Natural language interaction based data analytics

Patent metadata

Field	Value
Publication number	US-2021209168-A1
Application number	US-202016735141-A
Country	US
Kind code	A1
Filing date	Jan 6, 2020
Priority date	Jan 6, 2020
Publication date	Jul 8, 2021
Grant date	—

Abstract

Using a natural language processing (NLP) engine executing in conjunction with a machine that is engaged in first natural language interaction, an analytics intent comprising an analysis type to be performed on a dataset is extracted from the first natural language interaction. Within the dataset, a subset of the dataset comprising data having above a threshold relevance measure with respect to the analytics intent is identified. From the subset, a knowledge graph modeling a set of relationships between data in the subset is constructed. Using the analytics intent and the knowledge graph, a conversational template is customized, augmenting the conversational template with a set of entities corresponding to the analytics intent. To obtain a result, the subset is analyzed using the knowledge graph. A second natural language interaction is presented via the machine, the presenting comprising transforming by the NLP engine the result to fit the customized conversational template.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
extracting, using a natural language processing (NLP) engine executing in conjunction with a machine that is engaged in first natural language interaction, from the first natural language interaction, an analytics intent comprising an analysis type to be performed on a dataset; identifying, within the dataset, a subset of the dataset, the subset comprising data having above a threshold relevance measure with respect to the analytics intent; constructing, from the subset, a knowledge graph, the knowledge graph modeling a set of relationships between data in the subset; customizing, using the analytics intent and the knowledge graph, a conversational template, the customizing comprising augmenting the conversational template with a set of entities corresponding to the analytics intent; analyzing, to obtain a result, the subset using the knowledge graph; and presenting a second natural language interaction via the machine, the presenting comprising transforming by the NLP engine the result to fit the customized conversational template.

2 . The computer-implemented method of claim 1 , wherein constructing the knowledge graph comprises organizing data in the subset.

3 . The computer-implemented method of claim 1 , wherein constructing the knowledge graph comprises:
determining, by analyzing data in the subset and metadata of the subset, a type of data; selecting, according to the type of data, an analytic; and adding, to the knowledge graph, the analytic.

4 . The computer-implemented method of claim 3 , further comprising:
predicting, using data in the subset, metadata of the subset, and the analytic, a predicted analysis request; analyzing, according to the predicted analysis request to obtain a second result, the subset using the knowledge graph; and adding, to the knowledge graph, the second result.

5 . The computer-implemented method of claim 1 , wherein the customizing further comprises selecting a dialog tree corresponding to the analytics intent.

6 . The computer-implemented method of claim 1 , further comprising:
adjusting, using the result and the second natural language interaction, the knowledge graph.

7 . A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:
program instructions to extract, using a natural language processing (NLP) engine executing in conjunction with a machine that is engaged in first natural language interaction, from the first natural language interaction, an analytics intent comprising an analysis type to be performed on a dataset; program instructions to identify, within the dataset, a subset of the dataset, the subset comprising data having above a threshold relevance measure with respect to the analytics intent; program instructions to construct, from the subset, a knowledge graph, the knowledge graph modeling a set of relationships between data in the subset; program instructions to customize, using the analytics intent and the knowledge graph, a conversational template, the customizing comprising augmenting the conversational template with a set of entities corresponding to the analytics intent; program instructions to analyze, to obtain a result, the subset using the knowledge graph; and program instructions to present a second natural language interaction via the machine, the presenting comprising transforming by the NLP engine the result to fit the customized conversational template.

8 . The computer usable program product of claim 7 , wherein program instructions to construct the knowledge graph comprises program instructions to organize data in the subset.

9 . The computer usable program product of claim 7 , wherein program instructions to construct the knowledge graph comprises:
program instructions to determine, by analyzing data in the subset and metadata of the subset, a type of data; program instructions to select, according to the type of data, an analytic; and program instructions to add, to the knowledge graph, the analytic.

10 . The computer usable program product of claim 9 , further comprising:
program instructions to predict, using data in the subset, metadata of the subset, and the analytic, a predicted analysis request; program instructions to analyze, according to the predicted analysis request to obtain a second result, the subset using the knowledge graph; and program instructions to add, to the knowledge graph, the second result.

11 . The computer usable program product of claim 7 , wherein the customizing further comprises selecting a dialog tree corresponding to the analytics intent.

12 . The computer usable program product of claim 7 , further comprising:
program instructions to adjust, using the result and the second natural language interaction, the knowledge graph.

13 . The computer usable program product of claim 7 , wherein the stored program instructions are stored in the at least one of the one or more storage devices of a local data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.

14 . The computer usable program product of claim 7 , wherein the stored program instructions are stored in the at least one of the one or more storage devices of a server data processing system, and wherein the stored program instructions are downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

15 . A computer system comprising one or more processors, one or more computer-readable memories, and one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:
program instructions to extract, using a natural language processing (NLP) engine executing in conjunction with a machine that is engaged in first natural language interaction, from the first natural language interaction, an analytics intent comprising an analysis type to be performed on a dataset; program instructions to identify, within the dataset, a subset of the dataset, the subset comprising data having above a threshold relevance measure with respect to the analytics intent; program instructions to construct, from the subset, a knowledge graph, the knowledge graph modeling a set of relationships between data in the subset; program instructions to customize, using the analytics intent and the knowledge graph, a conversational template, the customizing comprising augmenting the conversational template with a set of entities corresponding to the analytics intent; program instructions to analyze, to obtain a result, the subset using the knowledge graph; and program instructions to present a second natural language interaction via the machine, the presenting comprising transforming by the NLP engine the result to fit the customized conversational template.

16 . The computer system of claim 15 , wherein program instructions to construct the knowledge graph comprises program instructions to organize data in the subset.

17 . The computer system of claim 15 , wherein program instructions to construct the knowledge graph comprises:
program instructions to determine, by analyzing data

Assignees

• IBM

Inventors

• Oswald Richard John
• Bhagi Vikremjeet Singh
• Shyr Jing-Yun

Classifications

• G06F16/90332 Primary

  Natural language query formulation or dialogue systems · CPC title

• G06F40/30

  Semantic analysis · CPC title

• G06F40/47

  Machine-assisted translation, e.g. using translation memory · CPC title