KR102292552B1 - Video synchronization system to improve viewing rights for the disabled - Google Patents

Abstract

The present invention relates to a video synchronization system for improving viewing rights for the disabled, which generates caption data by converting audio included in video content into text, and synchronizes the video content and the caption data using a timestamp generated together when the caption data is generated. The video synchronization system includes: a manager terminal which provides a video content; a stenographer terminal for generating stenography information for the video content; and a user terminal possessed by the disabled viewing the video content.

Description

{Video synchronization system to improve viewing rights for the disabled}

The present invention relates to a video synchronization system for improving the viewing rights of the disabled, and more particularly, to improve the viewing rights of the disabled, which displays the audio of a video as text, and automatically synchronizes the video and text using a timestamp that is generated together when text is created It relates to a video synchronization system for

In the case of digital video content currently screened in domestic movie theaters, as part of the government-level creation of a movie viewing environment for the disabled, an environment for viewing movies for the disabled has been prepared through the revision of the Act on the Prevention of Discrimination against Persons with Disabilities and the Entrepreneurship Act. The screening of sign language, subtitles, and screen explanations is made mandatory, and barrier-free theaters are made mandatory and support is provided so that there are no barriers and discrimination between the visually and visually impaired and non-disabled people through sign language, subtitles, and screen commentary. However, despite these measures, there is a problem in that it is practically difficult for the hearing-impaired to go to a movie theater and watch a movie together with the general public.

Recently, screen commentary and closed captioning have been limited to digital video content aired in the public interest for the hearing and visual impaired, such as on terrestrial broadcasting. However, for such screen commentary or subtitle broadcasting, screen commentary or subtitles must be produced by mixing and inserting digital video content into digital video content to be aired. In this case, copyright problems and high costs (Korean movie In the case of digital video content, it costs about 15 million won per episode, and in the case of foreign currency digital video content, about 20 million won per episode), it is not profitable to try it as a business model through a commercial level paid service. It is a situation in which the viewing accessibility of various digital image contents is not allowed to the disabled.

On the other hand, the "subtitle providing service system using commercial DVD contents", a patent invention disclosed in Patent Document No. 10-1052850 of the following prior art document, transfers subtitle information of commercial DVD contents from the subtitle providing server 120 to the user terminal 100. A technique for language learning by downloading through the network 11 and playing subtitles synchronized with the video/audio signal of the DVD content in synchronization with the playback time of the video/audio signal of the DVD content has been proposed.

However, in the prior patent invention, the user terminal 130 has a built-in mobile phone function that is currently universally used, and has a small size, so that a smart phone, a tablet PC, or a phablet PC, etc. As it is based on portable personal devices such as personal computers, notebook computers, and PDA terminals, there is a problem that it is inconvenient for the visually or hearing impaired to carry and use at all times. In addition, the display unit 210 is composed of a CRT monitor or LCD monitor, which is relatively small compared to the cinema screen, and not only digital video content is limited to DVD content, but also video/audio signal reproduction and subtitles. Although the reproduction of is spatially separated, it is reproduced by one display unit 210 provided in the user terminal 130, so it is inconvenient for the hearing impaired to watch digital video contents using the system proposed in the patent invention. However, in the case of the visually impaired, there was a problem that it was impossible to view digital image contents.

On the other hand, the above-mentioned background art is technical information that the inventor possessed for the derivation of the present invention or acquired in the process of derivation of the present invention, and it cannot be said that it is necessarily a known technique disclosed to the general public before the filing of the present invention. .

Korean Patent No. 10-1052850

An aspect of the present invention provides a video synchronization system for improving the viewing rights of the disabled, which displays the audio of a video as text, and automatically synchronizes the video and text using a timestamp generated together when text is generated.

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

A video synchronization system for improving viewing rights for the disabled according to an embodiment of the present invention generates caption data by converting audio included in video content into text, and uses a timestamp that is generated together when the caption data is generated. and the subtitle data are synchronized.

