JP2019213038A - Video information providing system - Google Patents

Abstract

To provide a video information providing system capable of quickly and appropriately supplying useful video contents to a user, for a large number of distributed video contents.SOLUTION: A system comprises: component appearance frequency determining means for determining an appearance frequency of an identical component on the basis of the component of distributed video content; video content extracting means for extracting a video content including the component when the appearance frequency is equal to or higher than a predetermined value on the basis of the determination by the component appearance frequency determining means, and video content providing means for providing a viewer with the video extracted by the video content extracting means.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a video information providing system, and more particularly, to a video information providing system that determines the appearance frequency of video content appearing on TV and the web and provides the user with video content having a high appearance frequency in a timely manner.

  Currently, a wide variety of video information is continuously distributed to viewers and users via TV and the web. Thus, it is becoming difficult for viewers and users to appropriately and timely extract useful video content from a large amount of video information that is automatically provided at any time for 24 hours. .

  In other words, a busy modern person visually recognizes a plurality of programs and a large amount of video information distributed from a broadcasting station for a predetermined time in front of a TV receiver as before, and needs it from among them. There is a situation where it is gradually impossible to obtain proper video content and information.

  There is a similar situation with regard to obtaining information from the web. That is, in order to obtain necessary information from the web, information is obtained by keyword search using an Internet search engine such as Google (registered trademark). A large amount of information called “noise” and similar to the desired information is extracted.

  Therefore, even when the search engine is used, the user needs to further extract information desired by the user from a large amount of related information, and the search operation is still complicated. .

  By the way, conventionally, for example, a technique for searching for a video similar to a video registered in advance in a certain period from videos output by television broadcasting as video content is known.

  Such a search technique is, for example, the detection of a specific title roll from a television broadcast signal to start / stop real-time recording, or the same news material broadcast at different times / broadcast stations to detect the structure of the video. It is used for techniques such as analysis (see, for example, Patent Document 1).

  Moreover, such a search technique is not limited to television broadcasting, but can also target distribution data such as video content received through the Internet line (see, for example, Patent Document 2).

  Further, such a search technique is not limited to video, and can deal with text, for example. Specifically, in addition to the subtitle text included in the video content, metadata such as the broadcast start time, broadcast end time, performer, and summary of the contents of the corner for each broadcast program corner are displayed after the broadcast program ends. Metadata provided by a service provider of a paid service to be distributed (also referred to as a program metadata service), text describing a video content input by a user operating a keyboard or the like can be adopted. (For example, refer to Patent Document 2).

JP 2010-262413 A JP 2012-038239 A

  However, these technologies, for example, target a single program or video content, and viewers and users have high importance or interest among all programs provided on TV as described above. Demand for timely and efficient acquisition of useful video content, and timely and effective acquisition of important or high interest video content from all the video content uploaded on the web It was not possible to meet the request to do so.

  In order to solve the above-described problems, an object of the present invention is to provide a video information providing system capable of quickly and appropriately supplying video content useful for a user from among a large number of distributed video contents. It is to provide.

  In order to achieve the above object, the video information providing system according to the present invention includes a component appearance frequency determining unit that determines the appearance frequency of the same component based on the component of the distributed video content, and the component occurrence Based on the determination by the frequency determination means, the video content extraction means for extracting the video content including the component when the appearance frequency is a predetermined value or more, and the video extracted by the video content extraction means are provided to the viewer Video content providing means.

  The distributed video content is analyzed by the component appearance frequency determining means, and the components included in the video content are analyzed and compared with the video content accumulated in the past to determine the appearance frequency of the same component. Is done. Here, the video content is mainly composed of moving images but also includes still images. In addition, audio and text as video components existing in the moving image are also determined.

  Then, when it is determined by the component appearance frequency determining means that the appearance frequency of the predetermined component has reached a predetermined value in a predetermined period, the video content including the component is accumulated by the video content extracting means. Extracted from a large number of video contents.

  Thereafter, the video content extracted by the video content providing means is provided to the viewer. The provision of the video content in this case includes not only provision by display of the video content but also recording and distribution of the video content and other output modes.

  In this case, AI (artificial intelligence) is used for the component appearance frequency determining means and the video content extracting means, and high-speed data processing is performed.

  According to a second aspect of the present invention, the component appearance frequency determining means determines the appearance frequency of the component based on a viewing request registered by a viewer.

  Therefore, the viewer who is the user of this system can register the video he / she wants to watch, the classification, type, genre, etc. of the video within an appropriate designated range, and the component appearance frequency judging means Based on the above, the appearance frequency of the component is determined.

  According to a third aspect of the present invention, the component is a character, audio, a video object, a character, or a background of the video object as a theme of the video content.

  In the case of a moving image, regarding how the component appearance frequency determining means recognizes and identifies a component in a specific video content, “text, audio, video object that is the subject of the video content, character Alternatively, it is performed from the viewpoint of “background of video object”.

  In this case, the “character” is a character such as a telop that appears in a moving image, which is performed based on a so-called character recognition technique and uses a morphological analysis technique.

  “Speech” is a variety of sounds and human voices included in moving images and the like, and includes background sounds, theme songs, spoken voices of characters, sound effects, and the like. When necessary, only the spoken voice of a specific character related to the topic that is the theme of the video is extracted from the various voices, and the appearance frequency is determined by the component appearance frequency determination means.

  In this case, when only the spoken voice of the person who is the subject of the specific video is specified, it is possible to extract only the voice of the person by specifying the frequency band of the voice of the person.

  In addition, the “video object as a theme” is an object as the theme of the video, and the “character” includes a person who appears as a leading role or a supporting character in relation to the video theme. . In this case, face authentication technology or the like is used for specifying the characters. In addition, the “background of the video object” refers to what is reflected as the background of the character or the object that is the subject of the video, such as a building, the sea, a mountain, the sky, a plain, or the like.

According to a fourth aspect of the present invention, the component appearance frequency determining means determines the frequency of appearance of the component with reference to a title portion displayed by characters in the video screen.
That is, in the case of a news video distributed from a TV broadcasting station, a title part made up of text may be displayed in the upper right of the video displayed on the screen. The image recognition, the voice recognition, the person recognition, the background recognition, etc. are performed with reference to the above, and the appearance frequency of the component requirement is determined.
The invention according to claim 5 is characterized in that the video content is distributed from a server via a telecommunication line.

Accordingly, in the invention according to claim 5, the component appearance frequency determining means determines the application frequency of the same component for video content including a moving image distributed via the web. Here, “video distributed via the web” refers to various videos uploaded to the web, videos on SNS (social network service), videos distributed via the Internet (for example, NETFLIX (registered trademark), including Amazon FIRE TV).
Further, in the following description, “web” is not limited to the case of a web system browsed by a browser, but includes the case of a cloud system. Accordingly, the video content includes a case where the video content exists in either the web server or the cloud server.

  The invention described in claim 6 is characterized in that the video content is distributed from a broadcasting station via a telecommunication line.

  Accordingly, in the invention described in claim 6, the component appearance frequency determining means determines the application frequency of the same component for all video contents displayed as TV images.

  According to a seventh aspect of the present invention, there is provided the video information providing system according to the seventh aspect of the present invention, wherein the video information providing system creates a summary by converting the audio data or video data in the video contents extracted from the video signals for the video contents into texts And weighting specialized for one or more predetermined conditions included in the summary with respect to the plurality of video contents while learning an optimum condition based on the accumulation result of the summary created by the summary creation means. Weighting assigning means for assigning, and the component appearance frequency determining means determines the appearance frequency of the component based on the summary.

  According to the seventh aspect of the present invention, the component appearance frequency determining means determines the appearance frequency of the video content, that is, the importance level based on the summary of the video content.

  In other words, the summarizing means determines the appearance frequency of the component based on the text data summary of the audio data or video data in the plurality of video contents extracted from the video signals of the plurality of video contents.

  In this case, the summary created by the summary creation means is targeted for a plurality of video contents by assigning a weight specific to at least one predetermined condition for the plurality of video contents by the weight assignment means. Provide more useful information with high importance and interest to users.

  The invention according to claim 8 is the video information providing system according to claim 7, wherein the weight assigning means refers to audio data or video data included in the plurality of video contents, and overlaps text. When the reference result is equal to or greater than a predetermined value, it is determined that the text is an important text that meets the predetermined condition, and weighting is performed.

  For example, in news programs, webs, SNSs, and the like that are broadcast daily, information on topics, incidents, accidents, and the like that have a great social value is socially important and highly relevant. As a result, information regarding such social events often appears as a plurality of video contents in a plurality of media.

  Therefore, in a plurality of video contents, the overlapping text is determined as the same component by morphological analysis of the text, etc., and stepwise etc. depending on the appearance frequency, for example, the number of appearances, the appearance time, the appearance rate, etc. The importance is set appropriately.

  According to a ninth aspect of the present invention, in the video information providing system according to the eighth aspect, the weighting assigning means determines whether or not the text is an important text for a plurality of video contents within a preset period. Features.

  The period required for determining the social importance of information such as the topic, incident or accident as described above is determined within a predetermined period.

  According to a tenth aspect of the present invention, in the video information providing system according to the eighth or ninth aspect, when the weighting assigning unit determines that the new video content is the video content including the important text. Is characterized by starting recording of the video content.

