Back to Details

patent-novelty-check

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Patent Novelty and Non-Obviousness Check

专利新颖性与非显而易见性检查

Assess patentability of: $ARGUMENTS
Adapted from 
/novelty-check
for patent legal standards. Research novelty is NOT the same as patent novelty.
评估以下内容的可专利性：$ARGUMENTS
本流程改编自
/novelty-check
，适配专利法律标准。学术研究新颖性与专利新颖性并非同一概念。

Constants

常量

  • REVIEWER_MODEL = gpt-5.4
    — Model used via Codex MCP for cross-model examiner verification
  • NOVELTY_STANDARD = patent
    — Always use legal patentability standard, not research contribution standard
  • REVIEWER_MODEL = gpt-5.4
    — 通过Codex MCP调用的模型，用于跨模型审查员验证
  • NOVELTY_STANDARD = patent
    — 始终采用法定可专利性标准，而非学术贡献标准

Inputs

输入项

  1. Invention description from 
    $ARGUMENTS
  2. patent/PRIOR_ART_REPORT.md
    (output of 
    /prior-art-search
    )
  3. patent/INVENTION_BRIEF.md
    if exists
  1. 来自
    $ARGUMENTS
    的发明描述
  2. patent/PRIOR_ART_REPORT.md
    （
    /prior-art-search
    的输出结果）
  3. 若存在则使用
    patent/INVENTION_BRIEF.md

Shared References

共享参考资料

Load 
../shared-references/patent-writing-principles.md
for novelty/non-obviousness standards. Load 
../shared-references/patent-format-us.md
for 102/103 analysis framework.
加载
../shared-references/patent-writing-principles.md
以获取新颖性/非显而易见性标准。 加载
../shared-references/patent-format-us.md
以获取102/103分析框架。

Workflow

工作流程

Step 1: Define Claim Elements

步骤1：界定权利要求要素

From the invention description, extract the key claim elements that would define the invention's scope:
  1. List the technical features that make the invention novel
  2. Identify which features are known from prior art vs. inventive
  3. Draft preliminary claim language for 2-3 independent claims (method + system)
从发明描述中提取定义发明保护范围的关键权利要求要素：
  1. 列出使发明具备新颖性的技术特征
  2. 区分哪些特征属于现有技术、哪些属于创造性特征
  3. 草拟2-3项独立权利要求的初步表述（方法类+系统类）

Step 2: Anticipation Analysis (Novelty)

步骤2：抵触申请分析（新颖性）

For each preliminary claim, test against EACH prior art reference in 
PRIOR_ART_REPORT.md
:
Single-reference test: Does any single reference disclose ALL claim elements?
Claim ElementRef 1Ref 2Ref 3...
Feature AYes/No + evidence
Feature BYes/No + evidence
Feature CYes/No + evidence
Feature DYes/No + evidence
Verdict per reference:
  • ANTICIPATED: One reference discloses every element → claim is not novel
  • NOT ANTICIPATED: At least one element missing from every single reference → claim is novel
针对每项初步权利要求，对照
PRIOR_ART_REPORT.md
中的每一份现有技术文献进行测试：
单文献测试：是否存在某一份文献披露了权利要求的全部要素？
权利要求要素文献1文献2文献3...
特征A是/否 + 证据
特征B是/否 + 证据
特征C是/否 + 证据
特征D是/否 + 证据
每份文献的结论:
  • 已抵触：某一份文献披露了所有要素 → 权利要求不具备新颖性
  • 未抵触：所有单篇文献均至少缺失一项要素 → 权利要求具备新颖性

Step 3: Obviousness Analysis (Inventive Step)

步骤3：显而易见性分析（创造性步骤）

If the invention is novel (passes Step 2), test for obviousness:
Two/three-reference combination test: Can 2-3 references be combined to render the claim obvious?
For each combination of the top references:
  1. Primary reference: Which reference is closest to the claimed invention?
  2. Secondary reference(s): Which reference(s) teach the missing element(s)?
  3. Motivation to combine: Would a POSITA have reason to combine these references?
    • Explicit suggestion in the references themselves?
    • Same field, same problem?
    • Common design incentive?
    • Known technique for improving similar devices?
Format as a matrix:
CombinationPrimarySecondaryMissing ElementsMotivation to CombineObvious?
Ref1 + Ref2Ref1Ref2Feature DSame field, similar problemYes/No
若发明通过步骤2具备新颖性，则进行显而易见性测试：
双/三文献组合测试：是否可通过组合2-3份文献使权利要求成为显而易见的？
针对排名靠前的文献组合：
  1. 主文献：哪份文献与所主张的发明最接近？
  2. 辅助文献：哪份文献披露了缺失的要素？
  3. 组合动机：本领域普通技术人员（POSITA）是否有理由组合这些文献？
    • 文献本身是否有明确的组合建议？
    • 是否属于同一领域、解决相同问题？
    • 是否存在通用设计激励？
    • 是否有用于改进类似设备的已知技术？
以矩阵形式呈现：
组合方式主文献辅助文献缺失要素组合动机是否显而易见？
文献1 + 文献2文献1文献2特征D同一领域，相似问题是/否

Step 4: Cross-Model Examiner Verification

步骤4：跨模型审查员验证

Call 
REVIEWER_MODEL
via 
mcp__codex__codex
with xhigh reasoning:
mcp__codex__codex:
  config: {"model_reasoning_effort": "xhigh"}
  prompt: |
    You are a senior patent examiner at the [USPTO/CNIPA/EPO].
    Examine the following invention for patentability.

