# US 2020/0402670 A1 · Systems and methods for reducing resource consumption via information technology infrastructure

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0402670 A1
- Document ID: US20200402670A1
- Status: Published application
- Kind: A1
- Application number: 17/012,756
- Filed: 2020-09-04
- Published: 2020-12-24
- Earliest claimed: 2015-12-16
- Assignees: Alegeus Technologies, LLC
- Applicants: Alegeus Technologies, LLC
- Inventors: John Bull; Chris Rodkey
- Web page: https://patentgrep.com/patent/US20200402670A1

## CPC

- G06Q 40/123: {Tax preparation or submission}
- G06F 16/24578: {using ranking}
- G06Q 10/10: Office automation; Time management
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

The present disclosure is directed to reducing resource consumption via information technology infrastructure. A server of the present disclosure receives one or more data packets including data indicating a healthcare transaction event. The server selects healthcare trend model trained by the server using previously received data packets. The server determines a correlation coefficient between each of a plurality of healthcare related recommendations and the selected healthcare trend model. The server retrieves a notification template from a notification data structure that maps to the highest ranking healthcare related recommendation. The server generates a request to deliver the notification corresponding to the highest ranking healthcare related recommendation at a destination address of a computing device of a participant.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

A system to manage transactions, comprising:
one or more processors, coupled to memory and configured to:
identify a healthcare transaction event corresponding to a participant of a plurality of participants of a healthcare platform;
select, based at least in part on a type of the healthcare transaction event, a healthcare trend model trained by a machine learning engine using historical healthcare transaction events corresponding to the plurality of participants of the healthcare platform, the healthcare trend model trained by the machine learning engine to include a baseline threshold for one or more features;
determine, based on a comparison between the healthcare transaction event and the baseline threshold of the one or more features of the selected healthcare trend model, to generate one or more notifications to control an occurrence of the type of the healthcare transaction event corresponding to the healthcare transaction event;
select, based at least in part on the selected healthcare trend model trained using the machine learning engine, a notification to control the occurrence of the type of the healthcare transaction event; and
transmit, via a network, the notification to a computing device associated with the participant to control the occurrence of the type of the healthcare transaction event.

### Claim 22 (depends on 21)

The system of claim 21, wherein the healthcare transaction events include one or more of a claim payment, a card denial, a password change, or a received deposit.

### Claim 23 (depends on 21)

The system of claim 21, wherein the one or more processors are further configured to:
determine the baseline threshold for one or more features comprising at least one of a type of event, geographic area, or time of year.

### Claim 24 (depends on 21)

The system of claim 21, wherein the one or more processors are further configured to:
receive the historical healthcare transaction events corresponding to the plurality of participants from a device of an administrator remote from the one or more processors via an administrator interface rendered by the one or more processors on the device of the administrator.

### Claim 25 (depends on 21)

The system of claim 21, wherein the machine learning engine is configured to use at least one of a decision tree learning, a predictive model, association rule learning, support vector machines, clustering, or reinforcement learning.

### Claim 26 (depends on 21)

The system of claim 21, wherein the one or more processors are further configured to:
select the healthcare trend model from a plurality of healthcare trend models based on a minimum vector distance between the healthcare transaction event and each of the plurality of healthcare trend models.

### Claim 27 (depends on 21)

The system of claim 21, wherein the type of the healthcare transaction event comprises a denial, and the one or more processors are further configured to:
retrieve a denial healthcare trend model responsive to the healthcare transaction event including the denial; and
select, based on the denial healthcare trend model, a denial recommendation comprising a recommended resource allocation responsive to determining that an insufficient amount of resources resulted in the denial.

### Claim 28 (depends on 21)

The system of claim 21, wherein the type of the healthcare transaction event comprises a partial denial, and the one or more processors are further configured to:
retrieve a denial healthcare trend model responsive to the healthcare transaction event including the partial denial; and
select, based on the denial healthcare trend model, a denial recommendation comprising an ordered list including at least one qualifying item and at least one non-qualifying item responsive to determining that the partial denial resulted from a transaction including one or more qualifying items and one or more non-qualifying items.

### Claim 29 (depends on 21)

The system of claim 21, wherein the one or more processors are further configured to:
perform, responsive to the determination to generate the notification, a lookup in a recommendation data structure using an identifier of the selected healthcare trend model to identify a plurality of healthcare related recommendations linked with the selected healthcare trend model; and
generate the notification based at least in part on a healthcare related recommendation of the plurality of healthcare related recommendations.

