KR100857381B1 - Contents service system and method - Google Patents

Abstract

The present invention relates to a content service system and method, wherein the system provides a video registration procedure to a user, a video service server for searching and providing video content to a user terminal according to a user's request, and index data from the video content. And a source extraction server that generates at least one of scene data and audio data and extracts a source of the moving image content based on at least one of the index data, the scene data and the audio data. According to the present invention, the text, scene and audio data can be extracted from the video content and the source of the video can be extracted by using pattern matching, thereby providing a basis for protecting copyright.

Content Service System, Video, Copyright, Text, Scene, Audio

Description

Content Service System and Method {CONTENTS SERVICE SYSTEM AND METHOD}

1 is a block diagram illustrating a content service system according to an exemplary embodiment of the present invention.

2 is a schematic diagram illustrating a metadata database and a copyright database of registered content used in a content service system according to an exemplary embodiment of the present invention.

3 is a flowchart illustrating an operation of a content service system according to an exemplary embodiment of the present invention.

FIG. 4 is a flowchart for explaining an example of text-based source extraction shown in FIG. 3.

5 is an exemplary diagram illustrating an example of extracting a text-based source according to the flowchart shown in FIG. 4.

FIG. 6 is a flowchart for explaining an example of video-based source extraction shown in FIG. 3.

FIG. 7 is a flowchart for explaining an example of audio-based source extraction shown in FIG. 3.

8 is an example of a video service screen displayed on a user terminal according to an embodiment of the present invention.

<Explanation of symbols for main parts of the drawings>

100: user terminal, 200: communication network,

300: video service server, 330: source extraction server,

360: asset update server, 400: video database,

450: asset database, 452: text database,

454: scene database, 456: audio database,

The present invention relates to a content service system and method, and more particularly to a content service system and method that can provide a basis for protecting the copyright for content such as video.

With the rapid spread of high speed internet in recent years, it has become an indispensable necessity in modern life. Many users use information retrieval, online games, e-commerce, internet banking, and e-mail through the Internet. Moreover, more and more users are actively attempting to create information and share the generated information with other users, instead of simply accepting information through the Internet. In particular, the video UCC (user created contents) based on Web 2.0, which promotes openness, sharing and participation, is very popular with netizens and is widely spread. Thanks to this atmosphere, video service providers, which provide services for storing and registering videos uploaded by netizens and playing them at the request of users, are rapidly increasing.

On the other hand, most of the users do not make their own video, but rather simply copy or edit the video, such as broadcasting, broadcast, animation, movies, music videos of others, such as broadcasters to create a video that suits their taste and enjoy it. However, since the broadcaster who made such a video has a copyright on the video, the user or the video service company may infringe the copyright if used arbitrarily. Video copyright holders, who have not been seriously considering copyright, have recently asked video service providers to protect the copyrights of their own productions. have.

In the meantime, video service providers are also trying to protect copyright in their own way by warning them of copyright infringement at the time of video upload or by strengthening monitoring functions on service sites. However, it is difficult to solve the copyright problem simply by this method. Users and video service providers as well as video copyright owners agree that the paradigm of video content consumption and production is already fundamentally changing. Video copyright owners and video service providers need to take a proactive approach to copyright issues in video services to find new revenue and new marketing opportunities in the new media environment. have.

Therefore, the present invention is to provide a content service system and method that can provide a more reasonable basis for protecting the copyright of the content.

The content service system according to an embodiment of the present invention for achieving the technical problem, a video service server for providing a video registration procedure to the user, and retrieves the video content to the user terminal according to the user's request, and the video And a source extraction server that generates at least one of index data, scene data, and audio data from content, and extracts a source of the video content based on at least one of the index data, the scene data, and the audio data.

An asset update server for generating at least one of source text information, source scene information, and source audio information in a video asset from a copyright holder, and a copyright database storing at least one of the source text information, the source scene information, and the source audio information. The source extracting server may extract the source of the video content based on at least one of the source text information, the source scene information, and the source audio information.

The source extracting server may search the asset database and extract a source related to the source text information if the source text information equal to the index data is present.

