, a spreadsheet supporting data input, arithmetic operations, and data management, and presentation programs supporting a presenter's presentation.

A document creation program supports various editing commands, and users often use only the editing commands they frequently use when creating a document. Accordingly, if an interfacing technology that allows a user to more easily use editing commands frequently used is introduced, the user's convenience in writing a document may be promoted.

Recently, as electronic devices equipped with artificial intelligence functions are released, when a user applies a command with a voice, a technology for performing control by recognizing the user's voice is attracting attention.

Speech recognition technology is a technology that, when a voice is input from a speaker, extracts a feature vector by analyzing the characteristics of the voice, recognizes a pattern of the feature vector, and outputs a text matching the speaker's voice as a result based on the pattern recognition result means

This speech recognition technology is configured to generate text matching the speech applied by the user by collecting various speech data and building it as predetermined speech recognition model data.

In order to improve the performance of the speech recognizer, it is necessary to secure various corpus, make an actual utterance based on the secured corpus, and train a speech recognition model based on the speech recognition result.

In this way, as the speech recognition technology draws attention, if a voice recognition module for editing commands frequently used by a user can be built in a document creation program, when a user creates a document, the frequently used editing commands and The user's convenience may be increased in that the corresponding editing command can be used only by applying the related command by voice.

Therefore, by identifying the editing commands frequently used by the user in the document creation program and building a voice recognition module for the corresponding editing commands, the user can easily use the frequently used editing commands just by applying the voice command. It is necessary to study the technology to support it.

An electronic device and an operating method thereof according to the present invention select editing commands frequently used in a document creation program, perform voice synthesis based on a corpus corresponding to the selected editing commands, and generate a synthesized voice, After creating a voice recognition module through machine learning using a synthesized voice for editing commands and a corpus, by recognizing the user's voice command through the voice recognition module, the user can use the voice to edit the frequently used editing commands when writing documents. We want to support you so that you can easily apply.

According to an embodiment of the present invention, an electronic device enabling voice recognition of an editing command frequently used in a document writing program includes a preset corpus corresponding to each of a plurality of editing commands supported by the document writing program. The stored corpus storage unit counts the number of times the plurality of editing commands are used by the user in the document creation program during a preset period, and then edits a preset number of the plurality of editing commands in the order of the highest number of use After extracting a corpus corresponding to each of the selected editing commands from the editing command selection unit for selecting commands, and the corpus storage unit, the corpus corresponding to each of the selected editing commands is input to a pre-built speech synthesis module. A voice synthesizer for generating a synthesized voice for a corpus corresponding to each of the selected editing commands by applying a voice synthesis to the corpus corresponding to each of the selected editing commands and to each of the selected editing commands and a voice recognition module generator configured to generate a voice recognition module for recognizing a voice command related to the execution of the selected editing commands by performing machine learning for constructing a voice recognizer based on the synthesized voice for the corresponding corpus.

In addition, according to an embodiment of the present invention, a method of operating an electronic device that enables voice recognition of an editing command frequently used in a document writing program is set in advance corresponding to each of a plurality of editing commands supported by the document writing program. maintaining a corpus storage unit in which a corpus is stored; after counting the number of times the plurality of editing commands are used by a user in the document creation program for a preset period, the number of times of use among the plurality of editing commands is selecting a preset number of editing commands in a large order; extracting a corpus corresponding to each of the selected editing commands from the corpus storage unit; generating a synthesized voice for the corpus corresponding to each of the selected editing commands by applying the selected corpus as an input to perform voice synthesis; and the corpus corresponding to each of the selected editing commands and the selected editing command and generating a voice recognition module for recognizing a voice command related to the execution of the selected editing commands by performing machine learning for constructing a voice recognizer based on the synthesized voice for the corpus corresponding to each of them.

An electronic device and an operating method thereof according to the present invention select editing commands frequently used in a document creation program, perform voice synthesis based on a corpus corresponding to the selected editing commands, and generate a synthesized voice, After creating a voice recognition module through machine learning using a synthesized voice for editing commands and a corpus, by recognizing the user's voice command through the voice recognition module, the user can use the voice to edit the frequently used editing commands when writing documents. We can support you for easy approval.

