내부,외부 시퀀스 기능 추가

design/backend/sequence/inner/ai-회의록자동작성.puml

@@ -1,10 +1,11 @@
 @startuml
 !theme mono
 
-title AI Service 내부 시퀀스 - 회의록자동작성
+title AI Service 내부 시퀀스 - 회의록자동작성 (실시간 추천 포함)
 
 participant "TranscriptController" as Controller
 participant "TranscriptService" as Service
+participant "SuggestionService" as SuggestService
 participant "LLMClient" as LLM
 participant "VectorService" as Vector
 participant "TranscriptRepository" as Repo
@@ -119,9 +120,134 @@ deactivate VectorDB
 Vector --> Service: 임베딩 생성 완료
 deactivate Vector
 
+== 실시간 추천 병렬 처리 ==
+
+Service -> SuggestService: generateRealtimeSuggestions(meetingId, transcriptText)
+activate SuggestService
+
+par 논의사항 제안 생성
+    SuggestService -> LLM: suggestDiscussionTopics(meetingId, transcript)
+    activate LLM
+
+    LLM -> OpenAI: POST /chat/completions
+    activate OpenAI
+    note right
+      프롬프트:
+      - 현재 대화 맥락 분석
+      - 빠진 논의 항목 찾기
+      - 추가하면 좋을 주제 제안
+
+      응답 형식:
+      {
+        "suggestions": [
+          {
+            "topic": "논의 주제",
+            "reason": "제안 이유",
+            "priority": "HIGH|MEDIUM|LOW"
+          }
+        ]
+      }
+    end note
+
+    OpenAI --> LLM: 논의사항 제안 목록
+    deactivate OpenAI
+
+    LLM --> SuggestService: discussionSuggestions
+    deactivate LLM
+
+    SuggestService -> Repo: saveSuggestions(meetingId, "DISCUSSION", suggestions)
+    activate Repo
+    Repo -> DB: INSERT INTO ai_suggestions
+    activate DB
+    DB --> Repo: 저장 완료
+    deactivate DB
+    deactivate Repo
+
+else 결정사항 제안 생성
+    SuggestService -> LLM: suggestDecisions(meetingId, transcript)
+    activate LLM
+
+    LLM -> OpenAI: POST /chat/completions
+    activate OpenAI
+    note right
+      프롬프트:
+      - "~하기로 함" 패턴 감지
+      - "~로 결정" 패턴 감지
+      - 결정 내용 구조화
+
+      응답 형식:
+      {
+        "decisions": [
+          {
+            "content": "결정 내용",
+            "category": "기술|일정|리소스",
+            "confidence": 0.0-1.0
+          }
+        ]
+      }
+    end note
+
+    OpenAI --> LLM: 결정사항 제안 목록
+    deactivate OpenAI
+
+    LLM --> SuggestService: decisionSuggestions
+    deactivate LLM
+
+    SuggestService -> Repo: saveSuggestions(meetingId, "DECISION", suggestions)
+    activate Repo
+    Repo -> DB: INSERT INTO ai_suggestions
+    activate DB
+    DB --> Repo: 저장 완료
+    deactivate DB
+    deactivate Repo
+
+else 실시간 액션아이템 추출
+    SuggestService -> LLM: extractRealtimeActionItems(meetingId, transcript)
+    activate LLM
+
+    LLM -> OpenAI: POST /chat/completions
+    activate OpenAI
+    note right
+      프롬프트:
+      - "~까지 하겠습니다" 패턴 감지
+      - "제가 담당하겠습니다" 패턴 감지
+      - 담당자 및 마감일 추출
+
+      응답 형식:
+      {
+        "actionItems": [
+          {
+            "content": "할 일 내용",
+            "assignee": "담당자",
+            "dueDate": "YYYY-MM-DD",
+            "priority": "HIGH|MEDIUM|LOW"
+          }
+        ]
+      }
+    end note
+
+    OpenAI --> LLM: 액션아이템 후보 목록
+    deactivate OpenAI
+
+    LLM --> SuggestService: actionItemSuggestions
+    deactivate LLM
+
+    SuggestService -> Repo: saveSuggestions(meetingId, "ACTION_ITEM", suggestions)
+    activate Repo
+    Repo -> DB: INSERT INTO ai_suggestions
+    activate DB
+    DB --> Repo: 저장 완료
+    deactivate DB
+    deactivate Repo
+
+end
+
+SuggestService --> Service: 모든 추천사항 생성 완료
+deactivate SuggestService
+
 == 이벤트 발행 ==
 
-Service -> Controller: 회의록 생성 완료 응답
+Service -> Controller: 회의록 및 추천사항 생성 완료 응답
 deactivate Service
 
 Controller -> Controller: TranscriptSummaryCreated 발행
@@ -130,15 +256,23 @@ note right
 - meetingId
 - transcriptId
 - content
+- suggestions:
+  * discussionTopics: []
+  * decisions: []
+  * actionItems: []
 end note
 
 note over Controller, DB
 처리 시간:
 - 맥락 조회: 100-200ms
-- LLM 생성: 3-5초
+- LLM 회의록 생성: 3-5초
 - 저장: 100-200ms
 - 벡터화: 500ms-1초
-총: 약 4-7초
+- 실시간 추천 병렬 처리: 5-8초
+  * 논의사항 제안: 2-3초
+  * 결정사항 제안: 2-3초
+  * 액션아이템 추출: 1-2초
+총: 약 9-15초
 end note
 
-@enduml
+@enduml