US-20260129011-A1 - FACILITATING GROUP DISCUSSIONS USING LARGE LANGUAGE MODELS

US20260129011A1US 20260129011 A1US20260129011 A1US 20260129011A1US-20260129011-A1

Abstract

The present disclosure describes systems and methods for facilitating real-time conversational dialog among distributed users, each using a separate networked computing device within a group chat environment. The method includes enabling dialog among users and at least one simulated conversational agent. During ongoing conversations, intervals of dialog are captured and processed using a large language model to extract key points and assess levels of agreement or disagreement among users. Extracted key points are optionally ordered based on assessed agreement or disagreement. The simulated conversational agent then expresses, as dialog, representations of important key points to the group. This process is repeated multiple times, allowing the group to converge on important points and consensus through iterative dialog and AI-mediated summarization and propagation of insights across the distributed users.

Inventors

Louis B. Rosenberg

Assignees

Unanimous A. I., Inc.

Dates

Publication Date: 20260507
Application Date: 20251224

Claims (20)

1 . A method of facilitating a conversation among a plurality of distributed users, each user associated with a separate networked computing device, the method comprising: providing to each user, through their separate computing device, access to a group chat environment that enables real-time conversational dialog among a group of distributed users and at least one simulated conversational agent; and repeating the following processes a plurality of times during an ongoing real-time conversation among a group of distributed users within a provided group chat environment: (a) capture an interval of conversational dialog among the group of users, (b) process the captured interval of dialog using a Large Language Model to extract at least one key point expressed by at least one user and to assess a level of agreement or disagreement among the group of users regarding the at least one key point, (c) order a set of extracted key points based at least in part on an assessed level of agreement or disagreement associated with each key point, and (d) Express to the group of distributed users, as dialog from a simulated conversational agent, a representation of one or more key points extracted from a prior interval of conversational dialog among a set of distributed users.
2 . The method of claim 1 wherein the chat environment is a video conference environment.
3 . The method of claim 1 wherein the chat environment is a text chat environment.
4 . The method of claim 3 wherein the at least one simulated conversational agent configured to express dialog as text chat messages on a screen.
5 . The method of claim 2 wherein the at least one simulated conversational agent is configured to express dialog as simulated voice through an audio display.
6 . The method of claim 1 wherein the expressing of dialog by a simulated conversational agent is timed to occur during a pause in an ongoing conversation among a plurality of human users.
7 . The method of claim 1 wherein the repeating is ceased when at least one extracted key point is assessed to have achieved a level of agreement above a threshold value.
8 . The method of claim 1 wherein the captured interval of dialog includes a set of ordered messages.
9 . The method of claim 8 wherein the each of the ordered messages is associated with a respective user identifier and a timestamp.
10 . The method of claim 8 wherein the processing of the captured interval of dialog further includes determining a response target indicator for at least one message, wherein the response target indicator provides an indication of a prior message to which the message is responding.
11 . The method of claim 8 wherein the processing of the captured interval of dialog further includes determining a whether a message agrees or disagrees with a prior message.
12 . The method of claim 1 wherein the one or more key points expressed to the group of distributed users by the simulated conversational agent are most important key points, the importance determined at least in part based on the assessed levels of agreement associated with those key points.
13 . The method of claim 1 that further includes storing a history of chat dialog in memory as it transpires over time among a group of distributed users, said history including a record of each speaker, the time of speaking, and conversational content.
14 . The method of claim 1 that includes a plurality of groups of distributed users, wherein each group of distributed users is provided access to a separate group chat environment that enables real-time conversational dialog among that group of users and a simulated conversational agent.
15 . The method of claim 14 that includes (a. extracting at least one key point from an interval of dialog captured from a first group chat environment accessed by a first set of users and (b. expressing the at least one key point within a second group chat environment accessed by a second group of users.
16 . The method of claim 15 wherein the expressing of the at least one key point in the second group chat environment is conveyed as conversational dialog from the simulated conversational agent associated with the second conversational environment.
17 . The method of claim 1 wherein the processing of the interval of dialog further includes identifying a chat message, identifying a prior chat message to which the chat message is responding, identifying whether the chat message agrees or disagrees with the prior chat message to which it responded, and assessing a strength of agreement or disagreement.
