← 返回 Skills 市场
linkfox-ai

Zhihuiya Patent Image Search

作者 linkfox-ai · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
92
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install linkfox-zhihuiya-patent-image-search
功能描述
基于智慧芽的专利图片相似度搜索,支持通过图片URL检索外观设计专利和实用新型专利。当用户提到专利图片搜索、外观设计专利侵权检查、外观专利搜索、视觉专利查询、以图搜专利、专利相似度检测、专利图片匹配、洛迦诺分类搜索、检查产品设计是否侵犯已有专利、patent image search, design patent...
使用说明 (SKILL.md)

Zhihuiya Patent Image Search

This skill guides you on how to perform image-based patent similarity searches using the Zhihuiya patent database, helping users identify potentially similar design patents and utility model patents.

Core Concepts

Patent Image Search uses visual AI models to compare a given product or design image against a global patent image database. It returns a ranked list of similar patents, enabling users to evaluate infringement risks or conduct prior-art research.

Two patent types are supported:

Type Code Description
Design Patent D Protects the ornamental appearance of a product (default)
Utility Model Patent U Protects the functional shape/structure of a product

Search models vary by patent type:

Model ID Patent Type Strategy Recommendation
1 Design (D) Intelligent Association Recommended for design patents
2 Design (D) Search This Image Exact visual match
3 Utility Model (U) Match Shape Shape-only comparison
4 Utility Model (U) Match Shape/Pattern/Color Recommended for utility model patents

Scoring logic: A higher score value means greater visual similarity. When presenting results, sort by score in descending order (highest similarity first) so users can prioritize the most relevant patents for review.

Parameter Guide

Required Parameters

Parameter Description Example
url The image URL to search against https://example.com/product.jpg
patentType Patent type: D (design) or U (utility model) D
model Search model ID (see table above) 1

Common Optional Parameters

Parameter Description Default
country Patent authority country codes, comma-separated (e.g., CN,US,JP) All countries
loc Locarno classification codes, connectable with AND/OR/NOT None
legalStatus Legal status codes, comma-separated None
simpleLegalStatus Simple legal status: 0 (expired), 1 (active), 2 (pending) None
assignees Applicant / patent holder name None
applyStartTime Application start date (yyyyMMdd) None
applyEndTime Application end date (yyyyMMdd) None
publicStartTime Publication start date (yyyyMMdd) None
publicEndTime Publication end date (yyyyMMdd) None
limit Number of results to return (1-100) 10
offset Pagination offset (0-1000) 0
field Sort field: SCORE, APD, PBD, ISD SCORE
order Sort order: desc or asc (for APD/PBD/ISD) desc
lang Title language preference: original, cn, en original
preFilter Enable country/LOC pre-filtering: 1 (on) / 0 (off) 1
stemming Enable stemming: 1 (on) / 0 (off) 0
mainField Search within title, abstract, claims, description, publication number, application number, applicant, inventor, IPC/UPC/LOC None
includeMachineTranslation Include machine-translated data in search None
scoreExpansion Enable score expansion None
isHttps Return HTTPS image URLs: 1 (yes) / 0 (no) 0
returnImgId Return image IDs in results false

Commonly Used Country Codes

Code Country/Region
CN China
US United States
JP Japan
KR South Korea
EP European Patent Office
WO WIPO
DE Germany
GB United Kingdom
FR France
AU Australia

API Usage

This tool calls the LinkFox tool gateway API. See references/api.md for calling conventions, request parameters, and response structure. You can also execute scripts/zhihuiya_patent_image_search.py directly to run queries.

Usage Examples

1. Basic design patent search (recommended starting point) Search for design patents similar to a product image across all countries:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "limit": 20
}

2. Design patent search limited to specific countries Search only in China and the United States:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "country": "CN,US",
  "limit": 20
}

3. Utility model patent search Check utility model patents with shape/pattern/color matching:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "U",
  "model": 4,
  "country": "CN",
  "limit": 20
}

4. Search with Locarno classification filter Narrow results to a specific product category (e.g., LOC 07-01 for tableware):

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "loc": "07-01",
  "preFilter": 1,
  "limit": 20
}

5. Search only active patents within a date range Find active design patents filed after 2020:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "simpleLegalStatus": "1",
  "applyStartTime": "20200101",
  "limit": 30
}

6. Search by specific assignee Find patents held by a particular company:

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "assignees": "Apple Inc.",
  "limit": 20
}

7. Get results with Chinese-translated titles

{
  "url": "https://example.com/my-product.jpg",
  "patentType": "D",
  "model": 1,
  "lang": "cn",
  "limit": 20
}

Display Rules

  1. Sort by score: Always sort results by score in descending order (highest similarity first) to help users quickly identify the most relevant infringement risks.

  2. Show complete details: When summarizing results or generating reports, include ALL of the following for each patent -- do NOT omit or abbreviate:

    • Application number (apno)
    • Patent title in Chinese (use lang: cn or provide translation)
    • Inventor (inventor)
    • Patent drawing (the matched url image)
    • Every patent image in the image list
    • Patent abstract
    • Patent description
    • LOC classification information (loc)
    • Radar result (radarResult) if available
    • Patent specification
  3. Legal disclaimer: Always append a friendly reminder at the end of results:

    This search result was generated by LinkfoxAgent. It is recommended to consult a professional patent attorney for legal advice.

  4. Score explanation: Remind users that the score represents visual similarity -- a higher score indicates a closer match, but does not constitute a legal determination of infringement.