The video synchronization system for improving the viewing rights of the disabled,

a manager terminal that provides video content;

a stenographer terminal for generating stenography information for the video content; and

Including a user terminal possessed by a person with a disability viewing the video content,

The manager terminal,

and generating subtitle data based on the stenography information received from the stenographer terminal, generating a timestamp in units of one word or one line of a character string constituting the subtitle data, and combining them with the subtitle data,

The user terminal,

In the process of outputting the video content combined with the caption data, if there is a time stamp in the text waiting to be output, the time information of the video content is compared with the time information checked when the text is displayed with the time information of the video If it is confirmed that is different from the time information of the text, the video content is displayed by delaying the video on the storage means in seconds according to the time information of the text to synchronize the video content and the subtitle data,

If it is determined that the video and the text are not synchronized even after the video is output according to the time information of the text, the video display is delayed by a preset reference time.

The user terminal is

In the process of outputting the video content combined with the caption data, if there is a time stamp in the text waiting to be output, the time information of the video content is compared with the time information checked when the text is displayed with the time information of the video If it is confirmed that is different from the time information of the text, the video content is displayed by delaying the video on the storage means in seconds according to the time information of the text to synchronize the video content and the subtitle data,

Even after outputting the video according to the time information of the text, if it is determined that the video and the text are not synchronized, the object constituting the still image constituting the video content is detected, and the subtitle data is divided by word and the detected object is It is characterized in that the synchronization is performed so that an image including the detected object is displayed at the time the searched word is displayed by searching for a corresponding word.

According to one aspect of the present invention described above, even the deaf person who cannot recognize sound can smoothly watch video content by receiving captions for the audio included in video data, and synchronize video and captions in real time when video is transmitted. This can improve the audience's immersion.

1 is a diagram showing a schematic configuration of an image synchronization system for improving the viewing right of the disabled according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating a detailed configuration of the manager terminal of FIG. 1 .
3 and 4 are diagrams illustrating a detailed configuration of the user terminal of FIG. 1 .

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS [0023] Reference is made to the accompanying drawings, which show by way of illustration specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different but need not be mutually exclusive. For example, certain shapes, structures, and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. In addition, it should 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 present invention. Accordingly, the detailed description set forth below is not intended to be taken in a limiting sense, and the scope of the invention, if properly described, is limited only by the appended claims, along with all scope equivalents to those claimed. Like reference numerals in the drawings refer to the same or similar functions throughout the various aspects.

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

1 is a view showing a schematic configuration of an image synchronization system for improving the viewing right of the disabled according to an embodiment of the present invention.

The video synchronization system 1000 for improving viewing rights for the disabled according to the present invention may include a manager terminal 10 possessed by a content manager, a stenographer terminal 20 possessed by a stenographer, and a user terminal 30 possessed by a disabled person. have.

The manager terminal 10 is a terminal possessed by a content manager who creates and manages video content to be provided to the disabled, and is an electronic device capable of wired or wireless communication with an external device and capable of input, output and processing of information, For example, it may be in the form of a smartphone, a PC, a tablet PC, a wearable device, or the like.

For example, the content manager delivers broadcast content to a content production system for the disabled, and the content production system for the disabled generates broadcast captions based on the broadcast content or generates content including caption data and delivers it to the set-top box. do. The set-top box encodes the received broadcast packet and outputs it to the viewer.

The content manager may include a broadcasting station as a representative example, and may include a business operator or an intermediate distributor that produces and provides content other than the broadcasting station. The content manager delivers content including audio and video to the content production system for the disabled. Here, the broadcast data delivered by the content manager generally does not include caption data for the hearing impaired or caption data for the visually impaired. It is necessary to generate subtitle data by typing the commentary manuscript.

On the other hand, the manager terminal 10 generates caption data based on typing information input from the stenographer, combines the generated caption data with image content, and transmits it directly to the user terminal 30 or through a broadcasting system. let it be

In this process, the manager terminal 10 generates a timestamp for synchronization in units of one word or one line of the caption data and combines it with the caption data. It is a situation where it is stamped in a state protected by a separate means of protection. This timestamp may be generated in the text separation step rather than the input step.

2 is a diagram illustrating a detailed configuration of the manager terminal 10 .

As shown, the manager terminal 10 may include an image receiving unit 110 , a voice recognition unit 120 , a stenographic information receiving unit 130 , a subtitle generating unit 140 , and a processing unit 150 .

The image receiver 110 receives broadcast content from the content manager. The image receiver 110 may include a broadcast receiver and an encoder. The image receiver 110 may receive broadcast content from the content manager through at least one of a terrestrial wave, a cable, and the Internet.

