Cognitive Intelligence Queries for Image Data in Relational Databases
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional Structured Query Language (SQL) queries fail to capture and exploit semantic relationships within relational databases, neglecting latent information and lacking a holistic view of inter-column and intra-column relationships, especially when dealing with image data types.
Innovation Solution
The implementation of cognitive intelligence queries that convert image tokens in relational databases to textual form, using word embedding techniques to produce word vectors, enabling the extraction of latent semantic information and enhancing query capabilities through machine learning models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional SQL queries are used to query relational databases, then query simplicity and ease of operation are maintained, but the ability to capture and exploit semantic relationships and latent information is lost
Solution Approach 1:
The system performs preliminary actions by pre-processing image data into feature vectors and pre-computing semantic relationships before queries are executed. This allows the database to capture latent information in advance, enabling SQL queries to leverage pre-computed semantic relationships without adding complexity to the query syntax itself.
Solution Approach 2:
The patent introduces an intermediary layer that translates between traditional SQL queries and cognitive intelligence operations. This mediator component handles the complexity of semantic relationship extraction and image feature matching, allowing users to continue using simple SQL syntax while the intermediary performs sophisticated information retrieval based on semantic similarities.
2Measurement precision
If cognitive intelligence techniques are implemented to extract semantic relationships, then information retrieval quality improves, but processing time and computational resources increase
Solution Approach 1:
The system extracts image features and computes semantic relationships in advance during data loading or preprocessing phases. By performing these computationally intensive operations before queries are executed, the system achieves high measurement precision in query results while keeping actual query processing time minimal, as the heavy lifting has already been completed.
3Adaptability or versatility
If image data is converted to textual form using word embeddings, then semantic relationships become exploitable, but data transformation complexity increases
Solution Approach 1:
The patent replaces traditional mechanical text-based search mechanisms with cognitive intelligence systems that use machine learning models and word embeddings. This substitution enables the system to understand semantic relationships and contextual meanings in image data, significantly enhancing query capabilities beyond simple keyword matching while the underlying complexity is handled by automated ML pipelines.
Data Source
AI summary
A computer-implemented method, a cognitive intelligence system and computer program product adapt a relational database containing image data types. At least one image token in the relational database is converted to a textual form. Text is produced based on relations of tokens in the relational database. A set of word vectors is produced based on the text. A cognitive intelligence query expressed as a structured query language (SQL) query may be applied to the relational database using the set of word vectors. An image token may be converted to textual form by converting the image to a tag, by using a neural network classification model and replacing the image token with a corresponding cluster identifier, by binary comparison or by a user-specified similarity function. An image token may be converted to a plurality of textual forms using more than one conversion method.