Assessing adherence fidelity to behavioral interventions using interactivity and natural language processing

A method of interacting with a user by a computing system, the method comprising:

• commencing, with the user, a behavior intervention designed to cause an increase in emotional well-being of the user, the behavior intervention having a plurality of conditions to be satisfied;
• receiving, via at least one sensor, input data from the user during the behavior intervention;
• performing, during the behavior intervention, on at least a portion of the received input data having text, semantic analysis to identify terms that satisfy the plurality of conditions;
• determine, during the behavior intervention, based on the identified terms, how many of the plurality of conditions are satisfied;
• assessing, during the behavior intervention, based on the determination of how many of the plurality of conditions are satisfied, a level of adherence to the behavior intervention;
• generating a prompt, during the behavior intervention, based on the assessed level of adherence, designed to elicit, from the user, a response specific to satisfying one or more of the plurality of conditions not satisfied and to advance level of adherence towards completion;
• including in the behavior intervention a programmed branching logic for responding to the received input data;
• and
• assigning, upon (i) a determination that one or more of the plurality of conditions have yet to be satisfied and (ii) generating the prompt designed to elicit, from the user, the response specific to satisfying the one or more of the plurality of conditions not satisfied, a priority to the generated prompt over a prearranged next-in-line prompt such that the generated prompt overrides the programmed branching logic for responding to the received input data to direct the user toward maximized adherence.

A computing system for interacting with a user, the computing system comprising:

• at least one processor;
• at least one sensor;
• and
• at least one memory storing executable software which, when executed by the at least one processor, causes the at least one processor to:
• commence, with a user, an empathy behavior intervention designed to cause an increase in expressing empathy by the user, the empathy behavior intervention having a plurality of conditions to be satisfied;
• receive, via the at least one sensor, input data from the user during the behavior intervention;
• perform, during the empathy behavior intervention, on at least a portion of the received input data having text, semantic analysis to identify terms that satisfy the plurality of conditions;
• determine, during the behavior intervention, based on the identified terms, how many of the plurality of conditions are satisfied;
• and
• assess, during the empathy behavior intervention, based on the determination of how many of the plurality of conditions are satisfied, a level of adherence to the behavior intervention,
• wherein the executable software stored in the at least one memory is adapted to cause the at least one processor to generate a prompt, during the empathy behavior intervention, based on the assessed level of adherence, designed to elicit, from the user, a response specific to satisfying one or more of the plurality of conditions not satisfied and to advance the empathy behavior intervention towards completion;
• and
• wherein the behavior intervention further includes a programmed branching logic for responding to the received input data, and wherein the executable software stored in the at least one memory is further adapted to cause the at least one processor to, upon:
• (i) a determination that one or more of the plurality of conditions have yet to be satisfied;
• and
• (ii) generating the prompt designed to elicit, from the user, the response specific to satisfying the one or more of the plurality of conditions not satisfied,
• assign a priority to the generated prompt over a prearranged next-in-line prompt such that the generated prompt overrides the programmed branching logic for responding to the received input data to direct the user toward maximized adherence.