1 is a diagram illustrating a structure of an electronic device that enables voice recognition for an editing command frequently used in a document creation program according to an embodiment of the present invention.
2 is a flowchart illustrating an operating method of an electronic device that enables voice recognition for an editing command frequently used in a document creation program according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. These descriptions are not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. While describing each drawing, like reference numerals are used for similar components, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, refer to those of ordinary skill in the art to which the present invention belongs. It has the same meaning as is commonly understood by those who have it.

In this document, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated. In addition, in various embodiments of the present invention, each of the components, functional blocks or means may be composed of one or more sub-components, and the electrical, electronic, and mechanical functions performed by each component are electronic. A circuit, an integrated circuit, an ASIC (Application Specific Integrated Circuit), etc. may be implemented as various well-known devices or mechanical elements, and may be implemented separately or two or more may be integrated into one.

On the other hand, the blocks in the accompanying block diagram or steps in the flowchart are computer program instructions that are loaded in a processor or memory of equipment capable of data processing, such as a general-purpose computer, a special-purpose computer, a portable notebook computer, and a network computer, and perform specified functions. can be interpreted as meaning Since these computer program instructions may be stored in a memory provided in a computer device or in a computer-readable memory, the functions described in the blocks of the block diagram or the steps of the flowchart are produced as articles of manufacture containing instruction means for performing the same. it might be In addition, each block or each step may represent a module, segment, or portion of code comprising one or more executable instructions for executing the specified logical function(s). It should also be noted that, in some alternative embodiments, it is also possible for the functions recited in blocks or steps to be executed out of the prescribed order. For example, two blocks or steps shown one after another may be performed substantially simultaneously or in the reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram illustrating a structure of an electronic device that enables voice recognition for an editing command frequently used in a document creation program according to an embodiment of the present invention.

Referring to FIG. 1 , the electronic device 110 according to the present invention includes a corpus storage unit 111 , an editing command selection unit 112 , a voice synthesis unit 113 , and a voice recognition module generation unit 114 .

The corpus storage unit 111 stores a preset corpus corresponding to each of a plurality of editing commands supported by the document creation program.

A corpus refers to a set of samples extracted from a language for a specific purpose for natural language research, and can be viewed as a set of predetermined sentences. These corpora can be used to build speech recognizers or speech synthesizers.

In relation to this, the corpus storage unit 111 may store a corpus corresponding to each of the plurality of editing commands in the form shown in Table 1 below.

Multiple editing commands corpus Enter table enter a ticket
enter a table
Execute table input function
... bold Make the letters bold
bold text
... delete letters delete the text
delete letters
Execute character deletion
...

The editing command selection unit 112 counts the number of times the plurality of editing commands are used by the user in the document creation program for a preset period, and then sets a preset number of the plurality of editing commands in the order of the highest number of uses. Select edit commands.

For example, if the preset period is '30 days' and the preset number is '10', the editing command selection unit 112 may be configured to select the plurality of After counting the number of times the edit commands are used, '10' edit commands may be selected in the order of the plurality of edit commands from among the plurality of edit commands.

The speech synthesis unit 113 extracts a corpus corresponding to each of the selected editing commands from the corpus storage unit 111, and then inputs the corpus corresponding to each of the selected editing commands to a pre-built speech synthesis module. By applying and performing voice synthesis, a synthesized voice for the corpus corresponding to each of the selected editing commands is generated.

Here, speech synthesis refers to a technology for converting text into speech (Text-To-Speech: TTS). In relation to, as in the above example, when it is said that '10' editing commands are selected through the editing command selection unit 112, the voice synthesis unit 113 is Synthesis of a corpus corresponding to each of the '10' editing commands by extracting a corpus corresponding to each of the '10' editing commands and applying the extracted corpus as an input to a pre-established speech synthesis module can generate voice.

The voice recognition module generating unit 114 performs machine learning for constructing a voice recognizer based on a synthesized voice for a corpus corresponding to each of the selected editing commands and a corpus corresponding to each of the selected editing commands, A voice recognition module for recognizing a voice command related to the execution of the selected editing commands is generated.