  In news programs that are broadcast every day, large incidents and accidents have high social importance and interest. Therefore, if such incidents / accidents are recorded and stored in the large-capacity storage unit separately from, for example, the summary creation, they can be left as edited by the operator, recorded video, or the like.

  According to an eleventh aspect of the present invention, in the video information providing system according to the sixth aspect, the weight assigning means is specified from text included in at least one of the audio data or the video data of the plurality of video contents. A feature is that a CM conversion value is calculated from the appearance frequency of a person / thing.

  The specific condition described above can include a specific person, object, incident, or accident. Here, for example, by targeting a specific person (including a corporate name, various organizations, etc.) as a specific condition, the appearance frequency of a specific person from a plurality of video contents, for example, the number of appearances, the appearance time, Appearance rate, etc. can be determined.

  Then, based on the number of appearances, the appearance time, the appearance rate, etc., it is possible to calculate a CM-converted value that is a measure of how much personal value (for example, setting of the galley) there is in the media and information world. . In the case of a specific corporation name, analysis of the ratio of provision to the entire CM, the importance of various products sold by the corporation (such as strength and identification of new products), and the correlation with stock price fluctuations. It can also be used for (weighting) and the like.

  The invention according to claim 12 is characterized in that the weight assigning means targets a specific corporate name from text included in at least one of the audio data or the video data of the plurality of video contents. To do.

  Therefore, in the invention described in claim 12, since the specific corporate name is a component subject to the appearance frequency judgment, the video content in which the specific corporate name appears is extracted, and the viewer as the user To the legal entity.

  According to the first to twelfth aspects of the present invention, more useful information can be automatically provided from the video system side to the user for a plurality of video contents.

  In other words, the video content related to the distributed video or still image is the same by analyzing the elements included in the video content by the component appearance frequency determining means and comparing with the video content accumulated in the past. When the appearance frequency of a constituent element is determined and it is determined that the appearance frequency of a predetermined constituent element has reached a predetermined value in a predetermined period, a large number of video contents in which video content including the constituent element is accumulated by the video content extracting means Since the video content extracted from the video content and provided by the video content providing means is configured to be provided to the viewer, the viewer does not need to always watch the video content distributed to the TV or the web. It is important to watch only video content that appears on TV or the web more than the predetermined frequency provided News of the check, it is possible to grasp.

  As a result, since the video content with high appearance frequency is important information or is often trendy information at that time, the viewer always checks the video and web information of a plurality of TV channels. It is not necessary, and only video content consisting of important information provided by the system according to the present invention and trendy information at that time is time-efficient without being tied to a TV receiver, personal computer or smartphone. Can watch.

  Therefore, even in a busy environment of viewers, it is important for TV, PC, and smartphones to always check TV programs with TV receivers and check web information frequently with PCs and smartphones. There is an effect that information can be efficiently acquired.

  In the invention according to claim 2, the component appearance frequency determining means is configured to determine the appearance frequency of the component based on the viewing request registered by the viewer, and is a user of the system. The viewer can register the video he / she wants to watch, the classification, type, genre, etc. of the video within an appropriate designated range, and the component appearance frequency determination means determines the appearance frequency based on the request. Therefore, the genre and type of video content that the user wants can be registered in the system in advance, and video content that appears frequently within the range of the genre and type is automatically and efficiently It becomes possible to watch.

Also, for example, when a specific company that is a user wants to collectively manage information related to the company that appears on TV or the web, the company name, corporate identity, abbreviation of the company name, etc. are registered. By doing so, it is possible to automatically collect and view all TV video content related to the company or video information on the web, and use it for business management from various viewpoints.
In the invention described in claim 4, regarding the video information transmitted from the TV broadcasting station, for example, in the case of a news program, the title portion of the news is expressed by a short text at a position such as the upper right in the screen. It may be displayed. In such a case, when performing video recognition, voice recognition, person recognition, and background recognition for determining the appearance frequency of a component, it can also be performed with reference to the title part. In this way, when video recognition, voice recognition, person recognition, and background recognition are performed with reference to the title part, more accurate recognition can be performed, and more efficient determination of the appearance frequency of components can be performed. It becomes possible to do.

  In the invention which concerns on Claim 5, a component appearance frequency judgment means is the various animations currently uploaded on the web, all the animations on SNS (social network service), various animations distributed over the internet, etc. Since the appearance frequency is judged as the target, video content with high importance is extracted from all video content that is available on the world via the web, and comprehensive video content with high importance for the viewer who is the user is exhausted. It is possible to search and provide quickly and automatically.

  According to the sixth aspect of the present invention, since the component appearance frequency determining means determines the application frequency of the same component for all video contents displayed as TV images, all of the components appearing in the world via TV are included. It is possible to extract video content with high importance from the video content, and comprehensively search for video content with high importance for viewers who are users, and quickly and automatically provide them.

  In the inventions according to claims 7 to 12, since the component appearance frequency determining means is configured to determine the appearance frequency of the video content, that is, the importance, based on the summary of the video content. Compared to video content directly, various advanced technologies such as face recognition technology, voice recognition, form recognition technology, etc., to narrow down the subject of each video, more quickly and accurately determine the appearance frequency of the component. Can be done.

  In the invention described in claim 7, since information on social events often appears as a plurality of video contents in a plurality of media, the information is duplicated in a plurality of video contents by morphological analysis of text or the like. Since the text is determined as the same component, and the frequency of appearance, for example, the number of times of appearance, the time of appearance, the appearance rate, etc., it is configured to appropriately set the degree of importance, such as stepwise, The appearance frequency of the constituent elements, that is, the social importance level is accurately determined, and the moving image content having an appropriate importance level is provided to the user.

  According to the ninth aspect of the invention, since the period required for determining the social importance level is determined within a predetermined period, it is possible to quickly provide socially important video content to the user. It becomes possible.

  The invention described in claim 10 can be used for editing, recording video, etc. of an operator if socially important incidents / accidents are recorded and stored in a large-capacity storage unit, for example, separately from the summary creation It is possible to provide a video information providing system that can be left and can be reused for analysis or the like as appropriate for the collected video content important to the user.

  The invention according to claim 11 can provide a video information calculation system that can be used as an analysis index of various economic activities by using the CM conversion value calculated by the weighting means.

  In the invention described in claim 12, since the specific corporate name is a constituent element for which the appearance frequency is determined, the video content in which the specific corporate name appears is extracted and the viewer is the viewer Since the information is provided to the corporation, for example, it is possible to quickly, appropriately, and comprehensively collect information on the company's social evaluation, reputation, etc., and to promptly reflect it on the company's management.

It is a block diagram which shows the whole structure of 1st embodiment of the video information provision system which concerns on this invention. It is a block diagram which shows the whole structure of 2nd embodiment of the video information provision system which concerns on this invention. It is a block diagram which shows the whole structure of the summary production system which concerns on 2nd embodiment of the video information provision system which concerns on this invention. It is a block diagram which shows the speech text conversion part in 2nd embodiment of the video information provision system which concerns on this invention, (a) is a block diagram, (b) is a figure which shows the flow of a process. It is a block diagram which shows the telop text conversion part of the summary production system in 2nd embodiment of the video information provision system which concerns on this invention, (a) is a block diagram, (b) is a figure which shows the flow of a process. It is a block diagram which shows the background image text conversion part of the summary preparation system in 2nd embodiment of the video information provision system which concerns on this invention, (a) is a block diagram, (b) is a figure which shows the flow of a process. . The logo mark text conversion part of the summary preparation system in 2nd embodiment of the video information provision system which concerns on this invention is shown, (a) is a block diagram, (b) is a figure which shows the flow of a process. It is a block diagram which shows the text integration part of the summary preparation system in 2nd embodiment of the video information provision system which concerns on this invention. It is a block diagram which shows the summary preparation part of the summary preparation system in 2nd embodiment of the video information provision system which concerns on this invention. It is a flowchart which shows the operation | movement process of the summary preparation system in 2nd embodiment of the video information provision system which concerns on this invention. The application example of the video information provision system according to the present invention is shown, (A) is an explanatory diagram when it is determined that the desired condition is met by character recognition, (B) is adapted to the desired condition by voice recognition It is explanatory drawing at the time of determining with having carried out.

FIG. 1 is a block diagram showing a first embodiment for realizing a video information providing system 1 according to the present invention.
The video information providing system 1 according to the present embodiment has a configuration of distributed video content for the purpose of quickly and appropriately supplying video content useful for a user for a large number of distributed video content. Based on the element, the component appearance frequency determining means 5a for determining the appearance frequency of the same component, and the image including the component when the appearance frequency is a predetermined value or more based on the determination by the component element appearance frequency determining means 5a Video content extracting means 5b for extracting content and video content providing means 7 for providing the viewer with the video extracted by the video content extracting means 5b are provided.

  In the present embodiment, as shown in FIG. 1, the video information providing system 1 is used only by a playback device 9 such as a television, personal computer, smartphone, tablet terminal or the like having a single computer function. The receiving unit 2 includes a tuner that receives a video signal related to content from a television station (television broadcasting station) or a web video distribution server, and an operation unit (including a remote controller) provided in the playback device 9. 3, a storage unit 4 that stores applications for realizing various functions as the playback device 9, a control circuit unit 5 that processes various functions based on the applications stored in the storage unit 4, and video metadata A large capacity storage unit 6 and an output unit 7 including an audio output speaker and a video output monitor.

  The receiving unit 2 includes a receiving antenna for television broadcasting including satellite broadcasting and the like, a modem for a telecommunication line such as the Internet line, a tuner, and the like, and can receive all data related to video content.

