received by the International Bureau on 05 December 2018 (05.12.2018)

We claim:

1. A method for tailoring an electronic digital assistant generated inquiry response as a function of previously detected user ingestion of related information, the method comprising: receiving, at an electronic processing device from a video capture device configured to track a gaze direction of a first user, a video stream including a first field-of-view substantially matching a field-of-view of the first user based on the tracked gaze direction of the first user;

identifying, by the electronic processing device, an object in the video stream first field-of-view that is determined, based on the tracked gaze direction of the first user, to remain in the first field-of-view for a configured minimum threshold period of time and, responsively, processing the object via a video processing algorithm and causing, by the electronic processing device, object information regarding the object output from the video processing algorithm to be stored in a non-volatile store;

subsequently receiving, at the electronic processing device, an inquiry for information from the first user;

determining, by the electronic processing device by matching information included in the inquiry to object information stored in the non-volatile store, that the inquiry is related to the object; and

providing, by the electronic processing device, a response to the inquiry as a function of the object information stored in the non-volatile store.

2. The method of claim 1, wherein the object is one of an alphanumerical text object and a graphical object including alphanumerical text, the object information includes alphanumerical text corresponding to the alphanumerical text object or extracted from the graphical object, and the response to the inquiry including at least a portion of one of the alphanumerical text itself or a transformation of the

alphanumerical text into an audio reproduction.

3. The method of claim 2, wherein the object is the alphanumerical text object and is a report regarding an incident or a work assignment order, and the response to the inquiry includes a name, location, address, time, or status extracted from the report or order and responsive to the inquiry.

4. The method of claim 2, wherein the object is the graphical object including alphanumerical text and is a street sign or roadside electronic display, and the response to the inquiry includes alphanumeric text extracted from the street sign or roadside electronic display.

5. The method of claim 1, wherein the object is a graphical object, the object information includes graphical object identification information that identifies the graphical object by type, definition, or identity, and the response to the inquiry includes a graphical representation of the graphical object.

6. The method of claim 5, wherein the graphical object is a capture of a human face, the graphical object identification information is an identity of a person matching the captured human face via a facial recognition look-up, and the response to the inquiry includes the capture of the human face and the identity of the person matching the captured human face.

7. The method of claim 5, further comprising identifying, by the electronic processing device, a central frame in time from the video stream having a minimum level of blur, and providing all or a portion of the central frame including the object in the response to the inquiry.

8. The method of claim 1, the method further comprising storing, accompanying the object information, a time and/or date at which the object first and/or last appeared in the video stream first field-of-view.

9. The method of claim 8, wherein the inquiry includes a time limitation, and the step of determining, by the electronic processing device, that the inquiry is related to the object information includes determining that the stored time and/or date matches the time limitation in the inquiry.

10. The method of claim 8, further comprising, after a configured second threshold period of time after the stored time and/or date, one of deleting the object information and refraining from providing a response to a subsequent inquiry from the user as a function of the object information.

11. The method of claim 10, wherein the configured second threshold period of time is a predetermined predicted time that the first user will independently retain information relative to the object after viewing the object in the first field of view.

12. The method of claim 11, wherein the configured second threshold period of time is varied based on one or both of a measured amount of time the object remained in the video stream first field of view and a measured number of repetitions in which the object reappeared in the video stream first field of view.

13. The method of claim 10, wherein the configured second threshold period of time is within a range of eight to twenty four hours.

14. The method of claim 1, the method further comprising storing, accompanying the object information, a geographical location of the first user and/or the object, at a time at which the object first and/or last appeared in the video stream first field-of- view.

15. The method of claim 14, wherein the inquiry includes a location limitation, and the step of determining, by the electronic processing device, that the inquiry is related to the object information includes determining that the stored geographical location matches the location limitation in the inquiry.

16. The method of claim 1, wherein the video capture device configured to track the gaze direction of the first user includes a user-mounted or vehicle-mounted video capture device having a relatively large field-of-view and a head-tracking or eye-gaze tracking device, and wherein the relatively large field-of-view is reduced to the first field-of-view via video processing and as a function of head-tracking information or eye-gaze tracking information of the first user received via the corresponding head- tracking or eye-gaze tracking device.

17. The method of claim 1, wherein the video capture device configured to track the gaze direction of the first user is a video capture device having a capture field-of- view substantially matching a wearer's field-of-view and is physically coupled to the first user's head.

18. The method of claim 1, further comprising refraining from storing object information regarding the objects output from the video processing algorithm in the non-volatile store for use in providing responses to inquiries from the user for those objects that are determined, based on the tracked gaze direction of the first user, to not remain in the first field-of-view for the configured minimum threshold period of time.

19. The method of claim 1, wherein the providing the response to the inquiry as a function of the object information comprises refraining from including in the response the object or the object information, and instead, providing additional information in the response that assumes that the first user is already aware of and has knowledge of the object and/or the object information.

20. An electronic processing device for tailoring an artificial intelligence inquiry response as a function of previously detected user ingestion of related information, the device comprising:

a memory;

a transceiver; and

one or more processors configured to:

receive, from a video capture device configured to track a gaze direction of a first user, a video stream including a first field-of-view substantially matching a field-of-view of the first user based on the tracked gaze direction of the first user;

identify an object in the video stream first field-of-view that is determined, based on the tracked gaze direction of the first user, to remain in the first field-of-view for a configured minimum threshold period of time and, responsively, process the object via a video processing algorithm and causing, by the electronic processing device, object information regarding the object output from the video processing algorithm to be stored in a non-volatile store; subsequently receive an inquiry for information from the first user; determine, by matching information included in the inquiry to object information stored in the non-volatile store, that the inquiry is related to the object; and

provide a response to the inquiry as a function of the object

information stored in the non-volatile store, via one of the transceiver, a display communicatively coupled to the electronic computing device, or a speaker communicatively coupled to the electronic computing device.