# US 2026/0030702 A1 · System and method for adaptive ideation and innovation management using graph-based similarity computation and real-time social facilitation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0030702 A1
- Document ID: US20260030702A1
- Status: Published application
- Kind: A1
- Application number: 19/347,427
- Filed: 2025-10-01
- Published: 2026-01-29
- Earliest claimed: 2017-04-03
- Inventors: Moses T. Ma
- Web page: https://patentgrep.com/patent/US20260030702A1

## CPC

- G06Q 50/184: {Intellectual property management}
- H04L 9/0637: {Modes of operation, e.g. cipher block chaining [CBC], electronic codebook [ECB] or Galois/counter mode [GCM]}
- H04L 9/12: Transmitting and receiving encryption devices synchronised or initially set up in a particular manner
- H04L 9/3236: {using cryptographic hash functions}
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- H04L 9/50: {using hash chains, e.g. blockchains or hash trees}
- H04L 2209/56: Financial cryptography, e.g. electronic payment or e-cash
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system and method for adaptive ideation and innovation management using graph-based similarity computation and real-time social facilitation are disclosed, and the system may include a plurality of client devices operated by a human user and one or more AI Agents. The system may further include a computing platform running a Precompute Similarity Engine that may be configured to embed and index idea objects, precompute similarity clusters, and generate candidate merge or purge operations together with diversity and novelty signals; and running a Social Physics Engine that may be configured to monitor human user and machine participant (AI agent) interactions, compute group metrics, and issue digital facilitation interventions. The Precompute Similarity Engine and the Social Physics Engine may operate in an interdependent feedback loop such that diversity and novelty signals guide the generation of digital facilitation interventions that are communicated via the network to the plurality of client devices and the one or more AI Agents.

## Claims

### Claim 1

A system for adaptive ideation and innovation management using graph-based similarity computation and real-time social facilitation, the system comprising:
a. a plurality of client devices in communication with a network, wherein at least one client device of the plurality of client devices is operated by a human user;
b. an AI Agent running on a first computing platform, wherein the first computing platform is in communication with the network;
c. a second computing platform one or more processors, wherein the second computing platform is in communication with the network; and
d. memory storing one or more computer-executable instructions that are executable by the one or more processors to perform operations comprising: running a Precompute Similarity Engine configured to embed and index idea objects, precompute similarity clusters, and generate candidate merge or purge operations together with diversity and novelty signals; and running a Social Physics Engine configured to monitor human and machine participant interactions, compute group metrics, and issue digital facilitation interventions, wherein the Precompute Similarity Engine and the Social Physics Engine operate in an interdependent feedback loop such that diversity and novelty signals guide the generation of digital facilitation interventions that are communicated via the network to the plurality of client devices and the AI Agent, and wherein newly generated idea objects are triaged by the Precompute Similarity Engine for merging or preservation of diversity.

### Claim 2 (depends on 1)

The system of claim 1, wherein the memory comprises a non-transitory computer-readable medium storing instructions for running the Precompute Similarity Engine and the Social Physics Engine.

### Claim 3 (depends on 1)

The system of claim 1, wherein the Precompute Similarity Engine employs hybrid retrieval combining lexical indices with approximate nearest-neighbor embeddings.

### Claim 4 (depends on 1)

The system of claim 1, wherein the Social Physics Engine issues digital facilitation interventions to the plurality of client devices and the AI Agent, and wherein the digital facilitation interventions selected from divergence prompts, convergence prompts, role-based assignments to AI agents, or private nudges to under-participating users.

### Claim 5 (depends on 1)

The system of claim 1, wherein diversity and novelty signals bias facilitation interventions toward under-explored clusters of ideas.

### Claim 6 (depends on 1)

The system of claim 1, further comprising a governance and orchestration layer configured to enforce consent and intellectual property policies and to schedule background precompute operations.

### Claim 7 (depends on 1)

The system of claim 1, wherein newly generated ideas are routed to the Precompute Similarity Engine within less than 300 milliseconds to enable near real-time triage, and reduce cognitive workload for human users to merge or prune/modify ideas.

### Claim 8

A computer-implemented method for adaptive ideation and innovation management using graph-based similarity computation and real-time social facilitation, the method comprising:
a. embedding and indexing idea objects in lexical and vector spaces;
b. precomputing similarity clusters and generating candidate merge or purge operations;
c. computing diversity and novelty signals from said clusters;
d. sensing conversational and interaction streams during a brainstorming session;
e. computing group metrics comprising participation equity, sentiment alignment, and topical coherence;
f. issuing, via a network, digital facilitation interventions to a plurality of client devices and to at least one AI Agent based on said metrics and said diversity and novelty signals; and
g. ingesting new idea objects produced during said interventions and triaging the objects via similarity operations to merge near-duplicates or preserve novel contributions.