The source extraction server extracts frame data of a predetermined scene from the video content, performs predetermined signal processing on the frame data to generate the scene data, and performs pattern matching on the scene data and the source scene information to obtain similarity. After the calculation, the source related to the source scene information may be extracted according to the magnitude of the similarity.

The source extraction server extracts audio information of a predetermined section from the video content, performs predetermined signal processing on the audio information to generate the audio data, and performs pattern matching on the audio data and the source audio information to obtain similarity. After calculation, a source related to the source audio information may be extracted according to the magnitude of the similarity.

The method of generating the scene data and the audio data may be substantially the same as the method of generating the source scene information and the source audio information, respectively.

Sources associated with the source text information, sources associated with the source scene information, and sources associated with the source audio information may be weighted differently, and sources may be ranked based on the similarity and the weight corresponding to each source. have.

The apparatus may further include a video database that stores the video content and receives and stores source information of the video content from the source extraction server.

The source exposure operation associated with the source of the video content may be performed or a copyright fee of the video content may be calculated based on the source of the video content.

According to another aspect of the present invention, there is provided a content service method, including registering video content, generating at least one of index data, scene data, and audio data from the video content, the index data, the scene data, and the audio data. Extracting a source of the video content based on at least one of the following; and searching and providing the video content to a user terminal.

Generating and storing at least one of source text information, source scene information, and source audio information in a video asset from a copyright holder, wherein the source extracting step comprises the source text information, the source scene information, and the source audio information The method may include extracting a source of the video content based on at least one of the methods.

The source extracting step may further include extracting a source related to the source text information if there is the same source text information as the index data.

The scene data generating step may include extracting frame data of a predetermined scene from the moving image content, and generating the scene data by performing a predetermined signal processing on the frame data. The method may further include calculating similarity by performing pattern matching on the scene data and the source scene information, and extracting a source related to the source scene information according to the magnitude of the similarity.

The generating of the audio data includes extracting audio information of a predetermined section from the video content, and generating the audio data by performing a predetermined signal processing on the audio information. The method may further include calculating similarity by performing pattern matching on audio data and the source audio information, and extracting a source related to the source audio information according to the magnitude of the similarity.

The method of generating the scene data and the audio data may be substantially the same as the method of generating the source scene information and the source audio information, respectively.

Sources associated with the source text information, sources associated with the source scene information, and sources associated with the source audio information may be weighted differently, and sources may be ranked based on the similarity and the weight corresponding to each source. have.

The method may further include performing a source exposing operation related to the source of the video content or calculating a copyright fee of the video content based on the source of the video content.

A computer readable medium according to another aspect of the present invention records a program for causing a computer to execute any of the above methods.

DETAILED DESCRIPTION Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art may easily implement the present invention.

First, a content service system according to an exemplary embodiment of the present invention will be described in detail with reference to FIGS. 1 and 2.

FIG. 1 is a block diagram illustrating a content service system according to an exemplary embodiment of the present invention, and FIG. 2 is a schematic diagram illustrating metadata information and a copyright database of registered content used in a content service system according to an exemplary embodiment of the present invention. .

Referring to FIG. 1, a content service system according to an embodiment of the present invention includes a video service server 300, a source extraction server 330, an asset update server 360, a video database 400, and an asset database 450. It includes, and is connected to the plurality of user terminals 100 through the communication network 200.

The user terminal 100 is a device that accesses a content service system to provide a video service and exchanges information. The user terminal 100 is a desktop computer as well as a laptop computer, a workstation, a palmtop computer, a personal digital assistant, PDA), a web pad, a mobile phone, a smart phone, etc. may be formed of a terminal having a computing capability with a memory means and a microprocessor.

The user terminal 100 includes a communication module (not shown) and an application program (not shown) for connecting to a content service system through the communication network 200, and a web camera or a PC camera (not shown) for capturing an image. Or not).

The application program accesses the content service system through the communication network 200 according to a user's operation and performs various functions. An example of the application may include a web browser such as Microsoft's Internet Explorer, but is not limited thereto and may be a dedicated program provided by a content service system. The application may include a module (not shown) for uploading a video recorded with a web camera or the like stored in the user terminal 100 to a content service system, and playing a video stored in the content service system. It may include a playback module (not shown). These modules can be implemented in activeX.

