Media system for generating playlist of multimedia files
Disclosed is a method and system for dynamically generating a playlist of multimedia files for a user based upon a mood of the user. The system comprises a mood detection module, a tag allocation module, and a playlist generation module. The mood detection module is configured to determine the mood of the user based upon the one or more emotion tags allocated to records of the user. The tag allocation module is configured to categorize the at least one multimedia file under one or more emotion tags based upon the weights assigned to the one or more emotion tags. The playlist generation module is configured to dynamically generate the playlist of multimedia files based upon the mood of the user and the categorization of the at least one multimedia file under one or more emotion tags.
1. A system comprising:
a processor; and
a memory coupled to the processor for executing a plurality of modules present in the memory, the plurality of modules comprising:
a mood detection module configured to
mine records associated with a user from one or more sources comprising at least one of social media, a personal information database, and a stream database associated with the user, wherein the records comprises user activity information on the social media, health parameters of the user and personal information of the user and wherein the stream database comprises information pertaining to the health parameters of the user, and wherein the health parameters are fetched from at least one biological sensor attached to the user for monitoring health of the user;
compare each word of the records with each keyword present in predefined lists of keywords, wherein each predefined list of keywords is indicative of an emotion;
allocate one or more emotion tags to the records mined from the one or more sources based on the comparison; and
determine a mood of the user based upon the one or more emotion tags allocated to the records; and
a tag allocation module configured to associate at least one multimedia file with a vector;
compare each word of a content of the at least one multimedia file with each keyword present in the predefined lists of keywords, wherein each predefined list of keywords is indicative of the emotion, and wherein the vector is indicative of a relationship of each word of the at least one multimedia file with the each emotion;
allocate one or more emotion tags to the at least one multimedia file based upon the comparison;
assign weights to each of the one or more emotion tags allocated to the at least one multimedia file, wherein the weights are assigned based upon a relevance of the content of the at least one multimedia file to the one or more emotion tags; and
categorize the at least one multimedia file under one or more emotion tags based upon the weights assigned to the one or more emotion tags; and
a playlist generation module configured to
dynamically generate a playlist of multimedia files based upon the mood of the user and the categorization of the at least one multimedia file under the one or more emotion tags.
2. The system of claim 1 , wherein the social media comprises at least one of social networking websites, review/feedback websites, and blogs being visited by the user.
3. The system of claim 1 , wherein the personal information database comprises information pertaining to at least one of age, e-mail, web-browsing history, peers, Rich Site Summary (RSS) feeds, and environment associated with the user.
4. The system of claim 1 , wherein the at least one biological sensor comprises at least one of an electro-cardiogram sensor, a piezo film sensor, a thermal sensor, and an electro-encephalogram sensor.
5. The system of claim 1 , wherein the mood detection module is further configured to generate a record document for keeping track of the mood of the user after every predefined periodic interval.
6. The system of claim 1 , wherein the content of the at least one multimedia file comprises at least one of lyrics, subtitles, and dialogues.
7. The system of claim 1 , wherein the relevance of the content of the at least one multimedia file to the one or more emotion tags is determined using a term frequency-inverse document frequency (TF-IDF) technique.
8. A method comprising:
mining records associated with a user from one or more sources comprising at least one of social media, a personal information database, and a stream database associated with the user, wherein the records comprises user activity information on the social media, health parameters of the user and personal information of the user and wherein the stream database comprises information pertaining to the health parameters of the user, and wherein the health parameters are fetched from at least one biological sensor attached to the user for monitoring a health of the user;
comparing each word of the records with each keyword present in predefined lists of keywords, wherein each predefined list of keywords is indicative of an emotion;
allocating one or more emotion tags to the records mined from the one or more sources based on the comparison; and
determining a mood of the user based upon the one or more emotion tags allocated to the records;
associating at least one multimedia file with a vector;
comparing each word of a content of the least one multimedia file with each keyword present in the predefined lists of keywords, wherein each predefined list of keywords is indicative of the emotion, and wherein the vector is indicative of a relationship of each word of the at least one multimedia file with the each emotion;
allocating one or more emotion tags to the at least one multimedia file based upon the comparison;
assigning weights to each of the one or more emotion tags allocated to the at least one multimedia file, wherein the weights are assigned based upon a relevance of the content of the at least multimedia file to the one or more emotion tags;
categorizing the at least one multimedia file under the one or more emotion tags based upon the weights assigned to the one or more emotion tags; and
dynamically generating a playlist of multimedia files based upon the mood of the user and the categorization of the at least one multimedia file under the one or more emotion tags.
9. The method of claim 8 , wherein the social media comprises at least one of social networking websites and blogs being used by the user.
10. The method of claim 8 , wherein the personal information database comprises information pertaining to at least one of age, e-mail, web-browsing history, peers, Rich Site Summary (RSS) feeds, and environment associated with the user.
11. The method of claim 8 , wherein the at least one biological sensor comprises at least one of an electro-cardiogram sensor, a piezo film sensor, a thermal sensor, and an electro-encephalogram sensor.
12. The method of claim 8 , further comprising:
generating a record document for keeping track of the mood of the user after every predefined periodic interval.
13. The method of claim 8 , wherein the content of the multimedia file comprises at least one of lyrics, subtitles, and dialogues.
14. The method of claim 8 , wherein the relevance of the content of the at least one multimedia file to the one or more emotion tags is determined using a term frequency-inverse document frequency (TF-IDF) technique.