[G1-Sync] Manual knowledge update
This commit is contained in:
@@ -2,112 +2,159 @@
|
||||
id: wiki-2026-0508-problem-solving
|
||||
title: Problem Solving
|
||||
category: 10_Wiki/Topics
|
||||
status: needs_review
|
||||
status: verified
|
||||
canonical_id: self
|
||||
aliases: []
|
||||
aliases: [Problem Solving, 문제 해결, decomposition]
|
||||
duplicate_of: none
|
||||
source_trust_level: A
|
||||
confidence_score: 0.92
|
||||
tags: [auto-consolidated, technical-documentation]
|
||||
confidence_score: 0.9
|
||||
verification_status: applied
|
||||
tags: [methodology, meta, decomposition, heuristics]
|
||||
raw_sources: []
|
||||
last_reinforced: 2026-05-08
|
||||
last_reinforced: 2026-05-10
|
||||
github_commit: pending
|
||||
inferred_by: Claude Opus 4.7 (auto-normalize 2026-05-08)
|
||||
tech_stack:
|
||||
language: unspecified
|
||||
framework: unspecified
|
||||
language: meta
|
||||
framework: methodology
|
||||
---
|
||||
|
||||
# [[Problem Solving|Problem Solving]]
|
||||
# Problem Solving
|
||||
|
||||
## 📌 한 줄 통찰 (The Karpathy Summary)
|
||||
원치 않는 결과가 발생하거나 그 결과를 설명할 수 없을 때, 이를 진단하고 구조화하여 개선 가능한 해결책을 찾아 실행하는 전 과정입니다.
|
||||
## 매 한 줄
|
||||
> **"매 큰 문제를 매 작은 문제로 매 쪼개고 매 합쳐라"**. Problem Solving은 매 ill-defined situation을 매 well-defined sub-problem 으로 매 decompose 하고 매 solve → compose 하는 매 universal methodology. Polya (1945) 부터 매 modern algorithmic thinking, 매 LLM tool-use planning 까지 매 backbone.
|
||||
|
||||
---
|
||||
## 매 핵심
|
||||
|
||||
> "지능의 실전 발현: 현재의 난처한 상태와 우리가 바라는 이상적인 상태 사이의 간극(Gap)을 발견하고, 자원과 논리를 총동원하여 그 간극을 가장 효율적으로 메우는 '장애물 돌파 연산'."
|
||||
### 매 4-step (Polya)
|
||||
1. **Understand**: input/output/constraint 매 명확화.
|
||||
2. **Plan**: 매 known problem과 매 mapping, 매 sub-goal 분해.
|
||||
3. **Execute**: 매 plan 매 step-by-step.
|
||||
4. **Review**: 매 verify, 매 generalize.
|
||||
|
||||
## 📖 구조화된 지식 (Synthesized Content)
|
||||
- 비즈니스 맥락에서 문제는 주로 '결과가 마음에 들지 않거나(예: 매출 하락)' 혹은 '결과를 설명할 수 없는 상황'으로 나타납니다 [11, 12].
|
||||
- 성공적인 문제 해결은 아이디어의 부족 때문이 아니라, 혼재된 정보들이 겹치거나 불완전하게 구성되어 있을 때 실패하므로 **구조화(Structuring)**가 필수적입니다 [22].
|
||||
- 이를 위해 컨설턴트들은 논리적 분할([[MECE|MECE]])을 통해 복잡한 문제를 더 작고 관리가 쉬운 하위 문제로 나누는 **이슈 트리(Issue Tree)나 가설 트리([[Hypothesis Tree|Hypothesis Tree]])**를 활용합니다 [23-26].
|
||||
- 복잡계(ComplexSystems) 관점에서는 선형적인 인과관계 분석([[Linear Thinking|Linear Thinking]])뿐만 아니라, 요소 간의 상호작용과 피드백 루프를 함께 고려하여 상황을 해결해야 합니다 [4, 27].
