System and method for scoring and selection of communication notification presentation through contextual feedback
A method for computer control of online social interactions based on conversation processing. A portion of a conversation with a given user is recorded, stored in memory, and processed so as to influence subsequent interactions. These may include audio or other contextualized annunciations of subsequent telephone calls. Other modes addressing conversational processing for social purposes can result in interwoven conversation guided among threads of interest, advertising and incented participation of conversational content and placement. The invention is capable of implementation in telecommunications systems such as cellular, local exchange, and VOIP, and in combination with other forms of internet-based telecommunication, including smart phones and adaptive forums chat rooms.
1. A system for scoring and selection of communication notification presentation through contextual feedback, the system comprising:
at least one data source including an original datastream and associated contextual datastream, where the contextual datastream are further associated with the original datastream by time sequence and further include text, gesture, sound, touch screens, and emotion sensors;
a recognizer coupled to the data source for extracting at least one feature from the original datastream and the associated contextual datastream and for synchronizing the at least one feature with the original datastream by time;
a scoring preprocessor coupled to the recognizer for specifying potential notifications and confidence scores, where the potential notifications include portions of the original datastream with beginning and ending points identified by the extracted features from the associated contextual datastream, and confidence scores are based on a degree of confirmation from the associated contextual datastream;
a comparator coupled to the scoring preprocessor for selecting a notification among, combining, and integrating said potential notifications to specify one for use based on the confidence scores of said potential notifications; and
a feedback manager for gauging the effectiveness of the selected notification so as to adjust subsequent operation of said scoring preprocessor where said feedback includes user evaluation, surveys, reporting metrics, medical compliance requirements, and call-answering frequencies.
2. The system of claim 1 , wherein:
the notification used is varied and refined through multiple occurrences based on feedback from the feedback manager;
the data sources include at least one of:
text,
sound including background and cues,
video,
conversation including human and simulated persons in a virtual conference,
social media, including adaptive forums,
gesture including hand and facial recognition, and
location and motion of people and devices;
the recognizer includes sound and gesture cues;
the scoring preprocessor output includes post-processing parameters for specification related to presentation of choices to the user;
the comparator includes presenting choices to a user; and
the feedback manager includes interactive parametric adjustments by the user.
3. The system of claim 2 wherein the feedback manager uses neural network learning and classification for gauging the effectiveness of the selected notification.
4. The system of claim 2 wherein the sound is voice and is analyzed for prosody.
5. The system of claim 3 wherein the feedback manager uses feedforward neural network learning and classification for gauging the effectiveness of the selected notification.
6. The system of claim 1 wherein the data sources further include biometric sensors, facial recognition, accelerometers, GPS, and multipoint touchscreens.
7. The system of claim 6 wherein the biometric sensors include somatic data as an indicator of emotional state and intent.
8. The system of claim 1 wherein the emotion sensors further include polygraph-type sensors for obtaining information about emotional state and intent.
9. The system of claim 1 wherein the scoring preprocessor uses somatic data to judge a candidate notification presentation.
10. The system of claim 1 wherein the gesture data source further includes a processor for feature extraction where an associated type of sensors includes cameras for video and touch sensitive surfaces.
11. The system of claim 1 wherein the sound data source further includes at least one recognizer that includes speech to text and general sound recognition where the recognized sound is not a spoken word or part thereof.
12. The system of claim 1 wherein the scoring preprocessor uses binary scoring to judge the candidate communication notification.
13. The system of claim 1 wherein the scoring preprocessor uses numeric scoring to judge a candidate communication notification.
14. The system of claim 1 wherein the scoring preprocessor relates at least two features from the recognizer to produce a score.
15. The system of claim 1 wherein the scoring preprocessor uses at least one emotion feature from the recognizer as a speech marker to produce a score.
16. The system of claim 1 wherein the comparator selects a notification from the potential notifications by selecting most overlapped area among the potential notifications.
17. The system of claim 1 wherein the feedback manager further uses interactive parametric adjustments by the user, artificial intelligence algorithms, artificial evolution, and neural networks to gauge the effectiveness of the notification.
18. The system of claim 1 wherein the communication notification presentation is a computer controlled reconveyance of a conversation segment without the user's control.
19. The system of claim 1 wherein the communication notification presentation is a reminder ring.
20. The system of claim 1 wherein the feedback manager further uses interactive parametric adjustments or profile information created by the user, artificial intelligence algorithms, artificial evolution, and neural networks to gauge the effectiveness of the notification and to modify a user profile.
21. A method for scoring and selection of communication notification presentation through contextual feedback, the steps comprising:
receiving an original datastream from at least one data source, the original datastream being associated with at least one associated contextual datastream by time sequence, said contextual datastream further including text, gesture, sound, touch screens, and emotion sensors;
extracting at least one feature from the original datastream and the associated contextual datastream;
synchronizing the at least one feature with the original datastream by time;
specifying potential notifications and confidence scores, where the potential notifications include portions of the original datastream with beginning and ending points identified by the extracted features from the associated contextual datastream, and confidence scores are based on a degree of confirmation from the associated contextual datastream;
selecting a notification among, combining, and integrating said potential notifications to specify one for use based on the confidence scores of said potential notifications; and
and gauging the effectiveness of the selected notification so as to adjust subsequent operation of said scoring preprocessor where said feedback includes user evaluation, surveys, reporting metrics, medical compliance requirements, and call-answering frequencies.