JP2018081390A - Video recorder - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a video recorder with which it is possible to semi- permanently record a television broadcast or Internet delivered moving-image video and media information on the Internet and examine, analyze or pursue the economical effect or cultural value of these.SOLUTION: A video recorder 10 comprises: recording means 12 for semi-permanently recording a video broadcast by a plurality of television broadcasting stations 50 or a video delivered via a plurality of Internet moving-image delivery sites; video information storage means 14 for storing information relating to videos; metadata storage means 16 for storing the metadata of a recorded video; media information storage means 20 for semi-permanently storing the media information acquired from the websites 17; information extraction means 22 for searching a metadata storage file 15 and a media information storage file 19 using a search keyword and extracting video information or media information; and information classification means 23 for classifying the extracted video information or media information for each prescribed genre.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a recording apparatus for recording a television broadcast of a television broadcast station or an Internet distribution moving image.

Currently, a large amount of program broadcasts and advertisement broadcasts are broadcast on television from early morning to late night. Until now, generally, TV broadcast images functioned as temporary media for viewers and were considered transient.
However, television broadcast images have a significant impact on viewers. For example, if a manufacturer press-releases a new product release that is broadcast on TV news, variety programs, etc., May be directly reflected in the group's stock price.

Even if there is no direct economic relevance, for example, in the case of a nuclear accident in the event of the Great East Japan Earthquake, the power generated by all TV broadcasters broadcasting the Fukushima nuclear accident situation for a long time. The economic and social impact on the company and affiliated companies is considered to have been very large.
In addition, if there are significant fluctuations in exchange rates or information on serious damages in foreign countries where Japanese companies are operating, such as news, it is easy for the stock prices of export-related companies and organizations to be greatly affected. Conceivable.
Furthermore, generally, program images and advertisement images are recognized as reflecting the culture of the broadcast age.

The economic impact and cultural value of such TV broadcast information has never been studied, analyzed and pursued.
The reason for this is that conventional recording devices that record TV broadcast video can only record up to two years from the viewpoint of the capacity and life of the storage medium. This is considered to be because there is a problem that analysis cannot be performed over a period of time.
Even if metadata related to TV broadcast video is saved, the content included is only a summary of the TV broadcast video, and if the original video is lost, the metadata cannot be corrected, There was a defect that good analysis could not be done.

Such inconveniences exist not only for television broadcast images but also for Internet-distributed moving image images that have been rapidly put into practical use. That is, from the viewpoint of the capacity and life of the storage medium, Internet distribution moving images cannot be analyzed over a long period of time.
Therefore, it can be said that the economic impact and cultural value of video information of such Internet-distributed moving images have not been studied, analyzed and pursued so far.

Furthermore, as with television broadcasts and Internet distribution videos, media information obtained from the websites of news organizations composed of major newspaper companies, local newspaper companies, news distribution companies, TV companies, etc. is stored on computers connected to the Internet. It can be easily obtained by accessing the website from a smartphone etc., but since it is updated with new information every second, it is difficult to track and analyze past information .
Therefore, such media information on the Internet has never been studied, analyzed and pursued with regard to its economic impact and cultural value.
From such a viewpoint, the applicant conducted a pre-application search, searched for related application information, and extracted Patent Document 1 below, but it was not a prior art related to the present invention.

2007-264969

  The present invention is for solving the above-described conventional drawbacks, and the problem is to store video information of television broadcast or Internet distribution video and media information on the Internet semipermanently for a long period of time. Another object of the present invention is to provide a recording apparatus that can study, analyze, or pursue the economic impact and cultural value of television broadcast information and media information on the Internet.

  In order to solve the above-mentioned problem, in the invention according to claim 1, all of the television broadcast video broadcasted by a plurality of television broadcast stations or the video of Internet distribution video distributed by a plurality of Internet video distribution sites are provided. A video recording means for recording or saving the video in a recording file semi-permanently, a video information storage means for storing information relating to the video as video information in a video information storage file, and a meta of video recorded or saved by the recording means. Metadata storage means for storing data in a metadata storage file, and connection to a plurality of websites via the Internet. Media information acquired from the website is stored in a media information storage file and stored semipermanently. Media information storage means to be used and a search keyword storage file storing search keywords. The search keyword is searched from the metadata storage file and the media information storage file, and the video information linked to the metadata corresponding to the search keyword or the media information corresponding to the search keyword is Information extraction means for extracting from the video information storage file or the media information storage file, and information classification means for classifying the video information or media information extracted by the information extraction means for each predetermined genre .

Here, recording means an act of recording and storing a television broadcast video or an Internet distribution video on a video recording medium such as a video tape, a DVD medium, or a hard disk.
The predetermined genre refers to politics, economy, administration, business, science, fashion, fashion, sports, entertainment, and the like.
Therefore, when all the videos are recorded or stored semi-permanently in the recording file by the recording unit, and when the video is recorded or stored in the recording file, the video information storage unit relates to the video. Information is stored in the video information storage file as video information, and the metadata of the broadcast video is stored in the metadata storage file by the metadata storage means, and from the website by the media information storage means. The acquired media information is stored in the media information storage file and stored semi-permanently, and the search keyword stored in the search keyword storage file is stored in the metadata storage file and the media information storage by the information extraction means. Search key searched from file Video information associated with metadata corresponding to a mode or media information corresponding to the search keyword is extracted, and the extracted video information or media information is classified for each predetermined genre by the information classification unit. The

  In the invention according to claim 2, the information extraction means extracts metadata corresponding to the search keyword from the metadata storage file and information corresponding to the search keyword. Media information extracting means for extracting from a media information storage file, and information collating means for collating the metadata and media information extracted by the metadata extracting means and the media information extracting means, respectively. To do.

