JP2004362280A - Broadcast program accumulation device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a new way to enjoy TV by surely retrieving a program desired by a user from many programs accumulated in a broadcast program accumulation device and performing a program retrieval by a pseudo conversations with the broadcast program accumulation device. <P>SOLUTION: In this broadcast program accumulation device, when a keyword is inputted by voice or through a keyboard from a user, the retrieval result of a program including the keyword is responded by a voice emitted in the program. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to a broadcast program storage device. Specifically, it has a function of recognizing all voices emitted during the broadcast together with the program contents and converting the text data into text data.The text data is stored as a keyword database, and an optimum answer to a user request and a program are described. The present invention relates to a broadcast program storage device having a function of searching from a keyword database.
[0002]
[Prior art]
The receiver of the BS digital broadcasting started on December 1, 2000 is rapidly developing, and it is estimated that the World Wide will reach 70 million units in 2005.
[0003]
One of the differences from the conventional BS analog broadcasting is that the number of channels is increased, and more than twice as many programs can be viewed. Also, if the number of channels of the 110-degree CS digital broadcast started on March 1, 2002 is combined with this, approximately 300 or more channels can be viewed.
[0004]
If the number of TV channels increases, the number of programs that can be enjoyed by the user increases, but channel selection becomes difficult. In the conventional BS / CS digital broadcast receiver, an EPG (Electronic Program Guide) can be used to display a program table similar to a TV program column of a newspaper on a TV screen, and a program can be selected on the EPG. It is possible to make reservations for programs. However, it is difficult to search for a program desired by the user from among the 300 or more channels using only the EPG. Further, there is a possibility that there are a plurality of programs including the contents desired by the user, and it has been extremely difficult to search for a program closest to the user's request from among them.
[0005]
In such a situation, the contents of the program are converted into text data using voice recognition and stored, and a keyword input by a user is compared with the stored text data to determine a broadcast program related to the matched text data. There is a way to play. (See, for example, Patent Document 1).
[0006]
[Patent Document 1]
JP 2001-309282 A (Page 6, FIG. 1)
[0007]
[Problems to be solved by the invention]
As described above, the conventional BS / CS digital broadcast receiver has a problem that it is difficult to search for a program desired by the user from among many channels.
[0008]
In Patent Document 1, the content of a program to be recorded is converted into a text database using voice recognition, and a program that matches a keyword input by a user from the text database is reproduced to solve the above problem. However, since there may be a plurality of programs that match the keyword, the reproduced program may not be a program desired by the user.
[0009]
The present invention has been made in view of the above problems, and when a user inputs a keyword by voice or a keyboard or the like, a search result of a program including the keyword can be responded to by a voice issued in the program. Another object of the present invention is to provide a broadcast program storage device that allows a user to discover and view a program while having fun through pseudo conversation.
[0010]
[Means for Solving the Problems]
In order to solve the above-mentioned problems, the present invention provides program content text conversion means for storing broadcast program content, recognizing all sounds emitted during the broadcast, and converting the text data into text data, and converting the text data into a keyword database. Is stored. A keyword input unit for inputting a voice or key input request by a user; a request matching search unit for searching a keyword database for a phrase that matches the keyword in the request; and It is configured to be provided with output means for outputting as character information and notifying the user.
[0011]
Since the present invention has the above-described configuration, for example, when a user inputs a keyword by voice or a keyboard or the like, the broadcast program storage device can issue a search result of a program including the keyword as a program. The user can easily search for a desired program because he / she can respond with a voice that is played.
[0012]
Further, the user can discover and view the program while having fun by pseudo-conversation with the main broadcast program storage device. Further, since the broadcast program storage device can enjoy other programs derived from the keyword instead of the program completely matching the first keyword input by the user, the program reproduction which cannot be imagined from the first keyword can be performed. Is performed, a new way of enjoying the television can be provided.
[0013]
BEST MODE FOR CARRYING OUT THE INVENTION
FIG. 1 shows an overall configuration of a method of using a broadcast program storage device according to a first embodiment of the present invention. In FIG. 1, 101 is an antenna of a BS / CS digital broadcast station, 102 is a broadcast program storage device equipped with the BS / CS digital broadcast receiving device, 103 is a storage medium such as an HDD, 104 is a voice recognition unit, and 105 is a voice recognition unit. A user application unit 106 is a display unit such as a TV.
