Back to Details

researcher-hand-skill

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Deep Research Expert Knowledge

AI深度研究专业知识

Research Methodology

研究方法论

Research Process (5 phases)

研究流程（5个阶段）

  1. Define: Clarify the question, identify what's known vs unknown, set scope
  2. Search: Systematic multi-strategy search across diverse sources
  3. Evaluate: Assess source quality, extract relevant data, note limitations
  4. Synthesize: Combine findings into coherent answer, resolve contradictions
  5. Verify: Cross-check critical claims, identify remaining uncertainties
  1. 定义：明确研究问题，区分已知与未知信息，设定研究范围
  2. 搜索：采用多种策略，在多样化来源中进行系统性搜索
  3. 评估：评估来源质量，提取相关数据，记录局限性
  4. 整合：将研究发现整合成连贯的结论，解决矛盾点
  5. 验证：交叉核对关键结论，识别剩余的不确定性

Question Types & Strategies

问题类型与对应策略

Question TypeStrategyExample
FactualFind authoritative primary source"What is the population of Tokyo?"
ComparativeMulti-source balanced analysis"React vs Vue for large apps?"
CausalEvidence chain + counterfactuals"Why did Theranos fail?"
PredictiveTrend analysis + expert consensus"Will quantum computing replace classical?"
How-toStep-by-step from practitioners"How to set up a Kubernetes cluster?"
SurveyComprehensive landscape mapping"What are the options for vector databases?"
ControversialMultiple perspectives + primary sources"Is remote work more productive?"
问题类型策略示例
事实类查找权威一手来源"东京的人口是多少？"
对比类多来源平衡分析"大型应用选React还是Vue？"
因果类证据链分析+反事实推理"Theranos为何失败？"
预测类趋势分析+专家共识"量子计算会取代经典计算吗？"
操作类从业者提供的分步指南"如何搭建Kubernetes集群？"
调研类全面的领域格局梳理"向量数据库有哪些可选方案？"
争议类多视角分析+一手来源佐证"远程办公效率更高吗？"

Decomposition Technique

问题分解技巧

Complex questions should be broken into sub-questions:
Main: "Should our startup use microservices?"
Sub-questions:
  1. What are microservices? (definitional)
  2. What are the benefits vs monolith? (comparative)
  3. What team size/stage is appropriate? (contextual)
  4. What are the operational costs? (factual)
  5. What do similar startups use? (case studies)
  6. What are the migration paths? (how-to)
复杂问题应拆解为多个子问题：
主问题："我们的创业公司应该使用微服务吗？"
子问题：
  1. 什么是微服务？（定义类）
  2. 微服务对比单体架构的优劣势是什么？（对比类）
  3. 适合的团队规模/发展阶段是怎样的？（场景类）
  4. 运维成本有哪些？（事实类）
  5. 同类创业公司都在使用什么架构？（案例类）
  6. 迁移路径有哪些？（操作类）

CRAAP Source Evaluation Framework

CRAAP来源评估框架

Currency

时效性（Currency）

  • When was it published or last updated?
  • Is the information still current for the topic?
  • Are the links functional?
  • For technology topics: anything >2 years old may be outdated
  • 内容的发布或最后更新时间是什么时候？
  • 该信息对于当前主题是否仍具时效性？
  • 链接是否可用？
  • 技术领域主题：发布超过2年的内容可能已过时

Relevance

相关性（Relevance）

  • Does it directly address your question?
  • Who is the intended audience?
  • Is the level of detail appropriate?
  • Would you cite this in your report?
  • 内容是否直接回应你的研究问题？
  • 目标受众是谁？
  • 内容的详细程度是否合适？
  • 你会在报告中引用该来源吗？

Authority

权威性（Authority）

  • Who is the author? What are their credentials?
  • What institution published this?
  • Is there contact information?
  • Does the URL domain indicate authority? (.gov, .edu, reputable org)
  • 作者是谁？其资质如何？
  • 发布机构是什么？
  • 是否有联系方式？
  • URL域名是否体现权威性？（如.gov、.edu、知名组织域名）

