Configuring a virtual companion

• US 10,140,882 B2
• Filed: 08/04/2016
• Issued: 11/27/2018
• Est. Priority Date: 05/27/2016
• Status: Active Grant

• Current Assignee: The Affinity Project, Inc.
• Original Assignee: The Affinity Project, Inc.
• Inventors: Fanty, Mark Alan, Suskind, Ronald Steven, Patterson, Stuart R., Nguyen, John, Springer, Stephen R.
• Primary Examiner(s): Grant, Michael
• Application Number:
  US15/229,070
• Publication Number:
  US 20170345324A1
• Time in Patent Office: 845 Days
• CPC Class Codes: G09B 19/00 Teaching not covered by other main groups of this subclass teaching or practice apparatus for gun-aiming or gun-laying F41G3/26
• CPC Class Codes: G09B 5/06 with both visual and audible presentation of the material to be studied
• CPC Class Codes: G09B 5/125 the stations being mobile
• 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

Abstract

A service may be provided that allows interacting users to interact with characters presented by devices of the interacting users. The operation of the character presented to an interacting user may be customized for that interacting user. For example, a first controlling user may specify first information for configuring or controlling the operation of the character when the character is interacting with a first interacting user, and a second controlling user may specify second information for configuring or controlling the operation of the character when the character is interacting with a second interacting user. The information provided by a controlling user may be used to select a segment to be used for a session between an interacting user and the character.

Claims

1. A system for controlling operation of a character presented by a first device to a first interacting user, the system comprising one or more computers configured to:

store information about;

one or more interacting users comprising the first interacting user,

one or more segments comprising a first segment, wherein each segment describes interactions between an interacting user and the character, and

one or more video clip data items comprising a first video clip data item, wherein each video clip data item corresponds to a video clip and comprises an identifier of a video character appearing in the video clip;

receive, from a first controlling user, control information for controlling the operation of the character when the character is interacting with the first interacting user, wherein the control information includes information about the first interacting user, information about segments to be presented to the first interacting user, or information about video clips to be presented to the first interacting user;

start a session with the first device to allow the first interacting user to interact with the character;

select the first segment using the control information;

select the first video clip data item using the control information, wherein the first video clip data item corresponds to a first video clip and comprises a first identifier of a first video character appearing in the first video clip;

cause the first device to present the first video clip to the first interacting user;

obtain information about the first video character using the first identifier;

construct a first phrase using the first segment and the information about the first video character; and

cause the character presented by the first device to present the first phrase to the first interacting user.

2. The system of claim 1, wherein the one or more computers are configured to cause the first device to present the first phrase by (i) transmitting configuration information to configure software on the first device, or (ii) transmitting audio or text of the first phrase to the first device.

3. The system of claim 1, wherein the first controlling user comprises a parent of the first interacting user.

4. The system of claim 1, wherein the information about the first interacting user comprises (i) preferences of the first interacting user or (ii) a skill level of the first interacting user.

5. The system of claim 1, wherein the information about segments to be presented to the first interacting user comprises (i) a script, (ii) a parameter indicating a type of segment, or (iii) a parameter of a segment.

6. The system of claim 1, wherein the first segment comprises a first script and a first data item.

7. The system of claim 1, wherein the one or more computers are configured to cause the first device to present the first phrase by at least one of (i) causing the first device to present audio using a text-to-speech voice, or (ii) causing the first phrase to be presented on a display of the first device.

8. A method for controlling operation of a character presented by a first device to a first interacting user, the method comprising:

storing information about;

one or more interacting users comprising the first interacting user,

one or more segments comprising a first segment, wherein each segment describes interactions between an interacting user and the character, and

one or more video clip data items comprising a first video clip data item, wherein each video clip data item corresponds to a video clip and comprises an identifier of a video character appearing in the video clip;

receiving, from a first controlling user, control information for controlling the operation of the character when the character is interacting with the first interacting user, wherein the control information includes information about the first interacting user, information about segments to be presented to the first interacting user, or information about video clips to be presented to the first interacting user;

starting a session with the first device to allow the first interacting user to interact with the character;

selecting the first segment using the control information;

selecting the first video clip data item using the control information, wherein the first video clip data item corresponds to a first video clip and comprises a first identifier of a first video character appearing in the first video clip;

causing the first device to present the first video clip to the first interacting user;

obtaining information about the first video character using the first identifier;

constructing a first phrase using the first segment and the information about the first video character; and

causing the character presented by the first device to present the first phrase to the first interacting user.

9. The method of claim 8, comprising:

receiving input from the first interacting user;

generating a second phrase using the first segment and the input; and

causing the character to present the second phrase.

10. The method of claim 8, comprising:

training a first mathematical model for the character using transcripts of previous sessions with the first interacting user, and wherein causing the first device to present the first phrase comprises generating the first phrase using the first mathematical model.

11. The method of claim 8, comprising:

selecting a second segment to present to the first interacting user using the control information;

generating a second phrase using the second segment; and

causing the character to present the second phrase.

12. The method of claim 8, wherein selecting the first segment comprises using a mathematical model or rules corresponding to the first interacting user.

13. The method of claim 12, wherein the control information comprises an indication of the mathematical model or the rules.

14. The method of claim 8, comprising:

determining to request assistance from an intervening user by processing data received from the first device;

receiving a second phrase specified by the intervening user; and

causing the character to present the second phrase.

15. The method of claim 14, wherein the intervening user is selected from a plurality of users.

16. The method of claim 14, wherein the control information comprises a goal for the first interacting user.

17. One or more non-transitory computer-readable media comprising computer executable instructions that, when executed, cause at least one processor to perform actions comprising:

receiving, from a first controlling user, control information for controlling operation of a character when the character is interacting with a first interacting user, wherein the control information includes information about the first interacting user, information about segments to be presented to the first interacting user, or information about video clips to be presented to the first interacting user;

starting a session with a first device of the first interacting user to allow the first interacting user to interact with the character;

selecting a first segment using the control information;

selecting a first video clip data item using the control information, wherein the first video clip data item corresponds to a first video clip and comprises a first identifier of a first video character appearing in the first video clip;

causing the first device to present the first video clip to the first interacting user;

obtaining information about the first video character using the first identifier;

constructing a first phrase using the first segment and the information about the first video character; and

causing the character presented by the first device to present the first phrase to the first interacting user.

18. The one or more non-transitory computer-readable media of claim 17, wherein the first segment comprises a first script and a first data item.

19. The one or more non-transitory computer-readable media of claim 17, wherein the actions comprise:

receiving, from a second controlling user, second control information for controlling operation of the character when the character is interacting with a second interacting user;

starting a session with a second device of the second interacting user to allow the second interacting user to interact with the character;

selecting a second segment using the second control information;

selecting a second video clip data item using the second control information, wherein the second video clip data item corresponds to a second video clip and comprises a second identifier of a second video character appearing in the second video clip;

causing the second device to present the second video clip to the second interacting user;

obtaining information about the second video character using the second identifier;

constructing a second phrase using the second segment and the information about the second video character; and

causing the character presented by the second device to present the second phrase to the second interacting user.

20. The one or more non-transitory computer-readable media of claim 18, wherein selecting the first segment comprises:

randomly selecting the first script from a plurality of scripts; and

randomly selecting the first data item from a plurality of data items.