18507916. DEVICE FOR TRAINING AND MANAGING A VISUAL SCENE GRAPH MODEL AND CONTROL METHOD THEREOF simplified abstract (LG ELECTRONICS INC.)
Contents
- 1 DEVICE FOR TRAINING AND MANAGING A VISUAL SCENE GRAPH MODEL AND CONTROL METHOD THEREOF
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DEVICE FOR TRAINING AND MANAGING A VISUAL SCENE GRAPH MODEL AND CONTROL METHOD THEREOF - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DEVICE FOR TRAINING AND MANAGING A VISUAL SCENE GRAPH MODEL AND CONTROL METHOD THEREOF
Organization Name
Inventor(s)
DEVICE FOR TRAINING AND MANAGING A VISUAL SCENE GRAPH MODEL AND CONTROL METHOD THEREOF - A simplified explanation of the abstract
This abstract first appeared for US patent application 18507916 titled 'DEVICE FOR TRAINING AND MANAGING A VISUAL SCENE GRAPH MODEL AND CONTROL METHOD THEREOF
Simplified Explanation
The abstract describes a method for controlling a device to manage a visual scene graph model by obtaining and combining datasets, generating common sense knowledge embeddings, training a visual scene graph model, and executing functions based on the model's output.
- The method involves obtaining a first dataset and a second dataset, combining them to generate a combined dataset, applying a knowledge embedding function to generate common sense knowledge embeddings, training a visual scene graph model based on the embeddings, and executing functions based on the model's output.
- The device can be a smart television, a mobile phone, or a robot.
Potential Applications
This technology can be applied in various fields such as virtual reality, augmented reality, robotics, and smart home devices.
Problems Solved
This technology helps in managing visual scene graph models efficiently, improving the understanding of causal and intention relations in datasets, and enhancing the performance of visual scene graph models.
Benefits
The benefits of this technology include improved data processing, better decision-making capabilities, enhanced user experiences, and increased efficiency in managing visual scene graph models.
Potential Commercial Applications
Potential commercial applications of this technology include smart home automation systems, virtual reality applications, augmented reality platforms, and robotics.
Possible Prior Art
One possible prior art could be research on knowledge embedding techniques in machine learning and artificial intelligence.
What are the specific knowledge embedding techniques used in this method?
The specific knowledge embedding techniques used in this method are not explicitly mentioned in the abstract. Further details on the knowledge embedding function and its implementation would provide more insight into the specific techniques employed.
How does the trained visual scene graph model improve decision-making processes?
The abstract does not elaborate on how the trained visual scene graph model improves decision-making processes. A detailed explanation of the model's decision-making capabilities and its impact on various applications would help in understanding this aspect better.
Original Abstract Submitted
A method for controlling a device to manage a visual scene graph model can include obtaining, via a processor in the device, a first dataset; obtaining, via the processor, a second data set different from the first dataset, the second dataset including one or more of a causal relation or an intention relation; combining, via the processor, the first dataset and the second dataset to generate a combined dataset. Also, the method can further include applying a knowledge embedding function to the combined dataset to generate learned common sense knowledge embeddings; and training a visual scene graph model based on the learned common sense knowledge embeddings to generate a trained visual scene graph model. Further, the method can include executing a function based on an output of the trained visual scene graph model. The device can include at least one of a smart television, a mobile phone or a robot.