In relation to, as in the above example, if the synthesized voice for the corpus corresponding to each of the '10' editing commands is generated, the voice recognition module generating unit 114 corresponds to each of the '10' editing commands. By performing machine learning for constructing a voice recognizer based on the corpus and the synthesized voice therefor, a voice recognition module for recognizing voice commands related to the execution of '10' editing commands can be created.

In this case, according to an embodiment of the present invention, the electronic device 110 may further include a voice command execution unit 115 .

After the creation of the voice recognition module is completed, the voice command execution unit 115 executes a voice command input function for executing an editing command frequently used by the user in the document creation program, and performs a first voice through a microphone. When a command is applied, the first voice command is recognized through the voice recognition module, and an editing command corresponding to the first voice command among the selected editing commands is executed.

At this time, according to an embodiment of the present invention, when the first voice command is applied through the microphone, the voice command execution unit 115 recognizes the first voice command through the voice recognition module to recognize the first voice command. A recognition text for a command is generated, and a sentence composed of a character string having the longest length of a longest common subsequence (LCS) with a character string constituting the recognition text among the selected editing commands is included in a corpus, and The existing editing command may be designated and executed as an editing command corresponding to the first voice command.

For example, it is assumed that a voice recognition module for recognizing a voice command related to the execution of '10' editing commands is generated by the voice recognition module generating unit 114 as in the above-described example. In this case, while the user is writing a document through the document writing program, the user executes a voice command input function on the electronic device 110 in order to apply a frequently used editing command by voice, and then the electronic device 110 When a first voice command is applied through a microphone connected to .

Then, the voice command execution unit 115 receives an edit command including, in a corpus, a sentence composed of a character string having the maximum LCS length with the character string constituting the recognition text among the '10' edit commands. It is possible to designate and execute an edit command corresponding to the first voice command.

Here, LCS means a continuous string that matches in two strings. When there are 'ACAYKP' and 'CAPCAK', the LCS between the two strings is 'ACAK', and the length of the LCS is '4'. . In this regard, it is assumed that an editing command of 'table input' is included among the '10' editing commands, and as a result of performing voice recognition on the first voice command applied by the user, 'enter a table' When the recognition text 'Do it' is generated, the length of the LCS between 'Enter table', which is a sentence included in the corpus corresponding to the edit command 'Enter table', and 'Enter table', which is the recognition text, It can be 5'. In this way, the voice command execution unit 115 measures the length of the LCS between the sentences constituting the corpus for the '10' editing commands and 'Enter a table', which is the recognition text, and then the ' Corresponding to the first voice command an editing command including a sentence in a corpus consisting of a character string having the maximum length of LCS and a character string constituting the recognition text 'Enter table' among the '10' editing commands It can be executed by specifying it as an editing command.

As a result, the electronic device 110 according to the present invention selects editing commands frequently used in a document creation program, performs voice synthesis based on a corpus corresponding to the selected editing commands to generate a synthesized voice, and the selection After generating a voice recognition module through machine learning using a corpus and synthetic voice for the edited edit commands, the voice recognition module recognizes the user's voice command, so that the user can use the voice for editing commands that are frequently used when writing documents. We can support you for easy authorization through

According to an embodiment of the present invention, the electronic device 110 includes a part count unit 116 , a feature vector generator 117 , a feature vector check unit 118 , a cosine similarity calculator 119 , and a recommended voice command display unit ( 120) may be further included.

The part counting unit 116 divides the preset period into k (k is a natural number greater than or equal to 2) partial periods, so that each of the selected editing commands in the document creation program is used within the k partial periods. count the number of times

The feature vector generator 117 generates, for each of the selected editing commands, a k-dimensional feature vector having, as a component, the number of times of use within the k partial periods.

In relation to this, as in the above example, the preset period is referred to as '30 days', the edit commands selected by the edit command selection unit 112 are referred to as '10' edit commands, and k is '3'. , the partial count unit 116 divides the period of '30 days' into three partial periods of '10 days', '10 days', and '10 days', and within the three partial periods may count the number of times each of the '10' editing commands is used in the document creation program.

