Predictive temperature scheduling for a thermostat using machine learning

A predictive temperature scheduling method, comprising:

• receiving a user input for controlling an HVAC system, wherein the user input comprises instructions for an occupancy setting;
• identifying a first plurality of time entries that are associated with a confidence level for a predicted occupancy status that is less than a predetermined threshold value in a predicted occupancy schedule, wherein the predicted occupancy schedule for a space comprises a plurality of time entries, wherein:
• each time entry is associated with a predicted occupancy status;
• and
• each predicted occupancy status associated with a confidence level;
• modifying the predicted occupancy schedule by setting the first plurality of time entries to an away status in response to determining that the user input indicates a first setting type;
• modifying the predicted occupancy schedule by setting the first plurality of time entries to a present status in response to determining that the user input indicates a second setting type;
• and
• outputting the modified predicted occupancy schedule;
• wherein:
• each time entry in the predicted occupancy schedule is associated with a predicted heating set point temperature;
• each predicted heating set point temperature is associated with a second confidence level;
• and
• further comprising:
• obtaining historical set point temperature information for the space within a predetermined time period, wherein the historical set point temperature information comprises a range of set point temperatures for the space during the predetermined time period;
• determining a lowest set point temperature for the space during the predetermined time period;
• identifying a second plurality of time entries that are associated with a second confidence level for a predicted heating set point temperature that is less than a second predetermined threshold value in the predicted occupancy schedule;
• and
• modifying the predicted occupancy schedule by setting the second plurality of time entries with a predicted heating set point temperature corresponding with the lowest set point temperature.

A non-transitory computer readable medium storing instructions that when executed by a processor cause the processor to:

• receive a user input for controlling an HVAC system, wherein the user input comprises instructions for an occupancy setting;
• identify a first plurality of time entries that are associated with a confidence level for a predicted occupancy status that is less than a predetermined threshold value in a predicted occupancy schedule, wherein the predicted occupancy schedule for a space comprises a plurality of time entries, wherein:
• each time entry is associated with a predicted occupancy status;
• and
• each predicted occupancy status associated with a confidence level;
• modify the predicted occupancy schedule by setting the first plurality of time entries to an away status in response to determining that the user input indicates a first setting type;
• modify the predicted occupancy schedule by setting the first plurality of time entries to a present status in response to determining that the user input indicates a second setting type;
• and
• output the modified predicted occupancy schedule;
• wherein:
• each time entry in the predicted occupancy schedule is associated with a predicted heating set point temperature;
• each predicted heating set point temperature is associated with a second confidence level;
• and
• further comprising instructions that when executed by the processor causes the processor to:
• obtain historical set point temperature information for the space within a predetermined time period, wherein the historical set point temperature information comprises a range of set point temperatures for the space during the predetermined time period;
• determine a lowest set point temperature for the space during the predetermined time period;
• identify a second plurality of time entries that are associated with a second confidence level for a predicted heating set point temperature that is less than a second predetermined threshold value in the predicted occupancy schedule;
• and
• modify the predicted occupancy schedule by setting the second plurality of time entries with a predicted heating set point temperature corresponding with the lowest set point temperature.