The communication network 200 does not select a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), the Internet, and the like. It doesn't matter what type of communication you have.

The video service server 300 provides a video registration procedure to the user, searches for the registered video at the user's request, and provides the video to the user terminal 100. That is, the video service server 300 uploads a video from the user terminal 100 according to a request from the user, and stores and registers the video in the video database 400. In the process of registering a video, the user may select a service category such as a video, for example, a video, a blog, a cafe, and the like, and may register information related to the video. The video service server 300 displays the video in the corresponding service category according to the user's search request so that the user can play the video. Meanwhile, the video service server 300 may perform an operation related to the source of the video such as displaying the source of the video or providing a link to a website related to the source.

The video database 400 stores a video uploaded by a user, and also stores a title, a video category, a tag, a text, a subtitle, and the like of the video input during the video registration. In addition, the video database 400 may store the source of the video inputted by the user in the process of registering the video, and may separately store the source of the video automatically extracted from the source extraction server 330.

The source extraction server 330 generates meta information MI from the video content uploaded and registered by the user. Referring to FIG. 2, the meta information MI includes index data TD, scene data SD, and audio data AD. The source extraction server 330 extracts a text-based source based on the index data TD, extracts a scene-based source based on the scene data SD, and extracts an audio-based source based on the audio data AD. Extract. In addition, based on the extracted text-based source, scene-based source, and audio-based source, the source of the registered video is comprehensively determined. The source extraction server 330 transmits the source of the video to the video service server 300 and stores the video in the video database 400 so that the content service system can perform an operation related to the video source.

The asset database 450 includes a text database 452, a scene database 454, and an audio database 456, and stores source information associated with the video asset. This source information includes source text information, source scene information, and source audio information. The asset database 450 receives the source text information, the source scene information, and the source audio information from the asset update server 360 and stores them in the text database 452, the scene database 454, and the audio database 456, respectively. The asset database 450 may store the video asset itself as needed.

The asset update server 360 receives the video asset from the copyright holder, generates source information from the video asset, and stores the same in the asset database 450 to update the source information related to the video asset. The source information includes the title of the video asset, the copyright holder, and the site address of the video asset, and the source text information includes keywords related to the video asset. The source scene information is information related to at least one representative scene of the moving picture asset, and the source audio information is information about at least one representative section of the moving picture asset. The manner in which the asset update server 360 generates the source scene information and the source audio information is substantially the same as the manner in which the source extraction server 330 generates the scene data SD and the audio data AD, respectively. Meanwhile, the content service provider may receive a video asset from the copyright holder and input the video asset into the asset update server 360, but the copyright holder may update the video asset by directly inputting the video asset into the asset update server 360 through the communication network 200. have.

The operation of the content service system will now be described in more detail with reference to FIGS. 3 to 8.

3 is a flowchart illustrating an operation of a content service system according to an exemplary embodiment of the present invention, FIG. 4 is a flowchart illustrating an example of text-based source extraction shown in FIG. 3, and FIG. 5 is illustrated in FIG. 4. This is an exemplary view showing an example of extracting a text-based source according to the flow chart shown. FIG. 6 is a flowchart for explaining an example of video-based source extraction shown in FIG. 3, FIG. 7 is a flowchart for explaining an example of audio-based source extraction shown in FIG. 3, and FIG. 8 is an embodiment of the present invention. According to an embodiment, it is an example of a video service screen displayed on a user terminal.

Referring to FIG. 3, the content service system provides a video registration procedure to the user, and the user registers the video by uploading the video captured by the video terminal or the web camera stored in the user terminal 100 to the content service system. (S500). The application program of the user terminal 100 encodes a video, edits such as section setting or scene selection, and uploads the video to the content service system. Alternatively, the video service may encode and edit the video. In the latter case, the encoding operation may be performed by the video service server 300, but may be performed with a separate encoding server.

The user may upload a video by selecting a service category in advance, and may register video related information such as a title, a video category, a tag, a text, and a caption of the video according to a format provided by the content service system. In addition, the user may register the source of the video determined by the user.