[0014]
In FIG. 1, a broadcast program storage device 102 stores, in a storage medium, data obtained by converting all sounds generated in the broadcast program into text by a voice recognition unit 104 together with a received broadcast program image. The broadcast program storage device 102 is provided with an interface such as a voice and a keyboard. The user inputs, for example, a keyword of interest through the voice and keyboard interface. The user application unit 105 searches the text-based program data for a program including the keyword input by the user, and reproduces the search result program.
[0015]
FIG. 2 shows an example of the configuration of the broadcast program storage device 102 in FIG.
In FIG. 2, reference numeral 201 denotes an antenna for receiving a radio wave from a satellite; and 202, a digital signal obtained by selecting, demodulating, and error correcting a signal from an LNB (Low Noise Block Converter) immediately below the antenna for each desired channel. An RF front-end unit 203 that outputs a transport stream signal (hereinafter, referred to as a TS signal) converts a TS signal supplied from the RF front-end unit into a video elementary stream (video-based PES (Packetized Elementary Stream)). ) And an audio elementary stream (audio PES), and character / graphic data of a data broadcast (for example, EPG (Electronic Program) transmitted by a predetermined transmission method included in the TS signal. a TS decoder section 204 for separating the video PES of the video system compressed by the MPEG (Moving Picture Experts Group) system, supplied from the TS decoder 203, and an MPEG2 Video Decoder section for decoding the PES of the video system supplied by the TS decoder 203. 205 decodes the character / graphic data supplied from the TS decoder 203, performs a predetermined conversion process to generate a character / graphic plane, and performs a predetermined conversion from the video signal supplied from the MPEG2 Video Decoder unit 204. A scan converter unit 206 that performs processing and generates a moving image plane, a database area 206 composed of, for example, an HDD for storing programs, and a user area 207 for a user to input keywords such as a sound and a keyboard. The user interface 208 is a CPU that controls the entire system, the 209 is an AAC decoder unit that decodes the audio PES supplied from the TS decoder 203, and the 210 is decoded by the AAC decoder unit 209. Audio Text Converter unit 211 for converting the converted audio data into text data stores program audio data converted to text by Audio Text Converter unit 210. Text database 212 is input from user interface 207. A voice recognition unit 213 that performs keyword recognition processing is a database area that stores dictionary data used in the processing of the voice recognition unit 212.
[0016]
The TS decoder 203 supplies the video PES to the MPEG2 Video Decoder 204 among the separated video PES and audio PES, and supplies the audio PES to the audio decoder 209. The TS decoder 203 also supplies the separated character / graphic data to the scan converter 205. The MPEG2 Video Decoder unit 204 decodes the video PES and accumulates image packets in the program database 206 together with time information. The AAC Decoder 209 decodes the audio PES, and inputs the audio packet to the Audio Text Converter 210 together with time information. The audio text converter 210 performs voice recognition and text data conversion of the input voice packet using the dictionary database 213, and inputs the text data to the text database 211 together with time information. Here, the dictionary database is, for example, the latest term data or user's enrollment data. As described above, in the main broadcast program storage device 102, all the audio information generated by the program together with the image information of the program is converted into text and stored in the database area with time information synchronized with each other.
[0017]
Hereinafter, a specific operation of the present embodiment will be described.
The user inputs a keyword of a program to be viewed from the user interface 207 by voice or a keyboard. The input keyword is converted into text by the voice recognition process 212. The CPU 208 searches the text database 211 for a program in which the text keyword is present. When a program including the keyword from the user is found, for example, one sentence including the keyword is reproduced by the sound emitted in the program. At this time, playback may be performed together with the video using the time information at the time of recording in the database. When the reproduced search result is a program desired by the user, an instruction to reproduce the entire program is input from the user interface 207 by voice or a keyboard. If not, the user is prompted to reproduce the next search result by voice or keyboard.
[0018]
As described above, in the present embodiment, the broadcast program storage device converts the program information, together with the video, into all texts generated and converted into text, and stores the texts. Searching for a program including the keyword from the data, and responding to the search result with a sound emitted in the program, the user can determine whether the keyword is issued in a news program or in a variety program. It is possible to ascertain whether the program is a keyword or the like, and to further narrow down from programs including the keyword.
[0019]
FIG. 3 shows a configuration of a broadcast program storage device according to a second embodiment of the present invention. 3, the same components as those of the first embodiment shown in FIG. 2 are denoted by the same reference numerals, and description thereof will be omitted. This embodiment differs from the first embodiment in that a function for responding to a keyword input from a user is provided.
