Video Tag Knowledge Graph Structuring for Semantic Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Video tags are unstructured and lack semantic information, making them ineffective for video recommendation and search.
Innovation Solution
A method that acquires tag entity words from a video, links them to a knowledge graph, and structures semantic information based on node and edge relationships to generate structured semantic information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If video tags are used for video recommendation and search, then video categorization and retrieval can be implemented, but the tags are unstructured and lack semantic information making them ineffective
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary between video tags and semantic information. The knowledge graph contains entities, attributes, and relationships that mediate the transformation of flat tags into structured semantic information, enabling effective video recommendation and search while preserving semantic meaning.
Solution Approach 2:
The patent transforms the parameter structure of video tags from flat, unstructured data into structured semantic information with multiple dimensions including entities, attributes, and relationships. This parameter transformation enables the tags to contain meaningful semantic information suitable for recommendation and search applications.
2Ease of manufacture
If flat unstructured video tags are used, then implementation is simple, but the tags are not applicable for video recommendation or search
Solution Approach 1:
The patent segments video tags into distinct components including entities, attributes, and relationships within a knowledge graph framework. This segmentation transforms simple flat tags into structured elements that can be independently processed and combined, enabling both ease of implementation and adaptability for recommendation and search applications.
Solution Approach 2:
The patent adds dimensional structure to video tags by organizing them into a knowledge graph with multiple dimensions including entity types, attributes, and relationships. This dimensional transformation maintains implementation simplicity while dramatically improving applicability for recommendation and search by enabling multi-dimensional querying and analysis.
Data Source
AI summary
A method, electronic device and storage medium for generating information are disclosed. The method includes: acquiring a plurality of tag entity words from a target video, the tag entity words including a person entity word, a work entity word, a video category entity word, and a video core entity word, the video core entity word including an entity word for characterizing a content related to the target video; linking, for a tag entity word among the plurality of tag entity words, the tag entity word to a node of a preset knowledge graph; determining semantic information of the target video based on a linking result of each of the tag entity words; and structuring the semantic information of the target video based on a relationship between the node and an edge of the knowledge graph, to obtain structured semantic information of the target video.