Information processing apparatus, information processing method, and computer program

1. An information processing apparatus configured to generate metadata corresponding to content comprising:

a data output section configured to output reproduced content;

a data input section configured to enter at least one of image data and voice data of a user viewing content is entered;

a control section configured to determine an action for said user on the basis of information entered through said data input section and reproduced content information;

an interaction execution section configured to execute an action determined by said control section;

an interaction metadata generation section configured to analyze at least one of input information of a user's image and a user's voice including a result of said interaction obtained through said data input section, thereby generating metadata corresponding to reproduced content; and

a content control section configured to record said metadata generated by said interaction metadata generation section as metadata that corresponds to said reproduced content.

2. The information processing apparatus according to claim 1 , wherein said interaction metadata generation section is configured to execute at least one of identification and recognition processing operations of face identification processing, general-object identification processing, smiling face identification processing, speaker identification processing, voice recognition processing, laughing voice identification processing, screaming voice identification processing, and crying voice identification processing, thereby extracting metadata on the basis of these identification and recognition processing operations.

3. The information processing apparatus according to claim 1 , further comprising:

a metadata generation section configured to generate metadata based on image data and voice data making up content,

said metadata generation section configured to generate content-base metadata by matching one of image data and voice data forming content with dictionary data, said matching being executed by selecting an applicable dictionary on the basis of content information estimated on the basis of said metadata generated by said interaction metadata generation section.

4. The information processing apparatus according to claim 3 , wherein said metadata generation section is configured to execute at least one of identification and recognition processing operations of face identification processing, general-object identification processing, smiling face identification processing, speaker identification processing, voice recognition processing, laughing voice identification processing, screaming voice identification processing, and crying voice identification processing, thereby extracting metadata on the basis of these identification and recognition processing operations.

5. The information processing apparatus according to claim 1 , further comprising:

a metadata integration section configured to relate metadata generated in said information processing apparatus with reproduction time information of reproduced content.

6. The information processing apparatus according to claim 1 , wherein said control section generates a question to said user as an action for said user on the basis of input information obtained through said data input section and reproduced content information;

said interaction execution section outputs, through said data output section, said question determined by said control section; and

said interaction metadata generation section obtains one of a reaction and an answer to said question through said data input section to generate metadata corresponding to said reproduced content on the basis of the analysis of the obtained information.

7. An information processing method configured to generate metadata corresponding to content in an information processing apparatus comprising the steps of:

outputting reproduced content;

entering at least one of image data and voice data of a user viewing content is entered;

determining an action for said user on the basis of information entered through said data input step and reproduced content information;

executing an action determined by said control step;

analyzing at least one of input information of a user's image and a user's voice including a result of said interaction obtained in said data input step, thereby generating metadata corresponding to reproduced content; and

recording said metadata generated by said interaction metadata generation step as metadata that corresponds to said reproduced content.

8. The information processing method according to claim 7 , wherein said interaction metadata generation step executes at least one of identification and recognition processing operations of face identification processing, general-object identification processing, smiling face identification processing, speaker identification processing, voice recognition processing, laughing voice identification processing, screaming voice identification processing, and crying voice identification processing, thereby extracting metadata on the basis of these identification and recognition processing operations.

9. The information processing method according to claim 7 , further comprising the step of:

generating metadata based on image data and voice data making up content,

said metadata generating step being configured to generate content-base metadata by matching one of image data and voice data forming content with dictionary data, said matching being executed by selecting an applicable dictionary on the basis of content information estimated on the basis of said metadata generated by said interaction metadata generation step.

10. The information processing method according to claim 9 , wherein said metadata generating step executes at least one of identification and recognition processing operations of face identification processing, general-object identification processing, smiling face identification processing, speaker identification processing, voice recognition processing, laughing voice identification processing, screaming voice identification processing, and crying voice identification processing, thereby extracting metadata on the basis of these identification and recognition processing operations.

11. The information processing method according to claim 7 , further comprising the step of:

relating metadata generated in said information processing apparatus with reproduction time information of reproduced content.

12. The information processing method according to claim 7 , wherein said control step generates a question to said user as an action for said user on the basis of input information obtained through said data input step and reproduced content information;

said interaction execution step outputs, through said data output section, said question determined by said control step; and

said interaction metadata generation step obtains one of a reaction and an answer to said question through said data input step to generate metadata corresponding to said reproduced content on the basis of the analysis of the obtained information.