# US 12,120,182 B2 · Systems and methods for modulating data objects to effect state changes

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

- Number: US 12,120,182 B2
- Document ID: US12120182B2
- Status: Granted
- Kind: B2
- Application number: 17/860,047
- Filed: 2022-07-07
- Published: 2023-02-09
- Granted: 2024-10-15
- Earliest claimed: 2021-07-07
- Assignees: Daily Rays Inc.
- Applicants: Daily Rays Inc.
- Inventors: Ashley Saye; Diego I. Medina-Bernal; Jonathon Nostrant
- Web page: https://patentgrep.com/patent/US12120182B2

## CPC

- H04L 67/12: specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04W 4/38: for collecting sensor information
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

Systems and methods for modulating content to effect state change are described. A state control system initiates a process for modulating output objects to effect one or more changes in a state profile associated with a user device. The system queries for historical data associated with the user device; determines whether any historical data is identified for user device and in response to determining that historical data is found predicts a current state profile associated with the user device. The system further collects real-time sensor data associated with user device; filters and normalizes the sensor data; and delivers a plurality of output objects to the user device or secondary device(s) based on real-time sensor data.

## Claims

### Claim 1

A system for modulating output objects for effecting state change, the system comprising:
a network-connected state control computer comprising a memory and a processor and further comprising programmable instructions stored in the memory and operating on the processor, the instructions when executed by the processor, cause the processor to:
receive user data indicative of a current state of a user associated with a user device, wherein the user data comprises real-time sensor data, historical data, user interaction data, and transactional data associated with the user device over a timeline wherein the timeline represents a difference between a predicted state and an expected state;
identify a plurality of output objects for delivery to the user device, the plurality of output objects collectively representing influenceable factors to affect a change a state of the user between the predicted state and the expected state over the timeline;
rank the plurality of output objects, wherein to rank the plurality of output objects, the programmable instructions when further executed by the processor cause the processor to:
create a user encoding representation vector and media encoding representation matrix for each output object of the plurality of output objects;
perform a dot-product operation, the dot product operation operable to identify a best output object wherein a higher dot-product equates to a higher satisfactory predictive ranking; and
wherein upon the dot-product operation being positive, the user device allows a receipt of the first output object, otherwise, the user device discards the first output object;
identify a plurality of points in time in the timeline wherein each point in time of the plurality of points in time represent a time to deliver an output object of the plurality of output objects to affect the change of a state of the user;
identify at least one category and sub-category associated with the plurality of output objects based on the user data;
select a first output object of the plurality of output objects for the user device from the at least one category and sub-category, wherein the selected object is a highest ranked output object designed to bring a change in the current state of the user;
deliver the first output object to the user device at a first point in time of the plurality of points in time, wherein the output object comprises text, an audio file, a video file, or haptic output;
receive feedback from the user device, wherein the feedback is received in response to the delivered selected output object; and
responsive to receiving feedback, predict a different plurality of points in time in the timeline for delivering other output objects of the plurality of output objects from the at least one category and sub-category.

### Claim 2 (depends on 1)

The system of claim 1, wherein the network-connected state control computer is in communication with the user device and iteratively receives feedback from the users at multiple intervals, wherein the feedback is associated with the delivered output objects.

### Claim 3 (depends on 1)

The system of claim 1, wherein to the plurality of instructions when executed by the processor, further cause the processor to:
encode the user data into a lower-dimensional representation vectors, wherein the user data is encoded after normalization of the received user data into vectors; and
decode the lower-dimensional representation vectors using pre-trained models to identify at least one category and sub-category for the received user data.