Then, the feature vector generating unit 117 may generate a three-dimensional feature vector having, as a component, the number of times of use within three partial periods for each of the '10' editing commands. For example, when the number of times of use within three partial periods in a specific edit command among the '10' edit commands is '5', '4', and '7', respectively, the feature vector generating unit Reference numeral 117 may generate a three-dimensional feature vector called '[5 4 7]' for the specific editing command.

The feature vector check unit 118 is configured to, when a first edit command is executed as an edit command corresponding to the first voice command among the edit commands selected by the voice command execution unit 115, Check the k-dimensional feature vector.

The cosine similarity calculating unit 119 calculates the cosine similarity between each of the k-dimensional feature vectors for the remaining editing commands except for the first editing command among the selected editing commands and the k-dimensional feature vector with respect to the first editing command. Calculate.

In relation to this, when it is said that the selected editing commands are '10' editing commands, the cosine similarity calculating unit 119 includes a feature vector for each of the '9' editing commands excluding the first editing command and the A cosine similarity between feature vectors with respect to the first editing command may be calculated.

Here, the cosine similarity may be calculated according to Equation 1 below.

Here, S is the cosine similarity between vectors A and B, and has a value between -1 and 1, and a larger value means a similar vector, A _i is the i-th component of the vector A, and B _i is the i of the vector B means the second component.

The recommended voice command display unit 120 selects a second editing command having a k-dimensional feature vector in which the cosine similarity is calculated at the maximum among the remaining editing commands, and then responds to the second editing command from the corpus storage unit 111 . Extracts any one sentence included in the A guide message is displayed on the screen.

For example, when the second editing command having the maximum cosine similarity is 'table input', the recommended voice command display unit 120 displays a corpus corresponding to 'table input' from the corpus storage unit 111 as shown in Table 1 above. After extracting any one sentence such as 'execution of table input function' from among the sentences included in At the same time, a guide message guiding to apply a voice command according to the recommended voice command may be displayed on the screen.

That is, in the electronic device 110 according to the present invention, when a first edit command among frequently used edit commands is executed as the user applies a voice command, the first edit command from among the frequently used edit commands is used. After checking the second editing command having a usage pattern similar to the pattern, a predetermined recommended voice command according to the second editing command may be displayed on the screen. Through this, the user may intuitively recognize that a voice command for the second edit command can be additionally applied as an edit command related to the first edit command.

2 is a flowchart illustrating an operating method of an electronic device that enables voice recognition for an editing command frequently used in a document creation program according to an embodiment of the present invention.

In step S210, a corpus storage unit in which a preset corpus corresponding to each of a plurality of editing commands supported by the document creation program is stored is maintained.

In step S220, after counting the number of times the plurality of editing commands are used by the user in the document creation program for a preset period, a preset number of editing commands are executed in the order of the highest number of use among the plurality of editing commands. select

In step S230, after extracting a corpus corresponding to each of the selected editing commands from the corpus storage unit, the corpus corresponding to each of the selected editing commands is applied as an input to a pre-built speech synthesis module to synthesize speech By performing , a synthesized voice for the corpus corresponding to each of the selected editing commands is generated.

In step S240, by performing machine learning for constructing a speech recognizer based on the synthesized speech for the corpus corresponding to each of the selected editing commands and the corpus corresponding to each of the selected editing commands, the selected editing Create a voice recognition module for recognizing a voice command related to the execution of the commands.

At this time, according to an embodiment of the present invention, in the method of operating the electronic device, after the generation of the voice recognition module is completed, a voice command input function for executing an editing command frequently used by the user in the document creation program is executed and when a first voice command is applied through the microphone, recognizing the first voice command through the voice recognition module and executing an editing command corresponding to the first voice command among the selected editing commands may further include.

At this time, according to an embodiment of the present invention, in the step of executing the editing command, when the first voice command is applied through the microphone, the first voice command is recognized through the voice recognition module to recognize the first voice command. A recognition text for a command is generated, and an editing command including, in a corpus, a sentence consisting of a character string having the maximum LCS length with a character string constituting the recognition text among the selected editing commands is applied to the first voice command. It can be executed by specifying it with the corresponding edit command.

