INTUITIVE COMPUTING METHODS AND SYSTEMS
A smart phone senses audio, imagery, and/or other stimulus from a user's environment, and acts autonomously to fulfill inferred or anticipated user desires. In one aspect, the detailed technology concerns phone-based cognition of a scene viewed by the phone's camera. The image processing tasks applied to the scene can be selected from among various alternatives by reference to resource costs, resource constraints, other stimulus information (e.g., audio), task substitutability, etc. The phone can apply more or less resources to an image processing task depending on how successfully the task is proceeding, or based on the user's apparent interest in the task. In some arrangements, data may be referred to the cloud for analysis, or for gleaning. Cognition, and identification of appropriate device response(s), can be aided by collateral information, such as context. A great number of other features and arrangements are also detailed.
1 . A method comprising the acts:
receiving sensor data, the sensor data including audio data sensed using a microphone of a user's portable device, and image data sensed using a camera of said device;
determining dynamically, based on context, a recognition-related operation to perform on the received sensor data, from among plural different recognition-related operations; and
determining dynamically, based on context, whether to make available more or less resources to said determined recognition-related operation;
wherein plural different recognition-related operations are performed on received sensor data, over time, due to different contexts; and
wherein resources made available to said determined recognition-related operation are changed, over time, due to changing context.
2 - 3 . (canceled)
4 . The method of claim 1 wherein said changing context comprises a new operation that has become ready to run, requiring reallocation of resources.
5 - 19 . (canceled)
20 . The method of claim 1 that includes determining said recognition-related operation based, at least in part, on a relevance score.
21 . The method of claim 20 that includes determining said recognition-related operation also based on a resource requirement.
22 . The method of claim 1 that includes determining said recognition-related operation based, at least in part, on a resource requirement.
23 . The method of claim 1 that includes determining to make more resources available to said determined recognition-related operation based, at least in part, on implied user encouragement.
24 . The method of claim 1 that includes determining to make more resources available to said determined recognition-related operation based, at least in part, on a detection state assessment of said recognition-related operation.
25 . The method of claim 1 that includes determining to make less resources available to said determined recognition-related operation based, at least in part, on an output from a different recognition-related operation.
26 . The method of claim 1 wherein plural different image recognition-related operations are performed on received sensor data, over time, due to different contexts.
27 . The method of claim 1 in which at least one of said determining acts is based on computing context.
28 . The method of claim 1 in which at least one of said determining acts is based on user context.
29 . The method of claim 1 in which at least one of said determining acts is based on physical context.
30 . The method of claim 1 in which at least one of said determining acts is based on temporal context.
31 . The method of claim 1 in which at least one of said determining acts is based on history of context.
32 . The method of claim 1 that includes determining said recognition-related operation using an N-ary tree-based planning exercise.
33 . A portable wireless device comprising:
a battery;
a camera and a microphone, said camera and microphone providing sensor information;
a wireless interface;
a processor; and
a memory, said memory containing software instructions that configure the device to perform actions including: determining dynamically, based on context, a recognition-related operation to perform on sensor information, from among plural different recognition-related operations; and determining dynamically, based on context, whether to make available more or less resources to said determined recognition-related operation;
wherein said instructions are operative to cause the device to perform plural different recognition-related operations on sensor information, over time, due to different contexts; and
wherein said instructions are operative to cause resources made available to said determined recognition-related operation to change, over time, due to changing context.
34 . The device of claim 33 in which said actions include determining to make more resources available to said determined recognition-related operation based, at least in part, on implied user encouragement.
35 . The device of claim 33 in which said actions include determining to make more resources available to said determined recognition-related operation based, at least in part, on a detection state assessment of said recognition-related operation.
36 . A computer readable storage medium for use with a portable device that includes a camera and a microphone for providing sensor information, said medium containing software instructions that, if executed by said device, cause the device to perform actions including:
determining dynamically, based on context, a recognition-related operation to perform on the sensor information, from among plural different recognition-related operations; and
determining dynamically, based on context, whether to make available more or less resources to said determined recognition-related operation;
wherein said instructions are operative to cause the device to perform plural different recognition-related operations on sensor information, over time, due to different contexts; and
wherein said instructions are operative to cause resources made available to said determined recognition-related operation to change, over time, due to changing context.
37 . The storage medium of claim 37 in which said actions include determining to make more resources available to said determined recognition-related operation based, at least in part, on a detection state assessment of said recognition-related operation.