Accuracy

准确性（Accuracy）

  • Is the information supported by evidence?
  • Has it been reviewed or refereed?
  • Can you verify the claims from other sources?
  • Are there factual errors, typos, or broken logic?
  • 信息是否有证据支撑？
  • 是否经过同行评审或审阅？
  • 能否通过其他来源验证结论？
  • 是否存在事实错误、拼写错误或逻辑漏洞？

Purpose

目的性（Purpose）

  • Why does this information exist?
  • Is it informational, commercial, persuasive, or entertainment?
  • Is the bias clear or hidden?
  • Does the author/organization benefit from you believing this?
  • 该信息存在的目的是什么？
  • 是信息性、商业性、说服性还是娱乐性内容？
  • 偏见是明确的还是隐藏的？
  • 作者/机构是否会因你相信该信息而获益？

Scoring

评分标准

A (Authoritative):  Passes all 5 CRAAP criteria
B (Reliable):       Passes 4/5, minor concern on one
C (Useful):         Passes 3/5, use with caveats
D (Weak):           Passes 2/5 or fewer
F (Unreliable):     Fails most criteria, do not cite
A（权威）：  满足全部5项CRAAP标准
B（可靠）：  满足4/5项，仅一项存在小问题
C（可用）：  满足3/5项，需谨慎使用
D（薄弱）：  仅满足2/5项或更少
F（不可靠）：大部分标准不满足，请勿引用

Search Query Optimization

搜索查询优化

Query Construction Techniques

查询构建技巧

Exact phrase: 
"specific phrase"
— use for names, quotes, error messages Site-specific: 
site:domain.com query
— search within a specific site Exclude: 
query -unwanted_term
— remove irrelevant results File type: 
filetype:pdf query
— find specific document types Recency: 
query after:2024-01-01
— recent results only OR operator: 
query (option1 OR option2)
— broaden search Wildcard: 
"how to * in python"
— fill-in-the-blank
精确短语：
"特定短语"
— 用于搜索名称、引用、错误信息等 指定站点：
site:domain.com 查询
— 在特定站点内搜索 排除术语：
查询 -无关术语
— 移除不相关结果 指定文件类型：
filetype:pdf 查询
— 查找特定格式的文档 限定时间：
查询 after:2024-01-01
— 仅显示指定时间后的结果 或操作符：
查询 (选项1 OR 选项2)
— 扩大搜索范围 通配符：
"how to * in python"
— 用于填空式搜索

Multi-Strategy Search Pattern

多策略搜索模式

For each research question, use at least 3 search strategies:
  1. Direct: The question as-is
  2. Authoritative: 
    site:gov OR site:edu OR site:org [topic]
  3. Academic: 
    [topic] research paper [year]
    or 
    site:arxiv.org [topic]
  4. Practical: 
    [topic] guide
    or 
    [topic] tutorial
    or 
    [topic] how to
  5. Data: 
    [topic] statistics
    or 
    [topic] data [year]
  6. Contrarian: 
    [topic] criticism
    or 
    [topic] problems
    or 
    [topic] myths
针对每个研究问题，至少使用3种搜索策略：
  1. 直接搜索：直接输入问题
  2. 权威来源搜索：
    site:gov OR site:edu OR site:org [主题]
  3. 学术搜索：
    [主题] research paper [年份]
    或 
    site:arxiv.org [主题]
  4. 实操指南搜索：
    [主题] guide
    或 
    [主题] tutorial
    或 
    [主题] how to
  5. 数据搜索：
    [主题] statistics
    或 
    [主题] data [年份]
  6. 反向视角搜索：
    [主题] criticism
    或 
    [主题] problems
    或 
    [主题] myths

