Searching for segments based on an ontology
The invention pertains to methods, systems, and apparatus for identifying media items relevant to a selected subject matter, the method comprising determining the subject matter of a first media item, the first media item comprising at least one of audio content and video content, determining the classification within an ontology of the subject matter of the first media item, analyzing the ontology to identify other subject matter related to the subject matter of the first media item, and performing a search for other media items relevant to the subject matter of the first media item as a function of at least the other related subject matter according to the ontology.
1. A method comprising:
determining, by one or more computing devices, a search query by:
deriving one or more first words based on an analysis of video or audio of audiovisual content,
determining one or more second words based on one or more relationships that are defined at a location in an ontology, the location corresponding to at least one of the one or more first words, and the one or more relationships associating the at least one of the one or more first words to the one or more second words,
assigning a first weight to the at least one of the one or more first words, and
assigning a second weight, which is different from the first weight, to at least one of the one or more second words;
determining, using the search query, one or more audiovisual content segments; and
causing display of information associated with the one or more audiovisual content segments.
2. The method of claim 1 , wherein the determining, using the search query, the one or more audiovisual content segments comprises searching for one or more matching audiovisual content segments that have an attribute matching at least one of the one or more first words or at least one of the one or more second words, and wherein each of the one or more matching audiovisual content segments comprises a segment of content at a sub-asset level.
3. The method of claim 1 , wherein a first relationship of the one or more relationships is a parent-child relationship between a particular first word of the one or more first words and a particular second word of the one or more second words, and wherein the difference between the first weight and the second weight is dependent on the parent-child relationship.
4. The method of claim 1 , wherein a first relationship of the one or more relationships is a sibling relationship between a particular first word of the one or more first words and a particular second word of the one or more second words.
5. The method of claim 1 , further comprising:
storing a plurality of attribute sets, each attribute set of the plurality of attribute sets comprising one or more attributes, and each attribute set of the plurality of attribute sets corresponding to one of a plurality of knowledge domains;
determining a particular knowledge domain of the plurality of knowledge domains for the audiovisual content;
selecting a specific process for determining subject matter data as a function of the particular knowledge domain for the audiovisual content; and
selecting a set of attributes from the plurality of attribute sets as a function of the particular knowledge domain for the audiovisual content,
wherein the analysis of the video or audio of the audiovisual content comprises performing the specific process for determining the subject matter data and determining values for the set of attributes based on the audio or video of the audiovisual content.
6. The method of claim 5 , wherein determining the particular knowledge domain for the audiovisual content comprises determining the particular knowledge domain for the audiovisual content based on a title of the audiovisual content.
7. The method of claim 1 , wherein the audiovisual content comprises multimedia assets.
8. The method of claim 1 , wherein the audiovisual content comprises television programming.
9. The method of claim 1 , wherein the analysis of the audio or video of the audiovisual content comprises at least one of the following: analyzing audio within the audiovisual content for non-speech subject matter data, performing speech recognition on audio within the audiovisual content, performing optical character recognition on video of the audiovisual content, or performing video analytics on video of the audiovisual content.
10. A method comprising:
responsive to receiving a signal indicating activation of a search function during consumption of audiovisual content:
deriving one or more first words based on an analysis of video or audio of the audiovisual content;
determining, by a computing device, one or more second words based on one or more associations for at least one of the one or more first words in an ontology;
assigning a first weight to the at least one of the one or more first words;
assigning a second weight, which is different from the first weight, to at least one of the one or more second words;
determining one or more audiovisual content segments using the at least one of the one or more first words, the at least one of the one or more second words, the first weight, and the second weight; and
causing display of information associated with the one or more audiovisual content segments.
11. The method of claim 10 , wherein the determining the one or more audiovisual content segments comprises searching for one or more matching audiovisual content segments that have an attribute matching at least one of the one or more first words or at least one of the one or more second words, and wherein each of the one or more matching audiovisual content segments comprises a segment of content at a sub-asset level.
12. The method of claim 10 , wherein a first association of the one or more associations is a parent-child relationship between a particular first word of the one or more first words and a particular second word of the one or more second words, wherein the difference between the first weight and the second weight is dependent on the parent-child relationship.
13. The method of claim 10 , wherein a first association of the one or more associations is a sibling relationship between a particular first word of the one or more first words and a particular second word of the one or more second words.
14. The method of claim 10 , further comprising:
storing a plurality of attribute sets, each attribute set of the plurality of attribute sets comprising one or more attributes, and each attribute set of the plurality of attribute sets corresponding to one of a plurality of knowledge domains;
determining a particular knowledge domain of the plurality of knowledge domains for the audiovisual content;
selecting a specific process for determining subject matter data as a function of the particular knowledge domain for the audiovisual content; and
selecting a set of attributes from the plurality of attribute sets as a function of the particular knowledge domain for the audiovisual content,
wherein the analysis of the video or audio of the audiovisual content comprises performing the specific process for determining the subject matter data and determining values for the set of attributes based on the audio or video of the audiovisual content.
15. The method of claim 14 , wherein the determining the particular knowledge domain for the audiovisual content comprises determining the particular knowledge domain for the audiovisual content based on a title of the audiovisual content.
16. The method of claim 10 , wherein the audiovisual content comprises multimedia assets.
17. The method of claim 10 , wherein the audiovisual content comprises television programming.
18. The method of claim 10 , wherein the analysis of the audio or video of the audiovisual content comprises at least one of the following: analyzing audio within the audiovisual content for non-speech subject matter data, performing speech recognition on audio within the audiovisual content, performing optical character recognition on video of the audiovisual content, or performing video analytics on video of the audiovisual content.
19. A method comprising:
determining, by one or more computing devices, a search query by:
deriving one or more first words based on an analysis of video or audio of audiovisual content, and
determining one or more second words based on one or more associations for at least one of the one or more first words in an ontology;
performing a search for audiovisual content segments using the search query; and
causing display of one or more results of the search.
20. The method of claim 19 , further comprising:
storing a plurality of attribute sets, each attribute set of the plurality of attribute sets comprising one or more attributes, and each attribute set of the plurality of attribute sets corresponding to one of a plurality of knowledge domains;
determining a particular knowledge domain of the plurality of knowledge domains for the audiovisual content;
selecting a specific process for determining subject matter data as a function of the particular knowledge domain for the audiovisual content; and
selecting a set of attributes from the plurality of attribute sets as a function of the particular knowledge domain for the audiovisual content;
wherein the analysis of the video or audio of the audiovisual content comprises performing the specific process for determining the subject matter data and determining values for the set of attributes based on the audio or video of the audiovisual content.