18192363. SYSTEM AND METHOD FOR DEEP MACHINE LEARNING MODEL USING PERSONAL DATA IN REAL TIME simplified abstract (Samsung Electronics Co., Ltd.)
SYSTEM AND METHOD FOR DEEP MACHINE LEARNING MODEL USING PERSONAL DATA IN REAL TIME
Organization Name
Inventor(s)
Tapas Kanungo of Redmond WA (US)
Qingxiaoyang Zhu of Woodland CA (US)
Nehal A. Bengre of Cupertino CA (US)
SYSTEM AND METHOD FOR DEEP MACHINE LEARNING MODEL USING PERSONAL DATA IN REAL TIME - A simplified explanation of the abstract
This abstract first appeared for US patent application 18192363 titled 'SYSTEM AND METHOD FOR DEEP MACHINE LEARNING MODEL USING PERSONAL DATA IN REAL TIME
Simplified Explanation
The method described in the abstract involves receiving an utterance from a user, delexicalizing a portion of the utterance using a named entity database, transmitting the encoded utterance to a server with a language model, receiving an intent and slots associated with the utterance (including representative tags), identifying a named entity corresponding to at least one slot based on the named entity database, and performing an action based on the intent and slots.
- User provides an utterance to an electronic device.
- Utterance is delexicalized using a named entity database on the device.
- Encoded utterance is sent to a server with a language model.
- Intent and slots (including representative tags) associated with the utterance are received.
- Named entity corresponding to at least one slot is identified based on the named entity database.
- Action is performed based on the intent and slots.
---
- Potential Applications
- Natural language processing systems - Virtual assistants - Chatbots
- Problems Solved
- Efficiently processing user utterances - Improving accuracy in identifying named entities - Enhancing interaction with electronic devices
- Benefits
- Streamlined communication between users and devices - Enhanced user experience - Increased efficiency in performing actions based on user input
Original Abstract Submitted
A method includes receiving, by at least one processing device of an electronic device, an utterance provided by a user. The method also includes delexicalizing at least a portion of the utterance using a named entity database stored on the electronic device to create an encoded utterance. The method further includes transmitting the encoded utterance to a server on which a language model is stored. The method also includes receiving an intent and one or more slots associated with the utterance, where at least one slot of the one or more slots is a representative tag. The method further includes identifying a named entity corresponding to the at least one slot based on the named entity database. In addition, the method includes performing an action based on the intent and the one or more slots.