Source Discovery by Domain

按领域划分的来源发现

DomainBest SourcesSearch Pattern
TechnologyOfficial docs, GitHub, Stack Overflow, engineering blogs
[tech] documentation
, 
site:github.com [tech]
SciencePubMed, arXiv, Nature, Science
site:arxiv.org [topic]
, 
[topic] systematic review
BusinessSEC filings, industry reports, HBR
[company] 10-K
, 
[industry] report [year]
MedicinePubMed, WHO, CDC, Cochrane
site:pubmed.ncbi.nlm.nih.gov [topic]
LegalCourt records, law reviews, statute databases
[case] ruling
, 
[law] analysis
StatisticsCensus, BLS, World Bank, OECD
site:data.worldbank.org [metric]
Current eventsReuters, AP, BBC, primary sources
[event] statement
, 
[event] official
领域优质来源搜索模式
技术官方文档、GitHub、Stack Overflow、技术博客
[技术] documentation
, 
site:github.com [技术]
科学PubMed、arXiv、Nature、Science
site:arxiv.org [主题]
, 
[主题] systematic review
商业SEC文件、行业报告、哈佛商业评论（HBR）
[公司] 10-K
, 
[行业] report [年份]
医学PubMed、WHO、CDC、Cochrane
site:pubmed.ncbi.nlm.nih.gov [主题]
法律法庭记录、法律评论、法规数据库
[案例] ruling
, 
[法律] analysis
统计人口普查、劳工统计局（BLS）、世界银行、经合组织（OECD）
site:data.worldbank.org [指标]
时事路透社、美联社、BBC、一手来源
[事件] statement
, 
[事件] official

Cross-Referencing Techniques

交叉验证技巧

Verification Levels

验证等级

Level 1: Single source (unverified)
  → Mark as "reported by [source]"

Level 2: Two independent sources agree (corroborated)
  → Mark as "confirmed by multiple sources"

Level 3: Primary source + secondary confirmation (verified)
  → Mark as "verified — primary source: [X]"

Level 4: Expert consensus (well-established)
  → Mark as "widely accepted" or "scientific consensus"
等级1：单一来源（未验证）
  → 标注为“来源：[具体来源]”

等级2：两个独立来源结论一致（已佐证）
  → 标注为“多来源确认”

等级3：一手来源+二手来源确认（已验证）
  → 标注为“已验证——一手来源：[X]”

等级4：专家共识（已确立）
  → 标注为“广泛认可”或“科学共识”

Contradiction Resolution

矛盾解决

When sources disagree:
  1. Check which source is more authoritative (CRAAP scores)
  2. Check which is more recent (newer may have updated info)
  3. Check if they're measuring different things (apples vs oranges)
  4. Check for known biases or conflicts of interest
  5. Present both views with evidence for each
  6. State which view the evidence better supports (if clear)
  7. If genuinely uncertain, say so — don't force a conclusion
当来源结论不一致时：
  1. 对比来源的CRAAP评分，判断哪个更权威
  2. 查看发布时间，较新的内容可能包含更新信息
  3. 确认是否在衡量不同事物（避免苹果对比橙子）
  4. 检查是否存在已知偏见或利益冲突
  5. 同时呈现两种观点及各自证据
  6. 若证据明确，说明哪一种观点更具说服力
  7. 若确实存在不确定性，直接说明——不要强行下结论

Synthesis Patterns

信息整合模式

Narrative Synthesis

叙事式整合

The evidence suggests [main finding].

[Source A] found that [finding 1], which is consistent with
[Source B]'s observation that [finding 2]. However, [Source C]
presents a contrasting view: [finding 3].