  Therefore, metadata corresponding to the search keyword is extracted from the metadata storage file by the metadata extraction unit, and information corresponding to the search keyword is extracted from the media information storage file by the media information extraction unit. The extracted metadata and media information are collated with each other by the information collating means.

  In the invention according to claim 3, the metadata storage means is acquired by the character information acquisition means for acquiring character information from the video recorded or stored in the recording file, and the character information acquisition means. Character information texting means that aggregates the text information into text, and the text information text-written by the text information text texting means is recorded as metadata of the video recorded or stored in the recording file. It is stored in a metadata storage file.

Here, the character information is information of words and sentences related to the video displayed on the video and is a concept including, for example, a character string of a telop displayed on the video.
Therefore, when the video is recorded or stored in the recording file by the recording unit, the character information displayed on the video recorded or stored in the recording file is acquired by the character information acquisition unit, The acquired character information is converted into text by the text information text conversion means, and the text information converted into text by the metadata storage means is stored in the metadata storage file as metadata of the video.

  According to a fourth aspect of the present invention, the character information acquisition means performs character analysis on the video recorded or stored in the recording file and extracts character information from the video. An image analysis method updating unit that updates the image analysis method, and when the image analysis method update unit updates the method, the character information extraction unit is recorded or stored in the recording file. The image analysis is performed again by the method updated on the video.

  Therefore, when the image analysis technique update unit updates the technique, the updated image analysis is performed again on the video recorded or stored in the recording file by the character information extraction unit. Is called.

  In the invention according to claim 5, the character information extracting means collates with an image analysis storage file having an image analyzed image and character information extracted from the image analyzed image. It has the image collation analysis means to analyze.

Here, the image analyzed image means an image that has been analyzed so far, and the character information extracted from the image analyzed image is correctly extracted from the image as a result of the image analysis. Means character information.
Therefore, the image analysis unit compares the video recorded or stored in the recording file with an image analysis storage file having an image analyzed video and character information extracted from the video analyzed video. Thus, image analysis is performed.

  In the invention according to claim 6, the character information extraction unit is configured to perform the image analysis based on the broadcast video image-analyzed by the image collation analysis unit and the character information extracted from the broadcast video. The image processing apparatus further includes image analysis learning means for correcting the accumulated file.

Here, the correction is a concept including addition and deletion.
Therefore, the image analysis learning unit corrects the image analysis storage file based on the video image analyzed by the image analysis unit and the character information extracted from the video.

  In the invention according to claim 7, the character information acquisition means includes a person, a logo, the personal belongings or the facial expression of the person, and personal information, logo information, physical information or facial expression information included in the video And image recognition information extracting means for extracting the person, logo, personal belongings of the person or the facial expression of the person as character information.

  Therefore, the image recognition information extraction means collates the person, logo, personal belongings or facial expression of the person included in the video with the personal information, logo information, physical information or facial expression information, and is included in the video. Character, logo, personal belongings or facial expression of the person are extracted as character information.

  In the invention according to claim 8, the character information acquisition means performs voice analysis on the voice recorded or saved together with the video recorded or saved in the recording file, and character information is obtained from the voice. It has a voice information extracting means for extracting.

  Accordingly, the voice information extracting means extracts voice information from the voice by analyzing the voice recorded or saved together with the video recorded or saved in the recording file.

  In the invention according to claim 9, the recording means has a recording target keyword storage file for storing a recording target keyword, and only the video corresponding to the metadata including the recording target keyword is recorded in the recording file. It is characterized by having an object extracting means for recording from video and recording or saving.

  Therefore, when a recording target keyword is stored in the recording target keyword storage file, only video corresponding to metadata including the recording target keyword is extracted from the recording file by the target extraction unit and recorded or recorded. Saved.

The invention described in claim 10 further includes statistical processing means for statistically processing the information extracted by the information extraction means.
Here, the statistical processing means known statistical processing such as correlation analysis, regression analysis, and factor analysis.
Therefore, the statistical processing means statistically processes the information extracted by the information extraction means.

  In the invention according to claim 11, the media information storage means stores a search site as a search target site in a search target storage file that is suitable for a field selected in advance from the plurality of websites. A storage means, a site structure analysis means for analyzing a site structure of each search target site for the search target sites stored in the search target storage file, and a search for each search target site, based on the analyzed site structure Site information acquisition means for acquiring site information described in each search target site, and site information storage means for storing the site information acquired from each search target site as the media information in the media information storage file It is characterized by having.

  Therefore, when the search target storage unit stores a website suitable for a field selected in advance from the plurality of websites as a search target site in the search target storage file, the search server stores the site. The structure analysis unit analyzes the site structure of each search target site based on the search target site stored in the search target storage file, the site information acquisition unit circulates each search target site, and the analysis The site information described in each search target site is acquired based on the site structure, and the site information acquired from each search target site by the site information storage means is the media information storage file as the media information. Stored in

  In the invention according to claim 12, the metadata storing file records the program content summary text data, a channel name on which the program content is broadcast, and a time code of the program content. It is characterized by being.

