# US 2026/0278427 A1 · System to detect, assess and counter disinformation

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

- Number: US 2026/0278427 A1
- Document ID: US20260278427A1
- Status: Published application
- Kind: A1
- Application number: 19/672,197
- Filed: 2026-05-08
- Published: 2026-09-17
- Earliest claimed: 2019-08-26
- Assignees: Chenope, Inc.
- Applicants: Chenope, Inc.
- Inventors: Elizabeth CHARNOCK; Steve ROBERTS; Kathrin HAAG
- Web page: https://patentgrep.com/patent/US20260278427A1

## CPC

- G06N 5/046: Forward inferencing; Production systems
- G06F 16/951: Indexing; Web crawling techniques
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/08: Learning methods
- G06Q 10/40: Business processes related to social networking or social networking services
- G06Q 10/44: Identification of trends within social networks, e.g. identification of trending topics
- G06Q 10/46: Determination of level of influence of users within social networking services
- G06Q 10/48: using social graphs
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G06F 40/186: Templates
- G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30)
- G06F 40/205: Parsing
- G06F 40/279: Recognition of textual entities
- G06N 5/025: Extracting rules from data
- G06N 20/00: Machine learning
- H04L 63/302: {gathering intelligence information for situation awareness or reconnaissance}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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)

## Abstract

A computer-readable medium for the identification, measurement, and combatting of the influence of large-scale creation and distribution of disinformation is herein disclosed. An embodiment of this invention is comprised of one or more repositories of data which involve online comments and articles and attributes derived from them, one or more technical targeting systems, a content analysis system, a cost and influence estimation system, a dialog system, a performance management system, a bot design and test system, a security system, a multimedia content generator, one or more machine learning components, a data collection mechanism, separate consumer and human operator applications, and a mechanism for the creation and management of bots across multiple channels.

## Claims

### Claim 1

A system for detecting synchronization relationships among online entities through hypergraph-based analysis, comprising:
one or more message queues configured to receive data records encoding online content collected from one or more electronic media;
one or more storage devices configured to store a hypergraph; and
one or more processors configured to execute instructions stored in one or more non-transitory computer-readable media, the instructions causing the one or more processors to:
decode incoming messages from the one or more message queues into structured data values;
filter the structured data values through an online query engine to produce observations, each observation representing an instance of online behavior by an entity;
direct the observations to a synchronization detector comprising a plurality of buckets, each bucket configured to accumulate observations satisfying a temporal or behavioral co-occurrence criterion;
for each bucket, determine whether accumulated observations constitute a synchronization relationship between two or more entities based on a frequency threshold derived from a null model representing a distribution of random co-occurrences;
generate synchronization edges in a hypergraph shard stored on the one or more storage devices, each synchronization edge referencing the two or more entities and one or more synchronization instance edges, each synchronization instance edge referencing one or more of the observations;
apply an aging policy to reduce weights on the synchronization edges over time; and
project the synchronization edges through a projection operator to one or more downstream message queues for consumption by one or more downstream analytic components.

### Claim 2 (depends on 1)

The system of claim 1, wherein the instructions further cause the one or more processors to:
maintain a cache data structure within each bucket having a bounded capacity, the cache data structure configured to store entity-frequency pairs;
when the cache is full and a new entity is encountered, replace a least recently used entity-frequency pair with the new entity;
increment a frequency value for an entity already present in the cache upon encountering a subsequent observation for that entity; and
generate a synchronization edge between two entities in the cache when both entities have accumulated at least a configurable minimum frequency value.

### Claim 3 (depends on 1)

The system of claim 1, wherein the instructions further cause the one or more processors to:
pre-allocate buckets using an interval tree data structure, each interval corresponding to a potential step in a sequence of observations;
upon creation of each new interval, store a reference to a prior interval to enable recovery of a complete sequence of observations; and
age out intervals whose creation times fall outside a time span determined by parameters supplied from a control model.

### Claim 4 (depends on 1)

The system of claim 1, wherein the instructions further cause the one or more processors to:
receive the synchronization edges from the projection operator;
derive a group artifact from the synchronization edges by computing connected components over the synchronization edges with edge filtering based on edge weight;
calculate a structure measure for each group artifact, the structure measure quantifying a degree of difference between the group artifact and a corresponding fully connected group;
discard group artifacts having a structure measure below a threshold; and
for each remaining group artifact, compute a partial edge intersection to identify one or more trajectories sharing a proportion of members with the group artifact.

### Claim 5 (depends on 4)

The system of claim 4, wherein the instructions further cause the one or more processors to:
compare structure scores of the group artifact against structure scores of candidate trajectories;
for candidate trajectories with close structure scores, apply a similarity test based on differences in neighborhoods of selected members; and
assign the group artifact to an existing trajectory when a single matching candidate trajectory is identified, or start a new trajectory when no matching candidate trajectory is identified.

### Claim 6 (depends on 1)

The system of claim 1, wherein the instructions further cause the one or more processors to:
compute an edge intersection starting from an input member set by accumulating counts into a table keyed by edge identifiers, wherein for each atom in the input member set, incident edges are enumerated and their counts incremented in the table;
scan the table and return edges that accumulate a count equal to a size of the input member set; and
reduce a size of the table by clearing entries after processing a second and subsequent members of the input member set when an edge count is less than a number of members processed.

### Claim 7 (depends on 1)

The system of claim 1, wherein the instructions further cause the one or more processors to:
compute an edge overlap starting from an input edge by enumerating incident members of the input edge to form a member set, optionally culling members based on a member pool;
perform an edge intersection on the member set to produce a set of resulting edges;
perform a member intersection on the set of resulting edges to identify additional members beyond the member set; and
return a member result set and an edge result set.