The weight of evidence favors [conclusion] because [reasoning].
A key limitation is [gap or uncertainty].
证据表明[核心结论]。

[来源A]发现[结论1]，这与
[来源B]观察到的[结论2]一致。不过，[来源C]
提出了相反观点：[结论3]。

综合证据更支持[最终结论]，原因是[推理过程]。
关键局限性在于[研究空白或不确定性]。

Structured Synthesis

结构化整合

FINDING 1: [Claim]
  Evidence for: [Source A], [Source B] — [details]
  Evidence against: [Source C] — [details]
  Confidence: [high/medium/low]
  Reasoning: [why the evidence supports this finding]

FINDING 2: [Claim]
  ...
结论1：[主张]
  支持证据：[来源A]、[来源B] — [细节]
  反对证据：[来源C] — [细节]
  可信度：[高/中/低]
  推理：[证据支持该结论的原因]

结论2：[主张]
  ...

Gap Analysis

差距分析

After synthesis, explicitly note:
  • What questions remain unanswered?
  • What data would strengthen the conclusions?
  • What are the limitations of the available sources?
  • What follow-up research would be valuable?
整合完成后，需明确指出：
  • 哪些问题仍未得到解答？
  • 补充哪些数据能强化结论？
  • 当前可用来源存在哪些局限性？
  • 哪些后续研究具有价值？

Citation Formats

引用格式

Inline URL

内联URL

According to a 2024 study (https://example.com/study), the effect was significant.
根据2024年的一项研究（https://example.com/study），该效应十分显著。

Footnotes

脚注

According to a 2024 study[1], the effect was significant.

---
[1] https://example.com/study — "Title of Study" by Author, Published Date
根据2024年的一项研究[1]，该效应十分显著。

---
[1] https://example.com/study — 《研究标题》，作者，发布日期

Academic (APA)

学术格式（APA）

In-text: (Smith, 2024)
Reference: Smith, J. (2024). Title of the article. *Journal Name*, 42(3), 123-145. https://doi.org/10.xxxx
For web sources (APA):
Author, A. A. (Year, Month Day). Title of page. Site Name. https://url
正文内：(Smith, 2024)
参考文献：Smith, J. (2024). Title of the article. *Journal Name*, 42(3), 123-145. https://doi.org/10.xxxx
网络来源的APA格式：
Author, A. A. (Year, Month Day). Title of page. Site Name. https://url

Numbered References

编号引用

According to recent research [1], the finding was confirmed by independent analysis [2].
近期研究[1]表明，该结论已被独立分析[2]确认。

References

参考文献

  1. Author (Year). Title. URL
  2. Author (Year). Title. URL

---
  1. 作者（年份）。标题。URL
  2. 作者（年份）。标题。URL

---

Output Templates

输出模板

Brief Report

简要报告

markdown
undefined
markdown
undefined

[Question]

[研究问题]

Date: YYYY-MM-DD | Sources: N | Confidence: high/medium/low
日期：YYYY-MM-DD | 来源数量：N | 可信度：高/中/低

Answer

答案

[2-3 paragraph direct answer]
[2-3段直接回答]

Key Evidence

核心证据

  • [Finding 1] — [source]
  • [Finding 2] — [source]
  • [Finding 3] — [source]
  • [结论1] — [来源]
  • [结论2] — [来源]
  • [结论3] — [来源]

Caveats

注意事项

  • [Limitation or uncertainty]
  • [局限性或不确定性]

Sources

来源

  1. Source
  2. Source
undefined
  1. 来源名称
  2. 来源名称
undefined

Detailed Report

详细报告

markdown
undefined
markdown
undefined

Research Report: [Question]

研究报告：[研究问题]

Date: YYYY-MM-DD | Depth: thorough | Sources Consulted: N
日期：YYYY-MM-DD | 研究深度：全面 | 参考来源数量：N

Executive Summary

执行摘要

[1 paragraph synthesis]
[1段整合内容]

Background

背景

[Context needed to understand the findings]
[理解结论所需的上下文信息]

Methodology

研究方法

[How the research was conducted, what was searched, how sources were evaluated]
[研究实施流程、搜索范围、来源评估方式]

Findings

研究结果

[Sub-question 1]