The content service system extracts a text-based source from the registered video (S510). Text-based source extraction will be described in more detail with reference to FIGS. 4 and 5.

Referring to FIG. 4, when a video is uploaded from a user and registered in the content service system, the source extraction server 330 extracts the text of the video content from the video database 400 (S511). The text includes the title, tag, title, body, subtitle, etc. of the video input by the user when registering the video. The source extraction server 330 performs parsing such as extracting a morpheme from the extracted text and extracting a word to generate index data TD that can represent a feature of the video in the text (S513). The index data TD may be mainly a noun but may be a specific set of words, such as a descriptive sentence. The number of index data TD in one video content may be one or more, and the frequency of occurrence of each index data TD in text may also be one or more.

The source extraction server 330 searches the text database 452 for the extracted index data TD (S515), and among the keywords related to the video stored in the text database 452, the same as that of the index data TD. It is determined whether there is (S517). As a result, if there is a keyword equal to the index data TD, a text-based source is extracted by referring to source information related to the keyword (S519). The source extraction server 330 repeats steps S515 to S519 until the search for the entire text database 452 is completed (S521), and for each index data TD, a text database ( Search 452) to extract text-based sources. The operation then returns when the search of the text database 452 is completed. In the case of text-based sources, a plurality of sources may be extracted in some cases.

As shown in Fig. 5, when the user registers a video, the text inputted is "Title: Jumong 45 episodes aired, tag: Jumong, text: Finally, Jumong makes the foundation of founding Sosono and Goguryeo. Khaha ~" . The source extraction server 330 may extract index data (TD) such as "Jumong", "Sosono", "Goguryeo", "Founding", etc. from this text. In this case, the number corresponding to each index data TD represents a ratio of the frequency of appearance of each index data TD in the entire index data TD. The index data (TD) of "Jumong" appears at the ratio of 0.6 and "Sorso" at the ratio of 0.2. On the other hand, the text database 452 stores the source information of the drama "Jumong" as "Jumong: MBC: www.imbc.com/broad/tv/drama/jumong ", and the keyword "Jumong, Sosono, and Mopalmo" as a keyword. Is input.

As a result of the search, the index data (TD) "Jumong" and "Sorso" match the keywords of the text database 452, so that text-based sources can be extracted by referring to the source information related to the keywords. In this example, the same source is extracted for two index data (TDs), so one source is extracted as a text-based source. If the extracted sources point to the same one, it means that the extracted sources are appropriate.

The extracted source may be displayed including index data (TD), ratio, copyright holder, website of the copyrighted work, and the like, as shown in FIG.

"Jumong: 0.6, MBC, www.imbc.com/broad/tv/drama/jumong ",

"Sosono: 0.2, MBC, www.imbc.com/broad/tv/drama/jumong ".

However, if the source corresponding to each index data (TD) is different, the source may be ranked according to the ratio of the index data (TD), or the source may be determined by referring to the scene-based source or the audio-based source. Alternatively, the similarity can be calculated by weighting the keywords stored in the text database 452 by multiplying the ratio and the weight of the corresponding index data, and ranking the sources according to the size of the similarity.

Referring to FIG. 3 again, the content service system extracts a scene-based source for the registered video (S530). Scene-based source extraction will be described in more detail with reference to FIG. 6.

Referring to FIG. 6, when a video is uploaded from a user and registered in the content service system, the source extraction server 330 captures at least one representative scene from the video content registered in the video database 400 (S531). Here, capturing the representative scene means extracting frame data of the representative scene.

A scene in which a person stands out may be captured as a representative scene through a predetermined algorithm, and a scene corresponding to a preset time may be captured as a representative scene. In contrast, when a user registers a moving picture, a typical scene is selected as a cover so that the cover can be captured as a representative scene. The scene capturing method of the registered video is substantially the same as the capturing the scene to obtain source scene information from the video asset.

The source extraction server 330 performs filter processing on the captured frame data to remove noise and to emphasize an image (S533). A normalization operation is performed such as enlarging or reducing the image, correcting the position of the image, rotating the image as necessary, and normalizing the density (S535). Then, parameters that faithfully represent the characteristics for the normalized picture are extracted. That is, the scene data SD is generated by extracting a feature related to image content such as color, texture, and shape from the normalized data (S537).