The recording apparatus according to any one of claims 1 to 12, wherein all video is recorded or stored in the recording file semipermanently by the recording unit, and video is recorded or stored in the recording file. The video information storage means stores information related to the video as video information in the video information storage file, and the metadata storage means stores the video metadata in the metadata storage file. The media information obtained from the website is stored in the media information storage file by the media information storage means and is semi-permanently stored, and the search is stored in the search keyword storage file by the information extraction means. The keyword is the metadata storage file and the media information storage file. Video information linked to the metadata corresponding to the search keyword or media information corresponding to the search keyword is extracted, and the extracted video information or media information is predetermined by the information classifying means. It is classified for each genre.
Accordingly, by designating a search keyword, the video information and the media information recorded or stored semipermanently can be searched and extracted in a state classified for each predetermined genre.
As a result, it is possible to record or store video information of television broadcast or Internet distribution video and media information on the Internet semi-permanently over a long period of time, and video information of television broadcast or Internet distribution video and media on the Internet. It is possible to provide a recording apparatus that can examine, analyze, or pursue the economic impact and cultural value of information.
As a result, the TV broadcast or Internet distribution video image information and the Internet media information that are currently regarded as transient and handled are comprehensively and semi-permanently stored. Video information of Internet-distributed moving images and media information on the Internet can be archived, and for example, it is possible to refer to, study, and learn as a culture by looking back at a certain era.

  3. The recording apparatus according to claim 2, wherein metadata corresponding to the search keyword is extracted from the metadata storage file by the metadata extraction means, and the search keyword is supported by the media information extraction means. Information is extracted from the media information storage file, and the extracted metadata and media information are collated with each other by the information collating unit, so that the search accuracy of the video information and media information extracted by the search keyword is increased. Can be increased.

In the recording device according to claim 3, when a video is recorded or stored in the recording file by the recording unit, the character information acquisition unit records or stores the video in the recording file. Character information displayed on the video is acquired, the acquired character information is converted into text by the text information texturing means, and the text information textified by the metadata storage means is converted to metadata of the video Is stored in the metadata storage file.
Therefore, the metadata of the video can be automatically generated with high accuracy from the character information which is displayed on the video and is related to words and sentences related to the video.
As a result, it is possible to create metadata relating to the video of the television broadcast or the video of the Internet distribution video in a short time, thereby reducing human costs.

  In the recording device according to claim 4, when the image analysis technique update unit updates the technique, the video information recorded or stored in the recording file by the character information extraction unit, Since the image analysis by the updated method is performed again, when an accurate image analysis method is developed due to the advancement of technology, the economic impact and the Consider, analyze, or pursue cultural values.

6. The recording apparatus according to claim 5, wherein the video recorded or stored in the recording file by the image analysis means is a video extracted from the video that has undergone image analysis and the video that has been analyzed. The image is analyzed by collating it with an image analysis storage file having information.
Therefore, it is possible to effectively perform image analysis using the image analysis results accumulated from the past, and as a result, the video metadata can be created with high accuracy and in a short time.

7. The recording apparatus according to claim 6, wherein the image analysis learning unit performs image analysis of the image analysis storage file by the image analysis unit and character information extracted from the image. Will be corrected.
Therefore, it is possible to add the image analysis result performed this time to the image analysis accumulation file or to delete erroneous information included in the image analysis accumulation file based on the image analysis result performed this time. The image analysis storage file can be updated and always used in the latest state.

  In the recording device according to claim 7, by the video recognition information extraction unit, a person, a logo, the personal belongings or the facial expression of the person, and personal information, logo information, physical information or Since the facial expression information is collated, and the person, logo, personal belongings or facial expression of the person included in the video is extracted as character information, the person, logo, personal belongings or personality included in the video The video metadata can be created from the facial expression.

9. The recording apparatus according to claim 8, wherein the voice information extraction unit analyzes the voice recorded or saved together with the video recorded or saved in the recording file, thereby analyzing characters from the voice. Information is extracted.
Accordingly, the character information can be efficiently extracted from the voice recorded or stored together with the video by voice analysis.

  10. The recording device according to claim 9, wherein when a recording target keyword is stored in the recording target keyword storage file, video corresponding to metadata including the recording target keyword is recorded by the target extraction unit. Since only video is extracted from the recording file and recorded or stored, the video and video information collected and stored can be compressed, and as a result, the economic impact and cultural value of the video information can be efficiently examined. , Analysis or pursuit.

  In the recording apparatus according to claim 10, since the information extracted by the information extraction unit is statistically processed by the statistical processing unit, the video information and the media information are examined, analyzed, or You can pursue.

