KR102060229B1 - Method for assisting consecutive interpretation self study and computer readable medium for performing the method - Google Patents

Abstract

Disclosed is a method for assisting self-interpretation and a recording medium for performing the same. In the sequential interpretation self-study assistance method according to the present invention, in the sequential interpretation self-study assistance method using a learner terminal possessed by a learner, receiving a text file for sequential interpretation self-study, the text file for a predetermined playback time by voice Outputting, and receiving voice response information generated during a sequential interpretation process performed by the learner during a predetermined recording time when the reproduction time elapses, generating an interpreted text that characterizes the response information, and generates the response information. Analyzing and interpreting at least one of a silence section, an interpreter start delay section, and a specific syllable duration section in the interpreter text when it is determined that an interpreter delay section representing the interpreter's interpretation characteristics occurs. Analyze the results of the sequential interpretation performed by the learner Generating evaluation data for self evaluation.

Description

Sequential interpretation self-study method and recording medium for performing the same {METHOD FOR ASSISTING CONSECUTIVE INTERPRETATION SELF STUDY AND COMPUTER READABLE MEDIUM FOR PERFORMING THE METHOD}

The present invention relates to a sequential interpretation self-study assistance method and a recording medium for performing the same, and more specifically, sequential interpretation self-study assistance that provides the ability to automatically evaluate the self-study file upload and sequential interpretation self-study results for sequential interpretation practice A method and a recording medium for performing the same.

As the development of technology related to smartphones and wireless Internet is advanced, online-based learning programs are emerging regardless of time and place. In particular, in the foreign language learning, online-based learning is very popular because it can be provided education according to the level of the learner at a relatively low cost.

On the other hand, repetitive training and proper feedback are important for interpreter learning. This has led to the launch of online-based programs that allow you to learn for yourself anytime, anywhere. However, even with the currently released programs, it is difficult to characterize voice recorded interpretation results and compare them with the original text.

Korea Patent Registration No. 10-1438087 Korean Patent Publication No. 10-2005-0119808

In one aspect of the present invention, the learner directly uploads the original text file for sequential interpretation training, and analyzes the sequential interpretation learning results for the original text file to easily check or interpret the learner's interpretation characteristics generated in the sequential interpretation process. It provides a method of assisting the sequential interpretation self-study to provide information and a recording medium for performing the same.

The technical problem of the present invention is not limited to the technical problem mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

In the sequential interpretation self-study assistance method according to an embodiment of the present invention, in the sequential interpretation self-study assistance method using a learner terminal possessed by the learner, receiving a text file for sequential interpretation self-study, the original text for a predetermined playback time Outputting a file by voice and receiving voice response information generated during the sequential interpretation process performed by the learner during a predetermined recording time when the reproduction time elapses, generating an interpreted text that characterizes the response information; Analyzing the response information, and if it is determined that an interpreting delay section indicating the interpreting characteristics of the learner is generated, displaying at least one section of a silence section, an interpreting start delay section, and a specific syllable duration section on the interpreting text. And analyzing the interpreted text to be performed by the learner. Generating evaluation data for self-assessing the interpretation result.

The displaying of the silence section representing the interpreter characteristics of the learner on the interpretation text may include converting the response information into the text text, and detecting a section in which the silence time lasts more than a predetermined reference time based on the response information. The method may include generating a silence symbol corresponding to the section, and generating the interpreted text in which the silence symbol is reflected between the text.

The evaluation data may include information on the number of times the silent symbols are inserted into the interpreted text and the number of times the average silent symbols appear for each sentence.

In the displaying of the specific syllable duration section representing the learner's interpretation characteristics on the interpreted text, converting the response information into the text text, analyzing the response information, the section in which the specific syllable lasts more than a predetermined reference time The method may include detecting a specific syllable duration symbol corresponding to the section, and generating the interpreted text reflecting the specific syllable duration symbol between the text.

The evaluation data may include information about the number of times the specific syllable duration symbol is inserted into the interpreted text and the number of occurrences of the average specific syllable duration symbol for each sentence.

The displaying of the interpretation start delay period representing the interpreter characteristics of the learner on the interpretation text may include checking an output end time of the original file and an input start time of the response information, the output end time and the input start. Generating an interpretation start delay symbol representing a time interval of time and generating the interpretation text reflecting the interpretation start delay symbol.

Generating the interpretation start delay symbol is generated when it is determined that a time interval between the output end time and the input start time exceeds a predetermined threshold time, and the interpretation start delay symbol is displayed at the front of the interpretation text. It can be characterized by.

The evaluation data may include information on the number of times the interpretation start delay symbol is inserted into the interpretation text, and information indicating a length of a time interval between the output end time and the input start time.

The evaluation data includes at least one of information on a missing rate and an additional rate or information on a missing number and an additional number, and generating the evaluation data includes converting the original file into original text and converting the original text into the original text. According to a result of comparing the text and the interpreted text, the information about the missing rate and the additional rate or the information about the missing number and the additional number may be calculated.

