US 12,340,791 B1
Enhanced voice-based presentation of user sentiment
Layne Christopher Price, Seattle, WA (US); and Bertrand Haas, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 10, 2021, as Appl. No. 17/344,688.
Int. Cl. G10L 15/02 (2006.01)
CPC G10L 15/02 (2013.01) [H04M 2250/12 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by at least one processor of a device comprising at least a portion of a perimeter reserved for indicating times corresponding to sentiment levels and energy levels, first voice data of a person at a first time;
receiving, by the at least one processor, second voice data of the person at a second time;
determining, by the at least one processor, based on the first voice data, a first energy level of the person at the first time;
determining, by the at least one processor, based on the second voice data, a second energy level of the person at the second time;
determining, by the at least one processor, based on the first voice data, a first sentiment level of the person at the first time;
determining, by the at least one processor, based on the second voice data, a second sentiment level of the person at the second time;
selecting, by the at least one processor, a first presentation color indicative of the first sentiment level;
selecting, by the at least one processor, a second presentation color indicative of the second sentiment level;
determining, by the at least one processor, based on the first energy level, a first light intensity of the at least a portion of the perimeter with which to present the first presentation color;
determining, by the at least one processor, based on the second energy level, a second light intensity of the at least a portion of the perimeter with which to present the second presentation color;
selecting, by the at least one processor, a first location of the at least a portion of the perimeter where a first indication of the first presentation color is to be presented, wherein the first location is indicative of the first time when the first energy level and the first sentiment level were detected using the first voice data;
selecting, by the at least one processor, a second location of the at least a portion of the perimeter where a second indication of the second presentation color is to be presented, wherein the second location is indicative of the second time when the second energy level and the second sentiment level were detected using the second voice data; and
presenting, by the at least one processor, the first indication of the first presentation color and the first time using the first location, and the second indication of the second presentation color and the second time using the second location, wherein the first presentation color is presented using the first light intensity, wherein the second presentation color is presented using the second light intensity, and wherein the first indication and the second indication are presented concurrently.