12. The recording apparatus according to claim 11, wherein a website suitable for a field selected in advance from among the plurality of websites is stored as a search target site in the search target storage file by the search target storage means. The site structure analysis unit analyzes the site structure of each search target site based on the search target site stored in the search target storage file, and the site information acquisition unit analyzes the search target site. Sites are visited, site information described in each search target site is acquired based on the analyzed site structure, and the site information acquired from each search target site by the site information storage means is used as media information. Since it is stored in the media information storage file, the service described in each search target site is stored. It can be stored bets information in advance the media information storage file.
Therefore, a conventional general search engine displays a large amount of irrelevant websites in the search results, and the user must further scrutinize the search results to select necessary information. However, in the recording apparatus according to the eleventh aspect, the situation does not occur, and as a result, useful information can be obtained accurately and quickly.
In addition, since the information related to the search keyword is extracted from the media information stored in the media information storage file, it is not necessary to visit each search target site every time the search is performed, and useful information can be more quickly collected. Can get to.

FIG. 1 is a block diagram showing an embodiment of a recording apparatus according to the present invention. FIG. 2 is a flowchart showing a flow of processing in the recording apparatus in the embodiment of the recording apparatus according to the present invention.

Hereinafter, the present invention will be described in detail based on embodiments shown in the accompanying drawings. In the present embodiment, description will be made assuming that the recording target is an image of a television broadcast broadcast by a television broadcast station.
(1) Configuration of Recording Apparatus 10 According to the Present Embodiment As shown in FIG. 1, the recording apparatus 10 according to an embodiment of the present invention relates to broadcast channels of a plurality of television broadcast stations 50, 50. Recording means 12 for recording all broadcast videos in the recording file 11 and storing them semi-permanently, video information storage means 14 for storing information relating to the video in the video information storage file 13 as video information, and recording means 12 The metadata storage means 16 for storing the metadata of the recorded video in the metadata storage file 15 can be connected to a plurality of websites 17, 17... Via the Internet 18, and the websites 17, 17. Media information storage means 20 for storing the media information acquired from the media information storage file 19 and storing it semipermanently, and a search keyword A search keyword storage file 21 in which the search keyword is stored, the search keyword is searched from the metadata storage file 15 and the media information storage file 19, and the video information associated with the metadata corresponding to the search keyword or the Information extraction means 22 for extracting media information corresponding to the search keyword from the video information storage file 13 or the media information storage file 19, and information classification means 23 for classifying the information extracted by the information extraction means 22 for each predetermined genre; have.

Also, as shown in FIG. 1, the information extraction unit 22 according to the present embodiment corresponds to the metadata extraction unit 24 that extracts metadata corresponding to the search keyword from the metadata storage file 15 and the search keyword. Media information extracting means 25 for extracting the media information to be extracted from the media information storage file 19, and information collating means 26 for collating the extracted metadata and media information with each other by the metadata extracting means 24 and the media information extracting means 25, respectively. And have.
As shown in FIG. 1, the recording apparatus 10 according to the present embodiment includes a statistical processing unit 27 that statistically processes the information extracted by the information extracting unit 22.
As shown in FIG. 1, the metadata storage unit 16 according to the present embodiment is acquired by the character information acquisition unit 28 that acquires character information from the video recorded in the recording file 11 and the character information acquisition unit 28. A text information writing means 29 for collecting the written text information into text, and writing the text information written by the text information text writing means 29 as metadata of a video recorded in the recording file 11. It is configured to store in the metadata storage file 15.
Specifically, the metadata storage means 16 has, for example, “(03/01 12:00) [XX News] ○ × Open top tennis in Japan as video content of the program content 42. The metadata “player △ player has advanced to the final” can be stored in the metadata storage file 15.

As shown in FIG. 1, the character information acquisition unit 28 according to the present embodiment performs image analysis on the broadcast video recorded in the recording file 11 and extracts character information from the video. 30 and image analysis technique updating means 51 for updating the image analysis technique.
The character information extracting unit 30 according to the present embodiment includes an image analyzing unit 31 that extracts a character string by performing image analysis on the video recorded in the recording file 11, and a morpheme for the extracted character string. Word analysis means 32 for extracting words included in the character string by performing analysis.
Here, morpheme analysis refers to morphemes (roughly speaking, based on information such as grammar of the target language and parts of speech of words called dictionaries from text data (sentences) in natural language without notes of grammatical information. , The smallest unit having meaning in the language), and determining the part of speech of each morpheme. Specifically, for example, words such as “XX” (competition name), “XX Open”, “Final”, “Progress”, “Final advance” are extracted from the character string “XX Open final advance”. be able to.

As shown in FIG. 1, the image analysis means 31 according to the present embodiment collates with an image analysis storage file 33 having an image analyzed image and character information extracted from the image analyzed image. It is configured for image analysis.
Here, the image analyzed image means an image that has been analyzed so far, and the character information extracted from the image analyzed image is correctly extracted from the image as a result of the image analysis. Means character information.

  As shown in FIG. 1, the character information extraction unit 30 according to the present embodiment is configured such that the broadcast video recorded in the recording file 11 when the image analysis method update unit 51 updates the image analysis method. The image analysis is performed again by the updated method.

  Further, as shown in FIG. 1, the character information extraction means 30 according to the present embodiment is based on the broadcast video image analyzed by the image analysis means 31 and the character information extracted from the broadcast video. An image analysis learning unit 53 for correcting the analysis accumulation file 33 is further provided.