Also, according to an embodiment of the present invention, in the method of operating the electronic device, the preset period is divided into k (k is a natural number greater than or equal to 2) partial periods, and the selected editing commands in the document creation program are counting the number of times each is used within the k partial periods, generating, for each of the selected editing instructions, a k-dimensional feature vector having as a component the number of times of use within the k partial periods When a first editing command is executed as an editing command corresponding to the first voice command among the selected editing commands through the step of executing the editing command, a k-dimensional feature vector for the first editing command confirming, calculating a cosine similarity between each of the k-dimensional feature vectors for the remaining editing commands except for the first editing command among the selected editing commands and the k-dimensional feature vector with respect to the first editing command After selecting a second editing command having a k-dimensional feature vector in which the cosine similarity is calculated at the maximum from among the remaining editing commands, the second editing command is selected from the corpus storage unit and is included in the corpus corresponding to the second editing command. Extracting a sentence, displaying the extracted sentence as a recommended voice command for executing the second editing command, and simultaneously displaying a guidance message guiding to apply a voice command according to the recommended voice command on the screen The step of displaying may be further included.

In the above, an operating method of an electronic device enabling voice recognition for an editing command frequently used in a document creation program according to an embodiment of the present invention has been described with reference to FIG. 2 . Here, the operating method of the electronic device for enabling voice recognition for an editing command frequently used in a document writing program according to an embodiment of the present invention is a method for editing commands frequently used in the document writing program described with reference to FIG. 1 . Since it may correspond to the configuration of the operation of the electronic device 110 that enables voice recognition, a detailed description thereof will be omitted.

According to an embodiment of the present invention, the method of operating an electronic device that enables voice recognition for an editing command frequently used in a document creation program may be implemented as a computer program stored in a storage medium for execution through combination with a computer. there is.

In addition, the method of operating an electronic device that enables voice recognition for an editing command frequently used in a document creation program according to an embodiment of the present invention is implemented in the form of a program command that can be executed through various computer means and is read by a computer. It can be recorded on any available medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, in the present invention, specific matters such as specific components, etc., and limited embodiments and drawings have been described, but these are only provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , various modifications and variations are possible from these descriptions by those of ordinary skill in the art to which the present invention pertains.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and not only the claims described below, but also all of the claims and all equivalents or equivalent modifications to the claims will be said to belong to the scope of the spirit of the present invention. .

110: Electronic device that enables voice recognition for frequently used editing commands in a document creation program
111: corpus storage unit 112: edit command selection unit
113: voice synthesis unit 114: voice recognition module generation unit
115: voice command execution unit 116: partial count unit
117: feature vector generator 118: feature vector checker
119: cosine similarity calculating unit 120: recommended voice command display unit

Claims (10)

