Report template generation based on user intent

Inventors

Bianchini, Leandro da Silva • Barcelos, Allan • Tosca, Fernanda • FARIA, RODRIGO

Assignees

ADP Inc

Abstract

The present disclosure relates generally to tools to determine a user's intent and, more particularly, to a system, method and computer program product to generate a report template based on user's intent. The method includes: extracting, by a computer system, text and user selected features from one or more reports built in a reporting application; classifying, by the computer system, keywords in the text and the select features; identifying, by the computer system, common keywords and associated selected features within the one or more reports; determining, by the computer system, an intent of the user based on the common keywords and associated selected features; and generating, by the computer system, a report template with prepopulated features of the selected features based on the intent of the user.

Core Innovation

The invention relates to a reporting-intent system that receives output data objects generated by one or more applications executed on a plurality of disparate computing systems. The output data objects include a plurality of fields, which are provided for display via an interface as a drop down menu, and a user selects a first field from the displayed plurality of fields.

The system extracts text from a set of output data objects including the first field, identifies keywords in the text and the first field that are common to similar output data objects that share one or more fields, and groups the shared keywords into one or more clusters. Based on the keywords of the one or more clusters and the first field, the system determines an intent of the user and generates a suggested title based on the keywords of the clusters.

Using the determined intent, the system generates a template that includes the suggested title and the first field and transmits the template for display via the interface. In response to receiving a second input from the user selecting the template, the system transmits an output data object generated using the template, or in a report-generating variant, a report generated using the template, with the output or report including the suggested title and the first field.

In refinements, the intent determining can use an intent classifier, the keyword grouping can be implemented using machine learning and natural language processing, and templates can be prepopulated with features obtained from previous output data objects created by one or more users that have a similar intent. Templates can also be stored in a user-accessible library for retrieval.

Claims Coverage

The provided document includes three independent claims that cover a computer-implemented method, a computer program product, and a system. Across these independents, the claims share a core flow consisting of field selection, text extraction, common-keyword identification, keyword clustering, user intent determination, suggested title generation, and template-based generation of a selected output data object or report.

Across the independent claims, the core coverage centers on clustering common keywords extracted from output data objects tied to a user-selected field, determining user intent from the clusters and the field, and generating a suggested title and a template that produces an output data object or report including the suggested title and selected field. Optional refinements disclosed in dependent claims include intent determination via an intent classifier using machine learning and natural language processing, keyword clustering via heuristic partitioning such as Kernighan-Lin, and template prepopulation and reuse through a user-accessible library.

Stated Advantages

Documented Applications

No documented applications found