17956514. METHODS AND SYSTEMS FOR ONTOLOGY CONSTRUCTION WITH AI-MEDIATED CROWDSOURCING AND CONCEPT MINING FOR HIGH-LEVEL ACTIVITY UNDERSTANDING simplified abstract (Robert Bosch GmbH)
METHODS AND SYSTEMS FOR ONTOLOGY CONSTRUCTION WITH AI-MEDIATED CROWDSOURCING AND CONCEPT MINING FOR HIGH-LEVEL ACTIVITY UNDERSTANDING
Organization Name
Inventor(s)
Ji Eun Kim of Pittsburgh PA (US)
Kevin H. Huang of Pittsburgh PA (US)
Alessandro Oltramari of Pittsburgh PA (US)
METHODS AND SYSTEMS FOR ONTOLOGY CONSTRUCTION WITH AI-MEDIATED CROWDSOURCING AND CONCEPT MINING FOR HIGH-LEVEL ACTIVITY UNDERSTANDING - A simplified explanation of the abstract
This abstract first appeared for US patent application 17956514 titled 'METHODS AND SYSTEMS FOR ONTOLOGY CONSTRUCTION WITH AI-MEDIATED CROWDSOURCING AND CONCEPT MINING FOR HIGH-LEVEL ACTIVITY UNDERSTANDING
Simplified Explanation
The patent application describes a method and system for building and augmenting a knowledge graph related to the ontology of events in images. This involves receiving image data from various scenes captured by cameras, building a knowledge graph with event-based ontology data, displaying scenes to crowdsourcing workers for natural-language input, generating triples using natural language processing, and augmenting the knowledge graph with the generated triples.
- Receiving image data from multiple scenes captured by cameras
- Building a knowledge graph with event-based ontology data
- Displaying scenes to crowdsourcing workers for natural-language input
- Generating triples using natural language processing
- Augmenting the knowledge graph with the generated triples
---
- Potential Applications
The technology described in this patent application could be applied in various fields such as:
- Image recognition and analysis
- Event detection in surveillance systems
- Content recommendation systems based on scene analysis
- Problems Solved
This technology addresses the following issues:
- Automating the process of annotating events in images
- Enhancing the understanding of complex scenes captured by cameras
- Improving the accuracy of event-based ontology in knowledge graphs
- Benefits
The benefits of this technology include:
- Efficient organization and retrieval of information from images
- Enhanced semantic understanding of events in visual data
- Facilitation of automated decision-making processes based on image analysis
- Potential Commercial Applications
The technology could find commercial applications in:
- Security and surveillance industries
- E-commerce platforms for personalized recommendations
- Media and entertainment for content categorization
---
- Possible Prior Art
One potential prior art in this field is the use of crowdsourcing for image annotation and semantic understanding. Another could be the application of natural language processing for generating triples from textual input.
---
- Unanswered Questions
- How does the system handle privacy concerns related to the use of image data from various scenes?
The patent application does not provide specific details on the privacy measures implemented in the system to protect the confidentiality of image data.
- What is the scalability of the system in processing a large volume of image data and generating triples for augmenting the knowledge graph?
The patent application does not elaborate on the scalability of the system in handling a significant amount of image data and efficiently augmenting the knowledge graph with generated triples.
Original Abstract Submitted
Methods and system of building and augmenting a knowledge graph regarding ontology of events occurring in images. Image data corresponding to a plurality of scenes captured by one or more cameras is received. A knowledge graph is built with event-based ontology data corresponding to events occurring in the plurality of scenes. One or more of the scenes is displayed to a plurality of crowdsourcing workers which provide natural-language input including event-based semantic annotations corresponding to the scene. Using natural language processing on the input, triples are generated. The knowledge graph is augmented with the generated triples to yield an augmented knowledge graph for use in determining event-based ontology associated with the plurality of scenes.