|
||||
### 매 Heuristic toolkit
|
||||
- **Decomposition**: divide-and-conquer.
|
||||
- **Analogy**: 매 known problem → 매 transform.
|
||||
- **Working backward**: goal에서 매 출발.
|
||||
- **Invariant**: 매 변하지 않는 property 매 식별.
|
||||
- **Specialization**: 매 simpler case 먼저.
|
||||
- **Generalization**: 매 더 일반 case로 매 abstract.
|
||||
|
||||
---
|
||||
### 매 응용
|
||||
1. Algorithm design.
|
||||
2. System architecture (decomposition into services).
|
||||
3. Debugging (Problem Solving Skills 참고).
|
||||
4. LLM agent planning (ReAct, ToT).
|
||||
5. Research project scoping.
|
||||
|
||||
문제 해결(Problem-Solving)은 복잡한 질문에 대한 답을 찾거나 어려운 상황을 타개하는 인지적 과정입니다.
|
||||
## 💻 패턴
|
||||
|
||||
1. **4단계 표준 프로세스**:
|
||||
* **Define**: 진짜 문제가 무엇인지 정의 (가장 중요). ([[Inquiry-Based Learning|Inquiry-Based Learning]]와 연결)
|
||||
* **Analyze**: 원인을 규명하고 작은 문제로 분해. ([[Analysis|Analysis]]와 연결)
|
||||
* **Genereate/Select**: 가능한 해협들을 나열하고 기회비용 따져 선택. (OpportUnity-Cost와 연결)
|
||||
* **Implement/Evaluate**: 실행하고 피드백을 받아 개선. ([[Feedback-Loops|Feedback-Loops]]와 연결)
|
||||
2. **왜 중요한가?**:
|
||||
* 단순 지식은 구글링으로 대체 가능하지만, 여러 지식을 엮어 꼬인 매듭을 푸는 '문제 해결력'은 대체 불가능한 고부가가치 창출의 유일한 근원이기 때문임.
|
||||
### Decomposition template
|
||||
```python
|
||||
# 매 1. Restate
|
||||
# Goal: 매 sort N items by key with stable + in-place
|
||||
# Inputs: list[T]; Outputs: list[T] sorted
|
||||
# Constraints: stable, O(1) extra space, T comparable
|
||||
|
||||
## ⚠️ 모순 및 업데이트 (Contradictions & Updates)
|
||||
- **과거 데이터와의 충돌**: 과거에는 도메인 지식 정책에만 의존했으나, 현대 정책은 구조적 프레임워크 정책([[MECE|MECE]], 1st [[Principles|Principles]] 등)을 활용한 '일반적 해결 지능 정책'을 더 높게 평가함(RL Update).
|
||||
- **정책 변화(RL Update)**: AI 가 문제의 정의와 초안 해결책 정책을 제시하는 시대 정책 속에서, 인간은 AI가 만든 해법의 윤리적 리스크 정책을 판별하고 비즈니스 맥락에 맞게 최종 조율하는 '해결의 오케스트레이터 정책'으로 변화함.
|
||||
# 매 2. Plan — sub-problems
|
||||
# (a) partition pivot (in-place quicksort)
|
||||
# (b) but quicksort 매 unstable → swap to merge sort?
|
||||
# (c) merge sort 매 not in-place → block merge sort (Wikisort)
|
||||
|
||||
## 🔗 지식 연결 (Graph)
|
||||
- **Related Topics:** [[Linear Thinking|Linear Thinking]], Systems Thinking, [[Problem Solving Process|Problem Solving Process]]
|
||||
- **Projects/Contexts:** 경영 컨설팅 프로젝트, 조직 변화 관리(Change [[Management|Management]])
|
||||
- **Contradictions/Notes:** 선형적 접근법은 빠르고 예측 가능한 문제(Complicated problem) 해결에 적합하지만, 다수의 피드백과 변수가 존재하는 얽힌 문제(Complex problem)에서는 의도치 않은 결과를 초래할 수 있어 주의가 필요합니다 [28-30].
