×

Method for voice assistant, location tagging, multi-media capture, transmission, speech to text conversion, photo/video image/object recognition, creation of searchable metatags/contextual tags, storage and search retrieval

DC
  • US 10,721,066 B2
  • Filed: 03/19/2019
  • Issued: 07/21/2020
  • Est. Priority Date: 09/30/2002
  • Status: Expired due to Term
First Claim
Patent Images

1. A method for capturing image and audio information for storage in a database at a location on a network, comprising the steps of:

  • interfacing a microphone with an external audio information source that generates external audio information and converting with a first data converter the external audio information from the microphone,interfacing a camera with an external image source to capture an image therefrom;

    the first data converter processing the captured external audio information and storing it in a first digital audio format as stored digital audio within the capture device, the camera for processing the captured image and storing it as a stored digital image;

    capturing with a data capture device, as captured data, location information and time information associated with at least the capture of the image and storing the captured data as stored captured data;

    combining with a data combiner for the stored digital audio, stored digital image and stored captured data as a composite data set;

    encrypting the composite data set as an encrypted composite data set;

    transmitting with a transmitter the encrypted composite data set to the location on the network; and

    wherein a system disposed at the location on the network operates to;

    receive the transmitted encrypted composite data set from the transmitter,decrypt the received encrypted composite data set as a decrypted composite data set to provide the decrypted composite data set as a received set of decrypted captured information,converting with a system data converter the received digital audio in the decrypted composite data set to a text based searchable file as a text context tag and creating an image recognition searchable context tag with image recognition of at least a portion of the digital image in the decrypted composite data set and associating the text and image recognition context tags with the digital image in the received decrypted composite data set, andstoring in the database the digital image in the decrypted composite data set in association with the text and image recognition context tags as a stored context based digital image and in association with the received captured data in the decrypted composite data set.

View all claims
  • 4 Assignments
Timeline View
Assignment View
    ×
    ×