Intelligent recommendation of convenient event opportunities

A system for implementing intelligent recommendations of convenient event opportunities, comprising:

• one or more computers with executable instructions that when executed cause the system to:
• identify a group of entities for one or more event opportunities or identifying the one or more event opportunities for the group of entities according to one or more entity selection criteria and one or more event criteria;
• execute machine learning logic to train, in a first stage, a suggested opportunity model using observed behavior, inclusive of activities of daily living (ADL), of each entity in the group of entities as input;
• match, based on the suggested opportunity model, the one or more event opportunities and the group of entities according to a level of convenience for attending the one or more event opportunities of the group of entities;
• rank the one or more matching event opportunities according to the level of convenience;
• suggest the ranked one or more matching event opportunities to the group of entities, wherein the one or more matching event opportunities each require at least one of the group of entities to perform and complete a plurality of actions in a predefined sequence to participate in a final event, and wherein suggesting the ranked one or more matching event opportunities includes suggesting scheduling arrangements for the at least one of the group of entities to perform the plurality of actions in the predefined sequence based on the level of convenience determined for each of the plurality of actions;
• and
• execute the machine learning logic to train, in a second stage, the suggested opportunity model using feedback data collected subsequent to suggesting the ranked one or more matching event opportunities, wherein the suggested opportunity model is iteratively updated using the feedback data to enhance an accuracy of future suggested event opportunities.

A computer program product for implementing intelligent recommendations of convenient event opportunities by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

• an executable portion that identifies a group of entities for one or more event opportunities or identifying the one or more event opportunities for the group of entities according to one or more entity selection criteria and one or more event criteria;
• an executable portion that executes machine learning logic to train, in a first stage, a suggested opportunity model using observed behavior, inclusive of activities of daily living (ADL), of each entity in the group of entities as input;
• an executable portion that matches, based on the suggested opportunity model, the one or more event opportunities and the group of entities according to a level of convenience for attending the one or more event opportunities of the group of entities;
• an executable portion that ranks the one or more matching event opportunities according to the level of convenience;
• an executable portion that suggests the ranked one or more matching event opportunities to the group of entities, wherein the one or more matching event opportunities each require at least one of the group of entities to perform and complete a plurality of actions in a predefined sequence to participate in a final event, and wherein suggesting the ranked one or more matching event opportunities includes suggesting scheduling arrangements for the at least one of the group of entities to perform the plurality of actions in the predefined sequence based on the level of convenience determined for each of the plurality of actions;
• and
• an executable portion that executes the machine learning logic to train, in a second stage, the suggested opportunity model using feedback data collected subsequent to suggesting the ranked one or more matching event opportunities, wherein the suggested opportunity model is iteratively updated using the feedback data to enhance an accuracy of future suggested event opportunities.