Further, as shown in FIG. 1, the character information acquisition means 28 according to the present embodiment includes a person, a logo, the personal belongings or the facial expression of the person, and personal information, logo information, and physical information included in the video. Alternatively, it includes video recognition information extraction means 34 that collates facial expression information and extracts a person, a logo, the personal belongings included in the video, or the facial expression of the person as character information.
Specifically, the video recognition information extracting means 34 collates person information, logo information, object information, and facial expression information against a person, a logo, a personal belonging, and a human facial expression included in the video of the program content 42. For example, it is verified that the person is “○ △ player”, the logo is “○ × open”, the person's belongings are “tennis (racquet)”, and the person ’s facial expression is “perfect expression”. It can be extracted as character information.
The personal information, logo information, object information, or facial expression information according to the present embodiment is composed of video that has undergone image analysis and character information that has been extracted from the video that has undergone image analysis.

  Further, as shown in FIG. 1, the character information acquisition means 28 according to the present embodiment performs voice analysis on the sound recorded together with the video recorded in the recording file 11, and extracts character information from the sound. Voice information extraction means 35 for performing

  As shown in FIG. 1, in the character information acquisition unit 28 according to the present embodiment, the character information extraction unit 30, the video recognition information extraction unit 34, and the voice information extraction unit 35 respectively extract the character information. A composite information collating means 36 for collating character information with each other is provided.

  Further, as shown in FIG. 1, the recording unit 12 according to the present embodiment has a recording target keyword storage file 54 for storing a recording target keyword, and broadcast video corresponding to metadata including the recording target keyword. Only the recording file 11 is extracted and stored.

  As shown in FIG. 1, the media information storage means 20 according to the present embodiment selects websites suitable for a field selected in advance from a plurality of websites 17, 17. As for the search target storage means 38 stored in the search target storage file 37 and the search target sites 17a, 17a... Stored in the search target storage file 37, the site structure for analyzing the site structure of each search target site An analysis unit 39, a site information acquisition unit 40 that circulates through each search target site and acquires site information described in each search target site based on the analyzed site structure, and is acquired from each search target site And site information storage means 41 for storing the site information as media information in the media information storage file 19. To have.

As shown in FIG. 1, the recording means 12 according to the present embodiment is composed of all program videos and advertisement videos broadcast from all broadcast stations, for example, all ground stations and satellite broadcast stations in Japan. It has a hard disk storage device with a predetermined capacity so that the broadcast video can be recorded and stored for a predetermined period, for example, 50 years.
Although not shown, the recording unit 12 according to the present embodiment includes a notification unit for notifying that the hard disk is replaced when two years have elapsed, for example, in consideration of the useful life of the hard disk, and ensures regular maintenance. It can be configured to be able to be performed. As a result, the broadcast video can be stored semipermanently.

In the present embodiment, the recording file 11 in the hard disk equipped in the recording means 12 includes a program content 42 composed of a video broadcast by the TV broadcasting station 50, a channel name 43 on which the program content 42 is broadcast, It has information regarding the time code 44 of the program content 42.
In this case, the program content 42 consists of a broadcast program unit, a corner unit constituting the broadcast program, or an article unit constituting the broadcast program.

As shown in FIG. 1, in the present embodiment, the metadata storage file 15 of the metadata storage means 16 includes the program content summary text data 45, the channel name 43 on which the program content 42 is broadcast, the program The time code 44 of the content 42 is recorded, and both are data constituting the metadata in the present embodiment.
The program content summary text data 45 is a summary of the contents of a television program broadcast by the television broadcast station 50 in text form. Similar to the program content 42, the program content summary text data 45 is composed of a broadcast program unit, a corner unit constituting the broadcast program, or an article unit constituting the broadcast program.
Further, the program content summary text data 45 can include nuance parameters. Here, the “nuance parameter” is obtained by quantifying the nuance (impression) of the site information in which a word corresponding to the search keyword appears by an automatic system such as artificial intelligence or human judgment.
For example, if the program content is good (good), it is high (plus evaluation), if it is bad (bad), it is low (minus evaluation), and if the program content is neutral (neutral), it is 0. (Zero evaluation).

The recording apparatus 10 according to the present embodiment is configured as a computer. Although not shown, the recording apparatus 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), a hard disk drive (hard Disc Drive), a communication control means for connecting to the Internet 18, and a keyboard. The input means such as a mouse and the output means such as a printer and a monitor are connected by a bus.
The recording file 11, the video information storage file 13, the metadata storage file 15, the media information storage file 19, the search keyword storage file 21, and the image analysis storage file 33 according to the present embodiment are configured as a database and are stored in the hard disk drive. It may be constructed, or it can be constructed on an external storage medium.
Further, as described above, the video information storage file 13 is information on broadcast video including all program videos and advertisement videos broadcast from all broadcast stations, for example, all ground stations and satellite broadcast stations in Japan. Since the hard disk drive or the external storage medium in which the video information storage file 13 is constructed is considered in consideration of the useful life of the hard disk, for example, two years have elapsed. It may be configured to have a notification means for notifying that the hard disk is to be replaced from time to time and to perform regular maintenance with certainty. As a result, it is possible to store video information recorded or stored from all broadcast stations semi-permanently.
In addition, as described above, the media information storage file 19 is configured to be able to store media information acquired from the Internet semi-permanently. Therefore, the hard disk drive in which the media information storage file 19 is constructed, or an external In consideration of the useful life of the hard disk, the storage medium has a notification means for notifying that the hard disk is to be replaced when, for example, two years have elapsed, and can be configured to ensure regular maintenance. As a result, media information acquired from the Internet semipermanently can be stored.
Further, the recording apparatus 10 according to the present embodiment may be configured by a classification search server and a user terminal.