  When the playback device 9 is a television receiver or the like (including a video deck or the like), the operation unit 3 is used by a user to view desired video content such as a main power source, a channel selection operation, a volume increase / decrease switch, and the like. This is for operation (including a remote control device). In addition, when the playback device 9 is a personal computer or the like, the operation unit 3 is used by a user to view desired video content such as a mouse, a keyboard, or a touch panel.

  The storage unit 4 stores, for example, various applications executed by the control circuit unit 5 in order for the playback device 9 to operate. In addition, the applications stored in the storage unit 4 include applications for functions for realizing the present embodiment.

  The control circuit unit 5 enables viewing of the received video content based on the application stored in the storage unit 4, and includes a component appearance frequency determination unit 5a and a video content extraction unit 5b.

  The large-capacity storage unit 6 stores video content data received by the receiving unit 2. Further, the large-capacity storage unit 6 can store the result of analyzing the video content by the control circuit unit 5.

  Specifically, video content distributed from a web server (cloud server) or a television broadcasting station and received by the receiving unit 2 is stored in the large-capacity storage unit 6.

  The constituent elements such as characters, sounds, video objects as the theme of the video content, characters, screen backgrounds, and the like included in the accumulated video content are displayed according to the application stored in the storage unit 4. The appearance frequency of each component is determined by the determination unit 5a.

  That is, the control circuit unit 5 greatly calculates the data that associates the calculation results with each component in order to sequentially calculate the appearance frequency of the target component, for example, the number of appearances, the appearance time, the appearance rate, and the like. It is stored in the capacity storage unit 16.

  The control circuit unit 5 includes a component appearance frequency determination unit 5 a and a video content extraction unit 5 b, and a display screen included in the output unit 7 constitutes a video content providing unit 7.

  The control circuit unit 5 determines whether or not the appearance frequency of each component calculated sequentially has reached a predetermined value or more, and if it is determined that the appearance frequency has reached a predetermined value or more, the component is included. Video content to be extracted is extracted and displayed on the display screen of the output unit 7 serving as content providing means.

  Note that the output unit 7 may be configured by, for example, a storage or a slot for storing the extracted video content on an external recording medium (not shown) (for example, an SD memory card or a USB memory stick).

  When recording the extracted video content data on such an external recording medium, for example, backup video data in which the resolution of the video data in the video content stored in the large-capacity storage unit 6 is lowered is generated and stored in the storage unit 4. The video data for backup may be recorded after being temporarily stored.

  In such a configuration, the distributed video content is the same when the constituent elements included in the video content are analyzed by the constituent element appearance frequency determination unit 5a and compared with the video contents accumulated in the past. The appearance frequency of the component is determined. Here, the video content mainly includes moving images, but also includes still images.

  When the appearance frequency of a predetermined component is determined to have reached a predetermined value in a predetermined period by the component appearance frequency determination unit 5a, a large number of video contents including the component are accumulated by the video content extraction unit 5b. Extracted from video content.

  Thereafter, the video content extracted by the video content providing means 7 is provided to the viewer. The provision of the video content in this case includes not only the display of the video content via an appropriate display but also the recording / distribution of the video content and other output modes.

  In this case, AI (artificial intelligence) is used for the component appearance frequency determination unit 5a and the video content extraction unit 5b, and high-speed data processing is performed.

  In other words, the video content related to the distributed video or still image is the same by analyzing the elements included in the video content by the component appearance frequency determination means 5a and comparing with the video content accumulated in the past. When the appearance frequency of the constituent element is determined and it is determined that the appearance frequency of the predetermined constituent element has reached a predetermined value in a predetermined period, a large number of video contents including the constituent element are accumulated by the video content extracting means 5b. Since the video content extracted from the video content and extracted by the video content providing means 7 is configured to be provided to the viewer, the viewer needs to always watch the video content distributed to the TV or the web. Video content that appears on TV and the web more frequently than the automatically provided frequency. .

  As a result, since the video content with high appearance frequency is important information or is often trendy information at that time, the viewer always checks the video and web information of a plurality of TV channels. It is not necessary, and only video content consisting of important information provided by the system according to the present invention and trendy information at that time is time-efficient without being tied to a TV receiver, personal computer or smartphone. Can watch.

  Therefore, even in a busy environment of viewers, it is important to check on TV, personal computer and smartphone without constantly checking TV program with TV receiver and checking web information frequently with personal computer and smartphone. There is an effect that information can be efficiently acquired.

  In the present embodiment, the control circuit unit 5 includes the desired video registration means 5C. Therefore, the viewer who is the user of this system registers the video that the user desires to view, the classification, type, and genre of the video by the desired video registration means 5C via the operation unit 3 within an appropriate designated range. The component appearance frequency determining means 5a determines the appearance frequency of the component based on the registered desired video.

In the present embodiment, with regard to how the component appearance frequency determining means 5a recognizes and specifies a specific video content with respect to a moving image, “text object, audio, video object as a video content theme, This is performed from the viewpoint of the “character or background of the video object”.

Therefore, in the present embodiment, the constituent elements for which the appearance frequency is determined are the background of the video object, the character, or the video object that is the theme of characters, audio, and video content.

  In this case, the “character” is a character such as a telop that appears in a moving image, which is performed based on a so-called character recognition technique and uses a morphological analysis technique.

  The “sound” is a variety of sounds included in a moving image or the like, and includes background sounds, theme songs, characters' speaking voices, sound effects, and the like.

  If necessary, the appearance frequency is determined by the component appearance frequency determination means 5a by extracting only the spoken voice of a specific character related to the topic that is the theme of the video from the various sounds.

  In this case, when only the spoken voice of the person who is the subject of the specific video is specified, it is possible to extract only the voice of the person by specifying the frequency band of the voice of the person.

  In addition, the “video object as a theme” is an object as the theme of the video, and the “character” includes a person who appears as a leading role or a supporting character in relation to the video theme. . In this case, face authentication technology or the like is used for specifying the characters. Further, the “background of the video object” refers to what is reflected as the background of the character or the object that is the subject of the video, for example, a building, the sea, a mountain, the sky, a plain, or the like.

  Thereby, the component appearance frequency determining means 5a is configured to determine the appearance frequency of the component based on the viewing request registered by the viewer, and the viewer who is the user of this system desires to view it. Video, video classification, type, genre, etc. can be registered within the appropriate designated range, and the component appearance frequency determination means can determine the appearance frequency based on the request, so the user wants The genre, type, and the like of the video content to be registered are appropriately registered in the system, and the video content having a high appearance frequency within the range of the genre and type can be automatically and efficiently viewed.

  Also, for example, if a specific company that is a user wants to collectively manage information related to the company appearing on TV or the web, register the company name, corporate identity, abbreviation of the company name, etc. By doing so, it is possible to automatically collect and view all TV video content related to the company or video information on the web and use it for business management from various viewpoints.

  When the video content is distributed from a web server (or cloud server) via a telecommunication line, the component appearance frequency determination means is the same component for the video content including the distributed video. Determine the frequency of application. Here, “video distributed via the web” refers to all types of videos uploaded to the web, videos on SNS (social network service), videos on services that provide videos over the Internet, etc. It can be.

  Thus, the component appearance frequency determining means determines the appearance frequency for various videos uploaded to the web, all videos on SNS (social network service), and videos distributed through the Internet. It is possible to extract video content with high importance from all video contents that are available on the world via the web, and to provide comprehensive and automatic video content with high importance or interest to the viewer who is the user It becomes.

  In addition, when the video content is distributed from a broadcasting station via a telecommunication line, the component appearance frequency determining unit 5a has the same configuration for all video content displayed as TV video. Determine the filing frequency of the element.

  Therefore, the component appearance frequency determining means 5a determines the application frequency of the same component for all video contents displayed as TV images, and therefore important from all the video contents that are available on the world via TV. It is possible to extract video content with a high degree of interest or a high degree of interest, and to comprehensively and automatically provide video content with a high degree of importance or a high degree of interest to viewers who are users.

The control circuit unit 5 can also determine the appearance frequency of the component under various weighting conditions described later.
In the present embodiment, regarding video information transmitted from a TV broadcast station,
For example, in the case of a news program, the title part of the news may be displayed as a short text at a position such as the upper right in the screen. In such a case, when performing video recognition, voice recognition, person recognition, and background recognition for determining the appearance frequency of a component, it can also be performed with reference to the title part.
In this way, when video recognition, voice recognition, person recognition, and background recognition are performed with reference to the title part, more accurate recognition can be performed, and more efficient determination of the appearance frequency of components can be performed. It becomes possible to do.

Next, a description will be given of a second embodiment configured to create a summary based on video content and determine the appearance frequency of the component using the summary.
FIG. 2 is a block diagram showing the overall configuration of the video information providing system 11 for realizing the video information providing system according to the embodiment of the present invention. The basic configuration of the system as a whole is the same as that of the first embodiment, but the present embodiment is different in that the summary creation system 10 is provided.