The outputting of the original file by voice may include analyzing the history of at least one of information about the missing rate and the additional rate or information about the missing number and the additional number, and after the predetermined recording time has elapsed. The audio reproduction speed of the original text file to be output next time can be varied.

The learner terminal displays the original text on the screen and the interpreted text at the bottom of the original text, from the time when the output of the original file is terminated for the predetermined reproduction time until the response information is started. The time required may be displayed between the original text and the interpreted text.

Outputting the original text file as a voice during the predetermined playing time is based on the playing time set by the learner so that the learner terminal plays the original text file during the predetermined playing time. Divided into a plurality of sub-groups, and outputs all sentences included in any one sub-group during the playback time as a voice, and records the voice input from the learner for a predetermined recording time after the playback time elapses. Response information for each subgroup can be generated.

The learner terminal outputs all sentences included in the next subgroup by voice after the predetermined recording time elapses, and repeats the process of recording the voice input from the learner, thereby constituting the original text file. The response information for each subgroup and all response information for each subgroup are generated to generate total response information. The response information may include at least one of the response information for each subgroup and the overall response information.

In addition, it may be a computer-readable recording medium having a computer program recorded thereon for performing the sequential interpretation self-study assistance method according to the present invention.

According to one aspect of the present invention described above, the learner does not need to operate the machine during the interpretation learning through the original text splitting function, can perform sequential interpretation training regardless of time and place, the learner's interpretation characteristics The reflected results can be used to carry out a reliable self-assessment.

1 is a diagram showing the configuration of a learner terminal providing a sequential interpretation self-study assistance system according to an embodiment of the present invention.
2 to 5 illustrate embodiments of screens output from the learner terminal of FIG. 1.
6 is a flowchart illustrating a schematic flow of a method for assisting sequential interpretation in accordance with an embodiment of the present invention.

DETAILED DESCRIPTION OF THE INVENTION The following detailed description of the invention refers to the accompanying drawings that show, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It is to be understood that the various embodiments of the invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein may be embodied in other embodiments without departing from the spirit and scope of the invention in connection with one embodiment. In addition, it is to be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. The following detailed description, therefore, is not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims, along with the full scope of equivalents to which such claims are entitled. Like reference numerals in the drawings refer to the same or similar functions throughout the several aspects.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the drawings.

1 is a block diagram showing the configuration of a learner terminal for providing a sequential interpretation self-study assistance system according to an embodiment of the present invention.

Learner terminal 100 is a device capable of communication and input and output of information, for example, may be implemented as a PC, smart phone, tablet PC, etc., software for providing a sequential interpretation self-study assistance method according to the present invention (application ) Can be installed and run.

The learner terminal 100 registers the original file for sequential interpretation training, divides and plays the original file for a predetermined play time, and then generates a response information by recording a learner's voice input for a predetermined recording time. In addition, the response information may be analyzed to generate information for self-evaluation.

Specifically, the learner terminal 100 for providing a sequential interpretation self-study assistance system according to an embodiment of the present invention, the communication unit 110, the input unit 120, the output unit 130 and the controller 140 Can be.

The learner terminal 100 may be implemented by more components than those shown in FIG. 1, and may be implemented by fewer components. For example, the learner terminal 100 may further include components such as a memory unit (not shown) for storing received or generated data and a battery unit (not shown) for supplying power to the learner terminal 100. . Alternatively, in the learner terminal 100, at least two components of the communication unit 110, the input unit 120, the output unit 130, and the control unit 140 are integrated into one component, and one component is a complex function. You can also do Hereinafter, the above-described components will be described in detail.

The communicator 110 may enable wired or wireless communication of the learner terminal 100, and may include one or more components for performing wired or wireless communication. For example, the communication unit 110 may be implemented to include a component that enables communication of any one of Bluetooth, 3G, 4G, 5G, infrared and wireless LAN communication.

The input unit 120 may generate input data by the learner. To this end, the input unit 120 may be composed of a keypad, a dome switch, a touch pad, a microphone, and the like. In particular, a touch screen for registering the original file according to the learner's operation, and a microphone for the voice recording of the learner are provided. It is preferable to comprise.

The output unit 130 is a configuration provided for outputting an audio signal or a video signal. For this purpose, the output unit 130 may include a display, a speaker, and the like. For example, the output unit 130 may output a user interface (UI) or a graphical user interface (GUI) executed by software (application) that provides a sequential interpretation study assistance method. Alternatively, the output unit 130 may output an original text file in a voice form for sequential interpretation training, response information corresponding to the original text file, and an interpreted text.

To this end, the output unit 130 outputs the original text file and the response information to the audio output unit 131, and the image output unit 132 for displaying the original text of the original text and the interpreted text of the response information ) May be included.

