US-12619807-B1 - Apparatus and method for generating a predicted output

Abstract

An apparatus and method for generating a predicted output. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor. The memory instructs the processor to receive a digital twin comprising at least a plurality of virtual nodes, wherein each node is associated with an entity of a plurality of entities, determine a first scenario of a plurality of scenarios comprising one or more candidate nodes, wherein each candidate node is assigned a role of a plurality of roles within the digital twin, integrate the first scenario with the digital twin, calculate, using an AI simulator, scores corresponding to a plurality of variables associated with the integration of the first scenario and the digital twin, wherein the AI simulator propagates learned parameters through the digital twin, generate a predicted output as a function of the integration and the scores.

Inventors

• Michael Mogill

Assignees

• Crisp, Inc.

Dates

Publication Date

20260505

Application Date

20251003

Claims (18)

1. 1 . An apparatus for generating a predicted output, wherein the apparatus comprises: at least a computing device, wherein the computing device comprises: a memory; and at least a processor communicatively connected to the memory, wherein the memory contains instructions configuring the at least a processor to: receive a digital twin comprising at least a plurality of virtual nodes, wherein each node is associated with an entity of a plurality of entities; determine a first scenario of a plurality of scenarios comprising one or more candidate nodes, wherein each candidate node is assigned a role of a plurality of roles within the digital twin; integrate the first scenario with the digital twin; calculate, using an artificial intelligence (AI) simulator, scores corresponding to a plurality of variables associated with the integration of the first scenario and the digital twin, wherein the AI simulator propagates learned parameters through the digital twin, wherein calculating, using the AI simulator, the scores further comprise: instantiating the one or more candidate nodes as agents within the digital twin; simulating interactions of the agents with other nodes according to the learned parameters; mapping a plurality of operational metrics of the one or more candidate nodes to corresponding operational metrics of the plurality of virtual nodes of the digital twin; comparing the mapped operational metrics; identifying a degree of concordance of the mapped operational metrics; and assigning a score to each variable of the plurality of variables associated with the integration; generate a predicted output as a function of the integration and the scores; and provide, using a user interface, a recommendation as a function of ranking a plurality of predictive outputs of the predictive output as a function of the scores and user input in real-time.
2. 2 . The apparatus of claim 1 , wherein the predictive output comprises one or more predicted operational outcomes.
3. 3 . The apparatus of claim 1 , wherein: each candidate node is associated with a third party of a plurality of third parties, and each candidate node comprises third party data associated with a corresponding third party.
4. 4 . The apparatus of claim 1 , wherein the at least a processor is further configured to generate the digital twin by: defining at least an objective of the digital twin; collecting operational data associated with the plurality of nodes and an environment; generating, using a machine learning model, the digital twin as a function of the operational data; and updating, using one or more data streams, the digital twin wherein the one or more data streams provide new operational data associated with the plurality of nodes and the environment.
5. 5 . The apparatus of claim 1 , wherein the at least a processor is further configured to transmit the predicted output to a downstream model, wherein the downstream model is configured to identify the one or more candidate nodes from a candidate database.
6. 6 . The apparatus of claim 1 , wherein the at least a processor is further configured to: integrate a second scenario with the digital twin; calculate, using the AI simulator, scores corresponding to the plurality of variables associated with the integration of the second scenario and the digital twin; and generate one or more alternative predicted outputs as a function of the integration and the scores.
7. 7 . The apparatus of claim 1 , wherein the at least a processor is further configured to generate a recommendation as a function of ranking a plurality of predictive outputs of the predictive output as a function of the scores and user input.
8. 8 . The apparatus of claim 1 , wherein the at least a processor is further configured to display, using the user interface, a visualization corresponding to the predicted output, wherein the visualization comprises a graphical representation of the plurality of scenarios and a simulation timeline.
9. 9 . The apparatus of claim 1 , wherein the at least a processor is further configured to calibrate the AI simulator using historical operational data associated with the plurality of nodes, wherein calibrating comprises adjusting node parameters within the digital twin to observed outcomes.
10. 10 . A method for generating a predicted output, wherein the method comprises: receiving, using at least a processor, a digital twin comprising at least a plurality of virtual nodes, wherein each node is associated with an entity of a plurality of entities; determining, using the at least a processor, a first scenario of a plurality of scenarios comprising one or more candidate nodes of a one or more candidate nodes, wherein each candidate node of the one or more candidate nodes are assigned a role of a plurality of roles within the digital twin; integrating, using the at least a processor, the first scenario with the digital twin; calculating, using an artificial intelligence (AI) simulator, scores corresponding to a plurality of variables associated with the integration of the first scenario and the digital twin, wherein the AI simulator propagates learned parameters through the digital twin wherein calculating, using the AI simulator, the scores further comprise: instantiating the one or more candidate nodes as agents within the digital twin; simulating interactions of the agents with other nodes according to the learned parameters; mapping a plurality of operational metrics of the one or more candidate nodes to corresponding operational metrics of the plurality of virtual nodes of the digital twin; comparing the mapped operational metrics; identifying a degree of concordance of the mapped operational metrics; and assigning a score to each variable of the plurality of variables associated with the integration; generating, using the at least a processor, a predicted output as a function of the integration and the scores; providing, using a user interface, a recommendation as a function of ranking a plurality of predictive outputs of the predictive output as a function of the scores and user input in real-time.
11. 11 . The method of claim 10 , wherein the predictive output comprises one or more predicted operational outcomes.
12. 12 . The method of claim 10 , wherein: each candidate node is associated with a third party of a plurality of third parties, and each candidate node comprises third party data associated with a corresponding third party.
13. 13 . The method of claim 10 , further comprising generating, using the at least a processor, the digital twin by: defining, using the at least a processor, at least an objective of the digital twin; collecting, using the at least a processor, operational data associated with the plurality of nodes and an environment; generating, using a machine learning model, the digital twin as a function of the operational data; updating, using one or more data streams, the digital twin wherein the one or more data streams provide new operational data associated with the plurality of nodes and the environment.
14. 14 . The method of claim 10 , further comprising transmitting, using the at least a processor, the predicted output to a downstream model, wherein the downstream model identifies the one or more candidate nodes from a candidate database.
15. 15 . The method of claim 10 , further comprising: integrating, using the at least a processor, a second scenario with the digital twin; calculating, using the AI simulator, scores corresponding to the plurality of variables associated with the integration of the second scenario and the digital twin; and generating, using the at least a processor, one or more alternative predicted outputs as a function of the integration and the scores.
16. 16 . The method of claim 10 , further comprising generating, using the at least a processor, a recommendation as a function of ranking a plurality of predictive outputs of the predictive output as a function of the scores and user input.
17. 17 . The method of claim 10 , further comprising displaying, using the user interface, a visualization corresponding to the predicted output, wherein the visualization comprises a graphical representation of the plurality of scenarios and a simulation timeline.
18. 18 . The method of claim 10 , further comprising calibrating, using the at least a processor, the AI simulator using historical operational data associated with the plurality of nodes by adjusting node parameters within the digital twin to observed outcomes.