(2) Process Flow of Recording Apparatus 10 According to this Embodiment As shown in FIG. 2, the recording apparatus 10 according to this embodiment performs processing according to the following steps.
First, video information will be described. As shown in FIG. 2, the recording unit 12 according to the present embodiment records the TV broadcast video broadcast by the TV broadcast station 50 in the recording file 11 (St1).
At this time, the recording means 12 transmits broadcast videos composed of all program videos and advertisement videos broadcast from all broadcast stations, for example, all ground stations and satellite broadcast stations in Japan, for a predetermined period, for example, 50 years. It is also possible to record in the recording file 11 and store it.

Next, as shown in FIG. 2, the character information acquisition unit 28 acquires the character information displayed on the video recorded in the recording file 11.
At this time, the character information extraction means 30 performs image analysis on the video recorded in the recording file 11 and extracts character information from the video (St2a).
In particular, as shown in FIG. 1, in the character information extraction unit 30 according to the present embodiment, the image analysis unit 31 performs image analysis on the video recorded in the recording file 11 to generate a character string. A word included in the character string is extracted by performing morphological analysis on the character string extracted and extracted by the word analysis unit 32.
As shown in FIG. 1, in the character information extraction unit 30 according to the present embodiment, the image analysis unit 31 includes a video recorded in the recording file 11, a video after image analysis, and the image analysis. The image analysis is performed by collating with the image analysis storage file 33 having the character information extracted from the completed video.

In addition, as shown in FIG. 2, the video recognition information extraction means 34 collates the person, logo, personal belongings or facial expressions included in the video with the personal information, logo information, physical information or facial expression information, The person, logo, person's belongings or person's facial expression included in the video is extracted as character information (St2b).
As shown in FIG. 1, in the present embodiment, the video recognition information extraction unit 34 extracts the video recorded in the recording file 11, the video that has been analyzed, and the video that has been analyzed. The person information, the logo information, the object information, or the expression information included in the video is extracted as the character information by collating the person information, the logo information, the object information, or the expression information included in the character information.

Further, as shown in FIG. 2, the voice information extracting means 35 performs voice analysis on the voice recorded together with the video recorded in the recording file 11, and extracts character information from the voice (St2c).

Subsequently, as shown in FIG. 2, the composite information collating unit 36 collates the extracted character information with each other by the character information extracting unit 30, the video recognition information extracting unit 34, and the voice information extracting unit 35. (St3).
In addition, when giving priority to the processing speed, the matching step St3 by the composite information matching unit 36 may be omitted.

Next, as shown in FIG. 2, the character information documenting means 29 aggregates the acquired character information into a document (St4).
At this time, the character information documenting means 29 refers to the metadata storage file 15 and converts the metadata related to the character information acquired by the character information acquiring means 28 from the created metadata into the text information. Can be used.

Next, as shown in FIG. 2, the metadata storage means 16 can search the metadata storage file 15 for the text information textified by the text information textification means 29 as video metadata recorded in the recording file 11. (St5).
As described above, video metadata can be created from character information that is displayed in the video and is related to words and sentences related to the video.

Next, media information will be described. As shown in FIG. 2, a search object storage means 38 selects a field selected in advance from a plurality of websites 17, 17... Connected to the Internet 18, for example, a news agency website related to news. , 17a... And the URL of the document root of the search target sites 17a, 17a... Is stored in the search target storage file 37 (Sm1).
As a result, a search target site to be visited is selected, and unnecessary time used for unnecessary information collection and noise information collection are eliminated, resulting in high accuracy.

  Next, the site structure analyzing means 39 analyzes the site structure of the selected search target sites 17a, 17a... And grasps the site structure of each search target site 17a, 17a.

Next, the site information acquisition means 40 periodically or sequentially visits each search target site 17a, 17a... To acquire site information described in each search target site 17a, 17a.
Thereafter, the site information storage means 41 stores the acquired site information as media information in a searchable manner in the media information storage file 19 (Sm4).
At this time, the site information storage means 41 can also store and save the media information acquired from the Internet in the media information storage file 19 for a predetermined period, for example, 50 years.
As described above, media information can be acquired from a website on the Internet.

Finally, information classification will be described. As shown in FIG. 2, when a search keyword is stored in the search keyword storage file 21, the metadata extraction unit 24 included in the information extraction unit 22 converts the metadata corresponding to the search keyword into the metadata storage file 15. (Sc1).
Next, as shown in FIG. 2, the media information extraction unit 25 included in the information extraction unit 22 extracts the media information corresponding to the search keyword from the media information storage file 19 (Sc2).
Next, as shown in FIG. 2, the information collating unit 26 collates the extracted metadata and media information with each other by the metadata extracting unit 24 and the media information extracting unit 25 (Sc3).
Finally, as shown in FIG. 2, the information classification means 23 extracts the information extracted by the information extraction means 22 for each predetermined genre such as politics, economy, government, business, science, fashion, fashion, sports, entertainment, etc. Classify (Sc4).
As described above, by specifying a search keyword, it is possible to search and extract video information and Internet media information in a state classified for each predetermined genre.

