User feedback during food tracking
Various implementations disclosed herein use user input received approximately around the time of food consumption to confirm and/or revise food predictions, e.g., regarding type of food, volume, etc. One or more food characteristics determinations may be associated with uncertainty. User input is implicitly or explicitly requested to resolve at least some of such ambiguities and uncertainties approximately around the time of food consumption. The user feedback experience may be configured to be easy and unobtrusive by presenting limited options in limited circumstances and using easy and intuitive input mechanisms. As examples, such feedback may involve a user using gaze input, a voice command, or a hand gesture to quickly identify whether an uncertain item is of one type or another type, e.g., mashed potatoes or ice-cream. In some implementations, the obtrusiveness/burden of requiring live input for every food determination is avoided or reduced by only asking about some items.
1 . A method comprising:
at an electronic device having a processor:
obtaining sensor data from one or more sensors in a physical environment, the sensor data associated with a time period during which food consumption by a user occurs;
determining a predicted characteristic of a food item based on the sensor data, wherein the predicted characteristic is associated with a confidence value corresponding to confidence that the food item has the predicted characteristic;
in response to determining that the confidence value corresponding to confidence that the food item has the predicted characteristic satisfies a criterion, presenting user interface content based on the predicted characteristic of the food item; and
receiving input regarding the presented user interface content, wherein the input is associated with the predicted characteristic.
2 . The method of claim 1 , wherein the user interface content is presented and the input is received during the time period during which the food consumption occurs.
3 . The method of claim 1 , wherein the user interface content is presented and the input is received during a meal during which the food consumption by the user occurs.
4 . The method of claim 1 , wherein the user interface content is presented within a threshold amount of time of a food consumption activity.
5 . The method of claim 1 , wherein determining that the confidence value satisfies the criterion is based on determining that the confidence level of the predicted characteristic is below a threshold.
6 . The method of claim 1 , wherein determining that the confidence value satisfies the criterion is based on determining that a food type could be either a first food type or a second food type based on the sensor data.
7 . The method of claim 1 , wherein the user interface content comprises graphical content corresponding to two or more options presented in an extended reality view.
8 . The method of claim 7 further comprising interpreting the input to select an option of the two or more options.
9 . The method of claim 1 , wherein the input is based on determining a gaze direction of the user.
10 . The method of claim 1 , wherein the input is based on a vocal utterance of the user.
11 . The method of claim 1 , wherein the input is based on a movement of the user or a second electronic device operated by the user.
12 . The method of claim 1 , wherein determining that the confidence value satisfies the criterion is based on a context of the physical environment determined based the sensor data.
13 . A system comprising:
a non-transitory computer-readable storage medium; and
one or more processors coupled to the non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium comprises program instructions that, when executed on the one or more processors, cause the system to perform operations comprising:
obtaining sensor data from one or more sensors in a physical environment, the sensor data associated with a time period during which food consumption by a user occurs;
determining a predicted characteristic of a food item based on the sensor data, wherein the predicted characteristic is associated with a confidence value corresponding to confidence that the food item has the predicted characteristic;
in response to determining that the confidence value corresponding to confidence that the food item has the predicted characteristic satisfies a criterion, presenting user interface content based on the predicted characteristic of the food item; and
receiving input regarding the presented user interface content, wherein the input is associated with the predicted characteristic.
14 . The system of claim 13 , wherein the user interface content is presented and the input is received during the time period during which the food consumption occurs.
15 . The system of claim 13 , wherein the user interface content is presented and the input is received during a meal during which the food consumption by the user occurs.
16 . The system of claim 13 , wherein the user interface content is presented within a threshold amount of time of a food consumption activity.
17 . The system of claim 13 , wherein determining that the confidence value satisfies the criterion is based on determining that a confidence level of the predicted characteristic is below a threshold.
18 . The system of claim 13 , wherein determining that the confidence value satisfies the criterion is based on determining that a food type could be either a first food type or a second food type based on the sensor data.
19 . The system of claim 13 , wherein the user interface content comprises graphical content corresponding to two or more options presented in an extended reality view.
20 . A non-transitory computer-readable storage medium storing program instructions executable via one or more processors to perform operations comprising:
obtaining sensor data from one or more sensors in a physical environment, the sensor data associated with a time period during which food consumption by a user occurs;
determining a predicted characteristic of a food item based on the sensor data, wherein the predicted characteristic is associated with a confidence value corresponding to confidence that the food item has the predicted characteristic;
in response to determining that the confidence value corresponding to confidence that the food item has the predicted characteristic satisfies a criterion, presenting user interface content based on the predicted characteristic of the food item; and
receiving input regarding the presented user interface content, wherein the input is associated with the predicted characteristic.