The controller 140 may control the overall operation of the learner terminal 100. In particular, the controller 140 controls the text file for sequential interpretation training to be registered through the input unit 120, and provides learners with a method for assisting sequential interpretation self-study for the registered text file. You can set the recording time. Subsequently, the controller 140 generates response information by recognizing the learner's voice input during the recording time, and analyzes the response information so as to evaluate the interpretation result performed by the learner, and interprets the interpreted text reflecting the interpreter's interpretation characteristics. Can be generated. To this end, the controller 140 may include a text file registration unit 141, a response information generation unit 142, an interpreter text generation unit 143, and an evaluation data generation unit 144.

The text file registration unit 141 may control to receive a text file for sequential interpretation self study from the learner through the input unit 120. In this regard, it will be described with reference to FIG.

2 is an example of a screen output from the learner terminal 100.

As shown, the learner terminal 100 may provide a UI for registering a text file for sequential interpretation training from a learner through software (application) providing a pre-installed sequential interpretation self-study assistance method. That is, the text file registration unit 141 may receive a text file for sequential interpretation training from the learner who manipulates the UI.

The original file registration unit 141 may receive the original file in various ways. In detail, the text file registration unit 141 may receive a text file in a voice form for sequential interpretation training according to any one of a method of searching for a pre-stored file, URL connection, or direct recording.

Here, the text file registration unit 141 may provide a file search function according to a search word input when the text file is input by a method of searching for a pre-stored file. In addition, when the text file registration unit 141 receives the text file by the URL connection method, the text file registration unit 141 may access the corresponding site through the communication unit 110 to obtain the text file. In addition, the original file registration unit 141 may receive the original file in a manner of recording the voice spoken by the learner through the input unit 120.

In this process, the original file registration unit 141 calculates the total length of the original text file when the original text file is input in the form of a voice according to any one of a method of searching for a pre-stored file, URL connection, or direct recording. You can give file names along the entire length. Alternatively, the text file registration unit 141 may control the text file registration date, the learner identification information, and at least one selected information according to the UI operation of the learner from among the information directly written by the learner to be set as a file name. In addition, the original text file registration unit 141 may provide an editing function for the original text or the text of the original text filed. To this end, the original text file registration unit 141 may receive not only the original text file in the form of a voice but also original text in which the original text file is characterized. In this case, the original file registration unit 141 may obtain the original text stored in advance through the file search, or may obtain the original text from the original file by applying a known voice characterization technique.

On the other hand, when the text file registration unit 141 receives the text file in the form of a voice, the text file is automatically divided into a plurality of subgroups according to the playback time set by the learner so that the learner interprets in a sequential interpretation manner. Can be.

Sequential interpretation is an interpreting method in which an interpreter is interpreted after a sentence is completely printed. That is, the text file output from the learner terminal 100 may be paused after the learning sentence is output for a predetermined play time. Then, the response information may be input while the recording function of the learner terminal 100 is activated for a predetermined recording time. Subsequently, when the playback starts again, the next sentence for learning may be output as a voice. Accordingly, the text file registration unit 141 may classify the text file into groups so that the learner can practice texts of various lengths during one playback time.

In other words, the text file registration unit 141 may divide the input text file into a plurality of subgroups. Each subgroup may include at least one sentence. For example, when 10 sentences are included in the original file, the original file registration unit 141 may divide the original text file into five subtitles according to the UI operation of the learner. Can be divided into groups. The text file registration unit 141 may divide the text file so that two sentences are included in each subgroup. As another example, the text file registration unit 141 may set the number of sentences included in each subgroup differently, and for this purpose, the learner may set a reproduction time of each subgroup. In this case, when the learner selects the original file through the learner terminal 100, the play time may be determined as a time when all sentences included in any one subgroup are output as voice. That is, the learner terminal 100 divides and reproduces the original text by the playback time for each subgroup set by the original file registration unit 141. When the playback time ends, the recording function is activated for a predetermined time interval to record the learner's voice. can do.

In some other embodiments, the text file registration unit 141 may divide the text file into a plurality of subgroups according to the division time received from the learner. For example, the text file registration unit 141 may divide the text file into 3 minute units based on the information about the split time (eg, 3 minutes) set by the learner. At this time, the original text file registration unit 141 may set the playback time so that the sentences included in each subgroup divided by three minutes are output as complete sentences. That is, the text file registration unit 141 may determine, as a final playback time, up to a section in which the reproduction of the sentences of any one subgroup ends with the complete sentence based on the division time set by the learner.

Accordingly, the learner terminal 100 may output the sentences included in any one subgroup divided by the text file registration unit 141 by voice. At this time, the controller 140 may control the input unit 120 to receive the learner's voice during the predetermined recording time when the predetermined playback time elapses. Accordingly, the learner may be provided with a sequential interpretation self-study assistance method that performs interpretation after all sentences included in any one subgroup constituting the original file are output as voice.

The response information generator 142 may generate response information about sentences included in the original file or the subgroup. In this regard, it will be described with reference to FIG.

3 is an example of a screen output from the learner terminal 100.

