US 12,231,383 B2
Methods and systems for enabling collective superintelligence
Louis B. Rosenberg, San Luis Obispo, CA (US); Gregg Willcox, Seattle, WA (US); and Hans Schumann, San Francisco, CA (US)
Assigned to Unanimous A. I., Inc., Arlington, VA (US)
Filed by UNANIMOUS A.I., INC., Arlinton, VA (US)
Filed on May 7, 2024, as Appl. No. 18/657,612.
Application 18/657,612 is a continuation in part of application No. 18/588,851, filed on Feb. 27, 2024.
Application 18/657,612 is a continuation in part of application No. 18/367,089, filed on Sep. 12, 2023.
Application 18/588,851 is a continuation of application No. 18/240,286, filed on Aug. 30, 2023, granted, now 11,949,638, issued on Apr. 2, 2024.
Application 18/367,089 is a continuation in part of application No. 18/240,286, filed on Aug. 30, 2023, granted, now 11,949,638, issued on Apr. 2, 2024.
Claims priority of provisional application 63/548,107, filed on Nov. 10, 2023.
Claims priority of provisional application 63/547,705, filed on Nov. 8, 2023.
Claims priority of provisional application 63/456,483, filed on Apr. 1, 2023.
Claims priority of provisional application 63/451,614, filed on Mar. 12, 2023.
Claims priority of provisional application 63/449,986, filed on Mar. 4, 2023.
Prior Publication US 2024/0297859 A1, Sep. 5, 2024
Int. Cl. H04L 51/216 (2022.01); H04L 51/04 (2022.01); H04L 51/046 (2022.01); H04L 51/56 (2022.01)
CPC H04L 51/046 (2013.01) [H04L 51/04 (2013.01); H04L 51/216 (2022.05); H04L 51/56 (2022.05)] 35 Claims
OG exemplary drawing
 
1. A system for real-time communication, conversation analysis and insight extraction, comprising:
a plurality of networked computing devices associated with members of a population of participants, and networked via a computer network; and
a central server in communication with the plurality of networked computing devices, the central server dividing the population into a plurality of subgroups and enabling a conversational surrogate agent (CSai) associated with each subgroup, each conversational surrogate agent comprising a large language model (LLM)-powered module that is assigned to a unique subgroup of the population of participants and tasked with repeatedly performing the following steps in real-time, comprising:
observing via the computer network a conversation among members of its assigned subgroup,
distilling and storing content of the conversation,
extracting insights from the conversation at intervals,
assessing a numerical measure of conviction, confidence or scope associated with each unique insight within the conversation among the members of the assigned subgroup,
storing the insights and associated numerical measures and associated members in a memory by passing data to one or more other computational processes accessible to the central server,
aggregating the associated numerical measures across unique insights expressed within the assigned subgroup,
passing insights to other conversational surrogate agents assigned to other subgroups, said insights being passed as language, each insight being passed along with said associated numerical measures having been aggregated,
receiving insights from the other conversational surrogate agents assigned to other subgroups, each insight including textual language representing the insight and aggregated numerical measures associated with the other subgroups, and
conversationally expressing received insights to the assigned subgroup, said expressing including modulating a strength of the textual language based at least in part on the received aggregated numerical measures.