That is, the video information providing system according to the second embodiment is based on the configuration of the video information providing system 1 according to the first embodiment, and further includes a plurality of video signals extracted from each video signal for a plurality of video contents. Summarizing means 10 for creating a summary by converting audio data or video data in the video content into text, and learning the optimum conditions based on the accumulation result of the summaries created by the summary creating means 10, and for a plurality of video contents Weighting means 15d for assigning weights specialized to one or more predetermined conditions included in the summary, and the component appearance frequency judging means 15a judges the appearance frequency of the component based on the summary. Is configured to do.
Further, in the present embodiment, the control circuit unit 15 includes the desired video registration unit 15c, and the user appropriately classifies videos and videos that the user desires to view via the operation unit 3. The desired video registration means 15C can register the type, genre, etc. in an appropriate designated range, and the component appearance frequency determination means 15a determines the appearance frequency of the component based on the registered desired video, and the video The video content is extracted by the content extraction unit 15b and displayed on a display or the like by the output unit 17 constituting the video content output unit, as in the first embodiment.

  In the present embodiment, the summary creation system 10 that constitutes the video information providing system 11 can be provided in the playback device 19, and the summary creation system 10 can also be configured by a dedicated management server or the like. The video output system portion that operates based on the summary created by the server may be realized by, for example, a television, personal computer, smartphone, tablet terminal, or the like (hereinafter referred to as “playback device 19”) having a computer function. Is possible. Note that the playback device 19 can be used not only by one unit but also by a plurality of units.

  In the following description, the case of airing on TV will be mainly described, and the case specific to video distribution on the web will be described as appropriate, and the use of video distribution on the web that is the same as or substantially the same as the form of use of airing on TV. The description of the form is omitted.

  Television broadcasting includes terrestrial digital broadcasting, satellite broadcasting, one-segment broadcasting, Internet broadcasting, and the like, and any broadcasting form or receiving form is acceptable.

  As shown in FIGS. 2 and 3, the video information providing system 11 includes a receiver 12 including a tuner that receives a video signal related to video content from a television station 30 or a video distribution server 40 on the web, and the playback device 9. An operation unit (including a remote controller) 13, a storage unit 14 that stores applications for realizing various functions as the playback device 19, and a control circuit unit that processes various functions based on the applications stored in the storage unit 14 15, the above-described summary creation system 10, a large-capacity storage unit 16 for storing various data for recording the created summary and video content, and an output unit 17 including a speaker for audio output and a monitor for video output. And has.

  The summary creation system 10 includes a video signal separation unit 20, a video signal processing unit 18, a text integration unit 500, and a summary creation unit 600. As shown in FIG. The image forming unit 100, the telop text converting unit 200, the background image text converting unit 300, and the logo mark text converting unit 400 are configured.

As illustrated in FIG. 2, the playback device 19 includes a reception unit 12, an operation unit 13, a storage unit 14, a control circuit unit 15, a summary processing system 11, a large capacity storage unit 16, and an output unit 17.
Further, the output unit 17 constitutes video content providing means having a function of outputting a result of assignment based on weighting calculated by the control circuit unit 15 serving as weighting means, for example, to monitor output or printer output.
The control circuit unit 15 is the same as that in the first embodiment in that it includes a component requirement frequency determination unit 15a, a video content extraction unit 15b, and a desired video registration unit 15C. In addition, weighting means 15d is further provided.

<Creation of summary (video metadata)>
Here, as an example of producing video metadata as a summary, a case will be described in which a television broadcast content is processed into a Japanese database. In this case, the video content is exemplified for one program or corner.

  In TV programs, especially “news” and “broadcast programs” that are broadcast every moment, “immediateness” and “accuracy” are important.

  On the other hand, in such news / broadcast programs in television broadcasting, some news content may be broadcast on other news programs with different time zones (regardless of differences in broadcasting stations). However, it can be said that the same program is not rebroadcast on different days of the week and disappears.

  Such “immediate” and “accurate” information has continuity depending on the news content, social importance and needs, or new information becomes clear. In some cases, for example, it is desirable that the news is weighted according to the degree of importance / needs such that the appearance frequency reaches a predetermined value. For example, the number of appearances, the appearance time, the appearance rate, and the like can be applied to the appearance frequency.

  Here, the importance / needs level has short-term, long-term, and seasonal factors. For example, graphs weighted by weekly, monthly, seasonal (seasonal), annual, and other statistics. It is also possible to create. At this time, the created graph can be output from the output unit 17 as a monitor or a printer.

  As a result, the importance and needs in the short term are high, but it is possible to suppress the importance and needs from becoming low throughout the year, and the importance and needs in the corresponding period are high. Weighting can be given.

  Specifically, it is possible to assign an effective weighting when the degree of importance / needs increases in a specific cycle such as “forecasting of cherry blossoms”, “famous place for cherry blossoms”, “olympic games”, and the like.

  Also, metadata for newly broadcast video information can be sequentially updated with a time lag of about 10 minutes, and can be updated to importance based on the latest information. At this time, it is also possible to simultaneously receive programs from a plurality of broadcasting stations and update them to the latest information.

  In addition to basic information such as broadcast stations and broadcast times, metadata includes text information such as news titles, content abstracts, commentator names and prominent logos, image authentication of background images, caster face authentication, Finer video metadata can be produced and distributed by voiceprint analysis.

  Furthermore, the result can be confirmed on the user side by web or mail. Therefore, if the video metadata is stored and accumulated on a large-capacity storage medium such as a hard disk on the user side, it can be used in various usage situations.

Specifically, from daily news broadcasts, it is possible to close up the behavior of a particular commentator, record the details completely, and verify the contents later.
In addition, if the specific commentator appears on the condition, it can be configured to always notify the user of the viewing, the news program that is currently broadcast, or recorded In a news program, when the commentator is commenting, it is also possible to make a notification that prompts the user to watch by increasing the volume in a spot manner.
When configured in this way, the user does not have to watch all TV program images, and only needs to watch it when notified, so that it is useful for the user while ensuring the user's time freedom. Information can be obtained.

If the user is busy and has no time to watch TV at all times, a condition corresponding to a predetermined video is set in the summary, and the video is displayed when the condition is met. It can also be configured to notify the user to the effect.
In this case, when contents that meet the notification conditions are included, notification to the viewer, who is the user of the video content being output, is performed in addition to increasing the volume as described above, and sounding a message, etc. This can be done for the user's hearing.
Further, in addition to notification to the user's hearing, notification to the user's vision, such as repetition of bright and dark inversion of the display image 7a shown in FIG. 11 and lighting / flashing of a dedicated lamp, may be used. Further, a combination of hearing and vision may be used. Furthermore, it can be used as a trigger signal for starting other operations (for example, recording) as well as mere notification.

Also, for example, in a news program, if the user wants to know only the result of sports news, and if the user has registered that fact by the desired video registration means 15C, the entire news program is not viewed. The component appearance frequency determining means 15 provided in the control circuit unit displays, for example, the case where the characters “sports” are displayed on the display screen 17a as a telop as shown in FIG. ), The user can be notified when the caster reads an announcement document including “sports”.

  In addition, as a mode of use of video metadata, characters in the video that flow during the program, for example, comment time and logical analysis of the above-mentioned specific commentator, politician introduced in the broadcast content (during the program) By creating a database of video metadata, such as broadcast times including (political parties) and athletes' video, etc., and clustering (a function that automatically classifies data without external standards) Weighting such as calculating a CM conversion value of an object is also possible.

  As described above using the summary creation process (AI process) that is a function of the summary creation system 10 that learns the optimum summary creation setting using the input data and output data of the past summary creation results accumulated as teaching materials. In addition to the AI processing, the CM conversion value is evaluated for each person by the manual input of the operator based on the audience rating or information not included in the video metadata such as newspapers and magazines. You may convert into a price (unit price per unit time).

  Furthermore, the weighted CM conversion value is generated as video metadata for a single broadcast station, a single program, a plurality of broadcast stations (for example, a key station in the Kanto area), and the weekly / monthly / seasonal ( (Quarterly) / half year / full year / unit. The collected data can be output from the output unit 7 as a monitor or a printer by a graph or a list (for example, for the top 100 people).

  In addition, text-formatted video metadata can be used as teletext broadcasting during simultaneous broadcasting. For example, TV news / broadcast programs, wide shows, discussion programs, political / economic programs, political / economic variety, etc. It is also possible to use the contents and the detailed information for each article as text information to be created by the operator for the information programs of the state-run broadcasting stations and private key stations that extend over 100 hours per day.

<Reproducing device 19>
The playback device 19 has a tuner function for television broadcasting (including terrestrial digital broadcasting, satellite broadcasting, and one-segment broadcasting) or a receiving function for receiving Internet distribution video as the receiving unit 2, as shown in FIG. In addition, since the video can be output to the display screen 17a of the output unit 7, a television, a personal computer, a smartphone, a tablet terminal, or the like can be used.

  The receiving unit 12 receives TV radio waves from TV stations or communication radio waves transmitted via the Internet. Further, when a summary is created outside the playback device 19, it may be configured to have a function of receiving summary information supplied via communication means. The summary received by the receiving unit 12 is stored or updated in the mass storage unit 16.

  The operation unit 13 can use various switches attached to the television, remote control devices attached to the television, mouse and keyboard for computers, various switches and touch panels attached to smartphones and tablet terminals, and the like.

  By the way, in the above-mentioned television broadcasting, when a certain incident occurs in news, a plurality of television broadcasting stations repeatedly broadcast the same scene. In such a case, it is often impossible to easily recognize the whole picture even if each TV media knows what and when it broadcasts.

  Therefore, if such an incident is set as a desired condition, the contents of all designated news broadcast programs can be converted into text data in seconds and then compiled into a database to create a summary.