In detail, the response information generator 142 may control the original file to be reproduced for each subgroup by the learner's UI manipulation, and may control the recording function for interpretation to be activated whenever the reproduction of each subgroup is finished. have. In this way, the response information generation unit 142 repeats the step of starting the playback of the next subgroup after the set recording time ends, so that the response information for each subgroup or all subgroups of one original file is repeated. It is possible to generate the overall response information in which the information is integrated. In this process, the controller 140 may allow the learner to control the reproduction speed of the sentence according to the reproduction speed for each subgroup in consideration of the difficulty and length of the original text. In addition, the controller 140 may control to output a warning sound or a notification sound when it is determined that voice information has not been input for a preset threshold time.

Here, the response information expressed in this specification will be described by defining as including the above-described response information and the entire response information for each subgroup. That is, the interpretation text generation unit 143 to be described later may generate the interpretation text for each subgroup based on the response information for each subgroup, or may generate the interpretation text for the entire original file based on the entire response information.

The response information generation unit 142 may generate a plurality of response information for one subgroup by generating response information whenever a sentence included in any one subgroup is reproduced according to a learner's UI manipulation. . The response information generation unit 142 may assign a number for distinguishing the generated plurality of response information and a file name according to the reproduction time of the corresponding subgroup. In this case, the controller 140 may control the learner to listen to the response information according to the learner's UI manipulation. Thus, when the learner generates a plurality of response information, the learner may listen to the plurality of response information and select the most satisfactory response information among the plurality of response information as the response information for the corresponding subgroup. The response information generator 142 may delete the remaining response information except for the selected response information.

The interpreter text generator 143 may generate an interpreted text by texturing the response information. As described above, the response information is generated by the response information generation unit 142 and may be defined as voice information recorded in the process of interpreting the sentences included in the original text file by the learner. The interpreter text generation unit 143 may generate an interpreted text that characterizes the response information by using any one of various well-known speech texting techniques.

In this process, the interpreter text generation unit 143 may generate an interpreted text reflecting the interpreter features of the learner.

Conventional voice texting technology can text the voice, but has a problem that can not reflect the characteristics of the input voice. For example, when a learner hears the original text 'I am going to English classes.' And then sequentially interprets, 'I am going to listen to English lessons.' The conventional online learning service providing technology simply provides a function of displaying 'I go to English class'. According to this prior art, there is a limit in evaluating learner's sequential interpretation results. Because in evaluating the learner's sequential interpretation, the meaning of the original text is relatively relatively when uttering a certain syllable such as 'up ~ up' or uttering an unnecessary and meaningless voice (intermission) such as 'um ~'. This is accurate, but cannot be interpreted as a smooth or good interpreter. As another example, 'Classes…' 'Silent' for which a voice is not input for a certain period of time is not displayed in the existing technology, but a 'silent' symbol should also be displayed for interpretation evaluation. That is, as described above, the interpreter's interpretation characteristics generated in the sequential interpretation process can be used as an important indicator in evaluating response information, and the software (application) for providing a sequential interpretation self-study assistance method according to the present invention. The learner terminal 100 installed may generate an interpreted text reflecting the interpreter characteristics of the learner.

To this end, the interpretation text generation unit 143 may analyze the response information to extract the interpretation delay interval according to the interpretation characteristics of the learner. The interpretation delay section is a section displayed as a specific symbol on the interpretation text, and may be defined as a section in which an undesired interpretation is performed during a certain time section while the learner performs sequential interpretation.

The interpreter text generation unit 143 generates a silence symbol, an interpreter start delay symbol, or a specific syllable continuous symbol for distinguishing a cause of an interpreter delay interval during sequential interpretation evaluation, and generates a generated silence symbol, an interpreter start delay symbol, and a specific syllable. Persistent symbols can be displayed on the interpreter text.

As an example, the interpreter text generation unit 143 may display a corresponding section on the interpreter text as a silence symbol when it is determined that the learner does not perform the interpreter during the sequential interpreter. In other words, the interpreter text generation unit 143 generates a silence symbol, for example, a '....' Section in which the learner's voice is not detected while receiving response information input from the learner. 'Can be displayed. Hereinafter, for convenience of explanation, the silence symbol displayed on the interpreter text is referred to as'. It will be defined as'. However, the silence sign must be '…' It does not need to be ', and may be replaced with other characters that can be distinguished from other symbols (interpretation start delay symbols, specific syllable duration symbols) to be described later.

As another example, the interpreter text generation unit 143 may display a time interval required to start an interpreter after the original text is output as an interpreter start delay symbol separated from the silence symbol. To this end, the interpreter text generation unit 143 determines the time until the sequential interpretation is started after the sentences of the subdivided text are output, that is, the output end time of the sentences of the subgroup and the input start time of the response information. You can check it. In this case, the interpreter text generator 143 may generate an interpreter start delay symbol when it is determined that the interval between the output end time and the input start time exceeds a preset threshold time.