[子问题1]

[Detailed findings with inline citations]
[详细结论及内联引用]

[Sub-question 2]

[子问题2]

[Detailed findings with inline citations]
[详细结论及内联引用]

Analysis

分析

[Synthesis across findings, patterns identified, implications]
[跨结论的整合内容、识别的模式、隐含意义]

Contradictions & Open Questions

矛盾点与待解问题

[Areas of disagreement, gaps in knowledge]
[存在分歧的领域、知识空白]

Confidence Assessment

可信度评估

[Overall confidence level with reasoning]
[整体可信度等级及推理过程]

Sources

来源

[Full bibliography in chosen citation format]

---
[所选引用格式的完整参考文献列表]

---

Cognitive Bias in Research

研究中的认知偏差

Be aware of these biases during research:
  1. Confirmation bias: Favoring information that confirms your initial hypothesis
    • Mitigation: Explicitly search for disconfirming evidence
  2. Authority bias: Over-trusting sources from prestigious institutions
    • Mitigation: Evaluate evidence quality, not just source prestige
  3. Anchoring: Fixating on the first piece of information found
    • Mitigation: Gather multiple sources before forming conclusions
  4. Selection bias: Only finding sources that are easy to access
    • Mitigation: Vary search strategies, check non-English sources
  5. Recency bias: Over-weighting recent publications
    • Mitigation: Include foundational/historical sources when relevant
  6. Framing effect: Being influenced by how information is presented
    • Mitigation: Look at raw data, not just interpretations
研究过程中需注意以下偏差：
  1. 确认偏差：偏好支持初始假设的信息
    • 缓解方法：主动搜索反驳性证据
  2. 权威偏差：过度信任知名机构的来源
    • 缓解方法：评估证据质量，而非仅看机构声望
  3. 锚定偏差：过度依赖最先获取的信息
    • 缓解方法：收集多个来源后再形成结论
  4. 选择偏差：仅获取易访问的来源
    • 缓解方法：多样化搜索策略，查看非英文来源
  5. 近期偏差：过度重视最新发布的内容
    • 缓解方法：相关时纳入基础/历史来源
  6. 框架效应：受信息呈现方式影响
    • 缓解方法：查看原始数据，而非仅看解读内容

Domain-Specific Research Tips

特定领域研究技巧

Technology Research

技术研究

  • Always check the official documentation first
  • Compare documentation version with the latest release
  • Stack Overflow answers may be outdated — check the date
  • GitHub issues/discussions often have the most current information
  • Benchmarks without methodology descriptions are unreliable
  • 优先查阅官方文档
  • 对比文档版本与最新发布版本
  • Stack Overflow的回答可能过时——注意查看发布日期
  • GitHub的issues/讨论区通常包含最新信息
  • 未说明方法论的基准测试不可靠

Business Research

商业研究

  • SEC filings (10-K, 10-Q) are the most reliable public company data
  • Press releases are marketing — verify claims independently
  • Analyst reports may have conflicts of interest — check disclaimers
  • Employee reviews (Glassdoor) provide internal perspective but are biased
  • SEC文件（10-K、10-Q）是最可靠的上市公司公开数据
  • 新闻稿属于营销内容——需独立验证结论
  • 分析师报告可能存在利益冲突——查看免责声明
  • 员工评价（Glassdoor）提供内部视角，但存在偏差

Scientific Research

科学研究

  • Systematic reviews and meta-analyses are strongest evidence
  • Single studies should not be treated as definitive
  • Check if findings have been replicated
  • Preprints have not been peer-reviewed — note this caveat
  • p-values and effect sizes both matter — not just "statistically significant"
  • 系统性综述和元分析是最有力的证据
  • 单一研究不应被视为定论
  • 检查结论是否已被重复验证
  • 预印本未经过同行评审——需标注该注意事项
  • p值和效应量都很重要——不能只看“统计显著” ",