The image receiver 110 may transmit the broadcast content to the voice recognition unit 120 to perform voice recognition, or decode the broadcast content so that a stenographer can see it and deliver it to the display device. Also, the image receiving unit 110 may transmit broadcast content to the processing unit 150 .

When the content delivered from the content manager is played, the voice recognition unit 120 automatically recognizes the voice and converts it into text. The voice recognition unit 120 may be a conventionally used voice-to-text conversion tool, and specific examples may be Google Cloud Speech API or Amazon Transcirbe. That is, the voice recognition unit 120 may machine-translate the voice included in the content to generate text.

Specifically, the voice recognition unit 120 according to an embodiment of the present invention may include a receiving unit, a converting unit, and an accuracy calculating unit.

The receiver acquires a voice signal from the content. For example, the receiver may be a microphone. The receiver may collect all the voice signals transmitted from the content, convert the collected voice signals into digital signals, and transmit them to the converter.

In another embodiment, the receiver may receive the voice of the stenographer from the stenographer terminal 20 . When it is difficult for the stenographer to input stenography through the stenography keyboard in a specific situation, the receiver may receive the voice of the stenographer and convert it into text. However, the data obtained by converting the voice of the stenographer into text may be processed differently from the data obtained by converting the voice signal of the content into text and transmitted to the processing unit 150 . The processing unit 150 may treat the text data converted from the voice of the stenographer in the same way as the supplementary stenographic input and use it to generate the final subtitle.

The converter converts the voice signal received from the receiver into text. Specifically, the conversion unit may be a machine learning application for automatic speech recognition through deep learning. The converter can transcribe audio files stored in common formats such as WAV and MP3 and add timestamps for each word.

The accuracy calculator may calculate the accuracy of voice recognition between automatic voice recognition. Specifically, the accuracy calculator may distinguish a human voice (nurture) from noise in the voice signal, and may calculate the accuracy based on a human voice volume, a ratio between a human voice and noise, or a voice recognition result.

In an embodiment, the accuracy calculator may view the accuracy as low when the human voice is low among the voice signals, and may view the accuracy as high when the human voice is large. In other words, the accuracy calculator may calculate the accuracy in proportion to the human voice. For example, there may be a case in which the speaker in the content speaks away from the microphone or the voice is relatively low. A criterion for judging whether a human voice is large or small may be the human voice volume in general content, and a specific value may be obtained through machine learning.

In another embodiment, the accuracy calculator may view that the higher the noise ratio in the ratio between the human voice and the noise in the voice signal, the lower the accuracy. In other words, the accuracy calculator may calculate the accuracy in inverse proportion to the noise ratio. For example, there may be a case where the intestine is noisy or the non-voice sound is the center in the content.

In another embodiment, the accuracy calculator may calculate the accuracy based on the recognition result. The accuracy calculation unit may calculate the accuracy by determining whether a result of recognizing a voice and converting it into a text conforms to the standard language notation. For example, there may be cases where the conversion result of the accuracy calculator does not match the spelling, and there may be cases where the speaker in the content speaks a dialect.

The accuracy calculator may generate a timestamp for correction of a corresponding word or section when the voice recognition result is less than or equal to a specific value. The generated calibration timestamp may be transmitted to the processing unit 150 .

The stenography information receiving unit 130 receives and obtains a stenography input from the stenographer terminal 20 .

On the other hand, the stenography information receiver 130 may transmit a notification signal to the stenographer terminal 20 . Here, the notification displayed to the stenographer may indicate that the voice recognition unit 120 recognizes that the recognition accuracy is less than or equal to a predetermined value. When the speech recognition accuracy is less than a certain value, there is a high probability that the result of the speech-text conversion is not accurate. At this time, the stenographer directly inputs the caption to generate caption data, and the generated caption data is received through the stenographer terminal 20 . By doing so, the result of automatic speech recognition can be corrected.

The processing unit 150 generates a final caption by integrating the text received from the voice recognition unit 120 and the stenographic information receiving unit 130 . Specifically, the processing unit 150 generates the final caption by integrating the speech-text conversion data received from the voice recognition unit 120 and the stenography input data received from the stenography information receiving unit 130 .