As a specific example in which an interpreter start delay symbol is generated by the interpreter text generation unit 143, the time at which the output of the sentences of the subgroup ends and the start time of the speech information (or the generation time of the interpreter text) for the corresponding sentences; If the time interval is 3 seconds and the predetermined threshold time is 2 seconds, the interpreter text generation unit 143 may insert an interpreter start delay symbol represented by '=' in front of the interpreter text. Therefore, the learner can be provided with information on which sentences are delayed in starting the sequential interpretation only by confirming the interpretation start delay symbol displayed in the interpretation text. Hereinafter, for convenience of explanation, an interpretation start delay symbol displayed on an interpretation text will be defined as '='. However, the interpretation start delay symbol does not necessarily have to be '=', and may also be replaced with other characters that can be distinguished from other symbols (silent symbols, specific syllable duration symbols) described above or later.

On the other hand, the interpreter text generation unit 143 analyzes the response information, and when it is confirmed that the learner utters a particular syllable while sequential interpretation of sentences of a specific subgroup, the corresponding syllable duration symbol in the interpreted text Can be displayed as

Specifically, the interpreter text generation unit 143 may analyze the response information to detect a section in which a particular syllable lasts more than a predetermined reference time. The interpreter text generator 143 may generate a specific syllable duration symbol for displaying a corresponding section. For example, the specific syllable duration symbol may be displayed as '~'. Hereinafter, for convenience of description, a specific syllable duration symbol displayed on an interpreted text is defined as '~'. However, the specific syllable continuation symbol does not necessarily have to be '~', and may be replaced by another character that can be distinguished from other symbols (interpretation start delay symbol, silence symbol).

In summary, the interpreter text generation unit 143 characterizes the response information to generate the interpreted text, and if the interpreted delay section is detected according to the interpreter's interpretation characteristics by analyzing the response information, it corresponds to the detected interpreted delay section. Interpretation delay symbol can be inserted at the location. Therefore, the learner only knows the interpretation delay symbol (silent symbol, interpretation start delay symbol, specific syllable continuation symbol) displayed in the interpretation text, and the information about where the interpreter was not desired in the sequential interpretation process of the original text. Can be provided.

In some other embodiments, the interpreter text generator 143 may control the time at which the interpreter delay interval is detected to be reflected on the interpreter text.

To this end, the interpreter text generation unit 143 may control the interpreter delay symbol (silent symbol, interpreter start delay symbol, specific syllable duration symbol) to be continuously displayed on the interpreter text according to the time interval in which the interpreter delay section is detected. .

For example, the interpretation text generation unit 143 has a time interval of 3 seconds between the end of the output of the sentences of the subgroup and the start time (or generation time of the interpretation text) of the response information for the sentences. When the predetermined threshold time is 2 seconds, the interpreter text generation unit 143 may insert an interpreter start delay symbol represented by '=' in front of the interpreter text. In this case, when the time at which the output of the sentences of the subgroup ends and the voice start time of the response information for the corresponding sentences is sensed as 4 seconds, the interpreter text generation unit 143 consecutively interprets the start delay of interpretation in front of the interpreted text. Can be displayed as In this case, the interpreter start delay symbol reflected in the interpreter text may be displayed as '=='. In a similar manner, the interpreter text generation unit 142 may control to display the silence symbol and the specific syllable duration symbol continuously according to the time period in which the silence section and the specific syllable duration section last.

Accordingly, the learner can quantitatively confirm the fluency of the interpreter only by confirming whether the delay symbol displayed in the interpreter text is continuously displayed.

Meanwhile, in the above-described embodiment, the interpreter text generation unit 143 has been described as continuously displaying one interpreter delay symbol whenever the duration detection interval of the interpreter delay section is increased by 1 second, but the sensing section may increase by 2 seconds. The continuous detection section may be set to various lengths according to the difficulty of the original file, the learner's learning ability, and the learner's setting, such as displaying one interpreting delay symbol consecutively each time.

The evaluation data generator 144 may generate evaluation data for evaluating the interpretation text in which the interpretation delay section is reflected. In this case, the evaluation data includes the total number of occurrences of the interpretation delay interval, the total number of occurrences / average occurrence of the interpretation delay intervals for each subgroup, the total number of occurrences of the silence symbol, the total number of occurrences / average occurrences of the silence symbol for each subgroup, The total number of occurrences of syllable duration symbols, the total number of occurrences / average number of specific syllable duration symbols for each subgroup, the total number of occurrences of delayed interpretation symbols, the total number of occurrences / average occurrences of delayed interpretation symbols for each subgroup, etc. May contain information. That is, the evaluation data generator 144 may analyze the interpreted text and count the number of occurrences of the silence section, the silence symbol, and the specific syllable duration symbol. In addition, the evaluation data generation unit 144 may calculate the average of the interpretation start delay time of the entire text and the interpretation start delay time for each subgroup and include it in the evaluation data.

In addition, the evaluation data may further include at least one of information on the interpretation missing rate and the additional rate or information about the missing number and the additional number. To this end, the evaluation data generation unit 144 may calculate the missing rate and the additional rate, or the missing number and the additional number by comparing the interpreted text with the original text that characterizes the original file.

