Text Exploration System for Unstructured Data Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional enterprise network systems face challenges in analyzing unstructured customer interaction data from various sources, requiring human analysts to manually read and interpret large volumes of text data, which is costly and inefficient, and current text analytics technologies lack intuitive features and require prior knowledge.
Innovation Solution
A text exploration system using unsupervised machine-learning to assist human analysts in identifying key themes from large corpora of text files, generating interactive graphical user interfaces that allow users to visualize and interact with data, enabling the automatic identification of themes, reasons, and solutions across multiple data sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If human analysts manually read and interpret text data from multiple data sources, then they can identify customer interaction themes and insights, but the process becomes costly, time-consuming, and inefficient
Solution Approach 1:
The patent replaces the mechanical system of manual human analysis with an automated text analytics system that uses natural language processing and machine learning algorithms to ingest, parse, and analyze unstructured text data from multiple sources, thereby maintaining measurement precision while dramatically reducing the time required for analysis
Solution Approach 2:
The system enables self-service text analytics by automatically performing data ingestion, parsing, theme identification, and insight generation without requiring human analysts to manually read and interpret each document, allowing the system to serve itself in analyzing large volumes of unstructured data
2Productivity
If traditional text analytics technologies are used, then analysis can be performed, but the systems lack intuitive features and require prior knowledge of the corpus content
Solution Approach 1:
The patent introduces an intermediary layer between the raw text data and the user that automatically performs parsing, theme extraction, and insight generation, mediating the complexity of text analytics algorithms and presenting simplified, intuitive results that do not require users to have prior knowledge of the corpus or underlying analytical methods
Solution Approach 2:
The system segments the text analytics process into distinct automated components including data ingestion, text parsing, theme identification, and result presentation, allowing each segment to be optimized independently while collectively providing an easy-to-use interface that hides operational complexity from the user
3Loss of information
If unstructured data from multiple disparate data sources is analyzed, then comprehensive customer interaction insights can be generated, but the data ingestion and parsing complexity increases
Solution Approach 1:
The patent implements a universal text analytics platform that can ingest and parse unstructured data from multiple disparate sources including customer service transcripts, social media posts, and survey responses using a single unified system that handles various data formats and sources through standardized parsing routines, thereby maintaining information completeness while managing processing complexity
Data Source
AI summary
Disclosed herein are systems and methods capable of performing text exploration on large volume of corpus without prior knowledge in an accurate and efficient manner and may also provide any number of additional or alternative benefits and advantages. In particular, embodiments described herein provide a text exploration executable environment that uses unsupervised machine-learning to assist a human analyst with distilling key emerging themes from a corpus of hundreds or thousands of text files presented in a time series graphical user interface (GUI). A document may be a unit of text under analysis received from a particular data source, such as word-processing documents, paragraphs, sentences, chat sessions, speech-to-text call segments, online texts, social media postings (e.g., Tweets®), and other machine-readable text. In operation, a human analyst may use a text exploration software tool to identify the themes and stories within the corpus, by using integrated, synchronized GUIs that are dynamically generated by the software exploration tool.