  Then, the results of classifying (summarizing) the contents of the summary into the same theme are analyzed. For example, if a user or an operator of a contracted dedicated company processes it, what, when and how much broadcasting It is also possible to obtain information that has been made or quantified.

  And by setting such quantified information as a desired condition, it becomes possible to set a more recent and accurate condition in subsequent news broadcasts. For example, it is possible to make a selection such as partial viewing of a program by notification and viewing of the entire program regarding other news broadcasts.

  For this quantification, for example, weighting can be given in an output function such as automatically recording a video portion of an incident (for example, a video portion regarding the progress of accident processing at a nuclear power plant) in the large-capacity storage unit 16. .

  In addition, as described above, weighting is given in usage forms such as how much broadcasts related to such incidents and accidents are handled in television media, and which stations have handled which themes and how they have been handled in terms of time and frequency. It is also possible to do.

  Furthermore, in such a summary, the contents of various entertainment programs can be analyzed from various perspectives, not limited to news broadcasts.

  As a result, for example, based on a comprehensively constructed entertainment database, it is possible to analyze the contents of entertainment programs such as dramas, movies, and varieties, genre comparisons, time zone grasps, etc. .

  Furthermore, the performance time of the specific performer can be converted, and the performer value can be easily calculated from, for example, the appearance ratio in units of days, weeks, and months.

  In addition, the voice of the performer described above can be given a weight for converting a dialect into a standard word when performing morphological analysis for text conversion after voice recognition.

  The control circuit unit 15 receives the summary created by the summary creation system 10 as appropriate (or sequentially) and stores it in the large-capacity storage unit 16, and sets optimum conditions for weighting based on the storage result of the summary. While learning, a plurality of video contents can be given a weight specific to one or more predetermined conditions included in the summary.

  As described above, the video information providing system 11 assigns a weight specialized to at least one predetermined condition for a plurality of video contents to the summary created by the summary creation means. Thus, it is possible to supply useful information to a user for a plurality of video contents.

  Also, in a plurality of video contents, the importance (eg, stepwise) can be set appropriately according to the appearance frequency. In news programs and the like that are broadcast daily, large incidents and accidents can be said to have high social importance (or interest). Therefore, the target condition can be automatically set to a predetermined condition by targeting a relatively short period of importance of such an incident or accident.

  Further, for example, if such incidents / accidents are recorded and stored in the large-capacity storage unit 6 separately from the summary creation, they can be left as edited by the operator, recorded video, or the like.

  The specific conditions described above can include specific people, things, incidents, and accidents. Here, for example, by targeting a specific person, company, various organizations, etc. in a specific condition, the appearance frequency of a specific person, company, group from a plurality of video contents, for example, the number of appearances, the appearance time, Appearance rate, etc. can be determined.

  Based on the appearance frequency, it is possible to calculate a CM-converted value that is a measure of how much person value (for example, the setting of the galley) is present.

In the case of a specific corporation name, analysis of the ratio of provision to the entire CM, prorated amount of various products sold by the corporation (determination of strength and identification of new products), and correlation with stock price fluctuations. It can also be used for (weighting) and the like.

  Appearance frequencies can be tabulated by day, week, month, year, and can also be tabulated separately for each TV broadcast station and time zone.

  In addition, the appearance frequency can include, for example, a case where the number of appearances is set to be 1 for each program in a specific program and a case where the number of appearances in the program is targeted.

  Here, the number of appearances in the program may include the case where the number of appearances and the appearance time are targeted, and the case where, for example, the number of times the name is called by a moderator or the like is targeted. it can.

In addition, in the case of a full name such as “○ × △ □”, only a name such as “○ × Ms.”, A name or name such as “△ □ -chan” or “△ -chan”, etc. It can be a condition.

  Further, if the performer belongs to a group, the case of calling by group name and the case of calling by name can be included (as weights). Similarly, for example, even if a junior player is called “XX II” due to having a good performance in the past in the field of sports, etc., both the former and the latter are used as weighting conditions. be able to.

  For example, in the case of an appeal by Mr. “X”, there are few cases where the same program includes the same person, but there is a high possibility that a plurality of people exist in the entire industry. Therefore, in such a case, only people who appear in the program can be included as weighting conditions except for those who do not appear in the program.

  On the other hand, for example, if you are a person who has not appeared in the program, but the name or video of another person belonging to the group to which the performer belongs appears, that person will appear. It can also be treated as being.

  Thus, in the present embodiment, summary creation means 600 for creating a summary by converting audio data or video data in a plurality of video contents extracted from each video signal for a plurality of video contents into text, and summary creation means Weighting assigning means 15d for assigning weights specific to one or more predetermined conditions included in the summary to a plurality of video contents while learning optimum conditions based on the accumulation result of the summary created in 600; The component appearance frequency determining means 15a is configured to determine the appearance frequency of the component based on the summary.

  The component appearance frequency determination means 15a determines the appearance frequency of the video content, that is, the importance level based on the summary of the video content.

  That is, the summarizing means 600 determines the appearance frequency of the constituent elements of the video content based on the audio data or the video data in the plurality of video contents extracted from the respective video signals for the plurality of video contents as text. The

  In this case, the summary created by the summary creation means 600 is assigned a plurality of video contents by assigning weights specific to at least one or more predetermined conditions to the plurality of video contents by the weight assigning means 15d. More useful information with high importance or interest is supplied to the user as a target.

  Therefore, in the video information system 11 according to the second embodiment, the component appearance frequency determination means 15a is configured to determine the appearance frequency of video content, that is, the degree of importance based on the summary of the video content. Therefore, compared to the case of narrowing down the subject of each video directly from video content, various advanced technologies such as face recognition technology, voice recognition, form recognition technology, etc. It is possible to determine the appearance frequency.

  Also, the weighting unit 15d refers to duplicate text from audio data or video data included in a plurality of video contents, and if the reference result is equal to or greater than a predetermined value, the text matches the predetermined condition. It is determined that the text is important, and weighting is given.

  For example, in news programs, webs, SNSs, and the like that are broadcast daily, it can be said that topics such as topics, incidents, accidents, and the like that have a great social value are of high social importance and interest. As a result, information regarding such social events often appears as a plurality of video contents in a plurality of media.

  Therefore, in a plurality of video contents, the overlapping text is determined as the same component by morphological analysis of the text, etc., and stepwise etc. depending on the appearance frequency, for example, the number of appearances, the appearance time, the appearance rate, etc. The importance is set appropriately.

  In this way, information related to social events often appears as multiple video contents in multiple media. Therefore, in multiple video contents, duplicate text is determined as the same component by morphological analysis of the text. In addition, since it is configured to appropriately set the importance, such as stepwise, according to its appearance frequency, for example, the number of appearances, the appearance time, the appearance rate, etc., the appearance frequency of the component accurately, That is, the social importance level is determined, and appropriate video content is provided to the user.

  The weight assigning unit 15d determines whether or not the text is an important text for a plurality of video contents within a preset period.

  A period required for determining the social importance of information such as a topic, an incident or an accident is determined within a predetermined period. Therefore, since the period required for determining the social importance level is determined within a predetermined period, it is possible to quickly provide socially important video content to the user.

  In this way, if socially important incidents / accidents, etc., are recorded and stored in a large-capacity storage unit, for example, separately from the summary creation, they are left as edited by the operator, recorded video, etc. Therefore, it is possible to provide a video information providing system that can appropriately reuse collected video content important for the user for analysis or the like.

  Further, when it is determined that the new video content is the video content including the important text, the weight assigning unit 15d starts recording the video content.

  In news programs that are broadcast every day, large incidents and accidents have high social importance and interest. Therefore, if such incidents / accidents are recorded and stored in the large-capacity storage unit separately from, for example, the summary creation, they can be left as edited by the operator, recorded video, or the like.

  Further, the weighting unit 15d calculates a CM conversion value from the appearance frequency of a specific person / thing from text included in at least one of audio data or video data of a plurality of video contents.

  The specific condition described above can include a specific person, object, incident, or accident. Here, for example, by targeting a specific person (including a corporate name, various organizations, etc.) as a specific condition, the appearance frequency of a specific person from a plurality of video contents, for example, the number of appearances, the appearance time, Appearance rate, etc. can be determined.

  Then, based on the number of appearances, the appearance time, the appearance rate, etc., it is possible to calculate a CM-converted value that is a measure of how much personal value (for example, setting of the galley) there is in the media and information world. . In the case of a specific corporation name, analysis of the ratio of provision to the entire CM, prorated amount of various products sold by the corporation (determination of strength and identification of new products), and correlation with stock price fluctuations. It can also be used.

  Accordingly, it is possible to provide a video information calculation system that can be used as an analysis index for various economic activities by using the CM conversion value calculated by the weighting unit 15d.

  Further, the weighting unit 15d targets a specific corporate name from text included in at least one of audio data or video data of a plurality of video contents.

  Therefore, since a specific corporate name is a constituent element for which the appearance frequency is determined, video content in which the specific corporate name appears is extracted and provided to the corporate entity that is a viewer as a user.

  Therefore, since a specific corporate name is a component subject to appearance frequency determination, video content in which a specific corporate name appears is extracted and provided to the legal entity that is a viewer as a user. For example, information on the company's social evaluation, reputation, etc. can be collected quickly, appropriately and comprehensively, and can be promptly reflected in the company's management.

