Skip to main content

Knowledge Base Search

Knowledge Base Intelligent Search

SERVICEME Intelligent Search Feature Details

To improve information retrieval efficiency, the SERVICEME platform provides two search methods: Quick Search and AI Search, both accessible from a unified entry point on the homepage. These two search modes are suitable for different types of queries, 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 (as shown below).

This entry is located at the center of the main operation area, alongside features such as AI Search, Data Analysis, and Webpage Summary, 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, enabling the system to quickly locate relevant content across multiple data sources, including:

  • Knowledge Base Document Retrieval: The system searches for document content in the knowledge base that contains the entered keywords;

    • For example, searching for Microsoft 365, the system will automatically look for content related to this term in all knowledge documents;
    • Matched documents are sorted by relevance, making it easy to view the most relevant materials first;
    • You can click "View More" below the search results to preview documents online.

  • QnA Matching: The system will also automatically identify and recommend frequently asked questions and answers related to the keywords.

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

✅ Applicable Scenarios: Quick Search is suitable for quickly locating and referencing information with known keywords, terms, product names, or feature points.

AI Search — Semantic Understanding, Intelligent Answer Generation​

AI Search is based on natural language processing technology, capable of deeply understanding the real intent behind user queries, converting them into internal system requests, and providing accurate, natural answers by integrating multiple data sources.

Feature Highlights​

  • Automatic Question Parsing: Users can directly enter complete questions or descriptive statements (e.g., "How to configure Microsoft 365 email auto-forwarding?"), and AI will automatically parse the intent and convert it into a searchable knowledge request.

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

    • Knowledge base documents
    • Configured QnA libraries
    • Online information (such as web content)

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

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

  • Intelligent Summary Output: After answering, users can also click the "Mind Map/Outline" button on the right side of the answer, and the system will automatically extract and summarize the current answer content:
    • Visualize key points and structure in mind map format;
    • Present a clear content structure in outline format, making it easy for 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 needed.

Feature Comparison Overview​

Feature ComparisonQuick SearchAI Search
Input MethodKeywordNatural language question
Matching MechanismKeyword matchingIntent recognition + multi-source search
Returned ContentDocuments, QnA, online resultsQuestion answers (with source citation)
Additional CapabilitiesDocument previewCitation jump, mind map/outline generation
Applicable ScenariosQuick content locationObtain structured answers

Search Scope​

  • Content Searched: File names, file content, QnA questions, QnA answers

  • Supported Languages: Simplified Chinese, Traditional Chinese, English (other languages can be added in multilingual settings)

  • Supported File Types: TXT, DOCX, XLSX, XLS, PPTX, PDF

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

  • Search Filter Criteria: File space, date, metadata filtering, document match similarity, QnA match similarity

  • Search Result Sorting: Match degree, time dimension

Homepage