ASR Interview Coder LLM System Flow

ML & AI · flowchart diagram · NOASSERTION

This diagram illustrates the complete processing flow for an ASR-based LLM system, from input to answer generation, including smart analysis, intent recogn

Source: https://github.com/lanzeweie/ASR-interview-coder-llm/blob/cad6297ac1dc16063215e57c175239b2019d44ab/README/Mermaid.md
Curated by lanzeweie
ASR LLM Conversational AI System Design Flowchart Agent Pipeline

Mermaid source

flowchart TD
    %% --- 系统入口 ---
    subgraph Entrances [系统入口]
        ASR([ASR消息输入])
        Manual([手动输入消息])
    end

    %% 第一层入口：ASR自动触发 或 手动消息
    ASR --> SmartCheck{智能分析开启？}
    Manual --> L1_Manual[手动进入第一层]

    %% 第一层：智能分析（可关闭）
    SmartCheck -- 否 --> L1_Manual
    SmartCheck -- 是 --> SmartTrigger[第一层：智能分析 Agent]
    SmartTrigger --> SmartResult{智能分析返回？}

    SmartResult -- false --> ContinueListen[继续监听]
    SmartResult -- true --> L1_Out[第一层完成]

    L1_Manual --> IntentCheck
    L1_Out --> IntentCheck

    %% 第二层：意图识别（可关闭）
    IntentCheck{意图识别开启？} -->|否| L3_Start
    IntentCheck -->|是| IntentAgent[第二层：意图识别 Agent]
    IntentAgent --> L2_Out[意图结果]
    L2_Out --> L3_Start

    %% 第三层：用户个性化（可关闭）
    L3_Start --> PersonalCheck{用户个性化开启？}
    PersonalCheck -- 否 --> L4_Start
    PersonalCheck -- 是 --> Personal[第三层：用户个性化]
    Personal --> L4_Start

    %% 第四层：回答生成（必选）
    subgraph Answering [第四层：回答生成]
        L4_Start --> ModeCheck{智囊团模式？}

        ModeCheck -- 是 --> ThinkTank[智囊团并行模型回答]
        ModeCheck -- 否 --> SingleModel[单模型回答]

        ThinkTank --> Collect[加载目标岗位提示词]
        SingleModel --> Collect
        Collect --> ENDs[输出]
    end

What this diagram shows

The diagram shows a four-layer processing pipeline for an ASR-driven LLM system. It starts with ASR or manual message input, proceeds through optional smart analysis, intent recognition, and user personalization layers, and concludes with answer generation using either a "Think Tank" (parallel model) or a single model.

When to use it

Use this diagram to understand the high-level architecture of an AI assistant or chatbot system that processes spoken input, performs intelligent analysis, identifies user intent, personalizes responses, and generates answers. It's suitable for designing conversational AI systems.

How to adapt it for your project

This flow can be adapted by modifying or disabling specific layers (e.g., smart analysis, intent recognition, personalization) based on application requirements. The "Think Tank" vs. "Single Model" decision in the answering layer can be extended to include different LLM orchestration strategies or model ensembles. Additional pre-processing or post-processing steps can be inserted.

Key concepts