18 . A method of facilitating a conversation among a group of users, each user associated with a separate networked computing device, the method comprising: providing to each user, via their associated computing device, access to a group chat environment that enables real-time dialog among the group of users and a simulated conversational agent; and repeating the following set of processes a plurality of times during an ongoing conversation among the group of users and the simulated conversational agent within the group chat environment: (a) capture an interval of conversational dialog among the group of users, (b) store a representation of the captured interval of conversational dialog in a memory, (c) process the interval of conversational dialog using a Large Language Model to identify a chat message, identify a prior chat message to which the chat message is responding, identify whether the chat message agrees or disagrees with the prior chat message, and assess a strength of agreement or disagreement, (d) identify at least one important point within the interval of dialog based at least in part based on an assessed level of conversational agreement among users, and (e) express to the group of users, as dialog from the simulated conversational agent, a representation of an important point identified within a prior interval of conversational dialog.
19 . The method of claim 18 wherein the simulated conversational agent expresses the important point as first person dialog within the ongoing conversation among the group of users.
20 . The method of claim 18 wherein the expressing of dialog by a simulated conversational agent is timed to occur during a pause in an ongoing conversation among a plurality of users.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. application Ser. No. 18/931,511 filed Oct. 30, 2024, for SYSTEM AND METHOD FOR AI-MEDIATED CONVERSATIONS AMONG LARGE NETWORKED POPULATIONS, which is a continuation of U.S. application Ser. No. 18/588,851, filed Feb. 27, 2024, for METHODS AND SYSTEMS FOR ENABLING CONVERSATIONAL DELIBERATION ACROSS LARGE NETWORKED POPULATIONS, now U.S. Pat. No. 12,166,735, issued Dec. 10, 2024, which is a continuation of U.S. application Ser. No. 18/240,286, filed Aug. 30, 2023, for METHODS AND SYSTEMS FOR HYPERCHAT CONVERSATIONS AMONG LARGE NETWORKED POPULATIONS WITH COLLECTIVE INTELLIGENCE AMPLIFICATION, now U.S. Pat. No. 11,949,638, issued Apr. 2, 2024, which in turn claims the benefit of U.S. Provisional Application No. 63/449,986, filed Mar. 4, 2023, for METHOD AND SYSTEM FOR “HYPERCHAT” CONVERSATIONS AMONG LARGE NETWORKED POPULATIONS WITH COLLECTIVE INTELLIGENCE AMPLIFICATION, all of which are incorporated in their entirety herein by reference. U.S. Pat. No. 10,817,158 filed on Dec. 21, 2018, U.S. Pat. No. 11,360,656 filed on Sep. 17, 2020, and U.S. application Ser. No. 17/744,464 filed on May 13, 2022, the contents of which are incorporated by reference herein in their entirety. BACKGROUND 1. Technical Field The present description relates generally to computer mediated collaboration, and more specifically to computer mediated collaboration via real-time distributed conversations over computer networks. 2. Discussion of the Related Art Whether interactive human dialog is enabled through text, video, or VR, these tools are often used to enable networked teams and other distributed groups to hold real-time interactive coherent conversation, for example, deliberative conversations, debating issues and reaching decisions, setting priorities, or otherwise collaborating in real-time. Unfortunately, real-time conversations become much less effective as the number of participants increases. Whether conducted through text, voice, video, or VR, it is very difficult to hold a coherent interactive conversation among groups that are larger than 12 to 15 people with some experts suggesting the ideal group size for interactive coherent conversation is 5 to 7 people. This has created a barrier to harnessing the collective intelligence of large groups through real-time interactive coherent conversation. SUMMARY The present disclosure describes systems and methods for enabling real-time conversational dialog among a large population of networked individuals, while facilitating convergence on groupwise decisions, insights and solutions. Embodiments of the disclosure include dividing a large user population into a plurality of smaller subgroups that are each suitable sized to enable coherent real-time deliberative conversations among its members in parallel with other subgroups. In preferred embodiments, an artificial intelligence agent performs an exchange of conversational content among subgroups to facilitate the propagation of conversational content across the population, to amplify the collective intelligence across all members, and enable the output of valuable insights generated across the subgroups. A method, apparatus, non-transitory computer readable medium, and system for computer mediated collaboration for distributed conversations are described. One or more aspects of the method, apparatus, non-transitory computer readable medium, and system include providing a collaboration server running a collaboration application, the collaboration server in communication with the plurality of the networked computing devices, each computing device associated with one member of the population of human participants, the collaboration server defining a plurality of sub-groups of the population of human participants, the collaboration server comprising: providing a local chat application on each networked computing device, the local chat application configured for displaying a conversational prompt received from the collaboration server, and for enabling real-time chat communication with other members of a sub-group assigned by the collaboration server, the real-time chat communication including sending chat input collected from the one member associated with the networked computing device to other members of the assigned sub-group; and enabling through communication between the collaboration application running on the collaboration server and the local chat applications running on each of the plurality of networked computing devices. According to some embodiments, the enabling of through conversation comprises the following steps: at step (a), sending the conversational prompt to the plurality of networked computing devices, the conversational prompt comprising a question to be collaboratively discussed by the population of human participants; at step (b), presenting, substantially simultaneously, a representation of the conversational prompt to each member of