Artificially intelligent hologram

• US 10,628,635 B1
• Filed: 10/03/2017
• Issued: 04/21/2020
• Est. Priority Date: 03/29/2017
• Status: Active Grant

• Current Assignee: Valyant AI, Inc.
• Original Assignee: Valyant AI, Inc.
• Inventors: Carpenter, II, Robley Theron, Thielker, Benjamin William
• Primary Examiner(s): Jackson, Jakieda R
• Application Number:
  US15/723,573
• Time in Patent Office: 931 Days
• Field of Search: 704270, 704260, 704235
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/00 Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06F 3/013 Eye tracking input arrangements G06F3/015 takes precedence
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A conversational holographic assistant displays a computer-generated human-like hologram capable of carrying on conversations in real-time with a user, remembering things about past interactions with the user to make the conversation realistic and more human-like. The system is intended to be utilized in retail, office, business and personal settings to provide service to users. The holographic person can interact with retail point of sale systems in order to process orders on behalf of a user, provide users with detailed directions, and answer questions about the holographic person'"'"'s surroundings, among other things. In some settings, the holographic person can integrate with existing internet of things devices. The holographic person is implemented through the use of a user recognition component, a user input component, an interpreter component, a machine-readable text processor component, a text-to-audio generator component and a text-to-visual display generator component, and an output processor component.

Claims

1. A system comprising:

a user recognition component, for recognizing users and their input preferences;

an input device component, for receiving user input;

an interpreter component, for interpreting the received user input to derive a first machine-readable text;

a machine-readable text processor component, for processing the first machine-readable text and the user input preferences to generate a service in the form of a second machine-readable text;

a text-to-audio generator component and a text-to-visual display generator component for generating an audio file and corresponding Computer-Generated Imagery (CGI) from the second machine-readable text, the audio file and CGI corresponding to an audiovisual output in the form of a human-like hologram configured to converse with a user; and

an output processor component, for displaying the audiovisual output in the form of the human-like hologram that converses with the user in real-time.

2. The system of claim 1, wherein the interpreter component further comprises:

a natural language interpreter component, for interpreting the received user input to derive the first machine-readable text when the received user input is a verbal command.

3. The system of claim 1, wherein the interpreter component further comprises:

a touchscreen interface interpreter component, for interpreting the received user input to derive the first machine-readable text when the received user input is a touchscreen command.

4. The system of claim 1, wherein the user recognition component comprises a camera physically coupled to a transparent rigid panel on which the hologram is displayed and communicatively coupled to one or more computing devices.

5. The system of claim 4, wherein the transparent rigid panel is made of glass or plastic.

6. The system of claim 5, wherein at least a portion of the transparent rigid panel has touch screen capabilities to receive user input.

7. The system of claim 1, wherein the input device component comprises a microphone to receive verbal command.

8. The system of claim 1, wherein the output processor component comprises display hardware to display the hologram generated by computer graphic imagery (CGI).

9. The system of claim 8, wherein the display hardware includes a projection system to optically project the hologram generated by computer graphic imagery (CGI).

10. The system of claim 1, wherein the user recognition component comprises facial recognition software that, when executed on the one or more computing devices, identifies a repeat user and the repeat user'"'"'s preferences.

11. The system of claim 1, wherein the conversational holographic assistant is trained to provide personalized user support.

12. The system of claim 11, wherein the personalized user support includes conversation in the user'"'"'s preferred language.

13. A method comprising:

at the one or more computing devices;

recognizing a user and the user'"'"'s input preferences;

receiving an input from the user;

interpreting the received user input to derive a first machine-readable text;

processing the first machine-readable text and the user input preferences to generate a service in the form of a second machine-readable text;

generating an audio file and corresponding Computer-Generated Imagery (CGI) from the second machine-readable text, the audio file and CGI corresponding to an audiovisual output in the form of a human-like hologram configured to converse with the user; and

causing a rigid transparent panel to display an audiovisual output in the form of a human-like hologram based on data received from the generated audio file and corresponding CGI, the audiovisual output conversing with the user in real-time.

14. The method of claim 13, wherein receiving an input from the user comprises receiving the user'"'"'s verbal command.

15. The method of claim 13, wherein recognizing the user comprises facial recognition software that, when executed on the one or more computing devices, takes one or more pictures of the user'"'"'s face and stores the one or more pictures in nonvolatile memory on the one or more computing devices.

16. The method of claim 15, wherein recognizing the user comprises facial recognition software that, when executed on the one or more computing devices, identifies a repeat user and the repeat user'"'"'s preferences.

17. The method of claim 13, wherein the conversational holographic assistant is displayed on a transparent rigid panel.

18. The method of claim 13, wherein the conversational holographic assistant is trained to provide personalized user support.

19. The method of claim 18, wherein the personalized user support includes conversation in the user'"'"'s preferred language.

20. A non-transitory computer-readable medium for implementing a conversational holographic assistant on one or more computing devices, the computer-readable medium having instructions stored thereon, the instructions, when executed by one or more processors, cause the processors to perform operations comprising:

recognizing a user and the user'"'"'s input preferences;

receiving an input from the user;

interpreting the received user input to derive a first machine-readable text;

processing the first machine-readable text and the user input preferences to generate a service in the form of a second machine-readable text;

generating an audio file and corresponding Computer-Generated Imagery (CGI) from the second machine-readable text;

causing an audiovisual output to be displayed in the form of a hologram representing the conversational holographic assistant based on data received from the generated audio file and corresponding CGI.