Description

FIELD OF THE INVENTION The present invention generally relates to the field of machine learning. In particular, the present invention is directed to an apparatus and a method for generating a predicted output. BACKGROUND In many systems, it is difficult to predict how changes will affect the overall operation when multiple elements are interacting at once. Conventional models often cannot capture the detailed behaviors of different components, especially when those components follow distinct rules or constraints. As a result, predictions may lack accuracy and fail to reflect the actual behavior of the system under new conditions. SUMMARY OF THE DISCLOSURE In an aspect, an apparatus for generating a predicted output includes at least a processor and a memory communicatively connected to the at least a processor. The memory contains instructions configuring the processor to receive a digital twin comprising at least a plurality of virtual nodes, wherein each node is associated with an entity of a plurality of entities, determine a first scenario of a plurality of scenarios comprising one or more candidate nodes, wherein each candidate node is assigned a role of a plurality of roles within the digital twin, integrate the first scenario with the digital twin, calculate, using an AI simulator, scores corresponding to a plurality of variables associated with the integration of the first scenario and the digital twin, wherein the AI simulator propagates learned parameters through the digital twin, generate a predicted output as a function of the integration and the scores. In another aspect, a method for generating a predicted output includes receiving, using at least a processor, a digital twin comprising at least a plurality of virtual nodes, wherein each node is associated with an entity of a plurality of entities, determining, using the at least a processor, a first scenario of a plurality of scenarios comprising one or more candidate nodes of a one or more candidate nodes, wherein each candidate node of the one or more candidate nodes are assigned a role of a plurality of roles within the digital twin, integrating, using the at least a processor, the first scenario with the digital twin, calculating, using an AI simulator, scores corresponding to a plurality of variables associated with the integration of the first scenario and the digital twin, wherein the AI simulator propagates learned parameters through the digital twin, generating, using the at least a processor, a predicted output as a function of the integration and the scores. These and other aspects and features of non-limiting embodiments of the present invention will become apparent to those skilled in the art upon review of the following description of specific non-limiting embodiments of the invention in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS For the purpose of illustrating the invention, the drawings show aspects of one or more embodiments of the invention. However, it should be understood that the present invention is not limited to the precise arrangements and instrumentalities shown in the drawings, wherein: FIG. 1 is a block diagram of an apparatus for generating a predicted output; FIG. 2 is a block diagram of an exemplary machine-learning process; FIG. 3 is a diagram of an exemplary embodiment of a neural network; FIG. 4 is a diagram of an exemplary embodiment of a node of a neural network; FIG. 5 is an exemplary embodiment of a graphical user interface of a digital twin; FIG. 6 is a block diagram of an exemplary method for generating a predicted output; and FIG. 7 is a block diagram of a computing system that can be used to implement any one or more of the methodologies disclosed herein and any one or more portions thereof. The drawings are not necessarily to scale and may be illustrated by phantom lines, diagrammatic representations and fragmentary views. In certain instances, details that are not necessary for an understanding of the embodiments or that render other details difficult to perceive may have been omitted. DETAILED DESCRIPTION At a high level, aspects of the present disclosure are directed to apparatus and methods for generating a predicted output. The apparatus includes at least a computing device comprised of a processor and a memory communicatively connected to the processor. The memory instructs the processor to receive a digital twin comprising at least a plurality of virtual nodes, wherein each node is associated with an entity of a plurality of entities. The processor determines a first scenario of a plurality of scenarios comprising one or more candidate nodes, wherein each candidate node is assigned a role of a plurality of roles within the digital twin. The processor integrates the first scenario with the digital twin. Additionally, the processor calculates, using an AI simulator, scores corresponding to a plurality of variables associated with the integration of the first sce