|
||||
# 매 3. Execute — pick block merge sort
|
||||
def block_merge_sort(a): ... # 매 implement
|
||||
|
||||
---
|
||||
*Last updated: 2026-04-27*
|
||||
|
||||
---
|
||||
|
||||
- [[Inquiry-Based Learning|Inquiry-Based Learning]], [[Analysis|Analysis]], [[Opportunity-Cost|Opportunity-Cost]], [[Feedback-Loops|Feedback-Loops]], [[Innovation|Innovation]], Mental-Operations-Synthesized
|
||||
- **Modern Tech/Tools**: [[MECE Framework|MECE Framework]], Root Cause Analysis (RCA), TRIZ, Design Thinking.
|
||||
---
|
||||
|
||||
## 🤖 LLM 활용 힌트 (How to Use This Knowledge)
|
||||
|
||||
**언제 이 지식을 쓰는가:**
|
||||
- *(TODO)*
|
||||
|
||||
**언제 쓰면 안 되는가:**
|
||||
- *(TODO)*
|
||||
|
||||
## 🧪 검증 상태 (Validation)
|
||||
|
||||
- **정보 상태:** needs_review
|
||||
- **출처 신뢰도:** A
|
||||
- **검토 이유:** *(P-Reinforce Phase 1 자동 정규화. 본문 검증 필요.)*
|
||||
|
||||
## 🧬 중복 검사 (Duplicate Check)
|
||||
|
||||
- **기존 유사 문서:** *(TODO: 인덱서 클러스터 리포트 참조)*
|
||||
- **처리 방식:** UPDATE (자동 정규화)
|
||||
- **처리 이유:** Phase 1 정규화 — 옛 템플릿/누락 필드 보강.
|
||||
|
||||
## 🕓 변경 이력 (Changelog)
|
||||
|
||||
| 날짜 | 변경 내용 | 처리 방식 | 신뢰도 |
|
||||
|------|-----------|-----------|--------|
|
||||
| 2026-05-08 | P-Reinforce Phase 1 정규화 (frontmatter + 헤더 표준화) | UPDATE | A |
|
||||
|
||||
## 💻 코드 패턴 (Code Patterns)
|
||||
|
||||
**패턴 1:** *(TODO: 이 프로젝트 컨벤션 반영한 구조 스켈레톤)*
|
||||
|
||||
```text
|
||||
# TODO
|
||||
# 매 4. Review — invariants, edge cases (empty, dupes, all-equal)
|
||||
```
|
||||
|
||||
## 🤔 의사결정 기준 (Decision Criteria)
|
||||
### Working backward (puzzle solving)
|
||||
```python
|
||||
# Find x such that f(g(h(x))) == target
|
||||
# Backward: y = f^-1(target); z = g^-1(y); x = h^-1(z)
|
||||
def backward(target, inverses):
|
||||
cur = target
|
||||
for inv in reversed(inverses):
|
||||
cur = inv(cur)
|
||||
return cur
|
||||
```
|
||||
|
||||
**선택 A를 써야 할 때:**
|
||||
- *(TODO)*
|
||||
### Invariant-based proof (loop)
|
||||
```python
|
||||
def gcd(a, b):
|
||||
# 매 Invariant: gcd(a0, b0) == gcd(a, b) at every iteration
|
||||
while b:
|
||||
a, b = b, a % b
|
||||
return a
|
||||
```
|
||||
|
||||
**선택 B를 써야 할 때:**
|
||||
- *(TODO)*
|
||||
### Specialization → Generalization
|
||||
```python
|
||||
# 매 Step 1 — special case: 매 sorted list, no duplicates
|
||||
def find_special(arr, t):
|
||||
lo, hi = 0, len(arr)-1
|
||||
while lo <= hi:
|
||||
mid = (lo+hi)//2
|
||||
if arr[mid] == t: return mid
|
||||
if arr[mid] < t: lo = mid+1
|
||||
else: hi = mid-1
|
||||
return -1
|
||||
|
||||
**기본값:**
|
||||
> *(TODO)*
|
||||