[0020]
Hereinafter, the operation of a portion different from the first embodiment will be described. In the figure, a request / response search unit 301 selects an optimum response keyword from a response database 302 for a keyword input by a user using a voice or a keyboard. When converting the audio of the program to be recorded into text, the response database 302 categorizes the questions into "questions" and "answers" and creates a database. The response database 302 is provided in an area different from the text database 211. When a program stored in the program database 206 is deleted, the text data corresponding to the program is automatically deleted. The content is retained without being erased, and the more types of programs are recorded, the more types of responses can be made. The CPU 208 searches the text database 211 for a program including the selected response keyword. When a program including the response keyword is found, for example, one sentence including the response keyword is reproduced by a sound emitted from the program. At this time, playback may be performed together with the video using the time information at the time of recording in the database. If the reproduced search result is a program desired by the user, an instruction to reproduce the entire program is input from the user interface 207 by voice or a keyboard. If not, the user is prompted to reproduce the next search result by voice or keyboard.
[0021]
FIG. 4 is a diagram illustrating a specific operation of the present embodiment.
The user inputs a keyword through the audio interface of the main broadcast program storage device (in FIG. 4, the keyword "tired"). The broadcast program storage apparatus searches for a program including an optimal response keyword in response to the keyword, and reproduces it with the sound emitted from the program (in FIG. 4, a response keyword of "do your best"). Here, when the user wants to view the program including the response keyword, the user inputs an instruction to reproduce the entire program (in FIG. 4, an audio instruction "show the program") through the audio interface, and Playback starts.
[0022]
Also, as shown in FIG. 5, a pseudo conversation with the main broadcast program storage device is realized by combining the function of reproducing a part of the program including the user keyword shown in the first embodiment. Thus, a desired program can be found and viewed.
[0023]
As described above, according to the present embodiment, the user can find and watch a program of interest through pseudo conversation with the broadcast program storage device. Also, since the sound used for the pseudo conversation is the sound and contents emitted in the recorded program, the means for determining whether or not the program is the desired program is increased for the user, and the fresh sound is basically always refreshed. You can enjoy conversation.
[0024]
FIG. 6 shows a configuration of an apparatus according to a third embodiment of the present invention.
6, the same components as those of the first embodiment shown in FIG. 2 are denoted by the same reference numerals, and description thereof will be omitted. This embodiment is different from the first embodiment in that a function for allowing a user to specify sex, age, language, etc., which responds to a keyword input from the user is provided.
[0025]
Hereinafter, the operation of a portion different from the first embodiment will be described. The voice recognition processing unit 212 analyzes the volume, frequency, and the like of the voice when converting the voice emitted in the program to be recorded into text, and uses the data in the gender determination database 401 to convert the voice into text. The gender and age of the person who issued the message are determined, and stored in the text database 211 for each gender and age. It is assumed that the gender determination database 401 stores data such as the volume and frequency of voice according to gender and age. The user sets gender and age to be adopted as responses in advance. The request response search means 301 selects an optimal response keyword from a response database 302 for a keyword input by a user using a voice or a keyboard. The CPU 208 searches for a program including the selected response keyword from the set gender / age text database 211. When a program including the response keyword is found, for example, one sentence including the response keyword is reproduced by a sound emitted from the program. At this time, playback may be performed together with the video using the time information at the time of recording in the database. If the reproduced search result is a program desired by the user, an instruction to reproduce the entire program is input from the user interface 207 by voice or a keyboard. If not, the user is prompted to reproduce the next search result by voice or keyboard.
[0026]
Further, in the above description, the gender and age that the user adopts in advance as a response are set, but the gender and age information of the user are determined in voice recognition of a keyword input by voice from the user. If a woman is 20 years old, a response according to the information may be dynamically determined, such as 20 to 25 years old.
[0027]
Further, for example, when recording a program in a bilingual broadcast, two text data in Japanese and a foreign language are created and stored in separate databases (language 1402 and language 2 403), respectively. Alternatively, it is also possible to adopt a configuration in which Japanese and foreign languages can be selected as a response to a keyword input with a keyboard or the like.
[0028]
As described above, according to the present embodiment, it is possible to specify the gender, age, and language of the voice used for the pseudo-conversation of the broadcast program storage device, so that the program can be searched and viewed while enjoying the conversation itself. can do.
[0029]
FIG. 7 shows the configuration of the device according to the fourth embodiment of the present invention.
7, the same components as those of the first embodiment shown in FIG. 2 are denoted by the same reference numerals, and description thereof will be omitted. This embodiment is different from the first embodiment in that a program including the largest number of the first keywords is searched from a text database in response to a keyword input from a user (hereinafter, a first keyword), and the first database is searched. , A second keyword is randomly selected from among the programs containing the most keywords, the program containing the second keyword is searched from the text database, and the program containing the second keyword is reproduced. It is equipped with the function to do.