Pattern matching is performed on the generated scene data SD and the source scene information stored in the scene database 454 to calculate a similarity between the two (S539). Similarity can be calculated in various ways. The source scene information is also the same as described above, and extracts the representative scene from the video asset, preprocesses, normalizes operations, and features, and generates the scene data (SD) for the representative scene of the registered movie. And stored.

When the similarity is greater than the threshold value by comparing the calculated similarity with the threshold value (S541), the scene-based source is extracted by referring to the source information related to the source scene information (S543). The source extraction server 330 repeats steps S539 to S543 until the pattern matching is completed for all source scene information in the scene database 454 (S545). When there are a plurality of scene data SDs, the same operation is repeated for each scene data SD to extract a scene-based source. The operation then returns when the pattern matching of the scene database 454 is completed.

Even in scene-based sources, a plurality of sources may be extracted in some cases. That is, one or more source scene information for calculating a similarity exceeding a threshold may be extracted, and in this case, the ranking of sources may be ranked according to the magnitude of the similarity. In some cases, scene-based sources may not be extracted.

Referring to FIG. 3 again, the content service system extracts an audio-based source for the registered video (S550). Audio-based source extraction will be described in more detail with reference to FIG. 7.

Referring to FIG. 7, when a video is uploaded from a user and registered in the content service system, the source extraction server 330 selects at least one representative section from the video content registered in the video database 400 (S551).

A section in which the voice is mainly highlighted may be selected as the representative section through a predetermined algorithm, and a section corresponding to a preset time may be selected as the representative section. Alternatively, the representative section may be selected as a section including the representative scene in the video-based source extraction. The section selection method of the registered video is substantially the same as the section selection method for obtaining source audio information from the video asset.

The source extraction server 330 cuts out the part without audio information in the representative section, extracts the audio from this section, and performs preprocessing (S553). In the case of extracting an audio-based source from voice, a process of determining whether data in a selected section is voice may be included in the preprocessing process. In operation S555, a normalization operation such as removing noise or removing audio distortion generated during encoding is performed. Then, the audio data AD is generated by extracting a parameter capable of faithfully representing audio characteristics such as a tone and tone for the normalized audio (S557).

Similarity between the two is calculated by performing pattern matching on the generated audio data AD and the source audio information stored in the audio database 456 (S559). Similarity can be calculated in various ways. As described above, the source audio information is data extracted from the video asset, preprocessing, normalization manipulation, and feature extraction. The audio information is generated in the same manner as that of generating audio data (AD) for the representative video segment of the registered video. And stored.

When the similarity is greater than the threshold value by comparing the calculated similarity with the threshold value (S561), the audio-based source is extracted by referring to the source information related to the corresponding source audio information (S563). The source extraction server 330 repeats steps S559 to S563 until the pattern matching is completed for all source audio information in the audio database 456 (S545). When the audio data AD is plural, the same operation is repeated for each audio data AD to extract an audio-based source. The operation then returns when the pattern matching of the audio database 456 is completed.

In audio-based sources, a plurality of sources may be extracted in some cases. That is, one or more source audio information having a similarity exceeding a threshold may be extracted, and in this case, the source may be ranked according to the size of the similarity. In some cases, scene-based sources may not be extracted.

So far, we have described text-based sources, scene-based sources, and audio-based sources in turn, but the order of each source extraction process can be changed. In addition, scene pattern matching and audio pattern matching may be performed in different ways.

Referring again to FIG. 3, the source extraction server 330 comprehensively determines a video source based on the extracted text-based source, scene-based source, and audio-based source (S570).

Text-based sources, scene-based sources, and audio-based sources can be weighted differently, and if there are multiple extracted sources, the source can be ranked in order of highest value by multiplying the similarity and weight corresponding to each source. . Due to the characteristics of the video, a relatively high weight may be given to the scene-based source.

