Image-Text Knowledge Base Queries for Field Product Identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current knowledge base querying systems rely solely on text input, limiting their utility when image data is available, such as in field scenarios where a field engineer needs to access product information from drone or camera images.

Innovation Solution

A system that combines image and text inputs to generate queries, using computer vision to extract product features and natural language processing to identify intent and missing information, forming a unified query for the knowledge base.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a user manually interprets images to formulate queries, then query accuracy is improved, but time consumption and operational complexity increase

Engineering Contradiction:
Improvequery accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service by automatically extracting features from images and generating queries without requiring manual user interpretation. The computer vision system autonomously processes images to identify objects, locations, and characteristics, then automatically formulates knowledge base queries, eliminating the need for users to manually analyze and interpret image data.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical process of manual image interpretation with automated computer vision technology. Instead of requiring human eyes and cognitive processing to analyze images, the system uses automated algorithms to extract features, identify objects, and generate queries, substituting human cognitive mechanics with automated computational processes.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Loss of time

If automated image processing is used, then time consumption is reduced, but system complexity increases

Engineering Contradiction:
Improvetime consumptionVSAvoidsystem complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The system segments the complex task of image processing and query generation into distinct functional modules: image input, computer vision feature extraction, query generation, and knowledge base querying. This segmentation allows each component to be optimized independently and simplifies the overall system architecture by dividing complex functionality into manageable units.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary query generation component that acts as a mediator between the computer vision system and the knowledge base. This intermediary layer processes extracted image features and translates them into appropriate knowledge base queries, simplifying the interaction between the vision system and database while reducing overall system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If only text queries are used, then system simplicity is maintained, but adaptability to image-based scenarios is reduced

Engineering Contradiction:
Improveadaptability to image scenariosVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system achieves universality by creating a multi-functional query generation platform that can handle both text-based queries and image-based queries through a unified architecture. The same knowledge base and querying mechanism serve both text and image inputs, allowing the system to adapt to different scenario types without requiring separate specialized systems for each modality.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250238466A1Generating knowledge base queries and obtaining answers to knowledge base queries
Publication Date: 2025.07.24 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
  • US20250238466A1 patent drawing
  • US20250238466A1 patent drawing
  • US20250238466A1 patent drawing

AI summary

A method of retrieving an answer to a query relating to an object from a knowledge base includes receiving an image of the object, identifying a location associated with the object, and retrieving an object feature model associated with the location. The object feature model including object features associated with objects present at the location. The method further includes extracting object features from the image using the object feature model. The object features include features associated with the objects. The method further includes receiving a language-based query associated with the object, analyzing the query to identify an aspect of the query, and combining information from the query and the extracted object features based on the identified aspect of the query to form a unified query for submission to the knowledge base. The unified query is submitted to the knowledge base to obtain an answer to the unified query.