Metadata generating apparatus

• US 7,519,618 B2
• Filed: 12/06/2005
• Issued: 04/14/2009
• Est. Priority Date: 12/08/2004
• Status: Expired due to Fees

• Current Assignee: Seiko Epson Corporation (Seiko Group)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: Hyuga, Takashi, Nagahashi, Toshinori
• Primary Examiner(s): Mahmoudi; Tony
• Assistant Examiner(s): Truong; Dennis
• Application Number:
  US11/294,719
• Publication Number:
  US 20060235869A1
• Time in Patent Office: 1,225 Days
• Field of Search: 348/231.2, 348/3, 348/4, 707/704, 707/104.1, 707/1, 707/100
• US Class Current: 1/1
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A metadata generating apparatus includes: a private-content-information creating unit that creates content information of an individual; a public-content-information collecting unit that collects public content information for which metadata for retrieval is created; a keyword extracting unit that extracts a keyword, which forms a basis of the metadata for retrieval, from the public content information collected by the public-content-information collecting unit; and a metadata generating unit that generates metadata for retrieval for a private content, which is created by the private-content-information creating unit, on the basis of the keyword extracted by the keyword extracting unit.

Claims

1. A metadata generating apparatus having a processor and a hard disk device, the apparatus comprising:

a private-content-information creating unit that creates content information of an individual;

an information collection setting unit that collects setting information for collection of public content information from a public broadcast, the information collection setting unit including a collection period setting section in which a collection period for the collection of public content information from the public broadcast is set and a type selecting section in which a type of public content information for the collection of public content information from the public broadcast is set, the public broadcast including a news program;

a public-content-information collecting unit that collects public content information for which metadata for retrieval is created from the public broadcast based on the collection period set in the collection period setting section and the type of public content information set in the type selecting section, the public-content-information collecting unit executing sound recognition processing of the news program, including a frequency analysis, a phoneme recognition, a word recognition, and a sentence recognition of the news program, to generate text data of the news program, the sound recognition processing being performed for a predetermined period at a beginning of the news program, said predetermined period corresponding to an introduction period of the news program before insertion of a commercial;

a keyword extracting unit that extracts a keyword, which forms a basis of the metadata for retrieval, from the public content information, including the text data of the news program, collected by the public-content-information collecting unit; and

a metadata generating unit that generates metadata with the processor and stores the metadata in the hard disk device for retrieval for a private content, which is created by the private-content-information creating unit, on the basis of the keyword extracted by the keyword extracting unit and the public content information, including the text data of the news program, collected by the public-content-information collecting unit.

2. A metadata generating apparatus according to claim 1, wherein

the public-content-information collecting unit collects public content information including metadata, and

the keyword extracting unit includes:

a metadata analyzing unit that analyzes metadata included in the public content information collected by the public-content-information collecting unit; and

a morphological analysis unit that subjects the public content information to morphological analysis on the basis of a result of the analysis of the metadata analyzing unit to extract a keyword.

3. A metadata generating apparatus according to claim 1, wherein

the keyword extracting unit has a keyword storing unit that stores a keyword for which metadata for retrieval is generated, and

the keyword extracting unit selects a keyword, which coincides with the keyword stored in the keyword storing unit, among keywords extracted from the public content information as an object keyword.

4. A metadata generating apparatus according to claim 3, wherein the keyword storing unit stores the keyword extracted from the public content information.

5. A metadata generating apparatus according to claim 1, wherein the metadata generating unit selects a keyword for retrieval on the basis of a predetermined degree of appropriateness from keywords extracted by the keyword extracting unit and generates metadata for retrieval on the basis of the keyword for retrieval selected.

6. A metadata generating apparatus according to claim 1, wherein the metadata generating unit sets a high appearance frequency as the predetermined degree of appropriateness and selects a keyword with a high appearance frequency as a keyword for retrieval.

7. A metadata generating apparatus having a processor and a hard disk device, the apparatus comprising:

a private-content-information creating unit that creates content information of an individual;

an information collection setting unit that collects setting information for collection of public content information from a public broadcast, the information collection setting unit including a collection period setting section in which a collection period for the collection of public content information from the public broadcast is set and a type selecting section in which a type of public content information for the collection of public content information from the public broadcast is set, the public broadcast including a news program;

a public-content-information collecting unit that collects public content information including metadata for which metadata for retrieval is created from the public broadcast based on the collection period set in the collection period setting section and the type of public content information set in the type selecting section, the public-content-information collecting unit executing sound recognition processing of the news program, including a frequency analysis, a phoneme recognition, a word recognition, and a sentence recognition of the news program, to generate text data of the news program, the sound recognition processing being performed for a predetermined period at a beginning of the news program, said predetermined period corresponding to an introduction period of the news program before insertion of a commercial;

a keyword input unit that inputs a keyword;

a public-content-information extracting unit that extracts public content information from the public broadcast, including the text data of the news program, including metadata describing a keyword coinciding with the keyword inputted by the keyword input unit; and

a metadata generating unit that generates the metadata with the processor, which is included in the public content information, including the text data of the news program, extracted by the public-content-information collecting unit, as metadata for storage in the hard disk device and retrieval for private content information.