Job Analysis and Dual-Mode Question Answering System

ML & AI · flowchart diagram · NOASSERTION

Illustrates a system for generating professional job analysis from user input and then using it to answer questions in either a direct or deep-thinking dua

Source: https://github.com/lanzeweie/ASR-interview-coder-llm/blob/cad6297ac1dc16063215e57c175239b2019d44ab/README/Mermaid.md
Curated by lanzeweie
AI LLM Job Analysis System Design Workflow Contextual Processing Interview Preparation

Mermaid source

graph TD
    %% 定义样式
    classDef base fill:#f9f9f9,stroke:#333,stroke-width:1px;
    classDef input fill:#e3f2fd,stroke:#1565c0,stroke-width:2px;
    classDef analysis fill:#fff9c4,stroke:#fbc02d,stroke-width:2px;
    classDef dualStart fill:#e8f5e9,stroke:#2e7d32,stroke-width:2px;
    classDef action fill:#ede7f6,stroke:#512da8,stroke-width:2px;
    classDef output fill:#212121,stroke:#000,stroke-width:2px,color:#fff;

    %% === 第一阶段：数据准备 ===
    subgraph 用户提取准备
        direction TB
        User([用户输入]) --> Inputs[/岗位名称 / 岗位JD/]
        Inputs --> GenAnalysis[生成: 专业版岗位分析]
    end

    %% === 第二阶段：双模式响应 ===
    subgraph 当回答问题时
        direction TB
        %% 双开头
        StartDirect[模式 A: 直接回答]
        StartThink[模式 B: 第四层 智囊团深度思考]
        
        %% 加载动作
        LoadContext(动作: 加载岗位分析)
        
        %% 输出
        FinalOutput([输出答案])
        
        %% 连线关系
        StartDirect --> LoadContext
        StartThink --> LoadContext
        LoadContext --> FinalOutput
    end

    %% === 跨阶段数据流（虚线代表数据引用） ===
    GenAnalysis -.->|作为上下文数据| LoadContext

    %% 应用样式
    class User,Inputs input;
    class GenAnalysis analysis;
    class StartDirect,StartThink dualStart;
    class LoadContext action;
    class FinalOutput output;

What this diagram shows

This diagram outlines a two-stage process: first, preparing data by taking user input (job title/JD) to generate a professional job analysis. Second, it shows a dual-mode response system for answering questions, where both direct and deep-thinking modes load the generated job analysis as context before producing a final answer.

When to use it

Use this diagram when designing AI-powered interview preparation tools, intelligent agents for job matching, or any system requiring contextualized responses based on detailed input analysis, especially for professional or domain-specific queries.

How to adapt it for your project

This model can be adapted by changing the 'analysis' stage to process different types of documents (e.g., resumes, legal texts) or by introducing more sophisticated 'dual modes' for response generation, such as integrating multiple AI models or human-in-the-loop validation. The output can be customized for various formats beyond simple answers.

Key concepts