Hereinafter, the summary creation system 10 according to the second embodiment will be described.
<Overall Configuration of Summary Generation System 10>
As shown in FIG. 3, the summary creation system 10 includes a video signal separation unit 20, an utterance text conversion unit 100, a telop text conversion unit 200, a background image text conversion unit 300, a logo mark text conversion unit 400, a text integration unit 500, And a summary creation unit 600. In the present embodiment, the summary generation system 10 acquires a video signal from a television broadcast from the television station 30. The video signal can be acquired from video on the Internet.

  The video signal V including the audio signal and the video signal is separated into the audio signal A and the video signal B by the video signal separation unit 20. The audio signal A is input to the utterance text unit 100, and the video signal B is input to the telop text unit 200, the background image text unit 300, and the logo mark text unit 400.

<Speech text unit 100>
As shown in FIG. 4, the utterance text unit 100 receives the audio signal A and outputs an utterance text that is a text describing a person's utterance content in the video content. The utterance text conversion unit 100 includes an utterance information extraction unit 110, an utterance content recognition unit 120, and an utterance content text conversion unit 130.

  The utterance information extraction unit 110 extracts utterance information from the audio signal A of the video signal V. That is, the noise in the voice signal A is removed, and the information of the human speech voice is extracted. The utterance information can include sound effects and characteristic music.

  The utterance content recognition unit 120 recognizes the utterance content from the utterance information. That is, utterance information is acoustically and grammatically analyzed to recognize the utterance content as a language. Parameters, conditions, and the like used for this recognition can be generated by machine learning from the past speech text generation data accumulated as described later.

  The utterance content text conversion unit 130 converts the utterance content into text and outputs it. The parameters, conditions, and the like used for this recognition can be generated by machine learning from past speech text input data and generation data accumulated as described later.

<Telop text converter 200>
As shown in FIG. 5, the telop text conversion unit 200 receives the video signal B and outputs telop text that is text describing the telop content in the video content. The telop text conversion unit 200 includes a telop information extraction unit 210, a telop content recognition unit 220, and a telop content text conversion unit 230.

  The telop information extraction unit 210 extracts telop information from the video signal B of the video signal V. That is, the background in the video signal B is removed, and only the telop image information is extracted.

  The utterance content recognition unit 120 recognizes the telop content from the telop image information. That is, the telop information is analyzed linguistically and grammatically to recognize the telop display content as a language. Parameters, conditions, and the like used for this recognition can be generated by machine learning from the past telop text input data and generation data accumulated as described later.

  The telop content text conversion unit 230 converts the telop content into text and outputs it. Parameters, conditions, and the like used for this recognition can be generated by machine learning from the past telop text input data and generation data accumulated as described later.

<Background image text unit 300>
As shown in FIG. 6, the background image text converting unit 300 receives the video signal B and outputs a background image text that is a text describing the background image content in the video content. Examples of the background image include a person, a person's belongings, a person's facial expression, a landscape, a building situation, an indoor situation, an animal, a vehicle, and other articles. The background image text conversion unit 300 includes a background image information extraction unit 310, a background image content recognition unit 320, and a background image content text conversion unit 330.

  The background image information extraction unit 310 extracts background image information from the video signal B of the video signal V. That is, the telop and unclear image in the video signal B are removed, and only the recognizable background image information is extracted.

  The background image content recognition unit 320 recognizes the content of the background image from the background image information. That is, a person, a personal belonging, a human facial expression, a landscape, a building situation, an indoor situation, an animal, a vehicle, and other articles represented by analyzing background image information are recognized. Parameters, conditions, and the like used for this recognition can be generated by machine learning from input data and generation data of past background image text accumulated as will be described later.

  The background image content text unit 330 converts the background image content into text and outputs it. Parameters, conditions, and the like used for this recognition can be generated by machine learning from input data and generation data of past background image text accumulated as will be described later.

<Logo Mark Textification Unit 400>
As shown in FIG. 7, the logo mark text converting unit 400 receives the video signal B and outputs a logo mark text which is a text describing the logo mark content in the video content. Examples of the logo include a trademark indicating the origin of the product and other marks.

  The logo mark text conversion unit 400 includes a logo mark image information extraction unit 410, a logo mark content recognition unit 420, and a logo mark content text conversion unit 430.

  The logo mark image information extraction unit 410 extracts logo mark image information from the video signal B of the video signal V. That is, the telop and the background image in the video signal B are removed, and only the recognizable logo mark image information is extracted.

  The logo mark content recognition unit 420 recognizes the content of the logo mark from the logo mark image information. That is, it recognizes products, services, stores, facilities, etc. represented by analyzing logo mark image information. Parameters, conditions, and the like used for this recognition can be generated by machine learning from the past logo mark text input data and generation data accumulated as described later.

  The logo mark content text conversion unit 430 converts the logo mark image content into text and outputs it. Parameters, conditions, and the like used for this recognition can be generated by machine learning from the past logo mark text input data and generation data accumulated as described later.

<Text integration unit 500>
As shown in FIG. 8, the text integration unit 500 includes the utterance text from the utterance text conversion unit 100, the telop text from the telop text conversion unit 200, the background text from the background image text conversion unit 300, and the logo mark text conversion unit 400. Integrate background text from That is, inconsistencies and errors in each text are corrected, and an integrated text is generated. Parameters, conditions, and the like used for text integration can be generated by machine learning from past text integration input and output data accumulated as described later.

<Summary creation unit 600>
As shown in FIG. 9, the summary creation unit 600 summarizes the integrated text from the text integration unit 500. That is, the number of characters specified by summarizing the contents of the summary text is used. Parameters, conditions, and the like used for this summarization can be generated by machine learning from input data and output data of combination processing such as the past accumulated as will be described later.

Next, machine learning processing of each unit will be described.
<Machine learning process of speech text unit 100>
FIG. 3 is a block diagram showing an utterance text conversion unit of the summary creation system. The utterance text conversion unit 100 includes an utterance information extraction unit 110, an utterance content recognition unit 120, an utterance content text conversion unit 130, a machine learning unit 140, a content recognition text creation setting unit 150, and a comparative evaluation unit 160. Further, an existing data storage unit 700 is connected to the speech text unit 100.

  The utterance text conversion unit 100 performs machine learning based on the existing video data stored in the existing data storage unit 700 and the existing utterance text, and optimizes the utterance content recognition unit 120 and the utterance content text conversion unit 130. The existing data storage unit 700 stores an existing video data storage unit 710 that stores a lot of video data that was used when a person created utterance texts in the past, and an utterance text created from the utterance contents of the video data. An existing utterance text storage unit 720 is provided. These video data and utterance texts are used as machine learning materials.

  Further, the utterance text conversion unit 100 includes switching units 170 and 180 that perform data output switching when machine learning is performed and when an utterance content text is created from new video data.

  The content recognition text creation setting unit 150 stores the settings of the speech content recognition processing of the speech content recognition unit 120 and the settings of the text conversion processing of the speech content text conversion unit 130. The utterance content recognition unit 120 and the utterance content text conversion unit 130 recognize the utterance content and convert it into text according to the conditions and parameters set by the content recognition text creation setting unit 150.

  The comparative evaluation unit 160 includes a comparison unit 161 and an evaluation unit 162. The comparison unit 161 receives the existing video data from the existing video data storage unit 710 and compares the utterance text created by the utterance content text conversion unit 130 with the existing utterance text from the existing utterance text storage unit 720. The evaluation unit 162 performs an evaluation based on the comparison result of the comparison unit 161, and gives a high score when the values match well.

  The machine learning unit 140 receives the evaluation from the evaluation unit 162 and changes the setting state of the content recognition text creation setting unit 150. This process is repeated for the same video data to make the evaluation value of the evaluation unit 162 as high as possible. This process can be repeated for a plurality of video data.

  By performing such machine learning, the abilities of the utterance content recognition unit 120 and the utterance content text conversion unit 130 are improved. After the predetermined machine learning is completed, the utterance text converting unit 100 processes the new video data and is in a state where the optimum utterance text can be output.

<Machine learning of telop text unit 200>
FIG. 4 is a block diagram showing a telop text conversion unit of the summary creation system. The telop text conversion unit 200 includes a telop information extraction unit 210, a telop content recognition unit 220, a telop content text conversion unit 230, a machine learning unit 240, a content recognition text creation setting unit 250, and a comparative evaluation unit 260. An existing data storage unit 700 is connected to the telop text conversion unit 200.

  The telop text conversion unit 200 performs machine learning based on the existing video data stored in the existing data storage unit 700 and the existing telop text, and optimizes the telop content recognition unit 220 and the telop content text conversion unit 230. The existing data storage unit 700 stores an existing video data storage unit 710 that stores a large number of video data used when a telop text was created by a person in the past, and a telop text created from the utterance content of the video data. An existing telop text storage unit 730 is provided. These video data and utterance texts are used as machine learning materials.

  The telop text conversion unit 200 includes switching units 270 and 280 that perform data output switching when machine learning is performed and when an utterance content text is created from new video data.

  The content recognition text creation setting unit 250 stores the text content recognition processing setting of the telop content recognition unit 220 and the text conversion processing setting of the telop content text conversion unit 230. The telop content recognition unit 220 and the telop content text conversion unit 230 perform content recognition and text conversion of the telop according to the conditions and parameters set by the content recognition text creation setting unit 250.

