# US 12,112,388 B2 · Utilizing a machine learning model for predicting issues associated with a closing process of an entity

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

- Number: US 12,112,388 B2
- Document ID: US12112388B2
- Status: Granted
- Kind: B2
- Application number: 17/247,092
- Filed: 2020-11-30
- Published: 2022-06-02
- Granted: 2024-10-08
- Earliest claimed: 2020-11-30
- Assignees: Accenture Global Solutions Limited
- Applicants: Accenture Global Solutions Limited
- Inventors: Chiranjit Seal; Bula Roy; Atrayee Chatterjee; Kaushik Dey; Punitha Nithyanandam
- Web page: https://patentgrep.com/patent/US12112388B2

## CPC

- G06Q 40/12: Accounting
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 10/063114: {Status monitoring or status determination for a person or group}
- G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis}
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A device may identify tasks relevant to closing processes for an entity during a period of time, and may generate a request for historical closing data associated with the tasks relevant to the closing processes. The device may provide the request to a server device associated with the entity, and may receive the historical closing data based on providing the request. The device may train a machine learning model, based on the historical closing data, to generate a trained machine learning model, and may receive current closing data associated with tasks relevant to a current closing process. The device may process the current closing data, with the trained machine learning model, to predict issue data identifying at least one potential issue associated with the current closing process, and may provide the issue data to a user device associated with the at least one potential issue.

## Claims

### Claim 1

A method, comprising:
identifying, by a device, tasks relevant to closing processes for an entity during a period of time;
generating, by the device, a request for historical closing data associated with the tasks relevant to the closing processes;
providing, by the device, the request to a server device associated with the entity;
receiving, by the device, the historical closing data based on providing the request to the server device,
wherein the historical closing data comprises information regarding historical issues that caused one or more historical tasks to be delayed including descriptions of historical reasons for historical delays and information identifying a measure of severity of the historical issues;
identifying, by the device, a trend with respect to the one or more historical tasks based on sorting the one or more historical tasks based on amounts of delays associated with the historical delays;
training, by the device, a machine learning model, based on the historical closing data, to generate a trained machine learning model,
wherein the machine learning model is trained to identify structural or organizational changes associated with reasons for the historic delays from the historical closing data, and
wherein the machine learning model is trained to identify particular tasks that are associated with delays and particular periods of time associated with lengths of the delays;
receiving, by the device, current closing data associated with tasks relevant to a current closing process;
processing, by the device, the current closing data, with the trained machine learning model, to predict issue data identifying at least one potential issue associated with the current closing process;
providing, by the device, the issue data to a user device associated with the at least one potential issue;
generating, by the device, a modification to the current closing process based on the issue data; and
causing, by the device, the server device to implement the modification to the current closing process.

### Claim 2 (depends on 1)

The method of claim 1, further comprising one or more of:
generating a recommendation based on the issue data and providing the recommendation to the user device;
generating a key performance indicator (KPI) based on the issue data and providing the KPI to the user device; or
retraining the machine learning model based on the issue data.

### Claim 3 (depends on 1)

The method of claim 1, further comprising one or more of:
generating a recommendation based on the issue data and causing the server device to implement the recommendation; or
generating a key performance indicator (KPI) based on the issue data and causing the server device to modify the current closing process based on the KPI.

### Claim 4 (depends on 1)

The method of claim 1, wherein the request for the historical closing data includes a request associated with one or more of:
nomenclature of the tasks relevant to the closing processes,
statuses of the tasks relevant to the closing processes,
functions of the entity,
geographical locations associated with the tasks relevant to the closing processes, or
periods of time associated with the tasks relevant to the closing processes.

### Claim 5 (depends on 4)

The method of claim 4, wherein the statuses of the tasks relevant to the closing processes include one or more of:
a status indicating that a task is executing,
a status indicating that a task is delayed,
a status indicating that a task is ready for execution,
a status indicating that a task is scheduled for execution, or
a status indicating that execution of a task is complete.

### Claim 6 (depends on 1)

The method of claim 1, wherein training the machine learning model, based on the historical closing data, to generate the trained machine learning model comprises:
training the machine learning model, based on the historical closing data, to identify one or more tasks having issues,
wherein the one or more tasks are included in the tasks relevant to the closing processes.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
generating a user interface based on the current closing data and the issue data,
wherein the user interface includes data indicating one or more of:
a quantity of completed tasks of the tasks relevant to the current closing process,
a quantity of in progress tasks of the tasks relevant to the current closing process,
a quantity of delayed tasks of the tasks relevant to the current closing process, or
a quantity of not started tasks of the tasks relevant to the current closing process; and
providing the user interface to the user device.

### Claim 8

A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
identify tasks relevant to closing processes for an entity during a period of time;
generate a request for historical closing data associated with the tasks relevant to the closing processes;
provide the request to a server device associated with the entity;
receive the historical closing data based on providing the request to the server device,
wherein the historical closing data comprises information regarding historical issues that caused one or more historical tasks to be delayed including descriptions of historical reasons for historical delays and information identifying a measure of severity of the historical issues;
identify a trend with respect to the one or more historical tasks based on sorting the one or more historical tasks based on amounts of delays associated with the historical delays;
train a machine learning model, based on the historical closing data, to generate a trained machine learning model,
wherein the machine learning model is trained to identify structural or organizational changes associated with reasons for the historic delays from the historical closing data, and
wherein the machine learning model is trained to identify particular tasks that are associated with delays and particular periods of time associated with lengths of the delays;
receive current closing data associated with tasks relevant to a current closing process;
process the current closing data, with the trained machine learning model, to predict issue data identifying at least one potential issue associated with the current closing process;
generate a recommendation based on the issue data;
provide the recommendation to a user device associated with the at least one potential issue;
receive, from the user device, feedback associated with the recommendation;
generate a modification to the current closing process based on the issue data; and
cause the server device to implement the modification to the current closing process; and
retrain the machine learning model based on the feedback.

