IP Library Patent Application 18791536
Patent Application
App. No. 18/791,536

APPARATUS AND METHOD OF GENERATING DIRECTED GRAPH USING RAW DATA

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 None
App. No.
18/791,536
Abstract

An apparatus and method of generating directed graph using raw data are disclosed. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to receive raw data from one or more data sources, determine a plurality of execution elements from the raw data, determine a data extrapolation of the plurality of execution elements, wherein determining the data extrapolation further includes determining at least an operation datum for the plurality of execution elements and generate a directed graph as a function of the data extrapolation, wherein the directed graph comprises an ordered series of the plurality of execution elements connected using the at least an operation datum.

Claims (55)

1 . An apparatus of generating directed graph using raw data, the apparatus comprising:

at least a processor; and

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

receive raw data describing an entity;

determine a plurality of execution elements from the raw data;

determine a data extrapolation of the plurality of execution elements; and

generate a directed graph as a function of the data extrapolation.

2 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to analyze the raw data using automatic speech recognition.

3 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to:

determine a weighted value of each of the plurality of execution elements; and

determine the data extrapolation as a function of the weighted value of each of the plurality of execution elements.

4 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to:

generate element training data, wherein the element training data comprises correlations between exemplary raw data and exemplary execution elements;

train an element machine-learning model using the element training data, wherein the element training data is iteratively updated through a feedback loop; and

determine the plurality of execution elements using the trained element machine-learning model.

5 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to:

determine an end user of the plurality of execution elements; and

determine the at least an operation datum as a function of a plurality of characteristics of the end user.

6 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to determine at least an executor of the plurality of execution elements.

7 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to determine an execution token datum of the plurality of execution elements.

8 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to generate a confidence level of the data extrapolation.

9 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to:

generate extrapolation training data, wherein the extrapolation training data comprises correlations between exemplary execution elements and exemplary data extrapolations;

train an extrapolation machine-learning model using the extrapolation training data, wherein the extrapolation training data is iteratively updated through a feedback loop; and

determine the data extrapolation using the trained extrapolation machine-learning model.

10 . The apparatus of claim 1 , wherein the memory contains the instructions configuring the at least a processor to convert the directed graph into a plurality of linguistic terms using a large language model.

11 . A method of generating a directed graph using raw data, the method comprising:

receiving, using at least a processor, raw data describing an entity;

determining, using the at least a processor, a plurality of execution elements from the raw data;

determining, using the at least a processor, a data extrapolation of the plurality of execution elements; and

generating, using the at least a processor, a directed graph as a function of the data extrapolation.

12 . The method of claim 11 , further comprising:

analyzing, using the at least a processor, the raw data using automatic speech recognition.

13 . The method of claim 11 , further comprising:

determining, using the at least a processor, a weighted value of each of the plurality of execution elements; and

determining, using the at least a processor, the data extrapolation as a function of the weighted value of each of the plurality of execution elements.

14 . The method of claim 11 , further comprising:

generating, using the at least a processor, element training data, wherein the element training data comprises correlations between exemplary raw data and exemplary execution elements;

training, using the at least a processor, an element machine-learning model using the element training data, wherein the element training data is iteratively updated through a feedback loop; and

determining, using the at least a processor, the plurality of execution elements using the trained element machine-learning model.

15 . The method of claim 11 , further comprising:

determining, using the at least a processor, an end user of the plurality of execution elements; and

determining, using the at least a processor, the at least an operation datum as a function of a plurality of characteristics of the end user.

16 . The method of claim 11 , further comprising:

determining, using the at least a processor, at least an executor of the plurality of execution elements.

17 . The method of claim 11 , further comprising:

determining, using the at least a processor, an execution token datum of the plurality of execution elements.

18 . The method of claim 11 , further comprising:

generating, using the at least a processor, a confidence level of the data extrapolation.

19 . The method of claim 11 , further comprising:

generating, using the at least a processor, extrapolation training data, wherein the extrapolation training data comprises correlations between exemplary execution elements and exemplary data extrapolations;

training, using the at least a processor, an extrapolation machine-learning model using the extrapolation training data, wherein the extrapolation training data is iteratively updated through a feedback loop; and

determining, using the at least a processor, the data extrapolation using the trained extrapolation machine-learning model.

20 . The method of claim 11 , further comprising:

converting, using the at least a processor, the directed graph into a plurality of linguistic terms using a large language model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 8, 2025
From: SMITH, BARBARA SUE; SULLIVAN, DANIEL J.
To: THE STRATEGIC COACH INC.
Reel/Frame 070768/0602 →