Granted Patent B1

US 12,314,325 · App. 18/600,429 · Granted May 27, 2025

Inventors: Barbara Sue Smith (Toronto, CA); Daniel J. Sullivan (Toronto, CA)

Assignee: The Strategic Coach Inc.

G06F16/906G06F16/901

Abstract

Claims (47)

1. An apparatus for generating a data structure for operational inefficiency, 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 related to a process from one or more data sources;

cluster each datum of the raw data into a plurality of data clusters, wherein clustering each datum of the raw data into the plurality of data clusters comprises a feature learning algorithm configured to condition the raw data, identify features in the raw data, detect co-occurrences of features of process, and cluster the raw data into the plurality of data clusters as a function of the detected co-occurrences of features of process, and wherein the features identified by the feature learning algorithm include at least a repeating task a user is processing;

aggregate a plurality of operational consumptions from the raw data in each of the plurality of data clusters, wherein the aggregation comprises converting a non-quantitative datum of the plurality of operational consumptions into a quantitative datum comprising numerical values by implementing a converting machine-learning model;

determine an operational inefficiency of each of the plurality of data clusters as a function of the aggregated operational consumptions, wherein determining the operational inefficiency comprises:

generating inefficiency training data, wherein the inefficiency training data comprises correlations between exemplary operational consumptions and exemplary operational inefficiencies;

iteratively updating the inefficiency training data through a feedback loop based on operation inefficiency data received form a process database;

training an inefficiency machine-learning model using the updated inefficiency training data; and

determining the operational inefficiency of each of the plurality of data clusters using the trained inefficiency machine-learning model; and

generate an operation data structure as a function of the operational inefficiency using a large language model, wherein the memory contains instructions further configuring the at least a processor to modify a formatting error of an operational consumption using a machine-learning model.

2. The apparatus of claim 1 , wherein receiving the raw data related to the process from one or more data sources comprises receiving data using a chatbot.

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

determine one clustering algorithm from a plurality of clustering algorithms; and

cluster the raw data into the plurality of data clusters using the determined clustering algorithm.

4. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to extract an operational consumption from the raw data in the plurality of data clusters using a language processing module.

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

determine a compatibility of each of the plurality of data clusters to the process; and

determine the operational inefficiency as a function of the compatibility.

6. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to determine a degree of operational inefficiency as a function of the aggregated operational consumptions.

7. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to transmit the operation data structure to a remote device.

8. A method for generating a data structure for operational inefficiency, the method comprising:

receiving, using at least a processor, raw data related to a process from one or more data sources;

clustering, using the at least a processor, each datum of the raw data into a plurality of data clusters, wherein clustering each datum of the raw data into the plurality of data clusters comprises a feature learning algorithm configured to condition the raw data, identify features in the raw data, detect co-occurrences of features of process, and cluster the raw data into the plurality of data clusters as a function of the detected co-occurrences of features of process, and wherein the features identified by the feature learning algorithm include at least a repeating task a user is processing;

aggregating, using the at least a processor, a plurality of operational consumptions from the raw data in each of the plurality of data clusters, wherein the aggregation comprises converting a non-quantitative datum of the plurality of operational consumptions into a quantitative datum comprising numerical values by implementing a converting machine-learning model;

determining, using the at least a processor, an operational inefficiency of each of the plurality of data clusters as a function of the aggregated operational consumptions, wherein determining the operational inefficiency comprises:

generating inefficiency training data, wherein the inefficiency training data comprises correlations between exemplary operational consumptions and exemplary operational inefficiencies;

iteratively updating the inefficiency training data through a feedback loop based on operation inefficiency data received form a process database;

training an inefficiency machine-learning model using the updated inefficiency training data; and

determining the operational inefficiency of each of the plurality of data clusters using the trained inefficiency machine-learning model;

generating, using the at least a processor, an operation data structure as a function of the operational inefficiency using a large language model; and

modifying, using the at least a processor, a formatting error of an operational consumption using a machine-learning model.

9. The method of claim 8 , further comprising:

receiving, using the at least a processor, data using a chatbot.

10. The method of claim 8 , further comprising:

determining, using the at least a processor, one clustering algorithm from a plurality of clustering algorithms; and

clustering, using the at least a processor, the raw data into the plurality of data clusters using the determined clustering algorithm.

11. The method of claim 8 , further comprising:

extracting, using the at least a processor, an operational consumption from the raw data in the plurality of data clusters using a language processing module.

12. The method of claim 8 , further comprising:

determining, using the at least a processor, a compatibility of each of the plurality of data clusters to the process; and

determining, using the at least a processor, the operational inefficiency as a function of the compatibility.

13. The method of claim 8 , further comprising:

determining, using the at least a processor, a degree of operational inefficiency as a function of the aggregated operational consumptions.

14. The method of claim 8 , further comprising:

transmitting, using the at least a processor, the operation data structure to a remote device.

Assignments (1)

References Cited (8)