### Claim 9 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the one or more instructions further cause the device to one or more of:
generate a key performance indicator (KPI) based on the issue data and provide the KPI to the user device;
retrain the machine learning model based on the issue data;
cause the server device to implement the recommendation; or
generate another KPI based on the issue data and cause the server device to modify the current closing process based on the other KPI.

### Claim 10 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the one or more instructions further cause the device to:
generate a user interface based on the current closing data and the issue data,
wherein the user interface includes data indicating one or more of:
a quantity of completed tasks of the tasks relevant to the current closing process,
a quantity of in progress tasks of the tasks relevant to the current closing process,
a quantity of delayed tasks of the tasks relevant to the current closing process, or
a quantity of not started tasks of the tasks relevant to the current closing process; and
provide the user interface to the user device.

### Claim 11 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the one or more instructions further cause the device to:
cause the server device to implement the recommendation;
receive, from the server device, additional feedback associated with implementing the recommendation; and
retrain the machine learning model based on the additional feedback.

### Claim 12 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the one or more instructions further cause the device to:
receive, from the server device, additional feedback associated with implementing the modification; and
retrain the machine learning model based on the additional feedback.

### Claim 13 (depends on 8)

The non-transitory computer-readable medium of claim 8, wherein the at least one potential issue includes one or more of:
a delay associated with one of the tasks relevant to the current closing process,
incomplete execution of one of the tasks relevant to the current closing process, or
an error associated with one of the tasks relevant to the current closing process.

### Claim 14

A device, comprising:
one or more memories; and
one or more processors, coupled to the one or more memories, configured to:
identify tasks relevant to closing processes for an entity during a period of time;
generate a request for historical closing data associated with the tasks relevant to the closing processes;
provide the request to a server device associated with the entity;
receive the historical closing data based on providing the request to the server device,
wherein the historical closing data comprises information regarding historical issues that caused one or more historical tasks to be delayed including descriptions of historical reasons for historical delays and information identifying a measure of severity of the historical issues;
identify a trend with respect to the one or more historical tasks based on sorting the one or more historical tasks based on amounts of delays associated with the historical delays;
train a machine learning model, based on the historical closing data, to generate a trained machine learning model,
wherein the machine learning model is trained to identify structural or organizational changes associated with reasons for the historic delays from the historical closing data, and
wherein the machine learning model is trained to identify particular tasks that are associated with delays and particular periods of time associated with lengths of the delays;
receive current closing data associated with tasks relevant to a current closing process;
process the current closing data, with the trained machine learning model, to predict issue data identifying at least one potential issue associated with the current closing process;
provide the issue data to a user device associated with the at least one potential issue;
generate a modification to the current closing process based on the issue data; and
cause the server device to implement the modification to the current closing process.

### Claim 15 (depends on 14)

The device of claim 14, wherein the one or more processors are further configured to one or more of:
generate a recommendation based on the issue data and providing the recommendation to the user device;
generate a key performance indicator (KPI) based on the issue data and providing the KPI to the user device; or
retrain the machine learning model based on the issue data.

### Claim 16 (depends on 14)

The device of claim 14, wherein the one or more processors are further configured to one or more of:
generate a recommendation based on the issue data and causing the server device to implement the recommendation; or
generate a key performance indicator (KPI) based on the issue data and causing the server device to modify the current closing process based on the KPI.

### Claim 17 (depends on 14)

The device of claim 14, wherein the request for the historical closing data includes a request associated with one or more of:
nomenclature of the tasks relevant to the closing processes,
statuses of the tasks relevant to the closing processes,
functions of the entity associated with the tasks relevant to the closing processes,
geographical locations associated with the tasks relevant to the closing processes, or
periods of time associated with the tasks relevant to the closing processes.

### Claim 18 (depends on 17)

The device of claim 17, wherein the statuses of the tasks relevant to the closing processes include one or more of:
a status indicating that a task is executing,
a status indicating that a task is delayed,
a status indicating that a task is ready for execution,
a status indicating that a task is scheduled for execution, or
a status indicating that execution of a task is complete.

### Claim 19 (depends on 14)

The device of claim 14, wherein the one or more processors, to train the machine learning model, based on the historical closing data, to generate the trained machine learning model, are configured to:
train the machine learning model, based on the historical closing data, to identify one or more tasks having issues,
wherein the one or more tasks are included in the tasks relevant to the closing processes.

### Claim 20 (depends on 14)

The device of claim 14, wherein the one or more processors are further configured to:
generate a user interface based on the current closing data and the issue data,
wherein the user interface includes data indicating one or more of:
a quantity of completed tasks of the tasks relevant to the current closing process,
providing the user interface to the user device.