# US 2022/0035795 A1 · Report management system

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

- Number: US 2022/0035795 A1
- Document ID: US20220035795A1
- Status: Published application
- Kind: A1
- Application number: 16/983,785
- Filed: 2020-08-03
- Published: 2022-02-03
- Earliest claimed: 2020-08-03
- Assignees: ADP, Inc.
- Applicants: Adp, LLC
- Inventors: Israel Oliveira; Allan Barcelos; Renata Palazzo; Leandro Bianchini; Fernanda Tosca
- Web page: https://patentgrep.com/patent/US20220035795A1

## CPC

- G06F 16/2379: {Updates performed during online database operations; commit processing}
- G06F 16/252: {between a Database Management System and a front-end application}
- G06F 16/338: Presentation of query results
- G06F 40/169: Annotation, e.g. comment data or footnotes
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 10/067: Enterprise or organisation modelling
- G06Q 10/105: Human resources
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

## Abstract

A method, computer system, and computer program product are provided for generating reports. Existing reports are collected and modeled to determine a number of contexts. An index of the existing reports is generated according the contexts determined by the modeling. a predicted context of a new report is predicted according to the modeling. According to the index, suggested reports are identified based on the predicted context for the new report. The suggested reports are presented in a graphical user interface.

## Claims

### Claim 1

A computer-implemented method for managing reports, the method comprising:
collecting, by a number of processors, existing reports;
modeling, by the number of processors, the existing reports to determine a number of contexts of the existing reports;
generating, by the number of processors, an index of the existing reports according the contexts determined by the modeling;
predicting, by the number of processors according to the modeling, a predicted context of a new report;
identifying, by the number of processors according to the index, suggested reports based on the predicted context for the new report; and
presenting, by the number of processors, the suggested reports in a graphical user interface.

### Claim 2 (depends on 1)

The method of claim 1, wherein each existing report including a title field, a description field, and at least one other field, and wherein modeling the existing reports further comprises:
generating annotations for the existing reports according to a title field and a description field of the existing reports; and
determining a number of contexts for the number of existing reports according to the annotations.

### Claim 3 (depends on 2)

The method of claim 2, wherein modeling the number of existing reports further comprises:
determining, according to the at least one other field of the existing reports, a number of features for the existing reports; and
for each context, weighting the number of features based on a normalization of a counting occurrences of the features within a context.

### Claim 4 (depends on 3)

The method of claim 3, wherein weighting the features are adjusted in order to maximize correct predictions.

### Claim 5 (depends on 1)

The method of claim 1, wherein a predicting the predicted context of a new report further comprises:
determining features of the new report; and
for each context, scoring the new report according to a weighting of the features for the existing reports; and
identifying a context having a highest score.

### Claim 6 (depends on 5)

The method of claim 5, wherein the suggested reports identified according to the context having the highest score.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
in response to receiving an indication of a suggested report, generating the new report according to the suggested reports.

### Claim 8

A system for managing reports, the system comprising:
a bus system;
a storage device connected to the bus system, wherein the storage device stores program instructions; and
a number of processors connected to the bus system, wherein the number of processors execute the program instructions:
to collect existing reports;
to model the existing reports to determine a number of contexts of the existing reports;
to generate an index of the existing reports according the contexts determined by the modeling;
to predict according to the modeling, a predicted context of a new report;
to identify according to the index, suggested reports based on the predicted context for the new report; and
to present the suggested reports in a graphical user interface.

### Claim 9 (depends on 8)

The system of claim 8, wherein each existing report including a title field, a description field, and at least one other field, and wherein in modeling the existing reports, the number of processors execute the program instructions:
to generate annotations for the existing reports according to a title field and a description field of the existing reports; and
to determine a number of contexts for the existing reports according to the annotations.

### Claim 10 (depends on 9)

The system of claim 9, wherein in modeling the number of existing reports, the number of processors execute the program instructions:
to determine, according to the at least one other field of the existing reports, a number of features for the existing reports; and
for each context, to weight the features based on a normalization of a counting occurrences of the features within a context.

### Claim 11 (depends on 10)

The system of claim 10, wherein weighting the features are adjusted in order to maximize correct predictions.

### Claim 12 (depends on 8)

The system of claim 8, wherein in predicting the predicted context of a new report, the number of processors execute the program instructions:
to determine features of the new report; and
for each context, to score the new report according to a weighting of the features for the existing reports; and
to identify a context having a highest score.

### Claim 13 (depends on 12)

The system of claim 12, wherein the suggested reports are identified according to the context having the highest score.

### Claim 14 (depends on 8)

The system of claim 8, wherein the number of processors further execute the program instructions:
to generate the new report according to the suggested reports in response to receiving an indication of a suggested report.

### Claim 15

A computer program product for managing reports, the computer program product comprising:
a computer-readable storage media; and
program code, stored on the computer-readable storage media, for collecting existing reports;
program code, stored on the computer-readable storage media, for modeling the existing reports to determine a number of contexts of the existing reports;
program code, stored on the computer-readable storage media, for generating an index of the existing reports according the contexts determined by the modeling;
program code, stored on the computer-readable storage media, for predicting, according to the modeling, a predicted context of a new report;
program code, stored on the computer-readable storage media, for identifying, according to the index, suggested reports based on the predicted context for the new report; and
program code, stored on the computer-readable storage media, for presenting the suggested reports in a graphical user interface.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein each existing report including a title field, a description field, and at least one other field, and wherein the program code for modeling the existing reports further comprises:
program code for generating annotations for the existing reports according to a title field and a description field of the existing reports; and
program code for determining a number of contexts for the existing reports according to the annotations.

### Claim 17 (depends on 16)

The computer program product of claim 16, wherein the program code for modeling the number of existing reports further comprises:
program code for determining, according to the at least one other field of the existing reports, a number of features for the existing reports; and
program code, for each context, for weighting the features based on a normalization of a counting occurrences of the features within a context.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein weighting the features are adjusted in order to maximize correct predictions.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein the program code for predicting the predicted context of a new report further comprises:
program code for determining features of the new report; and
program code, for each context, for scoring the new report according to a weighting of the features for the existing reports; and
program code for identifying a context having a highest score.

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein the suggested reports identified according to the context having the highest score.

### Claim 21 (depends on 15)

The computer program product of claim 15, further comprising:
program code, stored on the computer-readable storage media, for generating the new report according to the suggested reports in response to receiving an indication of a suggested report.
