Knowledge Base Updating from User Search Query Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing knowledge graph visualization technologies are inadequate for vertical fields, requiring manual updates and lacking efficient methods to incorporate user queries directly into knowledge bases.
Innovation Solution
A data updating method that involves acquiring search sentences, determining target query sentences based on sentence type, performing clustering when necessary, and sending search content to a service side for updating the knowledge base, utilizing pre-trained models for sentence recognition and entity identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual updates are used to maintain the knowledge base, then the knowledge base can be updated with expert knowledge, but human resources are wasted and the update process is inefficient
Solution Approach 1:
The system enables self-service by automatically capturing user search queries and updating the knowledge base without manual intervention. The knowledge base updates itself by leveraging user search behavior data, eliminating the need for manual knowledge base maintenance while improving update efficiency.
Solution Approach 2:
The system implements feedback by using user search queries as input to automatically update the knowledge base. User search behavior provides continuous feedback that drives knowledge base evolution, creating a closed-loop system that improves productivity without additional human resource investment.
2Ease of operation
If simple graphical visualization is used for knowledge graphs, then the visualization is easy to implement, but it does not facilitate in-depth mining and analysis of data in vertical fields
Solution Approach 1:
The system achieves multi-functionality by combining simple graphical visualization with automated knowledge base updating and analysis capabilities. The same platform that provides easy visual representation also performs automated data mining and analysis, serving multiple functions without compromising ease of operation.
Solution Approach 2:
The system merges visualization functionality with automated knowledge base updating and analysis capabilities into a unified platform. This combination allows the system to maintain visual simplicity while simultaneously providing advanced data mining and analysis features for vertical fields.
3Productivity
If user search queries are directly incorporated into the knowledge base without processing, then the update process is fast, but the knowledge quality and consistency cannot be ensured
Solution Approach 1:
The system performs preliminary processing of user search queries before incorporating them into the knowledge base. Search queries are pre-processed, validated, and structured appropriately before being added to the knowledge base, ensuring both speed and quality through advance preparation.
Solution Approach 2:
The system replaces manual quality control mechanisms with automated processing algorithms. Machine learning models and automated validation systems substitute for human review processes, maintaining knowledge quality and consistency while enabling rapid automated updates without sacrificing reliability.
Data Source
AI summary
The present disclosure provides a data updating method and apparatus, electronic device, and computer readable storage medium. The method includes: acquiring a search sentence; determining a target query sentence corresponding to the search sentence according to a sentence type corresponding to the search sentence; determining a target search content according to the search sentence, and sending the target search content to a service side, in the case that a query result corresponding to the target query sentence is not found in a knowledge base; acquiring a target query result edited by the service side according to the target search content; and updating the knowledge base according to the target query result.