In this process, the evaluation data generation unit 144 may calculate a missing rate and an additional rate, or a missing number and an additional number for the original text based on a result of determining whether the word of the original text is expressed in the interpreted text. Alternatively, the evaluation data generator 144 may calculate a missing rate and an additional rate, or a missing number and an additional number by comparing the total syllables of the original text with the total syllables of the interpreted text. For example, the evaluation data generation unit 144 calculates the total number of words of the original text, the missing number and the additional number of the words constituting the original text are missing or added in the interpretation text, and the total words of the original text. The ratio between the number and the calculated missing number (and the additional number) may be calculated as the missing rate and the additional rate, or the ratio between the total syllables in the original text and the total number of syllables in the interpreted text may be calculated as the missing rate and the additional rate. Here, the missing rate and the additional rate, or the missing number and the additional number, refer to the missing rate and the additional rate when all the sentences in the subgroup are interpreted, or the missing rate and the additional number, and the missing rate and the additional rate when all the translations are not interpreted. Rate, or both missing and additional numbers may be included.

As another example, the evaluation data generator 144 may obtain and display an automatic machine translation for the original text in which the original file is characterized. The evaluation data generator 144 may obtain an automatic machine translation for the original text by accessing a separate server that provides a translation service.

The evaluation data generation unit 144 may display the original text with the original text and the interpreted text with the response information. The rate and addition rate of the automatic machine translation and the interpreted text with respect to the original text, or the number of missing numbers may be displayed. And additional numbers can also be displayed. In this case, the automatic machine translation for the original text may be used for simple reference.

Thereafter, the evaluation data generator 144 may provide the table of the accumulated evaluation data.

In this case, the controller 140 may analyze the information on the calculated missing rate and the additional rate or information on the missing number and the additional number, and may control the voice reproduction speed of the sentences of the subgroup to be output next time to vary. . As a specific example, the controller 140 may calculate an average drop rate and an add rate for the drop rate and the add rate for each subgroup, and determine whether the average drop rate and the add rate exceed a predetermined threshold. . If it is determined that the average missing rate and the additional rate exceed the threshold, the controller 140 may control to slow down the voice reproduction rate of the sentences of the subgroup selected next time and output to the output unit 130. As another example, when the missing number and the additional number of sentences of any one subgroup currently output by voice exceed a predetermined threshold, the controller 140 is selected next time to voice through the output unit 130. The voice reproduction speed of the output subgroup sentences may be controlled. Since the missing rate and the additional rate, or the high number and the high missing number mean that the learner has difficulty in sequentially interpreting the learning sentences included in the subgroup, the control unit 140 subsequently outputs the sentences of the subgroup. By adjusting their output speed, they can improve their learning.

Alternatively, the controller 140 may receive a preset signal from the learner on whether to activate a sentence output speed change function of the subgroup before the original file is reproduced. In this process, the control unit 140 compares the average missing rate and the additional rate with the threshold only if it is approved to activate the corresponding function based on a preset signal received from the learner before playing the original file. It is possible to change the voice reproduction speed of the sentences of the sub-group selected to be output to the voice output unit 131. On the other hand, as described above, the controller 140 plays the subgroup set by the learner in consideration of the difficulty and length of the original text in the process of uploading the original text irrespective of the missing rate and the additional rate, or the calculation of the missing number and the additional number. The playback speed of the sentence may be controlled according to the speed.

4 to 5 are exemplary views of a screen output from the learner terminal 100 having the above-described functions.

First, referring to FIG. 4, a software (application) for providing a sequential interpretation self-study assistance method installed in the learner terminal 100 may provide a UI for checking an analysis result of response information.

The learner terminal 100 may output response information of any one of sub-group response information registered with respect to the original text file according to the UI manipulation of the learner, or may output response information of the entire text file as a voice.

In this case, the interpreter text generation unit 143 may display the interpreted text generated based on the learner's response information together with the original text that characterizes the original text file. At this time, the interpretation text generation unit 143 may display the interpretation text at the bottom of the original text, the time required to start the sequential interpretation from the end of the output of the original text, that is, the time required to record the response information Can be displayed separately.

In addition, the interpreter text generator 143 analyzes the response information and detects at least one section of the section in which the interpreter's interpretation characteristic is reflected, that is, the delay period of the interpretation start, the specific syllable duration section, and the silence section. Mark in the interpreter text. In this regard, it will be described with reference to FIG.

5 is an example in which the interpreter text reflecting the interpreter characteristics of the learner is output from the learner terminal 100.

Specifically, the interpreter text generation unit 143 may analyze the response information and display any one of an interpreter start delay symbol, a silence symbol, and a specific syllable duration symbol on the interpreter text. For example, the interpreter text generation unit 143, if it is determined that the time interval between the output end time of the original text and the input start time of the response information or the time interval in which the voice is not detected is out of the predetermined threshold period, the interpretation start delay symbol (A) can be generated. Alternatively, the interpreter text generation unit 143 may control to display a section in which the voice is not detected in the middle of the interpreter as a silence symbol B on the interpreter text. In addition, the interpreter text generation unit 143 may analyze the response information and display a section that has a specific syllable in the learner's voice as a specific syllable duration symbol (C) on the interpreter text.