(3) Effects of Recording Apparatus 10 According to this Embodiment As shown in FIG. 1, in the recording apparatus 10 according to this embodiment, all broadcast videos are recorded in the recording file 11 by the recording means 12. When the broadcast video is recorded in the recording file 11, the video information storage means 14 stores information related to the broadcast program video in the video information storage file 13 as video information. At the same time, the metadata of the broadcast program video is stored in the metadata storage file 15 by the metadata storage means 16, and the search keyword stored in the search keyword storage file 21 by the information extraction means 22 is extracted from the metadata storage file 15. The video information searched and linked to the metadata corresponding to the search keyword is the information storage file 1. 3 and the information classification means 23 classifies the extracted video information for each predetermined genre.
Therefore, by designating a search keyword, the video information stored semipermanently can be searched and extracted in a state classified for each predetermined genre.
As a result, television broadcast video information and Internet media information can be stored semi-permanently over a long period of time, and the economic impact and cultural value of TV broadcast video information and Internet media information can be preserved. It is possible to provide a recording device that can be examined, analyzed, or pursued.
As a result, the television broadcast video information and the Internet are accumulated by comprehensively and semi-permanently accumulating the television broadcast video information and the Internet media information that are currently considered and treated as transient. The above media information can be archived, and for example, it is possible to look back on a certain era and refer to, study, and learn as a culture.

  Also, as shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, metadata corresponding to the search keyword is extracted from the metadata storage file 15 by the metadata extraction means 24, and the media information Media information corresponding to the search keyword is extracted from the media information storage file 19 by the extraction unit 25, and the extracted metadata and media information are collated with each other by the information collation unit 26. It is possible to improve the retrieval accuracy of the television image information and media information that has been made.

As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, when video is recorded in the recording file 11 by the recording unit 12, the character information acquisition unit 28 stores the video in the recording file 11. Character information displayed in the recorded video is acquired, the acquired character information is converted into text by the character information writing unit 29, and the text information converted into text by the metadata storage unit 16 is converted into the text information. It is stored in the metadata storage file 15 as video metadata.
Therefore, the metadata of the video can be automatically generated with high accuracy from the character information which is displayed on the video and is related to words and sentences related to the video.
As a result, metadata relating to a television broadcast program can be created in a short time, and human costs can be reduced.

  As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, when the image analysis technique updating means 51 updates the technique, it is recorded in the recording file 11 by the character information extracting means 30. Since the image analysis using the updated method is performed again on the broadcast video, if a highly accurate image analysis method is developed due to technological progress, the newly analyzed highly accurate television broadcast information Based on the above, it is possible to examine, analyze or pursue economic impacts and cultural values.

As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, the video recorded in the recording file 11 by the image analysis unit 31 includes the video that has been analyzed and the video that has been analyzed. The image is analyzed by collating with the image analysis storage file 33 having the character information extracted from the video.
Therefore, it is possible to effectively perform image analysis using the image analysis results accumulated from the past, and as a result, the video metadata can be created with high accuracy and in a short time.

As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, the image analysis learning unit 53 extracts the image analysis storage file 33 from the image analyzed by the image analysis unit 31 and the image. Is corrected based on the character information.
Therefore, the image analysis result performed this time can be added to the image analysis accumulation file 33, or erroneous information included in the image analysis accumulation file 33 can be deleted based on the image analysis result performed this time. The image analysis storage file 33 can be updated and always used in the latest state.

  As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, the video recognition information extraction unit 34 causes a person, a logo, the personal belongings or the facial expression of the person, Information, logo information, object information or facial expression information is collated, and the person, logo, the personal belongings of the person or the facial expression of the person are extracted as character information, so the person, logo included in the video The metadata of the video can be created from the personal belongings or the facial expressions of the person.

As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, the audio information extracting means 35 analyzes the audio recorded together with the video recorded in the recording file 11 by performing audio analysis. Character information is extracted from the voice.
Therefore, the character information can be efficiently extracted from the voice recorded together with the video by voice analysis.

  As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, when a recording target keyword is stored in the recording target keyword storage file 54, the recording target keyword is stored by the target extraction unit 55. Since only the broadcast video corresponding to the included metadata is extracted from the recording file 11 and stored, the broadcast video and TV broadcast information collected and stored can be compressed, and as a result, the economics of the TV broadcast information can be reduced. Effectively consider, analyze, or pursue impacts and cultural values.

  As shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, the information extracted by the information extracting means 22 is statistically processed by the statistical processing means 27, so that the TV video information and the media information are included. On the other hand, you can study, analyze, or pursue.

Further, as shown in FIG. 1, in the recording apparatus 10 according to the present embodiment, the search target storage means 38 is adapted to a field selected in advance from a plurality of websites 17, 17. When the website is stored in the search target storage file 37 as the search target sites 17a, 17a..., Each site structure analyzing unit 39 determines each site based on the search target sites stored in the search target storage file 37. The site structure of the search target site is analyzed, the site information acquisition means 40 circulates each search target site, and the site information described in each search target site is acquired based on the analyzed site structure. The site information acquired from each search target site by the information storage means 41 is converted into media information as a media information storage file. Since it is stored in the Le 19, it can be stored to the each search target site advance media information storage file 19 site information described in.
Therefore, a conventional general search engine displays a large amount of irrelevant websites in the search results, and the user must further scrutinize the search results to select necessary information. In the recording apparatus 10 according to the present embodiment, the above situation does not occur, and as a result, useful information can be obtained accurately and quickly.
In addition, since the information related to the search keyword is extracted from the media information stored in the media information storage file 19, it is not necessary to visit each search target site every time the search is performed, and useful information can be more quickly obtained. Can get to.