In contrast, text-based sources, scene-based sources, and audio-based sources can be independently extracted and designated as the source of a video, and at least one of index data (TD), scene data (SD), and audio data (AD) is extracted from the video content. And extract the source of the video content based on at least one of the index data TD, the scene data SD, and the audio data AD.

The source of the video may not be extracted. If there is no extracted source, the video may be a video produced by a user who is not related to the asset.

Meanwhile, text-based sources, scene-based sources, and audio-based sources may be displayed on the server side, and the final source of the video may be determined according to the operator's selection of the content service system. That is, it displays the top rankings with the highest similarity among text-based sources, for example, the top ones with the top ten, similarly the top rankings with the highest similarity among the scene-based sources, and the high similarity among the audio-based sources. The source of the top rank is marked and the operator can review the representative scene of the actual registered video and determine the final source. The operator can check whether the source input when the user registers the video and the source extracted from the content service system are the same.

When the source of the video is extracted, the content service system performs a predetermined operation related to the source (S580). That is, the source extraction server 330 delivers the extracted source to the video service server 300. In addition, it is delivered to the video database 400 and recorded along with the video content. Thereafter, the video service server 300 may perform various exposure operations as follows with respect to the extracted source while displaying the video content on the user terminal 100 according to a request from the user.

As an example of the exposure operation, the content service system may display the extracted source together with the video content.

The content service system may also provide a link to a website related to the extracted source. Referring to FIG. 8, a website link 160 related to a source is disposed in the video player 150 displayed on the user terminal 100. Of course, the link 160 may be disposed outside the video player 150. When the user clicks on the website link 160, he or she can go to a site related to the source to view more video assets.

In addition, the content service system may post a banner advertisement 170 related to the extracted source together with the video content. Of course, a separate advertisement for the profit of the content service provider other than the banner advertisement 170 of the copyright holder may be displayed together, and in this case, the copyright owner and the corresponding advertisement revenue may be distributed.

In addition, the content service system includes a button inside or outside the video player 150 displayed on the user terminal 150, and when a user clicks the button, the content service system reads a video asset related to the video content from the asset database 450 and plays it. You can download it. In this case, a video asset may be used for a fee or free of charge. In case of a fee, a content service provider and a copyright holder may distribute the revenue. This removes the hassle of going to the copyright holder's website and using the video asset. In addition, the user may download and edit the video asset, and may also re-register or additionally register the edited video content. At this time, the entire video asset may be downloaded, but may be allowed only for necessary portions.

The content service system may expose content related to the video asset of the extracted source. In other words, the user's satisfaction with the video asset may be investigated, a questionnaire may be asked for a specific content, or a vote may be performed to ask for the user's opinion. In addition, information related to the contents of the video work, for example, the information of the favorite items that are used by the main character in the drama may be provided or a display for the purchase of the article may be performed.

As such, the extracted source may be used to perform various exposure operations related to the extracted source. The description here is just an example, and you can use extracted sources in more various ways.

On the other hand, apart from such an exposure operation, the content service system can know the source of the uploaded video so that the user can calculate the copyright fee to be paid to the copyright holder of the video according to the number of uploaded videos or the number of plays of the registered video. Can be.

Source-related operations described as examples above may be selectively performed according to the agreement of the content service provider and the copyright holder.

Since various business models can be created by performing the exposure operation related to the extracted source, a profit model that can satisfy both the content service provider and the copyright holder can be created. You can also use the extracted sources to calculate your royalty. Various processing can be performed based on the extracted source, thus providing a basis for protecting copyrights.

Although a description has been made of a video as an example so far, the same may be applied to content such as music, photos, and pictures.

Embodiments of the invention include a computer readable medium containing program instructions for performing various computer-implemented operations. This medium records a program or process for executing a method of serving content as described so far. The media may include, alone or in combination with the program instructions, data files, data structures, and the like. Examples of such media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CDs and DVDs, floppy disks and program commands such as magnetic-optical media, ROM, RAM, flash memory, and the like. Hardware devices configured to store and perform such operations. Alternatively, the medium may be a transmission medium such as an optical or metal wire, a waveguide, or the like including a carrier wave for transmitting a signal specifying a program command, a data structure, 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.