For example, as a result of analyzing the response information, the interpreted text reflecting the delayed interpretation interval is' === country. Learners can determine where the interpreter was not smooth by simply checking the interpreter text that reflects the delay. In other words, the '===' symbol displayed in front of the 'country' is a delay of the interpretation start (A) and is displayed at the very beginning of the interpretation text, so that the sequential interpretation may be slower than the reference time. Then, after the "country," 'Symbol is a silent symbol (B), so you can see that the silence occurred in the middle of the interpretation. In addition, since the '~' symbol displayed between the 'baro' is a specific syllable continuous symbol (C), it can be confirmed that the interpreter is fluent due to the unnecessary lasting of the specific syllable. In this process, three consecutive interpretation delay symbols are displayed, meaning that the time required for the interpretation voice to be uttered after the original text is recorded 3 seconds after the predetermined threshold time, and the learner is continuously indicated. Only by confirming the number of interpreting delay symbols to be interpreted can quantitatively determine the length of time for which the interpretation is delayed.

6 is a flowchart illustrating a schematic flow of a method for assisting sequential interpretation self study in accordance with an embodiment of the present invention performed using the learner terminal 100.

The learner terminal 100 may register an original text file for sequential interpretation self study in order to perform an interpretation process according to the sequential interpretation method (610).

The learner terminal 100 may receive an original text file according to any one of a method of finding a pre-stored file, a URL connection, or direct recording according to a learner's UI manipulation. In this process, the learner terminal 100 may determine the number of sentences included in each subgroup by dividing the original file into a plurality of subgroups and setting a reproduction time for each subgroup.

The learner terminal 100 outputs the original text as a voice for a predetermined playback time using the original text file divided by subgroups, and receives the interpreted response information from the learner as a voice during the predetermined recording time when the playback time elapses. 620.

The learner terminal 100 generates an interpreted text that characterizes the voice response information input during the recording time, and may display an interpreted delay section in which the interpreter's interpreting characteristics are reflected in the interpreted text (630).

In this case, the learner terminal 100 may display an interpreted text at the bottom of the original text in which the original text is characterized. For example, the learner terminal 100 may output the original text to be displayed at the top of the screen rather than the interpreted text.

In addition, the learner terminal 100 may analyze the response information and display any one of an interpretation start delay symbol, a silence symbol, and a specific syllable duration symbol on the interpretation text as a symbol. For example, the learner terminal 100 generates an interpreter start delay symbol when it is determined that the time interval between the output end time of the original text and the input start time of the response information or the time interval in which the voice is not detected is out of a predetermined threshold section. can do. Alternatively, the learner terminal 100 may control to display a section in which the voice is not detected in the middle of the interpretation as a silence symbol on the interpretation text. In addition, the learner terminal 100 may analyze the response information and display a section of the learner's voice in a specific syllable duration symbol on the interpretation text.

Thereafter, the learner terminal 100 may generate evaluation data for evaluating the sequential interpretation result by analyzing the interpretation text in which the interpretation delay section is displayed (640). The evaluation data may include information on the total number, the average frequency of appearance, the missing rate and the additional rate, the missing number, and the additional number of types of delayed interpretation intervals.

Such a technique for providing a sequential interpretation self-help method may be implemented in an application form or in the form of program instructions that may be executed by various computer components, and recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.

The program instructions recorded on the computer-readable recording medium are those specially designed and configured for the present invention, and may be known and available to those skilled in the computer software arts.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like.

Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform the process according to the invention, and vice versa.

Although the above has been described with reference to the embodiments, those skilled in the art will understand that various modifications and changes can be made without departing from the spirit and scope of the invention as set forth in the claims below. Could be.

Claims (14)

