Back to results
US 11,900,328 B2Granted
Reporting taxonomy
AssigneeADP, Inc.
InventorAllan Barcelos
Life of this patent
Estimating the term…
Abstract
A method, computer system, and computer program product are provided for managing reports. A subset of data fields is identified for inclusion in a new report. An intent of the new report is determined based on the subset of data fields. The intent is determined using a set of machine learning models trained from a set of existing reports and a taxonomy of human capital management (HCM) information. Based on the intent determined by the artificial intelligence system, a set of additional fields is predicted for the new report. The set of the additional fields is displayed in a graphical user interface on a display system.
Claims21
A report management system, comprising:
- a computer system;
- and
- a report manager in the computer system, wherein the report manager is configured:
- to identify a subset of data fields for inclusion in a new report;
- to identify a set of existing reports comprising the subset of data fields;
- to train a machine learning model comprising a neural network, by the computer system, with a training data set based on a taxonomy of human capital management (HCM) information and the set of existing reports;
- to determine, using the machine learning model an intent for the new report by comparing the subset of data fields to an index of intents of the set of existing reports and data fields, the data fields including the subset of data fields;
- to predict, using the machine learning model based on the intent determined by the machine learning model and the index, a set of additional fields for the new report by comparing the subset of data fields to the index;
- to compute, with the neural network using the intent determined by the machine learning model based on the subset of data fields, a plurality of probability density functions of likelihoods of inclusion of the set of additional fields in the new report;
- to rank the set of additional fields based on the likelihoods of inclusion;
- and
- to display the set of additional fields in a graphical user interface on a display system according to the ranking.
9 more elements
A method for managing reports, the method comprising:
- identifying, by a computer system, a subset of data fields for inclusion in a new report;
- identifying, by the computer system, a set of existing reports comprising the subset of data fields;
- training, by the computer system, a machine learning model comprising at least a neural network, using a training data set based on a taxonomy of human capital management (HCM) information and the set of existing reports;
- determining, by the machine learning model, an intent for the new report by comparing the subset of data fields to an index of intents of the set of existing reports and data fields, the data fields including the subset of data fields;
- predicting, by the machine learning model based on the intent determined by the machine learning model and the index, a set of additional fields for the new report by comparing the subset of data fields to the index;
- computing, by the neural network using the intent determined by the machine learning model based on the subset of data fields, a plurality of probability density functions of likelihoods of inclusion of the set of additional fields in the new report;
- ranking, by the computer system, the set of additional fields based on the likelihoods of inclusion;
- and
- displaying, by the computer system on a display system, the set of additional fields in a graphical user interface on the display system according to a ranking based on the plurality of probability density functions.
6 more elements
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 identifying, by a computer system, a subset of data fields for inclusion in a new report;
- program code, stored on the computer-readable storage media, for identifying a set of existing reports comprising the subset of data fields;
- program code, stored on the computer-readable storage media, for training a machine learning model comprising a neural network, using a training data set based on a taxonomy of human capital management (HCM) information and the set of existing reports;
- program code, stored on the computer-readable storage media, for determining, by the machine learning model, an intent for the new report by comparing the subset of data fields to an index of intents of the set of existing reports and data fields, the data fields including the subset of data fields;
- program code, stored on the computer-readable storage media, for predicting, by the machine learning model based on the intent determined by the machine learning model and the index, a set of additional fields for the new report by comparing the subset of data fields to the index;
- program code, stored on the computer-readable storage media, for computing, by the neural network using the intent determined by the machine learning model based on the subset of data fields, a plurality of probability density functions of likelihoods of inclusion of the set of additional fields in the new report;
- program code, stored on the computer-readable storage media, for ranking, by the computer system, the set of additional fields based on the likelihoods of inclusion;
- and
- program code, stored on the computer-readable storage media, for displaying, by the computer system on a display system, the set of additional fields in a graphical user interface on the display system according to a ranking based on the plurality of probability density functions.
8 more elements
Dependencies are inferred from the claim text.