Apparatus and methods for multiple stage process modeling

Patent metadata

Field	Value
Publication number	US-12596958-B2
Application number	US-202418414718-A
Country	US
Kind code	B2
Filing date	Jan 17, 2024
Priority date	Jan 17, 2024
Publication date	Apr 7, 2026
Grant date	Apr 7, 2026

Abstract

An apparatus and method for multiple stage process modeling is provided. The apparatus includes a processor and a memory connected to the processor. The memory containing instructions configuring the a processor to receive process data sets, each process data set representing a progression stage that describes a sequence of activities performed by an entity device, generate, using the process data sets and a machine learning algorithm, a progression outlook profile including progression stage profiles, each progression stage profile representative of a respective progression stage and may generate progression actions describing progression from a first progression stage to a second progression stage based on input data, and a progression stage profile classifier that may use input data and identify a progression stage currently occupied by a process based on input data. The processor may receive process data describing a process to classify received process data to a progression stage profile.

First claim

What is claimed is:

1 . An apparatus for multiple stage process modeling, the apparatus comprising:
a reconfigurable hardware module; at least a processor communicatively connected to the reconfigurable hardware module; and a memory connected to the at least a processor, the memory containing instructions configuring the at least a processor to:
receive a plurality of process data sets, each process data set representing a progression stage, wherein the progression stage describes a sequence of activities;
instantiate, at the reconfigurable hardware module, a progression stage profile classifier, wherein the progression stage profile classifier is generated, by a machine-learning module of the at least a processor, using a linear regression technique wherein the machine-learning module is configured to iteratively retrain the progression stage profile classifier based on user inputs indicating sub-optimal performance by performing an auditing process, wherein the progression stage profile classifier comprises a machine learning model and wherein iteratively retraining the progression stage profile classifier comprises:
sanitizing a training data of the progression stage profile classifier by eliminating training examples of the training data in order to reduce an interference of a convergence of the machine learning model in order to increase an accuracy of the machine learning model, and wherein the training examples comprise exemplary inputs and exemplary outputs;

generate, using at least some of the plurality of process data sets and the instantiated progression stage profile classifier, a progression outlook profile comprising:
a plurality of progression stage profiles, each progression stage profile representative of a respective progression stage and configured to generate progression actions describing progression from a first progression stage to a second progression stage based on input data;

receive current process data describing at least a process to be analyzed, wherein the process includes a current assessment of the sequence of activities;
classify received current process data to a progression stage profile using the progression stage profile classifier, wherein classifying comprises classifying the current assessment to at least the first progression stage;
output at least a current action datum using the progression stage profile, wherein output comprises at least a recommended action for an entity device;
generate an interface data structure including an input field, wherein the interface data structure configures a remote display device to:
display at least an input field;
receive at least a user-input datum into the input field, wherein the user-input datum describes data for updating at least the sequence of activities;
generate an activity sequence summary based on the updated sequence of activities;
display the recommended action for the entity device including data based on the user-input datum and the activity sequence summary; and
display at least a vector from the current assessment to the second progression stage, wherein the vector represents a divergence value, and wherein the divergence value describes a divergence between a first numerical classification of the current assessment and a second numerical classification of the second progression stage.

2 . The apparatus of claim 1 , wherein generating the interface data structure further comprises:
retrieving data describing attributes of the entity device from a database communicatively connected to the processor; and generating the interface data structure based on the data describing attributes of the entity device.

3 . The apparatus of claim 1 , wherein generating the recommended action for the entity device comprises:
retrieving data describing current preferences of the entity device between a minimum value and a maximum value from a database communicatively connected to the processor, wherein retrieving data further comprises receiving at least a form element input into the input field.

4 . The apparatus of claim 1 , further comprising generating at least an additional input field based on a divergence value that describes divergence between the current assessment to the second progression stage.

5 . The apparatus of claim 1 , wherein generating the recommended action for the entity device comprises:
classifying at least an instance of the current assessment to the second progression stage; determining a proximity of a respective current assessment to the second progression stage calculated based on at least the user-input datum; and adjusting the recommended action to reduce the proximity.

6 . The apparatus of claim 1 , wherein generating the recommended action for the entity device further comprises:
classifying the current assessment to the second progression stage, wherein classifying the current assessment further comprises:
comparing the current assessment to the second progression stage; and
determining a parity value based on comparison of the current assessment to the second progression stage, wherein the parity value is included within the recommended action.

7 . The apparatus of claim 4 , wherein generating the recommended action for the entity device further comprises:
determining a pattern, wherein the pattern describes entity interaction with a database communicatively connected to the processor; classifying at least an element of the pattern to the divergence value; and adjusting the pattern based on a magnitude of the divergence value.

8 . The apparatus of claim 1 , wherein generating the recommended action for the entity device further comprises:
classifying one or more new instances of the user-input datum to at least the second progression stage; generating at least a divergence value between the user-input datum and at least the second progression stage based on the classification; and displaying the divergence value.

9 . A method for multiple stage process modeling, the method comprising:
receiving, by a computing device incorporating a reconfigurable hardware module, a plurality of process data sets, each process data set representing a progression stage, wherein the progression stage describes a sequence of activities performed by an entity device; instantiating, at the reconfigurable hardware module, a progression stage profile classifier, wherein the progression stage profile classifier is generated, by a machine-learning module of the at least a processor, using a linear regression technique wherein the machine-learning module is configured to iteratively retrain the progression stage profile classifier based on user inputs indicating sub-optimal performance by performing an auditing process, wherein the progression stage profile classifier comprises a machine learning model and wherein iteratively retraining the progression stage profile classifier comprises:
sanitizing a training data of the progression stage profile classifier by eliminating training examples of the training data in order to reduce an interference of a convergence of the machine learning model to increase an accuracy of the machine learning model, and wherein the training examples comprise exemplary inputs and exemplary outputs;
generating, using at least some of the plurality of process data sets and the instantiated progression stage profile classifier, a progression outlook profile comprising:
a plurality of progression stage profiles, each progression stage profile representative of a respective progression stage and configured to generate progression actions describing progression from a first progression stage to a second progression stage based on input data;
receiving, by the

Assignees

• The Strategic Coach Inc

Inventors

• Smith Barbara Sue
• Sullivan Daniel J

Classifications

• G06N20/00 Primary

  Machine learning · CPC title