# US 2022/0301076 A1 · System and method for serverless modification and execution of machine learning algorithms

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

- Number: US 2022/0301076 A1
- Document ID: US20220301076A1
- Status: Published application
- Kind: A1
- Application number: 17/205,048
- Filed: 2021-03-18
- Published: 2022-09-22
- Earliest claimed: 2021-03-18
- Assignees: Automatic Data Processing, Inc.
- Applicants: Automatic Data Processing, Inc.
- Inventors: Roberto COUTINHO; Roberto SILVEIRA; Guilherme GOMES
- Web page: https://patentgrep.com/patent/US20220301076A1

## CPC

- G06Q 40/125: {Finance or payroll}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/08: Learning methods
- G06N 3/092: Reinforcement learning
- G06N 20/00: Machine learning
- G06Q 10/067: Enterprise or organisation modelling
- G06N 5/025: Extracting rules from data
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems, methods, and computer-readable storage media for identifying and generating insights using machine learning and serverless computing systems. When events are detected, data from those events is collected and formatted into predefined formats. That formatted data is then used within an instance, where a machine learning algorithm is executed by a serverless computing system using the data within the instance as input. The result from the machine learning algorithm is an insight into the event and event data, which can be presented to users for interpretation.

## Claims

### Claim 1

A method comprising:
receiving, at a computer system, a notification regarding an occurrence of an event;
formatting, via a processor within the computer system, the event into a predefined format, resulting in a formatted event item;
inserting, via the processor, the formatted event item into a serverless computing instance, resulting in a serverless instance for the event;
inserting, via the processor, additional details associated with the event into the serverless instance for the event, resulting in a modified serverless instance for the event;
transmitting, from the computer system to a serverless computing system, a request to execute the modified serverless instance for the event, wherein execution by the serverless computing system of the modified serverless instance comprises:
selecting a machine learning algorithm from a plurality of machine learning algorithms within the serverless computing system based on a type of the event;
selecting a set of business rules from a plurality of business rules;
modifying execution of the machine learning algorithm based on a comparison of the set of business rules and the additional details, resulting in a modified machine learning algorithm; and
executing the modified machine learning algorithm using the additional details, resulting in the insight;
receiving, at the computer system from the serverless computing system, an insight regarding the event; and
displaying, via a display of the computer system, the insight.

### Claim 2 (depends on 1)

The method of claim 1, wherein the displaying of the insight further comprises:
executing, via the processor, a reinforcement learning algorithm on the insight, resulting in display parameters;
contextually formatting, via the processor, the insight based on the display parameters, resulting in a contextual formation,
such that the display of the insight occurs according to the contextual formation.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
identifying, via the processor, the event based on natural language processing of at least one of audio and text from a user.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
identifying, via the processor, the event based on execution of a human capital activity.

### Claim 5 (depends on 4)

The method of claim 4, wherein the human capital activity comprises payroll processing.

### Claim 6 (depends on 1)

The method of claim 1, wherein the execution by the serverless computing system of the modified serverless instance further comprises:
compressing, via the processor, the modified machine learning algorithm into an ONNX (Open Neural Network Exchange) format, resulting in a compressed modified machine learning algorithm,
wherein the modified machine learning algorithm executed by the serverless computing system is the compressed modified machine learning algorithm.

### Claim 7 (depends on 6)

The method of claim 6, wherein the serverless computing system has a maximum data size of instances which can be executed.

### Claim 8

A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
receiving, at a computer system, a notification regarding an occurrence of an event;
formatting, via a processor within the computer system, the event into a predefined format, resulting in a formatted event item;
inserting, via the processor, the formatted event item into a serverless computing instance, resulting in a serverless instance for the event;
inserting, via the processor, additional details associated with the event into the serverless instance for the event, resulting in a modified serverless instance for the event;
transmitting, from the computer system to a serverless computing system, a request to execute the modified serverless instance for the event, wherein execution by the serverless computing system of the modified serverless instance comprises:
selecting a machine learning algorithm from a plurality of machine learning algorithms within the serverless computing system based on a type of the event;
selecting a set of business rules from a plurality of business rules;
modifying execution of the machine learning algorithm based on a comparison of the set of business rules and the additional details, resulting in a modified machine learning algorithm; and
executing the modified machine learning algorithm using the additional details, resulting in the insight;
receiving, at the computer system from the serverless computing system, an insight regarding the event; and
displaying, via a display of the computer system, the insight.