  The present invention is widely applicable to recording devices that record broadcast video, and has industrial applicability.

10: Recording device 11: Recording file 12: Recording means 13: Video information storage file 14: Video information storage means 15: Metadata storage file 16: Metadata storage means 17: Website 17a: Search target site 18: Internet 19: Media information storage file 20: Media information storage means 21: Search keyword storage file 22: Information extraction means 23: Information classification means 24: Metadata extraction means 25: Media information extraction means 26: Information matching means 27: Statistical processing means 28: Character information acquisition means 29: Character information textification means 30: Character information extraction means 31: Image analysis means 32: Word analysis means 33: Image analysis storage file 34: Video recognition information extraction means 35: Audio information extraction means 36: Composite information Verification means 37: Search target storage file 38: Search target storage means 3 : Site structure analysis means 40: Site information acquisition means 41: Site information storage means 42: Program content 43: Channel name 44: Time code 45: Program content summary text data 50: Television broadcast station 51: Image analysis technique update means 53: Image analysis learning means 54: recording target keyword storage file 55: target extraction means

Claims (12)

Recording means for semi-permanently recording or storing all videos in a recording file for video broadcast videos broadcast by a plurality of TV broadcasting stations or video distribution of Internet distribution videos distributed by a plurality of Internet video distribution sites, and the video Video information storage means for storing information as video information in a video information storage file;
Metadata storage means for storing metadata of the video recorded or saved by the recording means in a metadata storage file;
Media information storage means that is connectable to a plurality of websites via the Internet, stores the media information acquired from the websites in a media information storage file, and stores it semipermanently;
A search keyword storage file in which a search keyword is stored, the search keyword is searched from the metadata storage file and the media information storage file, and the video information associated with the metadata corresponding to the search keyword or the Information extraction means for extracting media information corresponding to a search keyword from the video information storage file or the media information storage file;
A recording apparatus comprising: information classification means for classifying the video information or the media information extracted by the information extraction means for each predetermined genre.   The information extraction means includes metadata extraction means for extracting metadata corresponding to the search keyword from the metadata storage file, and media information extraction means for extracting information corresponding to the search keyword from the media information storage file. 2. A recording apparatus according to claim 1, further comprising information collating means for collating the metadata and media information extracted by said metadata extracting means and said media information extracting means, respectively.   The metadata storage means includes: character information acquisition means for acquiring character information from video recorded or stored in the recording file; and character information for integrating the character information acquired by the character information acquisition means into a sentence. And writing means, and storing the character information written by the character information writing means in the metadata storage file as metadata of video recorded or stored in the recording file. The recording device according to claim 1.   The character information acquisition means performs image analysis on a video recorded or stored in the recording file, extracts character information from the video, and an image analysis technique for updating the image analysis technique. Update means, and when the image analysis technique update means updates the technique, the character information extraction means performs image analysis using the technique updated for the video recorded or stored in the recording file. 4. The recording apparatus according to claim 3, wherein the recording is performed again.   The character information extraction means includes image collation analysis means for collating with an image analysis storage file having image analyzed video and character information extracted from the image analyzed video. The recording apparatus according to claim 4.   The character information extraction means further comprises image analysis learning means for correcting the image analysis storage file based on the video image analyzed by the image collation analysis means and the character information extracted from the video. 6. A recording apparatus according to claim 5, wherein:   The character information acquisition means collates a person, logo, personal belongings or facial expression of the person included in the video with personal information, logo information, physical information or facial expression information, and a person included in the video, 4. The recording apparatus according to claim 3, further comprising video recognition information extraction means for extracting a logo, the personal belongings or the facial expression of the person as character information.   The character information acquisition means includes voice information extraction means for performing voice analysis on voice recorded or saved together with video recorded or saved in the recording file and extracting character information from the voice. The recording apparatus according to claim 3.   The recording means has a recording target keyword storage file for storing a recording target keyword, and includes a target extracting means for extracting only the video corresponding to the metadata including the recording target keyword from the recording file and recording or saving it. The recording apparatus according to claim 1, further comprising: a recording apparatus according to claim 1.   The recording apparatus according to claim 1, further comprising a statistical processing unit that statistically processes the information extracted by the information extraction unit. The media information storage means is a search target storage means for storing a website suitable for a field selected in advance from the plurality of websites as a search target site in a search target storage file;
Site structure analysis means for analyzing the site structure of each search target site for the search target sites stored in the search target storage file;
A site information acquisition unit that circulates each search target site and acquires site information described in each search target site based on the analyzed site structure;
The recording apparatus according to claim 1, further comprising site information storage means for storing the site information acquired from each search target site as the media information in the media information storage file. 12. The metadata storage file stores the program content summary text data, a channel name on which the program content is broadcast, and a time code of the program content. The recording device according to any one of claims.