### Claim 30 (depends on 21)

The system of claim 21, wherein the one or more processors are further configured to:
identify, responsive to the determination to generate the notification, a plurality of healthcare related recommendations linked with the selected healthcare trend model;
determine a correlation coefficient between each of the plurality of healthcare related recommendations and the selected healthcare trend model, wherein the correlation coefficient indicates a likelihood that the plurality of healthcare related recommendations reduces resource consumption of information technology infrastructure by reducing the occurrence of the type of the healthcare transaction event;
select, based on a rank of each correlation coefficient, a highest ranking healthcare related recommendation of the plurality of healthcare related recommendations; and
generate the notification based at least in part on the highest ranking healthcare related recommendation.

### Claim 31

A method of managing transactions, comprising:
identifying, by one or more processors, a healthcare transaction event corresponding to a participant of a plurality of participants of a healthcare platform;
selecting, by the one or more processors, based at least in part on a type of the healthcare transaction event, a healthcare trend model trained by a machine learning engine using historical healthcare transaction events corresponding to the plurality of participants of the healthcare platform, the healthcare trend model trained by the machine learning engine to include a baseline threshold for one or more features;
determining, by the one or more processors, based on a comparison between the healthcare transaction event and the baseline threshold of the one or more features of the selected healthcare trend model, to generate one or more notifications to control an occurrence of the type of the healthcare transaction event corresponding to the healthcare transaction event;
selecting, by the one or more processors, based at least in part on the selected healthcare trend model trained using the machine learning engine, a notification to control the occurrence of the type of the healthcare transaction event; and
transmitting, by the one or more processors via a network, the notification to a computing device associated with the participant to control the occurrence of the type of the healthcare transaction event.

### Claim 32 (depends on 31)

The method of claim 31, wherein the healthcare transaction events include one or more of a claim payment, a card denial, a password change, or a received deposit.

### Claim 33 (depends on 31)

The method of claim 31, comprising:
determining, by the one or more processors, the baseline threshold for one or more features comprising at least one of a type of event, geographic area, or time of year.

### Claim 34 (depends on 31)

The method of claim 31, comprising:
receiving, by the one or more processors, the historical healthcare transaction events corresponding to the plurality of participants from a device of an administrator remote from the one or more processors via an administrator interface rendered by the one or more processors on the device of the administrator.

### Claim 35 (depends on 31)

The method of claim 31, wherein the machine learning engine is configured to use at least one of a decision tree learning, a predictive model, association rule learning, support vector machines, clustering, or reinforcement learning.

### Claim 36 (depends on 31)

The method of claim 31, comprising:
selecting, by the one or more processors, the healthcare trend model from a plurality of healthcare trend models based on a minimum vector distance between the healthcare transaction event and each of the plurality of healthcare trend models.

### Claim 37 (depends on 31)

The method of claim 31, wherein the type of the healthcare transaction event comprises a denial, comprising:
retrieving, by the one or more processors, a denial healthcare trend model responsive to the healthcare transaction event including the denial; and
selecting, by the one or more processors, based on the denial healthcare trend model, a denial recommendation comprising a recommended resource allocation responsive to determining that an insufficient amount of resources resulted in the denial.

### Claim 38 (depends on 31)

The method of claim 31, wherein the type of the healthcare transaction event comprises a partial denial, comprising:
retrieving, by the one or more processors, a denial healthcare trend model responsive to the healthcare transaction event including the partial denial; and
selecting, by the one or more processors, based on the denial healthcare trend model, a denial recommendation comprising an ordered list including at least one qualifying item and at least one non-qualifying item responsive to determining that the denial healthcare transaction event resulted from a transaction including one or more qualifying items and one or more non-qualifying items.

### Claim 39 (depends on 31)

The method of claim 31, comprising:
performing, by the one or more processors responsive to the determination to generate the notification, a lookup in a recommendation data structure using an identifier of the selected healthcare trend model to identify a plurality of healthcare related recommendations linked with the selected healthcare trend model; and
generating, by the one or more processors, the notification based at least in part on a healthcare related recommendation of the plurality of healthcare related recommendations.

### Claim 40 (depends on 31)

The method of claim 31, comprising:
identifying, by the one or more processors responsive to the determination to generate the notification, a plurality of healthcare related recommendations linked with the selected healthcare trend model;
determining, by the one or more processors, a correlation coefficient between each of the plurality of healthcare related recommendations and the selected healthcare trend model, wherein the correlation coefficient indicates a likelihood that the plurality of healthcare related recommendations reduces resource consumption of information technology infrastructure by reducing the occurrence of the type of the healthcare transaction event;
selecting, by the one or more processors based on a rank of each correlation coefficient, a highest ranking healthcare related recommendation of the plurality of healthcare related recommendations; and
generating, by the one or more processors, the notification based at least in part on the highest ranking healthcare related recommendation.