[0030]
Hereinafter, the operation of a portion different from the first embodiment will be described. In FIG. 7, a first keyword input by a user using a voice or a keyboard or the like is converted into a text by a voice recognition process 212, and the CPU 208 determines a program or a program title in which the first text is most frequently present. First, the program including the first keyword is searched from the text database 211. The keyword selecting means 501 sets, for example, a phrase included next to the first keyword as the second keyword from text data of a program including the first keyword most. Other selection methods of the second keyword include a person name, a place name, and random selection, and the selection method may be set in advance by a user. Also, as shown in FIG. 8, the position of the first keyword (in the case of FIG. 8, “ABC era”) in the text data of the program that contains the largest amount of the first keyword is within a predetermined distance range from the position of the first keyword. A method of using a certain person name, place name, or the like as the second keyword (“AAA room” in FIG. 8) is also conceivable. The predetermined distance can be arbitrarily set by the user. The CPU 208 searches the text database 211 for a program in which the second keyword is most frequently present or a program including the keyword in the program title, and reproduces the program hit in the search.
[0031]
FIG. 9 is a diagram illustrating a specific operation of the present embodiment.
The user inputs a keyword through the audio interface of the main broadcast program storage device (in the case of the figure, the keyword “ABC era”). The broadcast program storage device searches for a program that includes the keyword most or a program that includes the keyword in the program title. The second keyword is selected from the text database of the program hit in the search ("Program Z!" In the figure) ("AAA" in the figure). The broadcast program storage device searches for a program including the second keyword most or a program including the keyword in the program title, and reproduces a hit program (in the illustrated example, “AAA room”).
[0032]
That is, it is possible to enjoy the unexpectedness that the program “AAA room”, which cannot be predicted from the first keyword “ABC era”, is reproduced. As described above, according to the present embodiment, it is possible to enjoy not only a program that completely matches the first keyword input by the user but also other programs derived from the keyword.
[0033]
Also, by repeating the keyword selection in the third, fourth,..., It is conceivable that a program reproduction that cannot be imagined is performed from the first keyword, thereby providing a new way of enjoying television that is unexpected. Can be. In the repetition of the keyword selection, the user may be allowed to set the number of repetitions in advance.
[0034]
Also, in the repetition of the keyword selection, the second, third, fourth,... Link statuses are displayed from the first keyword, so that the user can know how the current program has been reproduced. You may let it be notified.
[0035]
As described above, the main broadcast program storage device stores the program information together with the video in the form of all of the emitted sounds in the form of a text, and when a user inputs a keyword using a voice or a keyboard or the like, the stored data is converted from the stored data. Searching for a program including the keyword, and responding to the search result with a sound emitted in the program, the user can determine whether the keyword is emitted in a news program or a variety program, for example. It is possible to grasp, and it is possible to further narrow down from programs including the keyword. Further, according to the present invention, a pseudo conversation with the main broadcast program storage device allows the user to discover and view the program while having fun.
[0036]
Further, according to the present invention, since the user can enjoy a program that does not completely match the first keyword input by the user but other programs derived from the keyword, program playback that cannot be imagined from the first keyword Is performed, a new way of enjoying the television can be provided.
[0037]
【The invention's effect】
According to the present invention, it is possible to provide a broadcast program storage device that is easy to use for a user.
[Brief description of the drawings]
FIG. 1 is a diagram illustrating a first embodiment of the present invention; FIG. 2 is a diagram illustrating a configuration of a broadcast program storage device in the first embodiment; FIG. 3 is a diagram illustrating a second embodiment of the present invention; FIG. 4 is a diagram for explaining a specific example in the second embodiment. FIG. 5 is a diagram for explaining a specific example in the second embodiment. FIG. 6 is a third embodiment of the present invention. FIG. 7 is a diagram for explaining a mode. FIG. 7 is a diagram for explaining a fourth embodiment of the present invention. FIG. 8 is a diagram for explaining a keyword selecting method in a fourth embodiment of the present invention. Diagram for explaining a specific example in the second embodiment.
