Natural conversation storytelling system
The present application discloses a multi-media interactive story-telling system that provides natural conversational interactions between a human user and a contributor who appears in multi-media recordings. The multi-media interactive story-telling system includes an intake device for recording interview sessions in which a contributor tells a life story about her life experience. The contributor may rely on a script when creating the life story. The multi-media interactive story-telling system further comprises storage devices for storing the recorded interview sessions and processors for organizing the recorded interview sessions. The multi-media interactive story-telling system further comprises an interactive device for retrieving and playing a recorded interview session in response to a query from a user.
1. A multi-media interactive story-telling system, said system comprising:
an interactive device configured to retrieve and play a recorded session of a contributor stored on storage devices in response to a query from a user, wherein the query is interpreted as being directed to an interactive story of a contributor and the recorded session retrieved by the interactive device correlates to the interactive story of the contributor to which the query is directed;
comparing the query to a plurality of existing queries and using machine learning to identify similar wording and similar responses,
using the machine learning to match the query to retrieve and play the recorded session; and
wherein the interactive device uses a machine learning algorithm to predict a follow-up query and to retrieve and cache a predicted recorded session corresponding to a response to the follow-up query during the play of the recorded session, wherein the machine learning algorithm is trained on past patterns of inquiries.
2. The multi-media interactive story-telling system of claim 1 , wherein the recorded session is edited by the contributor before being committed to the storage devices.
3. The multi-media interactive story-telling system of claim 1 , wherein the recorded session can be edited after being committed to the storage devices.
4. The multi-media interactive story-telling system of claim 1 , wherein the recorded session is augmented by one or more auxiliary files before being committed to the storage device, and wherein the one or more auxiliary files include photos, documents or media files.
5. The multi-media interactive story-telling system of claim 1 , wherein recorded session is transcribed and one or more keywords are extracted from a transcript of the recorded session for cataloguing and retrieving.
6. The multi-media interactive story-telling system of claim 5 , wherein the transcript is stored as metadata of the recorded session.
7. The multi-media interactive story-telling system of claim 5 , wherein the transcript is stored in a natural language database.
8. The multi-media interactive story-telling system of claim 5 , wherein the one or more keywords are stored as metadata of recorded session, and wherein the metadata further include timestamps and location data.
9. The multi-media interactive story-telling system of claim 5 , wherein the recorded session is automatically transcribed by speech-to-text translation.
10. A multi-media interactive device, said multi-media interactive device comprising:
an input device that features a user interface, said input device configured to receive a query from a user;
an output device for playing back recorded interview sessions, wherein said interview sessions are recorded by one or more contributors;
processors configured to retrieve a recorded interview session in response to the query, wherein in the recorded interview session an answer from the one or more contributors correlates to the query;
comparing the query to a plurality of existing queries and using machine learning to identify similar wording and similar responses;
using the machine learning to match the query to retrieve and play the answer; and
wherein the interactive device uses a machine learning algorithm to predict a most-likely follow-up query following the query and to retrieve and cache a predicted answer to the follow-up query during a playback of the answer from the recorded interview session, wherein the machine learning algorithm is trained on past patterns of inquiries.
11. The multi-media interactive device of claim 10 , wherein the processors are configured to retrieve the recorded interview session in which the question the one or more contributors answer matches the query.
12. The multi-media interactive device of claim 10 , wherein a list of candidate contributors is presented in the user interface on the input device for the user to select one contributor from the list, and wherein only interview sessions featuring the selected contributor are retrieved and played back.
13. The multi-media interactive device of claim 12 , wherein the input device is a touch-screen, a microphone, a smart glass, or a virtual assistant device.
14. The multi-media interactive device of claim 12 , wherein the list of candidate contributors is generated based on common interests between the user and each candidate contributor.
15. The multi-media interactive device of claim 12 , wherein the list of candidate contributors is generated based on one or more of the following factors: popularity, subject domain, keywords, talents, experience, and names.
16. The multi-media interactive device of claim 12 , wherein the list of candidate contributors is generated based on the emotion of the user detected by the multi-media interactive device.
17. The multi-media interactive device of claim 10 , wherein the processors are configured to retrieve an auxiliary file along with the interview session for playing back.