  The comparative evaluation unit 260 includes a comparison unit 261 and an evaluation unit 262. The comparison unit 261 receives the existing video data from the existing video data storage unit 710 and compares the telop text created by the telop content text unit 230 with the existing telop text from the existing telop text storage unit 730. The evaluation unit 262 performs an evaluation based on the comparison result of the comparison unit 261, and gives a high score when the values match well.

  The machine learning unit 240 receives the evaluation from the evaluation unit 262 and changes the setting state of the content recognition text creation setting unit 250. This process is repeated for the same video data to make the evaluation value of the evaluation unit 262 as high as possible. This process can be repeated for a plurality of video data.

  By performing such machine learning, the capabilities of the telop content recognition unit 220 and the telop content text conversion unit 230 are improved. After completing the predetermined machine learning, the telop text conversion unit 200 processes the new video data and is in a state where it can output the optimum telop text.

<Machine learning of background image text unit 300>
FIG. 6 is a block diagram showing a background image text conversion unit of the summary creation system. In addition to the background image information extraction unit 310, the background image content recognition unit 320, and the background image content text conversion unit 330, the background image text conversion unit 300 includes a machine learning unit 340, a content recognition text creation setting unit 350, and a comparative evaluation unit 360. Prepare. An existing data storage unit 700 is connected to the background image text unit 300.

  The background image text conversion unit 300 performs machine learning based on the existing video data stored in the existing data storage unit 700 and the existing background image text, and optimizes the background image content recognition unit 320 and the background image content text conversion unit 330. To do. The existing data storage unit 700 stores an existing video data storage unit 710 that stores a large number of video data used when a person created telop text in the past, and a background image text created from the utterance content of the video data. The existing background image text storage unit 740 is provided. These video data and background image text serve as machine learning materials.

  The background image text converting unit 300 includes switching units 370 and 380 that perform data output switching when machine learning is performed and when an utterance content text is created from new video data.

  The content recognition text creation setting unit 350 stores the settings for the background image content recognition processing of the background image content recognition unit 320 and the settings for the text conversion processing of the background image content text conversion unit 330. The background image content recognition unit 320 and the background image content text conversion unit 330 perform content recognition and text conversion of the background image according to the conditions and parameters set by the content recognition text creation setting unit 350.

  The comparative evaluation unit 360 includes a comparison unit 361 and an evaluation unit 362. The comparison unit 361 compares the background image text generated by the background image content text unit 330 upon receiving the existing video data from the existing video data storage unit 710 and the existing background image text from the existing background image text storage unit 740. To do. The evaluation unit 362 performs an evaluation based on the comparison result of the comparison unit 361, and gives a high score when the values match well.

  The machine learning unit 340 receives the evaluation from the evaluation unit 362 and changes the setting state of the content recognition text creation setting unit 350. This process is repeated for the same video data to make the evaluation value of the evaluation unit 362 as high as possible. This process can be repeated for a plurality of video data.

  By performing such machine learning, the capabilities of the background image content recognition unit 320 and the background image content text conversion unit 330 are improved. After the predetermined machine learning is completed, the background image text converting unit 300 processes the new video data and can output an optimum background image text.

<Machine learning of logo mark text unit 400>
FIG. 7 is a block diagram showing a logo mark text conversion unit of the summary creation system. In addition to the logo mark image information extraction unit 410, the logo mark content recognition unit 420, and the logo mark content text conversion unit 430, the logo mark text conversion unit 400 includes a machine learning unit 440, a content recognition text creation setting unit 450, and a comparative evaluation unit 460. Is provided. Further, an existing data storage unit 700 is connected to the logo mark text unit 400.

  The logo mark text conversion unit 400 performs machine learning based on the existing video data stored in the existing data storage unit 700 and the existing logo mark text, and the logo mark content recognition unit 420 and the logo mark content text conversion unit 430 are optimal. Turn into. In the existing data storage unit 700, an existing video data storage unit 710 storing a large number of video data used when a person has created logo mark text in the past, and a logo mark text created from the utterance content of the video data are stored. The stored existing logo mark text storage unit 750 is provided. These video data and logo mark text are used as machine learning materials.

  In addition, the logo mark text converting unit 400 includes switching units 470 and 480 that switch data output when machine learning is performed and when an utterance content text is created from new video data.

  The content recognition text creation setting unit 450 stores the settings of the logo mark image content recognition processing of the logo mark content recognition unit 420 and the settings of the text conversion processing of the logo mark content text conversion unit 430. The logo mark content recognition unit 420 and the logo mark content text conversion unit 430 perform content recognition and text conversion of the logo mark according to the conditions and parameters set by the content recognition text creation setting unit 450.

  The comparative evaluation unit 460 includes a comparison unit 461 and an evaluation unit 462. The comparison unit 461 receives the existing video data from the existing video data storage unit 710 and compares the text created by the logo mark content text conversion unit 430 with the existing background image text from the existing logo mark text storage unit 750. The evaluation unit 462 performs an evaluation based on the comparison result of the comparison unit 461, and gives a high score when the values match well.

  The machine learning unit 440 receives the evaluation from the evaluation unit 462 and changes the setting state of the content recognition text creation setting unit 450. This process is repeated for the same video data to make the evaluation value of the evaluation unit 462 as high as possible. This process can be repeated for a plurality of video data.

  By performing such machine learning, the ability of the logo mark content recognition unit 420 and the logo mark content text conversion unit 430 is improved. After the predetermined machine learning is completed, the logo mark text conversion unit 400 processes the new video data and is in a state where it can output the optimum background image text.

<Machine learning of text integration unit 500>
FIG. 8 is a block diagram showing a text integration unit of the summary creation system. The text integration unit 500 includes an integrated text creation unit 510, an integrated text creation setting unit 520, a machine learning unit 530, and a comparative evaluation unit 540. An existing data storage unit 700 is connected to the text integration unit 500.

  The text integration unit 500 performs machine learning based on various existing types stored in the existing data storage unit 700, that is, speech text, telop text, background text, logo mark text, and existing integrated text, and an integrated text creation unit 510. Optimize the operation. The existing data storage unit 700 stores an existing various text storage unit 760 that stores various text data used when an integrated text was created in the past, and an existing integrated text storage unit 770 that stores an integrated text created from the various texts. With. These various texts and integrated texts serve as machine learning materials.

  In addition, the text integration unit 500 includes switching units 570 and 580 that perform data output switching when performing machine learning and when creating a new integrated text from various new texts.

  The integrated text creation setting unit 520 stores text integration processing settings of the integrated text creation unit 510. The integrated text creation unit 510 performs text integration processing according to the conditions and parameters set by the integrated text creation setting unit 520.

  The comparative evaluation unit 540 includes a comparison unit 541 and an evaluation unit 542. The comparison unit 541 receives the existing various texts from the existing various text storage units 760 and compares the integrated text created by the integrated text creation unit 510 with the existing integrated texts from the existing integrated text storage unit 770. The evaluation unit 542 performs an evaluation based on the comparison result of the comparison unit 541, and gives a high score when the values match well.

  The machine learning unit 530 receives the evaluation from the evaluation unit 542 and changes the setting state of the integrated text creation setting unit 520. This process is repeated for the same various text data to make the evaluation value of the evaluation unit 542 as high as possible. This process can be repeated for a plurality of various text data.

  By performing such machine learning, the ability of the integrated text creation unit 510 is improved. After completing the predetermined machine learning, the text integration unit 500 processes the new video data and is in a state where it can output the optimum integrated text.

<Machine learning of summary creation unit 600>
FIG. 9 is a block diagram showing a summary creation unit of the summary creation system. The summary creation unit 600 includes a summary text creation unit 610, a summary creation setting unit 620, a machine learning unit 630, and a comparative evaluation unit 640. An existing data storage unit 700 is connected to the summary creation unit 600.

  The summary creation unit 600 performs machine learning based on the integrated text and summary text stored in the existing data storage unit 700, and optimizes the operation of the summary text creation unit 610. The existing data storage unit 700 includes an existing integrated text storage unit 770 that stores integrated text data used when a summary text was created in the past, and an existing summary text storage unit 780 that stores a summary text created from the integrated text. With. These integrated texts and summary texts serve as machine learning materials.

  The summary creation unit 600 includes switching units 670 and 680 that perform data output switching when machine learning is performed and when a new summary text is created from a new integrated text.

  The summary creation setting unit 620 stores the summary processing settings of the summary text creation unit 610. The summary text creation unit 610 performs text summary processing according to the conditions and parameters set by the summary creation setting unit 620.

  The comparative evaluation unit 640 includes a comparison unit 641 and an evaluation unit 642. The comparison unit 641 compares the summary text created by the summary text creation unit 610 in response to the existing integration text from the existing integration text storage unit 770 and the summary text from the existing summary text storage unit 780. The evaluation unit 642 performs an evaluation based on the comparison result of the comparison unit 641 and gives a high score when the values match well.

  The machine learning unit 630 receives the evaluation from the evaluation unit 642 and changes the setting state of the summary creation setting unit 620. This process is repeated for the same various text data to make the evaluation value of the evaluation unit 642 as high as possible. This process can be repeated for a plurality of integrated text data.

  By performing such machine learning, the capability of the summary text creation unit 610 is improved. After completing the predetermined machine learning, the summary creation unit 600 can process the new video data and output an optimum summary text.

  Next, processing of the summary creation system 10 will be described. FIG. 10 is a flowchart showing the operation of the summary creation system.