  5. Pagination guidance: When the total count exceeds the returned results, inform users about the total number of matching patents and guide them to use offset and limit for additional pages.

  6. Error handling: When a query fails, explain the reason and suggest adjustments (e.g., verify the image URL is publicly accessible, check country codes, adjust date formats).

User Expression & Scenario Quick Reference

Applicable -- Image-based patent similarity searches:

User Says Scenario
"Check if my product design infringes any patents" Design patent infringement check
"Search for similar design patents" Design patent similarity search
"Find patents that look like this image" Visual patent lookup
"Are there any patents similar to my product appearance" Appearance risk assessment
"Utility model patent search by image" Utility model search
"Check patent risks for this product in China and US" Multi-country patent check
"Find active design patents in this category" Filtered patent search
"Who holds patents similar to this design" Competitor patent discovery

Not applicable -- Needs beyond patent image search:

  • Text-based patent search (keyword/abstract/claim search)
  • Patent legal status monitoring or annuity management
  • Patent valuation or licensing negotiation
  • Freedom-to-operate (FTO) legal opinions
  • Patent family or citation analysis

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

  1. The functionality or purpose described in this skill does not match actual behavior
  2. The skill's results do not match the user's intent
  3. The user expresses dissatisfaction or praise about this skill
  4. Anything you believe could be improved

Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.


For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.

安全使用建议
This skill's code implements the advertised patent image search and calls LinkFox/Zhihuiya endpoints, but the package metadata fails to declare that it requires an API key (LINKFOXAGENT_API_KEY). Before installing: 1) Treat the skill as a third‑party networked tool — any image URL you submit will be sent to https://tool-gateway.linkfox.com and may expose design images to that provider. Do NOT submit proprietary/confidential images unless you trust the service and its data handling. 2) Confirm the identity and trustworthiness of the skill owner (source/homepage is missing). 3) Only provide an API key with least privilege and rotate/remove it if you stop using the skill. 4) Ask the publisher to update the skill metadata to explicitly list LINKFOXAGENT_API_KEY (and to provide a homepage/privacy/terms link) so the credential requirement is transparent. If you need help vetting the remote endpoints or the API key provisioning process, obtain those details before enabling the skill.
功能分析
Type: OpenClaw Skill Name: linkfox-zhihuiya-patent-image-search Version: 1.0.0 The skill bundle provides a legitimate interface for performing patent image similarity searches via the Zhihuiya (PatSnap) database. The Python script (zhihuiya_patent_image_search.py) uses standard libraries to interact with a documented API endpoint and does not exhibit signs of data exfiltration, command injection, or malicious persistence.
能力评估
Purpose & Capability
The skill's code and references clearly call the LinkFox/Zhihuiya tool gateway and require an API key (environment variable LINKFOXAGENT_API_KEY) to authenticate requests. However, the registry metadata declares no required environment variables or primary credential. That omission is an incoherence: a networked API-backed patent-image search legitimately requires an API key, so the metadata should declare it. Also the skill source/homepage is unknown which reduces traceability.
Instruction Scope
SKILL.md and references/api.md instruct the agent to call the external endpoint https://tool-gateway.linkfox.com/zhihuiya/patentImageSearch and reference a separate feedback endpoint. The runtime instructions and included script are scoped to performing searches and formatting results; they do not instruct the agent to read unrelated local files. However, they do rely on sending the user-provided image URL (and thereby image content accessible via that URL) to an external service — this is expected for the stated purpose but is important privacy/ data-flow behavior to highlight.
Install Mechanism
There is no install spec (instruction-only skill) and no downloads or package installs. A Python script is included that can be run directly. No third-party installers or unusual network downloads are present in the manifest.
Credentials
The code requires a single secret-like environment variable LINKFOXAGENT_API_KEY for Authorization, but the skill metadata did not declare this requirement or a primary credential. That mismatch is concerning because users may not be aware a secret is needed. Additionally, using the skill transmits image URLs (and likely the image content fetched by the service) and search parameters to external LinkFox endpoints; for proprietary images or confidential designs this is a data-exfiltration/privacy risk. No other unrelated credentials are requested.
Persistence & Privilege
The skill does not request permanent 'always' inclusion, does not modify other skills or system-wide settings, and has no install-time persistence mechanism. Autonomous invocation is allowed by default but is not combined here with broad privileges or undisclosed credentials.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install linkfox-zhihuiya-patent-image-search
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /linkfox-zhihuiya-patent-image-search 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug linkfox-zhihuiya-patent-image-search
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Zhihuiya Patent Image Search 是什么?

基于智慧芽的专利图片相似度搜索,支持通过图片URL检索外观设计专利和实用新型专利。当用户提到专利图片搜索、外观设计专利侵权检查、外观专利搜索、视觉专利查询、以图搜专利、专利相似度检测、专利图片匹配、洛迦诺分类搜索、检查产品设计是否侵犯已有专利、patent image search, design patent... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 92 次。

如何安装 Zhihuiya Patent Image Search?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install linkfox-zhihuiya-patent-image-search」即可一键安装,无需额外配置。

Zhihuiya Patent Image Search 是免费的吗?

是的,Zhihuiya Patent Image Search 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Zhihuiya Patent Image Search 支持哪些平台?

Zhihuiya Patent Image Search 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Zhihuiya Patent Image Search?

由 linkfox-ai(@linkfox-ai)开发并维护,当前版本 v1.0.0。

💬 留言讨论