In one embodiment, the processing unit 150 is based on the voice text conversion data received from the voice recognition unit 120, and supplements a part of the voice text conversion data with the stenography input data received from the stenography information receiving unit 130. You can create final subtitles. As described above, the text conversion result may be inaccurate due to the low recognition accuracy of the voice recognition unit 120 under certain circumstances. have.

The processing unit 150 may obtain, from the voice recognition unit 120 , the correction timestamp information for the complementation target word or the complementation target section (time point) whose accuracy is less than or equal to a predetermined value. In addition, the processing unit 150 may generate a final caption by synchronizing the stenographic input data and the voice-to-text conversion data by comparing the correction timestamp of the complementary word or section with the stenographic input start time.

In a specific embodiment, the processing unit 150 compares the correction timestamp of the complementation target word or section with the start time of the supplementary shorthand input, and matches the supplementary shorthand input with the complementary shorthand input with the smallest difference to obtain the final subtitle create

In another embodiment, the processing unit 150 generates a final caption by comparing and matching only the temporal sequence of one or more complementary words or sections and the temporal sequence of one or more supplementary shorthand inputs. Since the number of supplementary words or sections and the number of supplementary shorthand inputs are the same, only each order is compared, and a final subtitle can be generated by sequentially replacing the supplementary target word or section with supplementary shorthand input.

In this process, the processing unit 150 generates a timestamp for synchronization in units of one word or one line of the subtitle data as described above and combines it with the subtitle data, and the inputted text (subtitle) combined with the moving picture is for synchronization. It is a situation where the timestamp is stamped in a protected state by a separate protection means. This synchronization timestamp may be generated in the text separation step instead of the input step.

The stenographer terminal 20 is an electronic device possessed by a stenographer, and is capable of wired or wireless communication with an external device, and is an electronic device capable of input, output and processing of information, for example, a smartphone, PC, tablet PC, smart TV, It may be in the form of a wearable device or the like.

The stenographer terminal 20 may receive the machine-translated text data from the manager terminal 10 and a proofreading timestamp indicating the corresponding word or section when the voice recognition result in the text data is less than or equal to a specific value.

Therefore, the stenographer uses the stenographer terminal 20 to generate stenographic information for the section in which the time stamp for proofreading is displayed and transmits it to the manager terminal 10, so that the manager terminal 10 is input from the machine-translated characters and the stenographer. By collecting the shorthand information, it is possible to generate the final subtitle data.

The user terminal 30 is a device that receives video content combined with caption data and displays the caption data together when the video content is reproduced so that the hearing impaired can enjoy video content. Wired or wireless communication with an external device is possible. and, an electronic device capable of inputting, outputting, and processing information, for example, may be in the form of a smartphone, PC, tablet PC, smart TV, wearable device, or the like.

The user terminal 30 receives caption data for broadcast content and caption data from the manager terminal 10 and synchronizes the caption data with the broadcast content. In addition, the user terminal 30 may encode broadcast content and caption data into one broadcast data.

3 is a block diagram showing the configuration of the user terminal 30 according to an embodiment of the present invention.

As shown in FIG. 3 , the user terminal 30 according to an embodiment of the present invention may include an object detection unit 210 and a synchronization unit 220 .

The object detecting unit 210 recognizes an image object in the broadcast content obtained from the image receiving unit 110 of the manager terminal 10 . Specifically, the object detecting unit 210 recognizes an object from a video image of broadcast content. Here, the object detecting unit 210 may be a generally used image object recognition tool. For example, the object detection unit 210 may be an application such as a cloud vision API.

Object recognition is a computer vision technology that identifies an object on an image or video, and may be performed through deep learning and machine learning algorithms. Object recognition can recognize objects included in images

For example, the object detection unit 210 extracts and recognizes a blue sky from a specific image frame, or when there is no object recognized as a person among the objects extracted from a specific image frame, it is assumed that a person does not appear in the image. can recognize

The synchronization unit 220 synchronizes subtitle data and broadcast content.

FIG. 4 is a diagram illustrating a detailed configuration of the synchronization unit 220 . The synchronization unit 220 includes a decryption unit 221 , a text management unit 222 , and an image and audio management unit 223 .