### Claim 9 (depends on 8)

The system of claim 8, wherein the displaying of the insight further comprises:
executing, via the processor, a reinforcement learning algorithm on the insight, resulting in display parameters;
contextually formatting, via the processor, the insight based on the display parameters, resulting in a contextual formation,
such that the display of the insight occurs according to the contextual formation.

### Claim 10 (depends on 8)

The system of claim 8, the non-transitory computer-readable storage medium storing additional instructions which, when executed by the processor, cause the processor to perform operations comprising:
identifying, via the processor, the event based on natural language processing of at least one of audio and text from a user.

### Claim 11 (depends on 8)

The system of claim 8, the non-transitory computer-readable storage medium storing additional instructions which, when executed by the processor, cause the processor to perform operations comprising:
identifying, via the processor, the event based on execution of a human capital activity.

### Claim 12 (depends on 11)

The system of claim 11, wherein the human capital activity comprises payroll processing.

### Claim 13 (depends on 8)

The system of claim 8, wherein the execution by the serverless computing system of the modified serverless instance further comprises:
compressing, via the processor, the modified machine learning algorithm into an ONNX (Open Neural Network Exchange) format, resulting in a compressed modified machine learning algorithm,
wherein the modified machine learning algorithm executed by the serverless computing system is the compressed modified machine learning algorithm.

### Claim 14 (depends on 13)

The system of claim 13, wherein the serverless computing system has a maximum data size of instances which can be executed.

### Claim 15

A non-transitory computer-readable storage medium having instructions stored which, when executed by a processor, cause the processor to perform operations comprising:
receiving, at a computer system, a notification regarding an occurrence of an event;
formatting, via a processor within the computer system, the event into a predefined format, resulting in a formatted event item;
inserting, via the processor, the formatted event item into a serverless computing instance, resulting in a serverless instance for the event;
inserting, via the processor, additional details associated with the event into the serverless instance for the event, resulting in a modified serverless instance for the event;
transmitting, from the computer system to a serverless computing system, a request to execute the modified serverless instance for the event, wherein execution by the serverless computing system of the modified serverless instance comprises:
selecting a machine learning algorithm from a plurality of machine learning algorithms within the serverless computing system based on a type of the event;
selecting a set of business rules from a plurality of business rules;
modifying execution of the machine learning algorithm based on a comparison of the set of business rules and the additional details, resulting in a modified machine learning algorithm; and
executing the modified machine learning algorithm using the additional details, resulting in the insight;
receiving, at the computer system from the serverless computing system, an insight regarding the event; and
displaying, via a display of the computer system, the insight.

### Claim 16 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the displaying of the insight further comprises:
executing, via the processor, a reinforcement learning algorithm on the insight, resulting in display parameters;
contextually formatting, via the processor, the insight based on the display parameters, resulting in a contextual formation,
such that the display of the insight occurs according to the contextual formation.

### Claim 17 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, having additional instructions which, when executed by the processor, cause the processor to perform operations comprising:
identifying, via the processor, the event based on natural language processing of at least one of audio and text from a user.

### Claim 18 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, having additional instructions which, when executed by the processor, cause the processor to perform operations comprising:
identifying, via the processor, the event based on execution of a human capital activity.

### Claim 19 (depends on 18)

The non-transitory computer-readable storage medium of claim 18, wherein the human capital activity comprises payroll processing.

### Claim 20 (depends on 15)

The non-transitory computer-readable storage medium of claim 15, wherein the execution by the serverless computing system of the modified serverless instance further comprises:
compressing, via the processor, the modified machine learning algorithm into an ONNX (Open Neural Network Exchange) format, resulting in a compressed modified machine learning algorithm,
wherein the modified machine learning algorithm executed by the serverless computing system is the compressed modified machine learning algorithm.