Although the preferred embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements of those skilled in the art using the basic concepts of the present invention defined in the following claims are also provided. It belongs to the scope of rights.

As described above, according to the present invention, the source of the video is extracted by extracting index data, scene data, and audio data from the video content, and performing pattern matching with source text information, source scene information, and source audio information stored in the asset database. Can be extracted.

When the video is exposed, various processing can be performed based on the extracted source, such as displaying the source, providing a link to the website, or displaying a banner advertisement, thereby providing a foundation for protecting copyright.

Claims (18)

A video service server that provides a video registration procedure to a user, retrieves video content according to a user's request, and provides the video to a user terminal; Generating at least one of index data, scene data, and audio data from the video content, and extracting a source of the video content based on at least one of the index data, the scene data, and the audio data; A source extraction server that extracts a source of the video content by referring to at least one of source scene information and source audio information Content service system comprising a. In claim 1, An asset update server for generating at least one of the source text information, the source scene information, and the source audio information in a video asset from a copyright holder; and And a work database for storing at least one of the source text information, the source scene information, and the source audio information. Content service system. In claim 2, And the source extracting server searches the asset database and extracts a source related to the source text information if there is the same source text information as the index data. In claim 2, The source extraction server extracts frame data of a predetermined scene from the video content, performs predetermined signal processing on the frame data to generate the scene data, and performs pattern matching on the scene data and the source scene information to obtain similarity. And calculating a source related to the source scene information according to the magnitude of the similarity. In claim 2, The source extraction server extracts audio information of a predetermined section from the video content, performs predetermined signal processing on the audio information to generate the audio data, and performs pattern matching on the audio data and the source audio information to obtain similarity. And calculating a source related to the source audio information according to the magnitude of the similarity. The method according to any one of claims 2 to 5, And a method of generating the scene data and the audio data is substantially the same as the method of generating the source scene information and the source audio information, respectively. The method according to any one of claims 2 to 5, Different weights may be assigned to sources related to the source text information, sources related to the source scene information, and sources related to the source audio information, and the ranking of the sources based on the similarity and the weight corresponding to each source. Service system. The method according to any one of claims 1 to 5, And a video database for storing the video content and receiving and storing source information of the video content from the source extraction server. The method according to any one of claims 1 to 5, A content service system that performs a source exposure operation related to the source of the video content or calculates a royalty fee for the video content based on the source of the video content. Registering video content, Generating at least one of index data, scene data, and audio data from the video content; Extracting a source of the video content based on at least one of the index data, the scene data, and the audio data, and Searching for the video content and providing the same to a user terminal; Including; The source extracting step may include extracting the source of the video content by referring to at least one of source text information, source scene information, and source audio information stored in advance. Content service method. In claim 10, Generating and storing at least one of the source text information, the source scene information, and the source audio information in a video asset from a copyright holder. In claim 11, The source extracting step may further include extracting a source related to the source text information if there is the same source text information as the index data. In claim 11, The scene data generation step, Extracting frame data of a predetermined scene from the video content; and Performing the predetermined signal processing on the frame data to generate the scene data; The source extraction step, Calculating similarity by performing pattern matching on the scene data and the source scene information, and Extracting a source related to the source scene information according to the magnitude of the similarity; Content service method. In claim 11, The audio data generating step, Extracting audio information of a predetermined section from the video content; and Performing the predetermined signal processing on the audio information to generate the audio data, The source extraction step, Calculating a similarity by performing pattern matching on the audio data and the source audio information, and Extracting a source related to the source audio information according to the magnitude of the similarity; Content service method. The method according to any one of claims 11 to 14, The method of generating the scene data and the audio data is substantially the same as the method of generating the source scene information and the source audio information, respectively. The method according to any one of claims 11 to 14, Different weights may be assigned to sources related to the source text information, sources related to the source scene information, and sources related to the source audio information, and the ranking of the sources based on the similarity and the weight corresponding to each source. Service method. The method according to any one of claims 10 to 14, Calculating a copyright fee of the video content based on the source exposure operation related to the source of the video content or the source of the video content. A computer-readable medium having recorded thereon a program for causing a computer to execute the method of claim 10.

Images