IP Library Granted Patent US 12,639,591
Granted Patent B1
US 12,639,591 · App. 18/957,617 · Granted May 26, 2026

Apparatus and methods for generating structured data outputs

Inventors: Blake Browder (Dallas, TX); Joy Figarsky (Little Rock, AR)
Assignee: BH Operations, LLC
G06N5/022
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,639,591
App. No.
18/957,617
Granted
May 26, 2026
Kind
B1
Abstract

Apparatus for generating structured data outputs and methods used therein include a processor and a memory connected to the processor, wherein the memory contains instructions configuring the processor to receive entity data associated with an entity, the entity data including projection data and location-based data, determine at least a selection criterion as a function of the entity data, receive from a data repository a plurality of metrics as a function of the at least a selection criterion, select at least an output parameter by applying the at least a selection criterion to a plurality of output parameters, as a function of the plurality of metrics, and synthesize, using an output generation machine-learning model trained on output generation training data, a structured data output as a function of the at least an output parameter, wherein the structured data output includes a plurality of event handler graphics.

Claims (54)

1 . An apparatus for generating structured data outputs using projection data and geographic data, the apparatus comprising:

a processor; and

a memory communicatively connected to the processor, wherein the memory contains instructions configuring the processor to:

receive entity data associated with an entity, the entity data comprising projection data and location-based data;

determine at least a selection criterion as a function of the entity data, wherein the at least a selection criterion is associated with a weight, wherein the weight reflects at least a level of flexibility of the at least a selection criterion;

receive from a data repository a plurality of metrics as a function of the at least a selection criterion;

select at least an output parameter by applying the at least a selection criterion to a plurality of output parameters, as a function of the plurality of metrics;

synthesize, using an output generation machine-learning model, a structured data output, wherein the output generation machine-learning model comprises a large language model (LLM), and wherein synthesizing the structured data output further comprises:

pretraining the LLM on a general set of training examples; and

fine-tuning the LLM, by adjusting at least a weight of the LLM to optimize performance, on a special set of training examples comprising a database associated with the entity, wherein the general and the special set of training examples are subsets of a plurality of training examples;

receiving output generation training data, wherein the output generation training data includes exemplary output parameters as inputs correlated with exemplary structured data outputs as outputs, wherein the structured data output comprises a plurality of event handler graphics;

iteratively training the output generation machine-learning model as a function of the output generation training data; and

synthesizing the structured data output using the trained output generation machine-learning model; and

display the structured data output comprising a color-coded visualization represented by a unique combination of red green blue (RGB) values wherein each color represents a different feature within the color-coded visualization using a graphical user interface.

2 . The apparatus of claim 1 , wherein receiving the entity data comprises:

aggregating user data pertaining to a plurality of users associated with the entity;

filtering the aggregated user data as a function of the location-based data; and

updating the entity data as a function of the filtered user data.

3 . The apparatus of claim 1 , wherein:

the entity data comprises a size of the entity; and

determining the at least a selection criterion comprises determining the at least a selection criterion as a function of the size of the entity.

4 . The apparatus of claim 1 , wherein the projection data comprises a projected level of occupancy.

5 . The apparatus of claim 1 , wherein the structured data output comprises a time-correlated list of action items.

6 . The apparatus of claim 1 , wherein the structured data output comprises a color-coded visualization.

7 . The apparatus of claim 6 , wherein displaying the structured data output using the graphical user interface comprises assigning a color to a visual element of the graphical user interface as a function of the at least an output parameter.

8 . The apparatus of claim 1 , wherein the processor is further configured to:

receive supplemental entity data; and

iteratively update the structured data output as a function of the supplemental entity data.

9 . A method for generating structured data outputs, the method comprising:

receiving, by a processor, entity data associated with an entity, the entity data comprising projection data and location-based data;

determining, by the processor, at least a selection criterion as a function of the entity data, wherein the at least a selection criterion is associated with a weight, wherein the weight reflects at least a level of flexibility of the at least a selection criterion;

receiving, by the processor from a data repository, a plurality of metrics as a function of the at least a selection criterion;

selecting, by the processor, at least an output parameter by applying the at least a selection criterion to a plurality of output parameters, as a function of the plurality of metrics;

synthesizing, by the processor using an output generation machine-learning model, a structured data output, wherein the output generation machine-learning model comprises a large language model (LLM), and wherein synthesizing the structured data output further comprises:

pretraining the LLM on a general set of training examples; and

fine-tuning the LLM, by adjusting at least a weight of the LLM to optimize performance, on a special set of training examples comprising a database associated with the entity, wherein the general and the special set of training examples are subsets of a plurality of training examples;

receiving output generation training data, wherein the output generation training data includes exemplary output parameters as inputs correlated with exemplary structured data outputs as outputs, wherein the structured data output comprises a plurality of event handler graphics;

iteratively training the output generation machine-learning model as a function of the output generation training data; and

synthesizing the structured data output using the trained output generation machine-learning model; and

displaying, by the processor using a graphical user interface, the structured data output comprising a color-coded visualization represented by a unique combination of red green blue (RGB) values wherein each color represents a different feature within the color-coded visualization.

10 . The method of claim 9 , wherein receiving the entity data comprises:

aggregating user data pertaining to a plurality of users associated with the entity;

filtering the aggregated user data as a function of the location-based data; and

updating the entity data as a function of the filtered user data.

11 . The method of claim 9 , wherein:

the entity data comprises a size of the entity; and

determining the at least a selection criterion comprises determining the at least a selection criterion as a function of the size of the entity.

12 . The method of claim 9 , wherein the projection data comprises a projected level of occupancy.

13 . The method of claim 9 , wherein the structured data output comprises a time-correlated list of action items.

14 . The method of claim 9 , wherein the structured data output comprises a color-coded visualization.

15 . The method of claim 14 , wherein displaying the structured data output using the graphical user interface comprises assigning a color to a visual element of the graphical user interface as a function of the at least an output parameter.

16 . The method of claim 9 , further comprising:

receiving, by the processor, supplemental entity data; and

iteratively updating, by the processor, the structured data output as a function of the supplemental entity data.

Assignments (2)
CORRECTIVE ASSIGNMENT TO CORRECT THE ASSIGNEE PREVIOUSLY RECORDED ON REEL 72292 FRAME 767. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Dec 16, 2025
From: SIGNET HEALTH CORPORATION
To: BH OPERATIONS, LLC
Reel/Frame 073992/0817 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 31, 2025
From: SIGNET HEALTH CORPORATION
To: BEHAVIORAL HEALTH OPERATIONS, LLC
Reel/Frame 072292/0767 →
References Cited (10)
US 11587683B2 · Frank · 2023 [cited by examiner]
US 11961622B1 · El Saadawi · 2024 [cited by examiner]
US 12243646B1 · Paul, Jr. · 2025 [cited by examiner]
US 20210344636A1 · Martin · 2021 [cited by examiner]
US 20230008936A1 · Adhikari · 2023 [cited by examiner]
US 20240266074A1 · Smurro · 2024 [cited by examiner]
US 20250200274A1 · Jaiswal · 2025 [cited by examiner]
US 20250225043A1 · Hänsel · 2025 [cited by examiner]
CN 110517781A · 2019 [cited by applicant]
CN 114898884A · 2022 [cited by applicant]