The decoding unit 221 decodes and decompresses the modulated and compressed image content and subtitle data. Video, audio and text are transmitted through their own modulation and compression for loss and smooth transmission in the process of transmission. wait for

The text management unit 222 checks the synchronization timestamp included in the caption data. If the text waiting to be output has a timestamp for synchronization taken at the time of text creation, the video is output according to the time information of the text. When checking the time information.

When the video and audio management unit 223 receives the video through the receiving means and separates it from the text, the video and audio management unit 223 checks time information taken every second in the video.

Thereafter, the synchronization unit 220 compares the time information of the text (subtitle data) with the time information of the video (video content), and when the time information of the video is different from the time information of the text, it is temporarily stored in the storage means according to the time information of the text. The stored video can be displayed with a delay in seconds.

In this process, even when the video is output according to the time information of the text, when the video and the text are not synchronized, the synchronization unit 220 may delay the display of the video by seconds and control it to be exported.

In some other embodiments, the synchronization unit 220 may perform synchronization by comparing the keyword of the caption data with the image object recognized by the object detection unit 220 .

In an embodiment, the synchronizer 230 may extract a keyword from the caption data. A method for the synchronization unit 230 to extract a keyword from the caption data is generally based on a well-known keyword extraction method. As a specific example, the synchronization unit 230 may include a keyword extraction tool based on big data or AI.

In another embodiment, the synchronization unit 230 may obtain a keyword for the screen commentary part of the characteristic. For example, the stenographer may input a specific key before entering a specific word to indicate that the corresponding word is a keyword.

For another example, in the case of a word input by a stenographer using an abbreviation input, the corresponding word may be processed as a keyword and transmitted to the synchronization unit 230 . Here, the abbreviation input refers to an input in which a pre-stored word is input even when the stenographer inputs only a specific combination of consonants rather than all specific words. A word input through an abbreviation input is a commonly used word, and may be highly likely to be used as a keyword.

The synchronization unit 230 compares the creation time of the manuscript, which is the basis of the subtitle data, and the image frame timeline in the video, and selects the one with a difference of less than or equal to a specific time, and selects the object recognized in the selected image frame and the screen commentary sound source. Synchronization can be performed by comparing keywords.

In addition, the synchronization unit 230 may generate new broadcast content by integrating the caption data synchronized with the broadcast content. In this case, the synchronization unit 230 may adjust the synchronization degree of the subtitle data so as not to overlap with the audio of the broadcast content.

As a result, the content production system for the visually and hearing impaired according to an embodiment of the present invention can solve the asynchronization of the broadcast content and subtitle data, which inevitably occurs due to the nature of the shorthand input input while viewing the broadcast content.

The manager terminal 100 for the visually impaired according to an embodiment of the present invention may further include an output unit (not shown). The output unit may output the generated integrated subtitle, subtitle data, or broadcast content for the visually impaired in which the subtitle data is synchronized. The output unit may separately tag and package the integrated subtitle and the subtitle data to output them. The set-top box may output integrated subtitles, output subtitle data, or both at once according to a user's settings.

In some other embodiments, the manager terminal 10 may include: a collection management module for setting a collection criterion of at least one of a collection target data source module, a collection target keyword, and a collection target period; a data collection module for collecting big data from the corresponding data source module according to the data collection standard set by the collection management module and storing it in the database module; a morpheme analysis module for analyzing morphemes of big data stored in the database module, classifying them by morpheme, and generating morpheme analysis data; and a data analysis module for calculating statistical values by processing morpheme analysis data with a distributed parallel processing-based statistical analysis algorithm and outputting a weak signal according to the statistical value; a big data analysis-based weak signal derivation system (for convenience of explanation) It is possible to extract illegal subtitle data that violates laws or terms and conditions from among the received subtitle data by using (not shown in the drawing).

Here, the manager terminal 10 includes: a distributed file system for generating morpheme analysis data by dividing the received caption data for each morpheme having a meaning and storing the morpheme analysis data; a data processing unit providing a virtualized database interface to process morphological analysis data existing in the distributed file system based on SQL (structured query language); And by executing a statistical analysis algorithm through the virtualized database interface provided by the data processing unit, from the morpheme analysis data, the number of occurrence frequencies by year (instance frequencies) by year, the number of simultaneous appearances between words by year, the number of appearances by year and by year The word-to-words may include a statistical analysis unit for calculating at least one or more of the processed values from the number of simultaneous appearances.