In the sequential interpretation self-study assistance method using a learner terminal possessed by the learner,
Receiving a text file for sequential interpretation study;
Outputting the original file as a voice during a predetermined reproduction time, and receiving response information generated by a learner during a sequential interpretation process during the predetermined recording time when the reproduction time elapses;
When it is determined that an interpreted delay section representing the interpreter characteristics of the learner is generated by generating the interpreted text that characterizes the response information and analyzing the response information, at least one of a silence section, an interpreter start delay section, and a specific syllable duration section. Displaying a section of on the interpreted text; And
Analyzing the interpreting text to generate evaluation data for self-assessing a sequential interpretation result performed by the learner;
The step of displaying a specific syllable duration on the interpretation text that represents the interpretation characteristics of the learner,
Converting the response information into text text;
Analyzing the response information to detect a section in which a specific syllable lasts more than a predetermined reference time;
Generating a specific syllable duration symbol corresponding to the section; And
Generating the interpreted text reflecting the specific syllable duration symbol between the text texts,
Outputting the original file as a voice during the predetermined playback time,
Dividing the original file into a plurality of subgroups, and outputting any one of the plurality of subgroups,
The evaluation data,
The total number of occurrences of the silent section in the response information for the original file;
The average number of occurrences of the silent section in the response information for the original file;
An average time for the time of the silent section in the response information for the original file;
The total number of occurrences of the silent section in the response information for any one of the plurality of subgroups,
A ratio of the total number of occurrences of the silent section in the response information for any one of the plurality of subgroups, the average number of occurrences of the silent section in the response information for the original file,
The total number of occurrences of the delay in the interpretation start in the response information on the original file;
The average number of occurrences of the delay period of interpretation start in the response information about the original file;
An average time for the delay period of the start of interpretation in the response information about the original file;
The total number of occurrences of the delayed interpretation interval in the response information for any one of the plurality of subgroups,
The ratio of the total number of occurrences of the delay of the interpretation start to the response information for any one of the plurality of subgroups, the average number of occurrences of the delay to the interpretation start from the response information to the original file,
The total number of occurrences of the duration of a particular syllable in the response information about the original file,
The average number of occurrences of the duration of a particular syllable in the response information about the original file,
An average time for the duration of a specific syllable duration in the response information for the original file;
The total number of occurrences of a specific syllable duration in response information for any one of the plurality of subgroups,
The ratio of the total number of occurrences of the specific syllable duration in the response information for any one of the plurality of subgroups and the average number of occurrences of the duration of the specific syllable duration in the response information for the text file are plotted. Secondary method.
The method of claim 1,
The step of displaying a silence interval on the interpretation text indicating the interpreter characteristics of the learner,
Converting the response information into text;
Detecting a section in which a silent time lasts for a predetermined reference time or more based on the response information;
Generating a silence symbol corresponding to the section; And
And generating the interpreted text in which the silence symbol is reflected between the texts.
The method of claim 2,
The evaluation data,
Method of assisting self-interpretation, including the information on the number of times the silence symbol is inserted into the interpreted text, the number of times the average silence symbol for each sentence.
delete The method of claim 1,
The evaluation data,
And the information on the number of times the specific syllable duration symbol is inserted into the interpreted text and the number of times the average specific syllable duration symbol for each sentence is included.
The method of claim 1,
The step of displaying the interpretation start delay period indicating the interpreter characteristics of the learner on the interpretation text,
Checking an output end time of the original file and an input start time of the response information;
Generating an interpretation start delay symbol representing a time interval between the output end time and the input start time; And
And generating the interpreted text in which the interpreter start delay symbol is reflected.
The method of claim 6,
Generating the interpretation start delay symbol,
Is generated when it is determined that a time interval between the output end time and the input start time exceeds a predetermined threshold time,
The interpretation start delay symbol is characterized in that displayed in front of the interpretation text, sequential interpretation self-study assistance method.
The method of claim 6,
The evaluation data,
And information indicating the number of times the interpreter start delay symbol is inserted into the interpreter text, and information indicating the length of the time interval between the output end time and the input start time.
The method of claim 1,
The evaluation data includes at least one of information on the missing rate and additional rate or information about the missing number and the additional number,
Generating the evaluation data,
And converting the original text file into original text and calculating the information about the missing rate and the additional rate or information about the missing number and the additional number according to a result of comparing the original text and the interpreted text. How to Assist Sequential Interpretation
The method of claim 9,
To output the original file in voice,
Analyzing a history of at least one of the information on the missing rate and the additional rate or the information on the missing number and the additional number, the audio of the original text file output next time after the predetermined recording time has elapsed A method for assisting sequential interpretation self study, characterized in that the reproduction speed is varied.
The method of claim 9,
The learner terminal,
The original text is displayed on the screen, and the interpreted text is displayed at the bottom of the original text, wherein the time required for the response information to start from the end of the output of the original file during the predetermined reproduction time is recalled. A method of assisting self-interpretation, characterized in that it is displayed between the original text and the interpreted text.
The method of claim 1,
Outputting the original file as a voice during the predetermined playback time,
Divide the original text file into a plurality of subgroups composed of at least one sentence based on the playback time set by the learner so that the learner terminal plays the original text file for a predetermined reproduction time;
Outputting all sentences included in any one subgroup during the play time as voice, and recording the voice input from the learner for a predetermined recording time when the play time elapses to generate response information for each sub group How to Assist Interpreters.
The method of claim 12,
The learner terminal,
After the predetermined recording time has elapsed, all the sentences included in the next subgroup are outputted as voices, and the voice input from the learner is repeated, and the response for each subgroup constituting the original file is repeated. Information and response information of all subgroups are generated.
The response information includes at least one of the response information for each subgroup and the overall response information, sequential interpretation self-study assistance method.
A computer-readable recording medium having a computer program recorded thereon for performing the sequential interpretation self-study assistance method according to any one of claims 1 to 3 and 5 to 13.

Images