| CPC G06F 40/284 (2020.01) [G06Q 30/0281 (2013.01); G10L 15/1815 (2013.01)] | 20 Claims |
|
1. A conversational system comprising:
a computer system having one or more computer processors, one or more data stores, and one or more transceivers, wherein the computer system is programmed with one or more sets of instructions that, when executed by the one or more computer processors, cause the computer system to execute operations comprising:
determining a macro goal for a conversational experience;
selecting an individual for participation in the conversational experience;
initiating the conversational experience with the individual, wherein initiating the conversational experience comprises transmitting first data comprising a first set of words to a personal device associated with the individual over one or more networks at a first time;
receiving second data from the personal device at a second time, wherein the second data represents at least a second set of words, and wherein the second time follows the first time;
processing the second data to recognize the second set of words;
establishing a first micro goal for the conversational experience based at least in part on the second set of words, at least one acoustic feature of the second data, and the macro goal, wherein the at least one acoustic feature of the second data comprises a pitch, a duration or an intensity of the second data;
selecting at least a third set of words and a tonality for presenting the third set of words to the individual based at least in part on the first micro goal and the second set of words, wherein the third set of words comprises a response to the second set of words, and wherein the tonality for presenting the third set of words comprises at least one of a tone by which the third set of words is to be presented to the individual, a pace at which the third set of words is to be presented to the individual, an emphasis pattern for presenting the third set of words to the individual, and a sentiment to be expressed when presenting the third set of words to the individual;
transmitting third data to the personal device at a third time, wherein the third data comprises the third set of words and data regarding the tonality for presenting the third set of words, and wherein the third time follows the second time;
causing at least the third set of words to be presented to the individual in accordance with the tonality for presenting the third set of words by way of the personal device;
receiving fourth data from the personal device at a fourth time, wherein the fourth data represents at least a fourth set of words, and wherein the fourth time follows the third time;
processing the fourth data to recognize the fourth set of words; and
determining that at least the first micro goal has been achieved based at least in part on the fourth set of words;
establishing a second micro goal for the conversational experience based at least in part on the fourth set of words, at least one acoustic feature of the fourth data, and the macro goal, wherein the at least one acoustic feature of the fourth data comprises a pitch, a duration or an intensity of the fourth data;
selecting at least a fifth set of words and a tonality for presenting the fifth set of words to the individual based at least in part on the second micro goal and the fourth set of words, wherein the fifth set of words comprises a response to the fourth set of words, and wherein the tonality for presenting the fifth set of words comprises at least one of a tone by which the fifth set of words is to be presented to the individual, a pace at which the fifth set of words is to be presented to the individual, an emphasis pattern for presenting the fifth set of words to the individual, and a sentiment to be expressed when presenting the fifth set of words to the individual;
transmitting fifth data to the personal device at a fifth time, wherein the fifth data comprises the fifth set of words and data regarding the tonality for presenting the fifth set of words, and wherein the fifth time follows the fourth time;
causing at least the fifth set of words to be presented to the individual in accordance with the tonality for presenting the fifth set of words by way of the personal device;
receiving sixth data from the personal device at a sixth time, wherein the sixth data represents at least a sixth set of words, and wherein the sixth time follows the fifth time;
processing the sixth data to recognize the sixth set of words; and
determining that at least the macro goal has been achieved based at least in part on the sixth set of words; and
in response to determining that at least the macro goal has been achieved based at least in part on the sixth set of words,
storing an indication that the macro goal has been achieved in association with the individual in the one or more data stores.
|