Knowledge-Graph Recommendation Data for Vague Search Needs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data recommendation systems struggle to provide personalized and relevant recommendations to users with vague search needs, especially in scenarios involving multiple categories of objects, leading to inefficiencies in data access and user experience.
Innovation Solution
A method that utilizes a knowledge graph to determine first and second definition information, generating combinations of categories based on predefined rules and user-specific data to create tailored recommendation data, even when users are unsure of specific search terms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional keyword-based search is used, then users can search for specific data, but users with vague search needs spend excessive time searching and cannot find relevant content efficiently
Solution Approach 1:
The system pre-generates recommendation data by combining multiple categories of objects before users perform searches. When a user accesses the system, relevant recommendation data is already prepared and can be immediately presented, eliminating the need for users to spend time formulating search queries and browsing through unrelated results.
Solution Approach 2:
The patent introduces an intermediary layer between the user's vague search intent and the data repository. This intermediary generates and presents recommendation data based on category combinations, acting as a mediator that translates uncertain user needs into targeted data presentations without requiring precise user input.
2Adaptability or versatility
If recommendation data is generated for all possible category combinations, then comprehensive coverage is achieved, but system complexity and computational resources increase significantly
Solution Approach 1:
The patent segments the recommendation generation process into distinct components: obtaining first definition information about individual categories, obtaining second definition information about category combinations, and then generating recommendation data. This segmentation allows the system to manage complexity by handling category combinations modularly rather than as a monolithic process.
Solution Approach 2:
The system generates recommendation data for category combinations that are likely to be relevant based on the knowledge graph, rather than exhaustively generating all possible combinations. This partial action approach provides sufficient coverage for practical scenarios while avoiding the prohibitive complexity of generating every possible category combination.
3Measurement precision
If knowledge graph is used to structure data, then data relationships are clarified and recommendations are more accurate, but data processing complexity increases
Solution Approach 1:
The knowledge graph structure and category definitions are pre-established before recommendation generation. The first definition information about categories and the second definition information about category combinations are prepared in advance, allowing the recommendation system to leverage this pre-structured knowledge without processing complexity during actual recommendation queries.
Data Source
AI summary
This application provides a method for processing recommendation data, a recommendation method, an electronic device, and a storage medium. The recommendation data processing method comprises: obtaining first definition information regarding a target scenario, wherein the first definition information is generated based on a knowledge graph related to the target scenario, the target scenario being a scenario involving a plurality of categories of objects, and the first definition information comprises the plurality of categories of objects; obtaining second definition information about the target scenario based on the first definition information, wherein the second definition information comprises a combination of target categories including at least one target category from the plurality of categories; generating recommendation data for an object corresponding to the combination of target categories based on the second definition information.