In addition, the statistical analysis unit, the statistical analysis unit may calculate an increase rate of the number of occurrences per word based on the number of occurrences per year (instance frequencies) and the number of simultaneous occurrences between words.

In addition, the statistical analysis unit divides the number of occurrences per year (instance frequencies) by the number of documents per year to standardize the number of appearances per year of the words per document to calculate a standardized increase rate of the frequency of appearance per word for the words. can

In addition, the statistical analysis unit calculates the increase rate of the degree of connection degree centrality for each word by using the word-to-word co-occurrence matrix, and the standardized increase rate of the frequency of appearance for each word and the increase rate of the degree of centrality of the connection degree are higher than a certain portion of the word or A word that is less than a certain lower part can be derived as a weak signal.

Meanwhile, the data collection module may collect big data including unstructured data of at least any one of image, video, voice, sensor, GPS, GIS, and M2M data.

Accordingly, the manager terminal 100 can improve the reliability of caption data by detecting caption data that is not suitable for broadcast transmission through big data analysis through the weak signal derivation system including the above-described configuration.

The term '~ unit' used in the above embodiments means software or hardware components such as field programmable gate array (FPGA) or ASIC, and '~ unit' performs certain roles. However, '-part' is not limited to software or hardware. The '~ unit' may be configured to reside on an addressable storage medium or may be configured to refresh one or more processors. Thus, as an example, '~' denotes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program patent code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

Functions provided in components and '~ units' may be combined into a smaller number of components and '~ units' or separated from additional components and '~ units'.

In addition, components and '~ units' may be implemented to play one or more CPUs in a device or secure multimedia card.

The technology for providing such a method for automatically generating non-face-to-face transcripts may be implemented as an application or implemented in the form of program instructions that may be executed through 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 specially designed and configured for the present invention, and may be known and available to those skilled in the computer software field.

Examples of the computer-readable recording medium include a hard disk, a magnetic medium such as a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and DVD, and a magneto-optical medium such as a floppy disk. 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. The hardware device may be configured to operate as one or more software modules to perform processing according to the present 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 to the present invention without departing from the spirit and scope of the present invention as set forth in the following claims. will be able

10: Administrator terminal
20: stenographer terminal
30: user terminal

Claims (3)

In a video synchronization system for improving viewing rights for persons with disabilities, generating caption data by converting audio included in video content into text, and synchronizing the video content and the caption data using a timestamp generated together when the caption data is generated ,
The video synchronization system for improving the viewing rights of the disabled,
a manager terminal that provides video content;
a stenographer terminal for generating stenography information for the video content; and
Including a user terminal possessed by a person with a disability viewing the video content,
The manager terminal,
and generating subtitle data based on the stenography information received from the stenographer terminal, generating a timestamp in units of one word or one line of a character string constituting the subtitle data, and combining it with the subtitle data,
The user terminal,
In the process of outputting the video content combined with the subtitle data, if there is a time stamp in the text waiting to be output, the time information of the video is compared with the time information checked when the text is displayed with the time information of the video of the video content. If it is confirmed that is different from the time information of the text, the video content is displayed by delaying the video on the storage means in seconds according to the time information of the text to synchronize the video content and the subtitle data,
If it is determined that the video and the text are not synchronized even after the video is output in accordance with the time information of the text, the video display is delayed by a preset reference time to be displayed,
The manager terminal,
a collection management module for setting at least one of a collection target data source module, a collection target keyword, and a collection target period; a data collection module for collecting big data from the corresponding data source module according to the data collection criteria set by the collection management module and storing it in the database module; a morpheme analysis module that analyzes morphemes of big data stored in the database module, classifies them by morpheme, and generates morpheme analysis data; and a data analysis module that processes morpheme analysis data with a distributed parallel processing-based statistical analysis algorithm to calculate statistical values and outputs a weak signal according to the statistical value; received using a big data analysis-based weak signal derivation system including A video synchronization system for improving viewing rights for persons with disabilities, characterized in that it extracts illegal subtitle data that conflicts with laws or terms and conditions from among the subtitle data.
delete delete

Images