Virtual representative conditioning system

Patent metadata

Field	Value
Publication number	US-12518482-B2
Application number	US-202318447963-A
Country	US
Kind code	B2
Filing date	Aug 10, 2023
Priority date	Aug 10, 2023
Publication date	Jan 6, 2026
Grant date	Jan 6, 2026

Abstract

Systems and techniques are provided for conditioning virtual representatives. For example, a method can include obtaining, by a conditioning engine, a baseline model for a virtual representative; obtaining, by the conditioning engine, one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative; generating, based on the baseline model and the one or more conditioning inputs configured to condition an action in one or more multi-user experiences of the virtual representative, a conditioned model for the virtual representative; and outputting the conditioned model for the virtual representative.

First claim

What is claimed is:

1 . An apparatus for conditioning virtual representatives comprising:
at least one memory; and at least one processor coupled to the at least one memory and configured to:
obtain, by a conditioning engine, a first model for a virtual representative;
obtain, by the conditioning engine, one or more conditioning inputs configured to condition an action in one or more experiences including the virtual representative;
generate, based on the first model and the one or more conditioning inputs configured to condition an action in one or more experiences including the virtual representative, a conditioned model for the virtual representative;
output the conditioned model for the virtual representative;
obtain, by the conditioning engine, a second model for an additional virtual representative;
generate an additional conditioned model configured to condition an action in one or more experiences including the additional virtual representative based on the second model and the one or more conditioning inputs configured to condition the action in one or more experiences including the virtual representative; and
output the additional conditioned model for the additional virtual representative.

2 . The apparatus of claim 1 , wherein the at least one processor is further configured to: obtain, by the conditioning engine, additional one or more conditioning inputs configured to condition an additional action in one or more experiences of an additional virtual representative; and generate, based on the first model and the additional one or more conditioning inputs configured to condition an action in one or more experiences of the additional virtual representative, the additional conditioned model for the additional virtual representative, wherein the one or more conditioning inputs and the additional one or more conditioning inputs differ with respect to at least one conditioning input.

3 . The apparatus of claim 2 , wherein:
the virtual representative performs the action in a first experience during a first time period; and the additional virtual representative performs the additional action in a second experience during a second time period, wherein the first time period at least partially overlaps with the second time period.

4 . The apparatus of claim 2 , wherein the action in the one or more experiences of the virtual representative comprises responding to queries according to a first style.

5 . The apparatus of claim 4 wherein responding to queries according to the first style comprises one or more of:
responding with a writing style in accordance with the conditioned model;
responding with a speech pattern in accordance with the conditioned model;
responding with a personality trait in accordance with the conditioned model;
responding with a tailored functionality in accordance with the conditioned model;
generating an audio output consistent with speech patterns of an individual; or generating an avatar representing one or more physical characteristics of the individual.

6 . The apparatus of claim 5 , wherein generating the avatar representing the one or more physical characteristics of the individual comprises generating a 3D model based on the one or more physical characteristics of the individual.

7 . The apparatus of claim 4 , wherein the additional action in the one or more experiences of the virtual representative comprises responding to queries according to a second style, the second style different from the first style.

8 . The apparatus of claim 7 , wherein the virtual representative responds to a query with a first response in accordance with the conditioned model for the virtual representative.

9 . The apparatus of claim 8 , wherein the additional virtual representative responds to the query with a second response in accordance with the additional conditioned model for the additional virtual representative, wherein the second response is different from the first response.

10 . The apparatus of claim 1 , wherein:
the action in one or more experiences of the virtual representative comprises responding to queries according to a first style; and the action in the one or more experiences of the additional virtual representative comprises responding to queries according to a second style, the second style different from the first style.

11 . The apparatus of claim 10 , wherein:
the virtual representative responds to a query with a first response in accordance with the first style; and the additional virtual representative responds to the query with a second response in accordance with the second style, wherein the second response is different from the first response.

12 . The apparatus of claim 1 , wherein the one or more conditioning inputs configured to condition the action in one or more experiences of the virtual representative comprise one or more of a meeting type of an experience, one or more types of functionality needed for the one or more experiences, a number of multi-user experience participants, an identity of one or more experience participants in the experience, a topic of the experience, a previous experience of the virtual representative in an additional experience, or at least one key performance indicator (KPI) associated with the virtual representative.

13 . The apparatus of claim 1 , wherein the virtual representative participates in an experience with at least one additional experience participant.

14 . The apparatus of claim 13 , wherein the at least one additional experience participant comprises a different virtual representative, wherein the virtual representative is associated with a first individual, and the different virtual representative is associated with a second individual, the second individual different from the first individual.

15 . The apparatus of claim 13 , wherein the virtual representative responds to a query from the at least one additional experience participant.

16 . The apparatus of claim 13 , wherein the at least one additional experience participant comprises an avatar representing an individual participating live in the experience.

17 . The apparatus of claim 13 , wherein the at least one processor is further configured to output, by the virtual representative, one or more notifications during the experience, wherein the one or more notifications comprise one or more of discussion of a sensitive topic, a dispute, or a request for authorization.

18 . The apparatus of claim 13 , wherein the at least one processor is further configured to generate experience data based on participation of the virtual representative in the experience.

19 . The apparatus of claim 18 , wherein the at least one processor is further configured to update, based on the experience data based on participation of the virtual representative in the experience, the conditioned model for the virtual representative.

20 . The apparatus of claim 19 , wherein, to update the conditioned model for the virtual representative, the at least one processor is configured to generate, based on the first model, the one or more conditioning inputs configured to condition the action in one or more experiences of the virtual representative, and the experience data, a third conditioned model for the virtual representative.

21 . The apparatus of claim 18 , wherein the experience data comprises one or more of a recording, a transcript, or a summary of the experience.

22 . The apparatus of claim 18 ,

Assignees

• Qualcomm Inc

Inventors

• Holland Wesley James
• Asghar Ziad
• Sinder Daniel Jared
• El-Maleh Khaled Helmi
• Gupta Vikram
• Oguz Seyfullah Halit
• Chun Miran
• Porikli Fatih Murat
• Shen Jian
• Sukumar Vinesh

Classifications

• G06T13/40

  of characters, e.g. humans, animals or virtual beings · CPC title

• G06T13/205

  driven by audio data · CPC title

• G06F16/436

  using biological or physiological data of a human being, e.g. blood pressure, facial expression, gestures · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• H04N7/157

  defining a virtual conference space and using avatars or agents (computer conference optimisation or adaptation H04L12/1827) · CPC title