Secure and private processing of gestures via video input
An always-listening-capable computing device is disclosed, comprising a camera for recording video of human actions, a module for communication with a remote server, and a gate-keeping module that, when enabled prevents the communication module from transmitting data external to the device. The device determines, based on the content of the video, a user desire or situation requiring human attention and transmits messages as appropriate for satisfying that desire or addressing that situation. Additional methods for handling user input directed to a recipient other than the device and for ensuring data security via controlling the device's network access are also disclosed.
1. An always-listening-capable computing device, comprising:
a first electronic sensor configured to record video data;
a communications module configured to transmit data to and receive data from a remote server;
a gate-keeping module, implemented by a processor, configured to:
enable a gate-keeping function, wherein no video data recorded by the first electronic sensor passes through the gate-keeping module to the communications module while the gate-keeping function is enabled;
receive, via an exclusive input lead-from the first electronic sensor, the video data;
determine that the video data recorded by the first electronic sensor comprises a first input content;
in response to determining that the video data comprises the first input content:
disable, for a defined period of time, the gate-keeping function;
allow the communications module to send the video data to a remote server, wherein video data recorded by the first electronic sensor passes through the gate-keeping module to the communications module while a gatekeeping function is disabled; and
re-enable, after the defined period of time, the gate-keeping function.
2. The always-listening-capable computing device of claim 1 , wherein the first electronic sensor comprises:
one or more power input leads; and
one or more data output leads to the gate-keeping module, wherein the first electronic sensor does not comprise any input leads from or output leads to other components of the always-listening-capable computing device.
3. The always-listening-capable computing device of claim 1 , wherein the gate-keeping module comprises one or more power input leads.
4. The always-listening-capable computing device of claim 1 , further comprising two or more gate-keeping modules, wherein a first gate-keeping module of the two or more gate-keeping modules is enabled or disabled by a second gate-keeping module of the two or more gate-keeping modules.
5. The always-listening-capable computing device of claim 1 , further comprising:
a second electronic sensor,
wherein the gate-keeping module is further configured to:
activates the second electronic sensor, in response to the first electronic sensor receiving a first wake up input; and
transmit data in response to input received, by the second electronic sensor, comprising a second wake up input different from the first wake up input.
6. The always-listening-capable computing device of claim 1 , wherein the gate-keeping module is configured to prevent the communications module from transmitting data external to the always-listening-capable computing device by disrupting a power source powering the communications module.
7. The always-listening-capable computing device of claim 1 , wherein the message is determined, in part, by the remote server analyzing the video data to determine a response comprising at least one of:
actuating a determined possible user desire;
soliciting additional information from a user to enable a response; and
providing responsive information to the user.
8. The always-listening-capable computing device of claim 1 , comprising:
a second electronic sensor, and wherein the first electronic sensor comprises a camera and the second electronic sensor comprises a microphone.
9. The always-listening-capable computing device of claim 1 , wherein the gate-keeping module is configured to:
generate, based on the determination that the video data comprises the first input content, a message;
output, via an exclusive output lead configured to output all data to a component other than the first electronic sensor, the message;
determine that the message is being played in a frequency range outside of human hearing; and
alert a user that the message is being played.
10. A computer-implemented method for providing always listening assistive response, comprising:
enabling, by a gate-keeping module, a gate-keeping function, wherein no video data received from a first electronic sensor passes through the gate-keeping module to a communications module while the gate-keeping function is enabled;
recording, via a first electronic sensor, video data;
receiving, by the gate-keeping module via an exclusive input lead from the first electronic sensor, the video data;
determining that the video data recorded by the first electronic sensor comprises a first input content;
in response to determining that the video data comprises the first input content:
disabling, for a defined period of time, the gate-keeping function;
allowing the communications module to send the video data to a remote server, wherein the video data passes through the gate-keeping module to the communications module while the gate-keeping function is disabled; and
re-enabling, after the defined period of time, the gate-keeping function.
11. The computer-implemented method of claim 10 , wherein the first electronic sensor comprises:
one or more power input lead; and
one or more data output leads to the gate-keeping module, and wherein the first electronic sensor does not comprise any input leads from or output leads to other components of an always-listening-capable computing device.
12. The computer-implemented method of claim 10 , wherein the first input content comprises at least one of: a gesture or an expression.
13. The computer-implemented method of claim 10 , further comprising:
updating a remote data store associated with a user.
14. The computer-implemented method of claim 10 , further comprising:
activating, via the gate-keeping module, a second electronic sensor in response to the first electronic sensor receiving a first wake up input; and
transmitting data in response to input received, by the second electronic sensor, comprising a second wake up input different from the first wake up input.
15. The computer-implemented method of claim 10 , further comprising:
preventing the communications module from transmitting data external to an always-listening-capable computing device by disrupting a power source from powering the communications module.
16. The computer-implemented method of claim 10 , further comprising:
generating, based on a determination that the video data comprises the first input content, a message;
output, via an exclusive output lead configured to output all data to a component other than the first electronic sensor, the message;
determining that the message is being played in a frequency range outside of human hearing; and
alerting a user that the message is being played.
17. The computer-implemented method of claim 10 , further comprising:
recording both video data and audio data via the first electronic sensor.
18. The computer-implemented method of claim 16 , wherein the message is determined, in part, by a remote server analyzing the video data to determine a response comprising at least one of:
actuating a determined possible user desire;
soliciting additional information from the user to enable a response; or
providing responsive information to the user.
19. The computer-implemented method of claim 10 , wherein the first input content comprises a command in sign language.
20. The computer-implemented method of claim 10 , wherein the disabling the gate-keeping function for the defined period of time comprises:
allowing data to be exchanged via at least one of: a wired connection or a limited-range wireless connection, wherein the gate-keeping function remains enabled for other communication capabilities.