Back to Details

prior-art-search

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Prior Art Search

Prior Art 检索

Search patents and literature for prior art relevant to: $ARGUMENTS
Adapted from 
/research-lit
for patent-specific searching.
检索与**$ARGUMENTS**相关的专利和文献中的现有技术
改编自
/research-lit
，专为专利检索场景设计。

Constants

常量

  • MAX_PATENT_RESULTS = 20
    — Maximum patent documents to analyze in detail
  • MAX_PAPER_RESULTS = 15
    — Maximum academic papers to analyze in detail
  • SEARCH_YEARS = 10
    — How many years back to search
  • PATENT_DATABASES = "google-patents, espacenet"
    — Patent databases to search
  • MAX_PATENT_RESULTS = 20
    — 需详细分析的专利文档最大数量
  • MAX_PAPER_RESULTS = 15
    — 需详细分析的学术论文最大数量
  • SEARCH_YEARS = 10
    — 检索的时间回溯范围（年）
  • PATENT_DATABASES = "google-patents, espacenet"
    — 待检索的专利数据库

Inputs

输入来源

Read the invention description from:
  1. $ARGUMENTS
    if it contains technical details
  2. patent/INVENTION_BRIEF.md
    if it exists
  3. INVENTION_BRIEF.md
    if it exists at project root
从以下来源读取发明描述：
  1. $ARGUMENTS
    若包含技术细节，则从中读取
  2. patent/INVENTION_BRIEF.md
    若文件存在，则从中读取
  3. INVENTION_BRIEF.md
    若项目根目录下存在该文件，则从中读取

Shared References

共享参考资料

Load 
../shared-references/prior-art-databases.md
for search strategy templates and IPC/CPC classification guidance.
加载
../shared-references/prior-art-databases.md
文件，获取检索策略模板及IPC/CPC分类指导。

Workflow

工作流程

Step 1: Extract Search Concepts

步骤1：提取检索概念

From the invention description, identify:
  1. Core inventive concept: The primary technical contribution (1-2 sentences)
  2. Technical problem: What problem it solves
  3. Key technical features: 4-6 specific technical elements that define the invention
  4. IPC/CPC classes: Predict relevant classification codes (e.g., G06N, G06F)
从发明描述中识别以下内容：
  1. 核心发明概念：主要技术贡献（1-2句话）
  2. 技术问题：该发明解决的问题
  3. 关键技术特征：定义该发明的4-6个具体技术要素
  4. IPC/CPC分类：预测相关分类代码（例如：G06N、G06F）

Step 2: Patent Search

步骤2：专利检索

For EACH search concept, search via:
Google Patents (via WebSearch):
WebSearch: "site:patents.google.com [keywords]"
WebSearch: "[keywords] patent"
  • Try primary keywords + technical problem keywords
  • Search in English regardless of target jurisdiction
  • For CN inventions, also search Chinese keywords via WebSearch
Espacenet (via WebFetch):
  • WebFetch worldwide.espacenet.com/search results for key queries
  • Search by predicted IPC/CPC classes
Assignee/Inventor Search:
  • If known companies/universities work in this area, search their patent portfolios
  • WebSearch: "[assignee name] patent [technical area]"
For each potentially relevant patent found:
  • WebFetch the patent page to extract: title, abstract, representative claims, filing date, assignee, current status
  • Record IPC/CPC classification codes
针对每个检索概念，通过以下方式进行检索：
Google Patents（通过WebSearch）：
WebSearch: "site:patents.google.com [keywords]"
WebSearch: "[keywords] patent"
  • 尝试使用核心关键词+技术问题关键词
  • 无论目标管辖区域，均使用英文检索
  • 针对中国发明，同时通过WebSearch使用中文关键词检索
Espacenet（通过WebFetch）：
  • 通过WebFetch获取worldwide.espacenet.com上关键查询的检索结果
  • 根据预测的IPC/CPC分类进行检索
申请人/发明人检索：
  • 若已知有企业/高校从事该领域研究，检索其专利组合
  • WebSearch检索："[申请人名称] patent [技术领域]"
针对每一项找到的潜在相关专利：
  • 通过WebFetch获取专利页面，提取以下信息：标题、摘要、代表性权利要求、申请日期、申请人、当前状态
  • 记录IPC/CPC分类代码

Step 3: Academic Literature Search

步骤3：学术文献检索

Search the same concepts in academic databases:
  1. Google Scholar (via WebSearch): 
    WebSearch "[keywords] site:scholar.google.com"
  2. arXiv (via 
    /arxiv
    if available, or WebSearch): Search for preprints
  3. Semantic Scholar (via 
    /semantic-scholar
    if API key set, or WebSearch)
For each relevant paper found:
  • Extract title, authors, venue, year, key contribution
在学术数据库中检索相同概念：
  1. Google Scholar（通过WebSearch）：
    WebSearch "[keywords] site:scholar.google.com"
  2. arXiv（若可用则通过
    /arxiv
    ，否则通过WebSearch）：检索预印本
  3. Semantic Scholar（若已设置API密钥则通过
    /semantic-scholar
    ，否则通过WebSearch）
针对每一篇找到的相关论文：
  • 提取标题、作者、发表平台、年份、核心贡献

