QlikTech International AB

A user might submit a question, and an answer could be generated using a knowledge base. User feedback on the answer might be collected and sent for review. Refined knowledge may be determined based on the review. This refined knowledge could be stored in a question and answer (Q&A) source of the knowledge base. New questions might be answered by determining semantic similarity to stored refined knowledge.

Methods and systems for improved natural language processing and generation of insights are described herein. Aspects of machine learning and natural language processing may be employed to interpret user queries and provide insights, recommendations, and visualizations. The system employs large language models and machine learning services to enhance the natural language interaction between users and their analytics.

The disclosed methods and systems may transform existing datasets into a format that may be consumed by Large Language Models (LLMs). A Retrieval-Augmented Generation application may provide natural language (NL) answers to queries related to the existing data, which may be stored in a knowledge base following transformation. The knowledge base may generate NL responses for users according to their corresponding access rights.

Described herein are methods and systems for updating knowledge bases for Retrieval-Augmented Generation (RAG) applications. The methods employ Change Data Capture (CDC) to efficiently detect modifications in source data. These CDC techniques may enable targeted updates to semantic indexing tables by traversing data models from leaf tables to root entities, ensuring that only affected embeddings are regenerated rather than reprocessing entire document collections.

Natural language can be used to conduct a conversation that yields analytic results. An interactive user interface can present suggestive content associated with a natural language input to a user. The suggestive content can guide assist the user in obtaining analytic data/information relating to a business, industry, and/or the like. An ontology comprising one or more content items associated with the natural language input can generated. The ontology can be represented as and/or associated with a data structure that temporal correlates a plurality of content items to the natural language input.

Set analysis may be used to determine the best data analysis model(s) (e.g., data charts, data tables, data graphs, data maps, graphical objects, key performance indicators (KPIs), etc.) for representing the results of an undetermined query (e.g., an imprecise query, an undefined query, an incomplete query, a partially expressed query, a portioned query, etc.).