Knowledge Base Search

Knowledge Base Intelligent Search

AI Central Intelligent Search Feature Overview

To improve information retrieval efficiency, the AI Central platform offers two search methods: "Quick Search" and "AI Search," both accessible through a unified entry point on the homepage. These two search modes cater to different types of query needs, meeting diverse usage scenarios.

Intelligent Search Entry

Below the input box on the platform homepage, you can click "AI Search" to enter the intelligent search interface.

This entry is located in the central main operation area, alongside Deep Research, Data Analysis, AI Translator, and other functions, allowing users to initiate intelligent Q&A or query operations at any time.

Quick Search — Direct Access to Information Sources via Keywords

Quick Search is based on a keyword matching mechanism. The system quickly locates relevant content across multiple data sources, including:

• Knowledge Base Document Retrieval: The system searches the knowledge base for documents containing the input keywords;

  • For example, searching Microsoft 365 will automatically find related content in all knowledge documents;

  • Matched documents are sorted by relevance, making it easier to prioritize the most pertinent materials;

  • Supports clicking “View More” below search results to preview documents online.

• QnA Matching: The system also automatically identifies and recommends frequently asked questions and answers related to the keywords.

• Online Search: If the knowledge base does not contain relevant content, the system will provide extended information sources through online search.

✅ Applicable Scenarios: Quick Search is suitable for fast locating and consulting known keywords, terms, product names, feature points, and other information.

AI Search — Semantic Understanding, Intelligent Answer Generation

AI Search is based on natural language processing technology, capable of deeply understanding the true intent behind user queries and converting them into internal system question processing requests, combining multiple data sources to provide accurate and natural answers.

Features

• Automatic Question Parsing: Users can directly input complete questions or descriptive sentences (e.g., “Reasons why the notebook battery cannot be charged?”), and AI will automatically parse the intent and convert it into a searchable knowledge request.

• Multi-source Fusion Retrieval: AI Search answers can come from:

  • Knowledge base documents

  • Configured QnA libraries

  • Network(such as web content)

• Cited Source Annotation: Each AI answer automatically includes the source document of the referenced knowledge;

  • Clicking the citation opens the document on the left side for content preview, facilitating verification and in-depth reading.

• Intelligent Summary Output: After the answer is completed, users can click the “Mind Map/Outline” button on the right side of the answer. The system will automatically extract and summarize the current answer content:

  • Visualize core points and structure in a mind map format;

  • Present a clear and organized content structure in an outline format, facilitating subsequent organization, reuse, or documentation.

✅ Applicable Scenarios: AI Search is suitable for scenarios where keywords are uncertain, or when systematic answers or more complex questions are desired.

Feature Comparison Overview

Search Scope

• Search Content: File names, file contents, QnA questions, QnA answers

• Search Result Display: All, Documents, QnA, Online

• Search Filter Conditions: Workspace, date, Metadata Filters, Document match similarity, QnA match similarity

• Search Result Sorting: Relevance, Time Dimension

• Retrieval strategy: Hybrid, Embedding, Text

• Metadata Filters: None, Sorting, Filtering