Step 4: Classification and Analysis

步骤4：分类与分析

For each reference found, assess:
  1. Relevance: How closely does it relate to the invention?
  2. Overlap Risk: Does it disclose the same or similar technical solution?
    • HIGH: Anticipates one or more claim elements
    • MEDIUM: Discloses a related but different approach
    • LOW: Same general field, different approach
  3. Relationship: Is it anticipating, relevant, or merely background?
Organize results by IPC/CPC classification to see the technical landscape.
针对每一项找到的参考文献，评估以下内容：
  1. 相关性：与该发明的关联程度如何？
  2. 重叠风险：是否披露了相同或相似的技术方案？
    • HIGH: 覆盖一项或多项权利要求要素
    • MEDIUM: 披露相关但不同的技术方案
    • LOW: 属于同一通用领域，但技术方案不同
  3. 关系类型：属于预判性文献、相关文献还是仅为背景资料？
按IPC/CPC分类整理结果，呈现技术全景。

Step 5: Freedom-to-Operate Assessment (Preliminary)

步骤5：自由实施评估（初步）

Based on the search results:
  • Identify patents with claims that potentially cover the invention
  • Note any expired patents (public domain)
  • Flag areas where claim scope overlap is significant
Disclaimer: This is a preliminary assessment only. A professional freedom-to-operate analysis by a patent attorney is recommended before filing.
根据检索结果：
  • 识别权利要求可能覆盖该发明的专利
  • 记录已过期专利（公有领域）
  • 标记权利要求范围重叠较大的领域
免责声明：本评估仅为初步评估。建议在提交专利申请前，由专利律师进行专业的自由实施分析。

Step 6: Output

步骤6：输出结果

Write 
patent/PRIOR_ART_REPORT.md
with:
markdown
undefined
撰写
patent/PRIOR_ART_REPORT.md
文件，内容如下：
markdown
undefined

Prior Art Search Report

Prior Art Search Report

Invention Summary

Invention Summary

[1-2 sentence description of the searched invention]
[1-2 sentence description of the searched invention]

Search Strategy

Search Strategy

  • Keywords used: [...]
  • IPC/CPC classes searched: [...]
  • Databases searched: Google Patents, Espacenet, Google Scholar, arXiv
  • Date range: [year] to present
  • Keywords used: [...]
  • IPC/CPC classes searched: [...]
  • Databases searched: Google Patents, Espacenet, Google Scholar, arXiv
  • Date range: [year] to present

Patent References Found

Patent References Found

#Patent No.TitleDateAssigneeIPC/CPCKey TeachingOverlap Risk
1CN... / US...[title][date][assignee][codes][2-3 sentences]HIGH/MEDIUM/LOW
#Patent No.TitleDateAssigneeIPC/CPCKey TeachingOverlap Risk
1CN... / US...[title][date][assignee][codes][2-3 sentences]HIGH/MEDIUM/LOW

Non-Patent Literature Found

Non-Patent Literature Found

#ReferenceTitleAuthors/VenueYearKey ContributionRelevance
1[DOI/link][title][authors][year][1-2 sentences]HIGH/MEDIUM/LOW
#ReferenceTitleAuthors/VenueYearKey ContributionRelevance
1[DOI/link][title][authors][year][1-2 sentences]HIGH/MEDIUM/LOW

Prior Art Landscape

Prior Art Landscape

[Organized by technical approach or IPC class, not just chronological]
[Organized by technical approach or IPC class, not just chronological]

Freedom-to-Operate Preliminary Assessment

Freedom-to-Operate Preliminary Assessment

[Which existing patents might block the invention? What is the risk level?]
[Which existing patents might block the invention? What is the risk level?]

Recommendations

Recommendations

  • Suggested claim scope adjustments based on prior art
  • Areas where novelty appears strongest
  • References to watch during prosecution
undefined
  • Suggested claim scope adjustments based on prior art
  • Areas where novelty appears strongest
  • References to watch during prosecution
undefined

Key Rules

核心规则

  • Never fabricate patent numbers or citations. Mark uncertain references with 
    [VERIFY]
    .
  • Search in English AND the target jurisdiction language (Chinese for CN).
  • Patent prior art includes everything published before the priority date, not just patents.
  • Academic papers are valid prior art for both novelty and inventive step.
  • Include expired patents -- they are public domain but still relevant for novelty.
  • 不得编造专利号或引用文献。对不确定的参考文献标记
    [VERIFY]
    。
  • 同时使用英文和目标管辖区域语言进行检索（中国区域使用中文）。
  • 专利现有技术包括优先权日之前公开的所有内容，而非仅专利。
  • 学术论文对于新颖性和创造性而言均为有效现有技术。
  • 需包含已过期专利——它们虽属于公有领域，但仍与新颖性相关。