Channel Name Dictionary Filtering for Voice Intent Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing natural language processing systems degrade in performance due to the inclusion of channel names for channels that are unlikely to be tuned in the vocabulary dictionary, affecting named entity recognition (NER) and intent analysis.
Innovation Solution
A natural language processing device that dynamically configures a vocabulary dictionary based on a tuned channel list using electronic program guide (EPG) information to establish a second channel named entity dictionary, excluding unnecessary channel names.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all channel names are included in the NE dictionary, then the dictionary is comprehensive for all possible channels, but the dictionary size increases and NER performance degrades due to inclusion of channels unlikely to be tuned
Solution Approach 1:
The patent extracts only the necessary channel names from the complete channel list by comparing with the EPG information. This creates a reduced NE dictionary that contains only channel names currently available for tuning, removing unnecessary entries and improving NER performance while reducing dictionary size.
Solution Approach 2:
The NE dictionary is made dynamic by updating it based on current EPG information. The dictionary is regenerated whenever EPG data changes, ensuring it always contains the most relevant channel names and adapts to the current broadcasting context rather than being static.
2Adaptability or versatility
If a complete channel dictionary is maintained, then all channels are supported, but database load increases and maintenance becomes more difficult
Solution Approach 1:
The system performs preliminary filtering of channel names by comparing the complete channel list with EPG information before creating the NE dictionary. This preliminary action ensures that only relevant channels are included, reducing subsequent processing load and simplifying maintenance.
Solution Approach 2:
The system uses EPG information as feedback to dynamically adjust the NE dictionary contents. By continuously comparing current EPG data with the channel list, the system automatically updates the dictionary to reflect actual broadcasting availability, reducing manual maintenance requirements.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A natural language processing device according to an embodiment of the present disclosure may comprise: a memory for storing a first channel named entity dictionary including basic channel names and a synonym of each of the basic channel names; a communication interface for receiving, from a display device, voice data corresponding to a voice instruction uttered by a user; and a processor which: acquires multiple channel names included in electronic program guide information; extracts channel names matching the acquired multiple channel names from the first channel named entity dictionary so as to acquire a second channel named entity dictionary; acquires the intention of a speech of the voice instruction on the basis of text data of the voice data and the second channel named entity dictionary; and transmits the acquired intention of the speech to the display device through the communication interface.