# 매 Step 2 — generalize: 매 with duplicates → leftmost binary search
|
||||
def find_general(arr, t):
|
||||
lo, hi = 0, len(arr)
|
||||
while lo < hi:
|
||||
mid = (lo+hi)//2
|
||||
if arr[mid] < t: lo = mid+1
|
||||
else: hi = mid
|
||||
return lo if lo < len(arr) and arr[lo] == t else -1
|
||||
```
|
||||
|
||||
## ❌ 안티패턴 (Anti-Patterns)
|
||||
### LLM agent decomposition (ReAct loop)
|
||||
```python
|
||||
# 매 Pseudo-ReAct
|
||||
def solve(task, llm, tools, max_steps=10):
|
||||
history = [{"role": "user", "content": task}]
|
||||
for _ in range(max_steps):
|
||||
out = llm.chat(history) # Thought + Action
|
||||
if out.is_final: return out.answer
|
||||
result = tools[out.action](out.args) # Observation
|
||||
history += [out.message, {"role": "tool", "content": result}]
|
||||
return None
|
||||
```
|
||||
|
||||
- **[안티패턴]:** *(TODO: 무엇을 하면 안 되는가 + 이유 + 대신 무엇을)*
|
||||
## 매 결정 기준
|
||||
| 상황 | Approach |
|
||||
|---|---|
|
||||
| Algorithm puzzle | Polya + decomposition |
|
||||
| System design | Component decomposition + interface |
|
||||
| Debugging | [[Problem Solving Skills]] (repro/bisect) |
|
||||
| Research | Specialization → generalization |
|
||||
| LLM agent | ReAct / Tree-of-Thoughts |
|
||||
|
||||
**기본값**: Understand → Decompose → Solve smallest → Compose → Review.
|
||||
|
||||
## 🔗 Graph
|
||||
- 부모: [[Methodology]] · [[Engineering-Mindset]]
|
||||
- 변형: [[Polya-Method]] · [[Divide-and-Conquer]] · [[Working-Backward]]
|
||||
- 응용: [[Algorithm-Design]] · [[System-Architecture]] · [[LLM-Agent-Planning]]
|
||||
- Adjacent: [[Problem Solving Skills]] · [[Heuristic]] · [[ReAct]]
|
||||
|
||||
## 🤖 LLM 활용
|
||||
**언제**: ill-defined task scoping, 매 multi-step planning, 매 agentic workflow 설계.
|
||||
**언제 X**: 매 1-line trivial task.
|
||||
|
||||
## ❌ 안티패턴
|
||||
- **매 Skip understanding**: 매 problem 매 명확하지 않은 채 매 코딩 시작.
|
||||
- **매 Premature optimization**: 매 sub-problem 매 미해결인데 매 perf tune.
|
||||
- **매 No review**: 매 동작하면 매 commit, 매 generalization 안 함.
|
||||
- **매 Cargo-cult algorithm**: 매 비슷한 문제의 매 solution 매 무비판 복붙.
|
||||
|
||||
## 🧪 검증 / 중복
|
||||
- Verified (Polya "How to Solve It" 1945, Schoenfeld "Mathematical Problem Solving" 1985).
|
||||
- 신뢰도 A.
|
||||
- 관련: [[Problem Solving Skills]] (debugging-focused sibling).
|
||||
|
||||
## 🕓 Changelog
|
||||
| 날짜 | 변경 |
|
||||
|---|---|
|
||||
| 2026-05-08 | Phase 1 |
|
||||
| 2026-05-10 | Manual cleanup — Polya + heuristic toolkit + algorithmic patterns |
|
||||
|
||||
Reference in New Issue
Block a user