US 2025/0054006 A1Published application

Transforming qualitative survey into quantitative survey using domain knowledge and natural language processing

AssigneeTata Consultancy Services Limited

InventorsBHASKARJYOTI DAS, SHIVANI TARUN GANWANI, SYLVAN LOBO, RAVI HANMANT MAHAMUNI

Life of this patent

Estimating the term…

Loading patent…

Abstract

The disclosure relates generally to methods and systems for transforming qualitative survey into quantitative survey. Current approaches depend on manual analysis of these user responses which is so troublesome task. The present disclosure transforms the qualitative survey questionnaire into the quantitative survey questionnaire using a domain knowledge and a natural language processing. The method first receives responses to each question present in qualitative survey questionnaire, from multiple batches. Then valid responses out of all the responses are determined for each question, pertaining to each batch, using domain taxonomy and natural language knowledge graph. Further, semantic relation-based technique is employed to determine the questions that are transformable batch wise. Then, the response options are created for each transformable question. The non-transformable questions are considered for the next batch and the responses pertaining to the next batch are processed and so on until all the questions becomes transformable.

Claims15

Dependent claims

A processor-implemented method, comprising the steps of:

receiving, via one or more hardware processors, (i) a qualitative survey questionnaire comprising one or more questions, wherein the qualitative survey questionnaire is associated with a predefined domain category (ii) a batch size defining a number of a plurality of batches, and a participant size defining a number of a plurality of participants present in each batch, (iii) a plurality of responses received for each question of the one or more questions, from the plurality of participants present in each batch, (iv) a domain taxonomy of the predefined domain category, and (v) a natural language knowledge graph;
and
performing, via the one or more hardware processors, for each question of the one or more questions, using the plurality of responses received for each batch at a time:
(a) determining one or more valid responses for each question, out of the plurality of responses pertaining to a current batch, using the domain taxonomy of the predefined domain category and the natural language knowledge graph;
(b) applying a transformation decision criterion, for each question, using the associated one or more valid responses pertaining to the current batch, to determine (i) one or more transformable questions and (ii) one or more non-transformable questions, out of the one or more questions;
(c) creating one or more quantitative response options, for each transformable question of the one or more transformable questions, using the associated one or more valid responses pertaining to the current batch;
and
(d) repeating the steps (a) through (c), for a successive batch and for each of the one or more non-transformable questions, by considering (i) the successive batch as the current batch, (ii) the one or more non-transformable questions as the one or more questions, and (iii) the one or more valid responses pertaining to the current batch and the one or more valid responses pertaining to the successive batch together as the one or more valid responses pertaining to the current batch, for each non-transformable question, until one of (i) all of the one or more questions become transformable questions, and (ii) the number of the plurality of batches are completed, is met to transform the qualitative survey questionnaire into a quantitative survey questionnaire.

5 more elements

A system comprising:

a memory storing instructions;
one or more input/output (I/O) interfaces;
and
one or more hardware processors coupled to the memory via the one or more I/O interfaces, wherein the one or more hardware processors are configured by the instructions to:
receive (i) a qualitative survey questionnaire comprising one or more questions, wherein the qualitative survey questionnaire is associated with a predefined domain category (ii) a batch size defining a number of a plurality of batches, and a participant size defining a number of a plurality of participants present in each batch, (iii) a plurality of responses received for each question of the one or more questions, from the plurality of participants present in each batch, (iv) a domain taxonomy of the predefined domain category, and (v) a natural language knowledge graph;
and
perform for each question of the one or more questions, using the plurality of responses received for each batch at a time:
(a) determining one or more valid responses for each question, out of the plurality of responses pertaining to a current batch, using the domain taxonomy of the predefined domain category and the natural language knowledge graph;
(b) applying a transformation decision criterion, for each question, using the associated one or more valid responses pertaining to the current batch, to determine (i) one or more transformable questions and (ii) one or more non-transformable questions, out of the one or more questions;
(c) creating one or more quantitative response options, for each transformable question of the one or more transformable questions, using the associated one or more valid responses pertaining to the current batch;
and
(d) repeating the steps (a) through (c), for the a successive batch and for each of the one or more non-transformable questions, by considering (i) the successive batch as the current batch, (ii) the one or more non-transformable questions as the one or more questions, and (iii) the one or more valid responses pertaining to the current batch and the one or more valid responses pertaining to the successive batch together as the one or more valid responses pertaining to the current batch, for each non-transformable question, until one of (i) all of the one or more questions become transformable questions, and (ii) the number of the plurality of batches are completed, is met to transform the qualitative survey questionnaire into a quantitative survey questionnaire.

9 more elements

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:

receiving, (i) a qualitative survey questionnaire comprising one or more questions, wherein the qualitative survey questionnaire is associated with a predefined domain category (ii) a batch size defining a number of a plurality of batches, and a participant size defining a number of a plurality of participants present in each batch, (iii) a plurality of responses received for each question of the one or more questions, from the plurality of participants present in each batch, (iv) a domain taxonomy of the predefined domain category, and (v) a natural language knowledge graph;
and
performing, for each question of the one or more questions, using the plurality of responses received for each batch at a time:
(a) determining one or more valid responses for each question, out of the plurality of responses pertaining to a current batch, using the domain taxonomy of the predefined domain category and the natural language knowledge graph;
(b) applying a transformation decision criterion, for each question, using the associated one or more valid responses pertaining to the current batch, to determine (i) one or more transformable questions and (ii) one or more non-transformable questions, out of the one or more questions;
(c) creating one or more quantitative response options, for each transformable question of the one or more transformable questions, using the associated one or more valid responses pertaining to the current batch;
and
(d) repeating the steps (a) through (c), for a successive batch and for each of the one or more non-transformable questions, by considering (i) the successive batch as the current batch, (ii) the one or more non-transformable questions as the one or more questions, and (iii) the one or more valid responses pertaining to the current batch and the one or more valid responses pertaining to the successive batch together as the one or more valid responses pertaining to the current batch, for each non-transformable question, until one of (i) all of the one or more questions become transformable questions, and (ii) the number of the plurality of batches are completed, is met to transform the qualitative survey questionnaire into a quantitative survey questionnaire.

5 more elements

Dependencies are inferred from the claim text.