Contextual responses based on automated learning techniques

A computer-readable medium whose contents cause a wearable computing device to improve automated responses to a current context for a user of the wearable computing device based on automated learning, the current context being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, by performing a method comprising:

• repeatedly,
• receiving an indication of current context information that includes current values for each of at least some of the plurality of context attributes;
• determining one of the defined contextual situations that matches the indicated current context information;
• automatically providing one of the automated response that is associated with the one defined contextual situation;
• receiving an indication from the user of an alternate automated response to be provided;
• and
• storing an indication of the indicated current context information and the alternate automated response;
• automatically detecting a relationship between an identified contextual situation and one of the alternate automated responses based on analysis of patterns of that alternate automated response being indicated by the user;
• and
• creating an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.

A wearable computing system configured to improve automated responses to a current context for a user, the current context being represented by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, comprising:

• a first component that is configured to repeatedly, receive an indication of current context information that includes current values for each of at least some of the plurality of context attributes, determine one of the defined contextual situations that matches the indicated current context information, determine one of the automated responses that is associated with the one defined contextual situation, receive an indication from the user of an alternate automated response, and store an indication of the indicated current context information and the alternate automated response;
• and
• a second component that is configured to automatically detect a relationship between an identified contextual situation and one of the alternate automated responses based on that alternate automated response being previously indicated by the user and to create an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.

A wearable computing system configured to improve automated responses to a current context for a user, the current context being represent by a plurality of context attributes that each model an aspect of the context, multiple defined contextual situations each specifying values for at least one of the context attributes, multiple automated responses being associated with the defined contextual situations, comprising:

• first means for repeatedly receiving an indication of current context information that includes current values for each of at least some of the plurality of context attributes, determining one of the defined contextual situations that matches the indicated current context information, determining one of the automated responses that is associated with the one defined contextual situation, receiving an indication from the user of an alternate automated response, and storing an indication of the indicated current context information and the alternate automated response;
• second means for automatically detecting a relationship between an identified contextual situation and one of the alternate automated responses based on that alternate automated response being previously indicated by the user;
• and
• third means for creating an association between the identified contextual situation and the one alternate automated response so that the one alternate automated response can in the future be provided to the user for that contextual situation.