a corpus storage unit in which a preset corpus corresponding to each of a plurality of editing commands supported by the document creation program is stored;
After counting the number of times the plurality of editing commands are used by the user in the document creation program for a preset period, edit command selection for selecting a preset number of edit commands in the order of the highest number of use among the plurality of editing commands wealth;
Partial count for dividing the preset period into k (k is a natural number greater than or equal to 2) partial periods to count the number of times each of the selected editing commands in the document creation program is used within the k partial periods wealth;
a feature vector generator for generating, for each of the selected editing commands, a k-dimensional feature vector having as a component the number of times of use within the k partial periods;
After extracting a corpus corresponding to each of the selected editing commands from the corpus storage unit, the corpus corresponding to each of the selected editing commands is applied as an input to a pre-established voice synthesis module to perform voice synthesis. a voice synthesizer for generating a synthesized voice for a corpus corresponding to each of the selected editing commands;
By performing machine learning for constructing a speech recognizer based on a corpus corresponding to each of the selected editing commands and a synthesized voice for a corpus corresponding to each of the selected editing commands, execution of the selected editing commands is related a voice recognition module generator generating a voice recognition module for recognizing a voice command;
After the creation of the voice recognition module is completed, a voice command input function for executing an editing command frequently used by the user is executed in the document creation program, and when a first voice command is applied through a microphone, the voice recognition a voice command execution unit recognizing the first voice command through a module and executing an editing command corresponding to the first voice command among the selected editing commands;
When a first editing command is executed as an editing command corresponding to the first voice command among the editing commands selected by the voice command execution unit, a feature vector for confirming a k-dimensional feature vector for the first editing command confirmation unit;
a cosine similarity calculator configured to calculate a cosine similarity between each of the k-dimensional feature vectors for the remaining editing commands except for the first editing command among the selected editing commands and the k-dimensional feature vectors for the first editing command; and
After selecting a second editing command having a k-dimensional feature vector in which the cosine similarity is calculated at the maximum among the remaining editing commands, any one sentence included in the corpus corresponding to the second editing command is selected from the corpus storage unit. Extracting and displaying the extracted sentence as a recommended voice command for executing the second editing command on the screen and simultaneously displaying a guide message guiding to apply a voice command according to the recommended voice command on the screen Recommended voice command display
An electronic device that enables speech recognition for editing commands frequently used in document creation programs comprising: delete According to claim 1,
The voice command execution unit
When the first voice command is applied through the microphone, the first voice command is recognized through the voice recognition module to generate recognition text for the first voice command, and the recognition text among the selected editing commands An editing command including a sentence consisting of a character string having the longest length of the longest common subsequence (LCS) with the character string constituting the corpus is designated as the editing command corresponding to the first voice command and executed An electronic device that enables speech recognition for frequently used editing commands in document creation programs. delete maintaining a corpus storage unit in which a preset corpus corresponding to each of a plurality of editing commands supported by the document creation program is stored;
counting the number of times the plurality of editing commands are used by the user in the document creation program during a preset period, and then selecting a preset number of edit commands from among the plurality of editing commands in an order of the greatest number of use;
dividing the preset period into k (k is a natural number equal to or greater than 2) partial periods, and counting the number of times each of the selected editing commands is used within the k partial periods in the document creation program;
generating, for each of the selected editing instructions, a k-dimensional feature vector having as a component the number of uses within the k partial periods;
After extracting a corpus corresponding to each of the selected editing commands from the corpus storage unit, the corpus corresponding to each of the selected editing commands is applied as an input to a pre-established voice synthesis module to perform voice synthesis. generating a synthesized voice for a corpus corresponding to each of the selected editing commands;
By performing machine learning for constructing a speech recognizer based on a corpus corresponding to each of the selected editing commands and a synthesized voice for a corpus corresponding to each of the selected editing commands, execution of the selected editing commands is related generating a voice recognition module for recognizing a voice command;
After the creation of the voice recognition module is completed, a voice command input function for executing an editing command frequently used by the user is executed in the document creation program, and when a first voice command is applied through a microphone, the voice recognition recognizing the first voice command through a module and executing an editing command corresponding to the first voice command among the selected editing commands;
When a first editing command is executed as an editing command corresponding to the first voice command among the selected editing commands through the step of executing the editing command, a k-dimensional feature vector for the first editing command is checked. step;
calculating a cosine similarity between each of the k-dimensional feature vectors for the remaining editing commands excluding the first editing command among the selected editing commands and the k-dimensional feature vectors for the first editing command; and
After selecting a second editing command having a k-dimensional feature vector in which the cosine similarity is calculated at the maximum among the remaining editing commands, any one sentence included in the corpus corresponding to the second editing command is selected from the corpus storage unit. Extracting and displaying the extracted sentence as a recommended voice command for executing the second editing command on the screen and simultaneously displaying a guide message guiding to apply a voice command according to the recommended voice command on the screen step
An operating method of an electronic device that enables voice recognition for editing commands frequently used in a document creation program comprising a. delete 6. The method of claim 5,
The step of executing the editing command is
When the first voice command is applied through the microphone, the first voice command is recognized through the voice recognition module to generate recognition text for the first voice command, and the recognition text among the selected editing commands An editing command including a sentence consisting of a character string having the longest length of the longest common subsequence (LCS) with the character string constituting the corpus is designated as the editing command corresponding to the first voice command and executed A method of operating an electronic device that enables voice recognition for editing commands frequently used in document creation programs. delete A computer-readable recording medium recording a computer program for executing the method of any one of claims 5 or 7 through combination with a computer. A computer program stored in a storage medium for executing the method of any one of claims 5 or 7 through combination with a computer.

Images