    INVENTION: [invention description + preliminary claims]

    PRIOR ART: [prior art references with key teachings]

    Please analyze:
    1. Anticipation (novelty): Does any single reference anticipate any claim?
    2. Obviousness: Can any combination of references render claims obvious?
    3. Claim scope: Are the claims broad enough to be valuable?
    4. Recommended amendments if any claim is rejected.
    Be rigorous and cite specific references.
通过
mcp__codex__codex
调用
REVIEWER_MODEL
，启用超高推理强度：
mcp__codex__codex:
  config: {"model_reasoning_effort": "xhigh"}
  prompt: |
    You are a senior patent examiner at the [USPTO/CNIPA/EPO].
    Examine the following invention for patentability.

    INVENTION: [invention description + preliminary claims]

    PRIOR ART: [prior art references with key teachings]

    Please analyze:
    1. Anticipation (novelty): Does any single reference anticipate any claim?
    2. Obviousness: Can any combination of references render claims obvious?
    3. Claim scope: Are the claims broad enough to be valuable?
    4. Recommended amendments if any claim is rejected.
    Be rigorous and cite specific references.

Step 5: Jurisdiction-Specific Assessment

步骤5：针对特定司法管辖区的评估

For each target jurisdiction, provide a patentability assessment:
Under 35 USC 102/103 (US):
  • Novelty: PASS / FAIL (cite specific reference if fail)
  • Non-obviousness: PASS / FAIL (cite combination if fail)
Under Article 22 CN Patent Law (CN):
  • 新颖性 (Novelty): 通过 / 未通过
  • 创造性 (Inventive Step): 通过 / 未通过
Under Article 54/56 EPC (EP):
  • Novelty: PASS / FAIL
  • Inventive step: PASS / FAIL (problem-solution approach)
针对每个目标司法管辖区提供可专利性评估：
依据美国35 USC 102/103条款:
  • 新颖性：通过 / 不通过（若不通过请引用具体文献）
  • 非显而易见性：通过 / 不通过（若不通过请引用组合文献）
依据中国专利法第22条:
  • 新颖性 (Novelty): 通过 / 未通过
  • 创造性 (Inventive Step): 通过 / 未通过
依据欧洲专利公约（EPC）第54/56条:
  • 新颖性：通过 / 不通过
  • 创造性：通过 / 不通过（采用问题-解决方案法分析）

Step 6: Output

步骤6：输出结果

Write 
patent/NOVELTY_ASSESSMENT.md
:
markdown
undefined
生成
patent/NOVELTY_ASSESSMENT.md
文件：
markdown
undefined

Patentability Assessment

可专利性评估

Invention Summary

发明摘要

[description]
[描述内容]

Overall Assessment

总体评估

[PATENTABLE / PATENTABLE WITH AMENDMENTS / NOT PATENTABLE]
[具备可专利性 / 修改后具备可专利性 / 不具备可专利性]

Anticipation Analysis

抵触申请分析

[claim-by-claim matrix against each reference]
[针对每份文献的逐权利要求分析矩阵]

Obviousness Analysis

显而易见性分析

[combination analysis with motivation to combine]
[含组合动机的组合分析内容]

Cross-Model Examiner Review

跨模型审查员评审意见

[summary of GPT-5.4 examiner feedback]
[GPT-5.4审查员反馈摘要]

Recommended Claim Amendments

推荐的权利要求修改方案

[If claims need modification to overcome prior art, suggest specific amendments]
[若权利要求需修改以规避现有技术，请提出具体修改建议]

Risk Factors

风险因素

[What could cause rejection during actual prosecution?]
undefined
[实际审查过程中可能导致驳回的因素]
undefined

Key Rules

核心规则

  • Patent novelty is absolute: any public disclosure before the priority date counts as prior art, worldwide.
  • Research novelty ("has anyone published this?") is NOT the same as patent novelty ("does any single reference teach every claim element?").
  • Obviousness requires BOTH: (1) a combination of references AND (2) a motivation to combine them.
  • Never assume the invention is patentable just because no identical patent exists.
  • The assessment is advisory only -- actual prosecution may reveal different prior art.
  • If 
    mcp__codex__codex
    is not available, skip cross-model examiner review and note it in the output.
  • 专利新颖性是绝对的：优先权日之前的任何公开披露，无论地域，均视为现有技术。
  • 学术研究新颖性（“是否有人发表过该内容？”）与专利新颖性（“是否存在某份文献披露了权利要求的全部要素？”）并非同一概念。
  • 判定显而易见性需同时满足：(1) 存在可组合的文献 (2) 具备组合动机。
  • 绝不能因未检索到完全相同的专利，就默认发明具备可专利性。
  • 本评估仅为参考意见——实际审查过程中可能会发现其他现有技术。
  • 若无法调用
    mcp__codex__codex
    ，则跳过跨模型审查员评审环节，并在输出结果中注明。