18510086. ELECTRONIC DEVICE FOR PROCESSING UTTERANCE, OPERATING METHOD THEREOF, AND STORAGE MEDIUM simplified abstract (Samsung Electronics Co., Ltd.)
Contents
- 1 ELECTRONIC DEVICE FOR PROCESSING UTTERANCE, OPERATING METHOD THEREOF, AND STORAGE MEDIUM
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 ELECTRONIC DEVICE FOR PROCESSING UTTERANCE, OPERATING METHOD THEREOF, AND STORAGE MEDIUM - 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
ELECTRONIC DEVICE FOR PROCESSING UTTERANCE, OPERATING METHOD THEREOF, AND STORAGE MEDIUM
Organization Name
Inventor(s)
JeongYeol Kim of Suwon-si (KR)
ELECTRONIC DEVICE FOR PROCESSING UTTERANCE, OPERATING METHOD THEREOF, AND STORAGE MEDIUM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18510086 titled 'ELECTRONIC DEVICE FOR PROCESSING UTTERANCE, OPERATING METHOD THEREOF, AND STORAGE MEDIUM
Simplified Explanation
The electronic device described in the patent application includes a microphone, a memory, and at least one processor. The processor acquires utterance data from the user's voice, determines the user's intent, and provides content based on that intent. If intent determination fails, the models are updated using text from the utterance data, focusing on named entities and domains determined by categories found through named entity search.
- Acquiring utterance data through microphone
- Determining user intent and providing content
- Updating models when intent determination fails
- Searching for named entities and determining domains for model updates based on categories found through named entity search
Potential Applications
This technology could be applied in various voice-activated devices such as virtual assistants, smart speakers, and other IoT devices to improve user interaction and content delivery based on user intent.
Problems Solved
This technology addresses the issue of accurately determining user intent from voice commands, especially when there is no clear verb or predicate in the user's utterance. By updating models based on named entities and categories, the system can better understand and respond to user requests.
Benefits
- Enhanced user experience through improved intent determination - More accurate content delivery based on user needs - Efficient updating of models for better performance over time
Potential Commercial Applications
- Virtual assistants for smart homes - Voice-activated search engines - Customer service chatbots with voice capabilities
Possible Prior Art
One potential prior art could be the use of named entity recognition and domain categorization in natural language processing systems to improve intent determination in voice-activated devices. Another could be the use of machine learning algorithms to update models based on user input in similar systems.
Unanswered Questions
How does the system handle multiple intents in a single utterance?
The patent application does not specify how the system deals with cases where a user expresses multiple intents in a single utterance. This could be a potential challenge in accurately determining the user's desired action.
What languages or dialects is the system capable of understanding?
The patent application does not mention the language capabilities of the system. It is unclear whether the technology is designed to work with multiple languages or specific dialects. This could impact the usability and effectiveness of the device in different regions or among diverse user groups.
Original Abstract Submitted
An electronic device includes a microphone, a memory and at least one processor. The at least one processor is configured to acquire utterance data corresponding to a voice of a user through the microphone, determine an intent and provide content to the user based on the intent. When intent determination fails, then one or more models are updated using text obtained from the utterance data. The intent determination may fail when there is no verb (predicate) in the user utterance. The models are updated by searching for named entities and determining domains to be used for the model updates. The domains are determined based on categories. The categories are found using a named entity search (NES). Examples of categories are music artists, music albums, movie titles, TV program channels, video clip channels, radio programs, and podcast titles.