  First, the existing video data storage unit 710, the existing utterance text storage unit 720, the existing telop text storage unit 730, the existing background image text storage unit 740, the existing logo mark text storage unit 750, and the existing various text storage units of the existing data storage unit 700 760, an existing video signal and various text data are read into the existing integrated text storage unit 770 and the existing summary text storage unit 780 (step ST1).

  Next, machine learning processing is performed in the speech text unit 100, the telop text unit 200, the background image text unit 300, and the logo mark text unit 400 (steps ST2a, ST2b, ST2c, and ST2d). This learning process can also be performed sequentially.

  Next, the existing input data and output data are read into the existing data storage unit 550 of the text integration unit 500 and the existing data storage unit 650 of the summary creation unit 600 (step ST3). Next, machine learning processing is performed in the text integration unit 500 and the summary creation unit 600 (steps ST3a and 3b). This learning process can also be performed sequentially. Note that the machine learning processing of the utterance text conversion unit 100, the telop text conversion unit 200, the background image text conversion unit 300, and the logo mark text conversion unit 400, and the machine learning processing of the text integration unit 500 and the summary creation unit 600 are as follows. Regardless of the order of processing, it can be performed in the reverse order.

  When the learning process is completed (yes in step ST4), the video signal to be processed is input to the video signal separation unit 20 (step ST5). Thereby, the utterance text conversion unit 100, the telop text conversion unit 200, the background image text conversion unit 300, and the logo mark text conversion unit 400 execute text conversion processing (steps ST6a, ST6b, ST6c, ST6d).

  Then, each text is integrated by the text integration unit 500 (step ST7), the integrated text is further summarized by the summary creation unit 600 (step ST8), and the summary text is output. finish.

  From the next summary creation process, the optimum summary creation can be performed only by inputting the target video signal for summary creation (step ST5) immediately without performing the machine learning process (steps ST1 to ST4). The machine learning process can be performed as necessary.

  The above system includes a CPU (Central Processing Unit) as a processing device, a RAM (Random Access Memory), a ROM (Read Only Memory), an HDD (Hard Disc Drive), an SSD (Solid State Drive), and the like as a storage device. It can be realized by executing application software on a computer system. Moreover, each part does not need to be arrange | positioned in the same place, and it can implement | achieve by arrange | positioning a part on a web and connecting with a network. In addition, since these processes target a large amount of data, it is preferable to perform processing using a GPU (Graphics Processing Unit).

  That is, the integrated text is simply converted into characters such as voice, characters, background video, etc., and is data on a huge amount of text. Therefore, GPU can be processed at high speed by specializing in text processing.

  Further, text input by the text integration unit 500 is not limited to speech text, telop text, background image text, and logo mark text.

  For example, when a TV program (terrestrial digital TV broadcast program) is targeted, characters and voices acquired from an electronic program guide (EPG), caption broadcasting, and commentary broadcasting can be acquired and input as text. Thereby, while improving the quality and quantity of an integrated text, the versatility and preference of a text can be improved.

  Similarly, in the case of Internet video distribution, third party evaluation (including comments) and reputation can be acquired and input as text. As a result, the quality and quantity of the integrated text can be improved, and the versatility and taste of the text can be improved.

  For “weighting”, it is possible to use an evaluation ratio with respect to the number of times of viewing or the ratio of good / bad, etc., using the number of times of viewing (number of times of reproduction) or third party evaluation (good / bad). It is.

  As described above, in the video information providing system 11 according to the second embodiment, at least one summary created by the summary creation unit 600 is targeted for a plurality of video contents by the weighting unit 15d. By assigning weights specialized to the predetermined conditions, useful information can be supplied to the user for a plurality of video contents.

  In the second embodiment, data processing is summarized at high speed and appropriately by AI (artificial intelligence) processing. The AI process can be realized by the machine learning (ML) described above. Furthermore, supervised learning with existing data as correct answers can be adopted as machine learning. Further, it is effective to perform deep learning (DL: Deep Learning) as machine learning.

  In deep learning, a large number of existing video data, various text data corresponding to each video data, integrated text, and summary text are learned as big data. Each machine learning unit includes an input layer, a plurality of intermediate layers, and an output layer, and performs processing by a neural network including a large number of neurons. That is, an intermediate layer so that new video data input to the summary creation system according to the present invention, various texts based on the video data, integrated texts, and an output with the summary as input are close to existing various texts, integrated texts, and summaries. The weights and parameters in the neurons are optimized by a method such as the least square method.

  The scope of rights of the present invention is not limited to the configurations described in the first and second embodiments, but covers all configurations included within the scope of the present invention.

1: video information providing system 2: receiving unit 3: operation unit 4: storage unit 5: control circuit unit 5a: component appearance frequency determination unit 5b: video content extraction unit 5C: desired video registration unit 6: large capacity storage unit 7 : Output unit (video content providing means, output means)
7a: Display video object 9: Playback device 10: Summary creation system (summary creation means)
11: video information providing system 12: receiving unit 13: operation unit 14: storage unit 15: control circuit unit 15a: component appearance frequency determining unit 15b: video content extracting unit 15c: desired video registration unit 15d: weighting unit 16: Large-capacity storage unit 17: output unit (output means)
17a: Display screen 18: Video signal processing unit 19: Playback device 20: Video signal separation unit 30: TV station 40: Internet 100: Utterance text conversion unit 110: Utterance information extraction unit 120: Utterance content recognition unit 130: Utterance content text conversion Unit 140: machine learning unit 150: content recognition text creation / setting unit 160: comparison evaluation unit 161: comparison unit 162: evaluation unit 170: switching unit 180: switching unit 200: telop text converting unit 210: telop information extracting unit 220: telop Content recognition unit 230: telop content text conversion unit 240: machine learning unit 250: content recognition text creation setting unit 260: comparison evaluation unit 261: comparison unit 262: evaluation unit 270: switching unit 280: switching unit 300: background image text conversion Unit 310: Background image information extraction unit 320: Background image content recognition unit 330: In the background image Text conversion unit 340: Machine learning unit 350: Content recognition text creation setting unit 360: Comparison evaluation unit 361: Comparison unit 362: Evaluation unit 370: Switching unit 380: Switching unit 400: Logo mark text conversion unit 410: Logo mark image information Extraction unit 420: Logo mark content recognition unit 430: Logo mark content text conversion unit 440: Machine learning unit 450: Content recognition text creation setting unit 460: Comparison evaluation unit 461: Comparison unit 462: Evaluation unit 470: Switching unit 480: Switching Unit 500: text integration unit 510: integrated text creation unit 520: integrated text creation setting unit 530: machine learning unit 540: comparative evaluation unit 541: comparison unit 542: evaluation unit 550: existing data storage unit 570: switching unit 580: switching Part 600: Summary creation part (summary creation means)
610: summary text creation unit 620: summary creation setting unit 630: machine learning unit 640: comparative evaluation unit 641: comparison unit 642: evaluation unit 650: existing data storage unit 670: switching unit 680: switching unit 700: existing data storage unit 710: Existing video data storage unit 720: Existing utterance text storage unit 730: Existing telop text storage unit 740: Existing background image text storage unit 750: Existing logo mark text storage unit 760: Existing various text storage unit 770: Existing integrated text storage Part 780: Existing summary text storage part

Claims (12)

  When the appearance frequency is greater than or equal to a predetermined value based on the determination by the component appearance frequency determination unit that determines the appearance frequency of the same component based on the component of the distributed video content, and the determination by the component appearance frequency determination unit A video information providing system comprising: video content extracting means for extracting video content including the constituent elements; and video content providing means for providing the viewer with the video extracted by the video content extracting means.   2. The video information providing system according to claim 1, wherein the component appearance frequency determining means determines the appearance frequency of the component based on a viewing request registered by a viewer.   The video information providing system according to claim 1, wherein the component is a character, sound, a video object, a character, or a background of the video object as a theme of the video content.   4. The component appearance frequency determining means determines an appearance frequency of a component element by referring to a title part displayed by characters in a video screen. The video information providing system according to claim 1.   5. The video information providing system according to claim 1, wherein the video content is distributed from a server via a telecommunication line.   5. The video information providing system according to claim 1, wherein the video content is distributed from a broadcasting station via a telecommunication line. Summary creating means for creating a summary by converting audio data or video data in the video content extracted from each video signal of the video content into a text;
While learning the optimum condition based on the accumulation result of the summary created by the summary creation means, a weight specific to one or more predetermined conditions included in the summary is given to the plurality of video contents 2. The video information providing system according to claim 1, further comprising weighting means, wherein the component appearance frequency determining means determines the appearance frequency of the component based on the summary.   The weight assigning means matches the text with the predetermined condition when the reference result is a predetermined value or more after referring to the duplicate text from the audio data or video data included in the plurality of video contents. The video information providing system according to claim 7, wherein the important text is determined and weighting is given.   9. The video information providing system according to claim 8, wherein the weighting unit determines whether the text is an important text for a plurality of video contents within a preset period.   10. The weighting assigning unit starts recording the video content when it is determined that the video content includes the important text for a new video content. The video information providing system according to any one of the above.   The weight assigning means calculates a CM conversion value from the appearance frequency of a specific person / thing from a text included in at least one of the audio data or the video data of the plurality of video contents. The video information providing system according to claim 7.   8. The video information providing system according to claim 7, wherein the weight assigning unit targets a specific corporate name from text included in at least one of the audio data or the video data of the plurality of video contents. .