101: antenna of BS / CS digital broadcasting station, 102: broadcast program storage device, 103 storage medium, 104: voice recognition unit, 105: user application unit, 106: TV, 201: antenna, 202: RF front end unit, 203: TS decoder unit, 204: MPEG2 Video Decoder unit, 205: Scan converter unit, 206: Database area, 207: User interface unit, 208: CPU, 209: AAC Decoder unit, 210: Audio Text Converter unit, 211: Text Database unit, 212: Voice recognition unit, 213: Dictionary database area, 301: Request response search means, 401: Sex determination database area, 402: Language 1 database area, 403: Language 2 database Source region, 501 ... keyword selection means

Claims (18)

A program content text conversion unit for storing broadcast program contents, recognizing audio uttered during the broadcast program, converting the text data into text data, and storing the text data as a keyword database; A broadcast program storage device characterized by being searchable. 2. The broadcast program storage device according to claim 1, further comprising: keyword input means for inputting a voice or key input request by the user; and request matching search means for searching the keyword database for a phrase matching the keyword in the request. A broadcast program storage device, comprising: output means for outputting the search result together with the program information as audio or text information to notify a user. 2. A means for converting program contents into text data in the broadcast program storage device according to claim 1, further comprising means for converting each of Japanese and foreign languages into text data for audio and multiplex broadcasting in Japanese and foreign languages, and creating a keyword database. In response to a user's voice or key input request, a keyword matching the keyword in the request is searched from the keyword database including Japanese and foreign languages, and the search result is combined with the program information with the voice or character information A broadcast program storage device, which informs a user of the broadcast program. 4. The broadcast program storage device according to claim 3, wherein keyword databases for Japanese and each foreign language are separately created, and a keyword database to be searched according to whether a user's voice or a key input request is in Japanese or a foreign language. A broadcast program storage device, comprising: means for dynamically switching the search result; and notifying the user of the search result in the same language as the input language. 2. A program content texting means in the broadcast program storage device according to claim 1, wherein said gender identification means recognizes whether the voice is uttered by a man or a woman, and the program content is converted into text data together with the gender information by said gender identification means. Request means for creating a keyword database, for a request by the user, the request including the gender information, request match search means for searching the keyword database for a phrase that matches the gender information and the keyword in the request, A broadcast program storage device comprising an output unit for outputting the search result together with the program information as audio or text information to notify a user. 6. The gender identification means in the broadcast program storage device according to claim 5, wherein the gender identification means has a function of identifying an age by a volume, a frequency, and the like of a sound emitted during the program, and the age information is used as a keyword database in addition to the gender information and the text data. A broadcast program storage device characterized by performing a search. 2. A program content text conversion means in a broadcast program storage device according to claim 1, further comprising means for converting date information into text data together with the program content to create a keyword database. Request matching search means for searching for a phrase that matches the keyword in the request from a keyword database of date information specified by the user, and output means for outputting the search result together with the program information as audio or text information to inform the user A broadcast program storage device comprising: 8. The broadcast program storage device according to claim 2, wherein request response search means for searching a keyword database for an optimum answer as a response to the user's request, and said answer as voice or character information. A broadcast program storage device comprising output means for outputting and informing a user. The broadcast program storage device according to any one of claims 2, 3, 5, and 7, further comprising a function of responding to a user's request with a voice over the stored program. apparatus. The broadcast program storage device according to any one of claims 2, 3, 5, and 7, further comprising a function of responding to a user request with audio and video on the stored program. Program storage device. The broadcast program storage device according to any one of claims 2, 3, 5, and 7, wherein a character selected or created by the user in advance to reply to the user's request responds by voice on the stored program. A broadcast program storage device, comprising: The broadcast program storage device according to any one of claims 2, 3, 5, and 7, further comprising a function of starting reproduction of a stored program including a responded keyword in response to an instruction by a user's voice or key input. Broadcast program storage device. 2. The broadcast program storage device according to claim 1, further comprising means for inputting a voice or key input request by a user and searching a keyword database for a program containing the most keywords in the request, wherein the keyword is most frequently used. A broadcast program storage device for starting reproduction of a program including the broadcast program. 14. The broadcast program storage device according to claim 13, further comprising: a link search unit that searches a keyword database for a program that includes the largest number of keywords in the title of the searched program. A broadcast program storage device characterized by starting reproduction of a program including many programs. 15. The broadcast program storage device according to claim 14, wherein the link search means of the broadcast program storage device repeats the number of times specified by the user. 14. The broadcast program storage device according to claim 13, wherein, in the text data of the program that has been searched for, a distance link search unit that extracts another keyword within an arbitrary range in the text data centering on the position of the keyword in the request. And starting reproduction of a program containing the most of the different keywords. 17. The broadcast program storage device according to claim 16, wherein the distance link search means of the broadcast program storage device repeats the number of times specified by the user. 17. The broadcast program storage device according to claim 14, further comprising a function of displaying a link status from a keyword of a first request by a user.

Images