SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillslinkfox-ruiguan-detection-patent-design

linkfox-ruiguan-detection-patent-design

Design & creation

View repository

Updated 10-16 00:00

About this skill

Ruiguan Design Patent Detection

This skill guides you on how to perform design patent infringement detection using the Ruiguan engine, helping e-commerce sellers and IP professionals identify potential design patent risks before listing products.

Core Concepts

Design patent detection compares a product image against a global design patent database using visual similarity algorithms. The system returns patents ranked by similarity score, along with TRO (Temporary Restraining Order) litigation history, helping users assess infringement risk.

Similarity score: A value between 0 and 1. Higher values indicate greater visual resemblance to the patent drawing. Patents with similarity >= 0.7 or those flagged with TRO enforcement history deserve special attention and should be reviewed carefully.

Radar analysis: When radar is enabled, each patent result includes a radarResult with a same flag (suspected infringement: true/false) and an exp field (explanation). This provides an AI-powered judgment beyond raw similarity.

LOC classification: The Locarno Classification (LOC) is an international system for categorizing industrial designs. You can optionally specify LOC codes to narrow the search scope, or leave it unset to let the model predict the appropriate categories automatically.

Parameters Guide

Parameter Required Default Description
imageUrl Yes - Product image URL to check against the patent database
queryMode Yes hybrid Search mode: physical (real product photo), line (line drawing), hybrid (combined)
topNumber Yes 100 Number of patent results to return (max 100)
regions No US Country/region codes, comma-separated for multiple (e.g., US,EU,CN)
productTitle No - Product title for supplementary context
productDescription No - Product description for supplementary context
patentStatus No 1 Patent validity: 1 (active), 0 (expired), 1,0 (both)
enableRadar No true Enable AI radar analysis for suspected infringement judgment
topLoc No - LOC level-1 codes to restrict search scope (e.g., 06,07). Omit to use auto-prediction
sourceLanguage No - Source language code for translation (e.g., zh-CN). Leave empty if text is already in English

Supported Regions

US (United States), EU (European Union), CN (China), JP (Japan), KR (South Korea), DE (Germany), GB (United Kingdom), FR (France), IT (Italy), AU (Australia), CA (Canada), BR (Brazil), MX (Mexico), IN (India), TH (Thailand), SE (Sweden), CH (Switzerland), IE (Ireland), IL (Israel), DK (Denmark), NZ (New Zealand), AT (Austria), BX (Bolivia), FI (Finland), WO (WIPO)

Default region is US. Use US when the user does not specify a region.

LOC Level-1 Categories

Code Category
01 Food
02 Clothing, haberdashery and sewing accessories
03 Travel goods, cases, parasols and personal items n.e.c.
04 Brushes
05 Textiles, artificial and natural sheet material
06 Furniture and household goods
07 Household items n.e.c.
08 Tools and hardware
09 Packages and containers for transport or handling of goods
10 Clocks, watches, measuring/checking/signaling instruments
11 Ornamental articles
12 Means of transport or hoisting
13 Equipment for production, distribution or transformation of electricity
14 Recording, telecommunication or data processing equipment
15 Machines n.e.c.
16 Photographic, cinematographic and optical apparatus
17 Musical instruments
18 Printing and office machinery
19 Stationery, office equipment, art materials, teaching materials
20 Sales and advertising equipment, signs
21 Games, toys, tents and sports goods
22 Arms, pyrotechnic articles, hunting/fishing/pest-killing articles
23 Fluid distribution, sanitary, heating, ventilation, air-conditioning equipment, solid fuel
24 Medical and laboratory equipment
25 Building units and construction elements
26 Lighting apparatus
27 Tobacco and smoking supplies
28 Pharmaceutical/cosmetic products, toilet articles and apparatus
29 Devices and equipment against fire, for accident prevention and rescue
30 Articles for care and handling of animals
31 Machines and apparatus for preparing food or drink n.e.c.
32 Graphic symbols, logos, surface patterns, ornamentation, interior/exterior arrangements
ALL All categories

How to Call

  • API Endpoint：POST /ruiguan/detectionPatentDesign(For full parameters/responses/error codes, see references/api.md）
  • Python Script：python scripts/ruiguan_detection_patent_design.py '<JSON 参数>' [--inline]
  • Cost Constraints: This tool consumes compute; by default, the same parameter combination in the same session is called only once, and the script has a 24h local cache. On failure/empty results, do not automatically switch keywords, paginate, or change the ZIP code to probe continuously; if you need to continue searching, first explain to the user that additional consumption will be incurred.

Output Strategy (Default Script Behavior)：

  • Alwayswrite the full response to <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-ruiguan-detection-patent-design-<timestamp>.json（<cwd> is the working directory when the script is executed, which in Claude Code is the current project directory;<session> is taken from the environment variable SESSION_ID, automatically aggregated according to the user's task;writing to /tmp is prohibited, and if the current directory is not writable, report an error)
  • Response body ≤ 8 KB: after writing to disk, print the full JSON to stdout
  • Response body > 8 KB: after writing to disk, stdout outputs only a summary (top-level fields, common counts such as total/costToken, the length of the largest list field + the first 3 samples)
  • Add --inline to force full printing to stdout (also written to disk)

Data Reading Suggestions: First look at the summary to determine whether it is sufficient; when specific fields are needed, prefer to use jqorConvertFrom-Json to extract on demand from the saved json file, avoiding bringing the entire JSON into context.

Resolve Authentication and Compute Issues

When the following abnormal situations occur, use references/onboarding.md to guide resolution:

Abnormal Situations

  • API Key not configured: The environment variable is not configured with LINKFOX_AGENT_API_KEY, and LINKFOXAGENT_API_KEY。
  • Response 401 or 402 status code
  • Response indicates insufficient compute or balance: The message contains "insufficient compute balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/recharge required/please recharge", or content with a similar meaning.

Local Image Upload

This tool requires a publicly accessible image URL. If the user provides a local image file path (e.g., C:\Users\...\photo.png, /home/.../image.jpg), you must upload it first to obtain a public URL.

Run the upload script:

python scripts/upload_image.py /path/to/local/image.png

The script will return a public URL (valid for 24 hours) that can be used as the image URL parameter.

Usage Examples

1. Basic patent check for a product image (US market)

{
  "imageUrl": "https://example.com/product.jpg",
  "queryMode": "hybrid",
  "topNumber": 50,
  "regions": "US"
}

2. Multi-region check with product context

{
  "imageUrl": "https://example.com/product.jpg",
  "queryMode": "physical",
  "topNumber": 100,
  "regions": "US,EU,CN",
  "productTitle": "Portable Wireless Charger Stand",
  "productDescription": "A foldable wireless charging stand for smartphones",
  "enableRadar": true
}

3. Narrowed search using LOC classification (furniture)

{
  "imageUrl": "https://example.com/chair.jpg",
  "queryMode": "hybrid",
  "topNumber": 80,
  "regions": "US,DE",
  "topLoc": "06",
  "patentStatus": "1"
}

4. Line drawing mode for sketch-based search

{
  "imageUrl": "https://example.com/sketch.png",
  "queryMode": "line",
  "topNumber": 50,
  "regions": "CN,JP,KR"
}

5. Check both active and expired patents

{
  "imageUrl": "https://example.com/product.jpg",
  "queryMode": "hybrid",
  "topNumber": 100,
  "regions": "US",
  "patentStatus": "1,0"
}

Display Rules

  1. High-risk patent highlighting: When generating summaries or reports, display ALL patents with similarity >= 0.7 or troCase = true in full detail. For each such patent, include: application number, patent title (Chinese), inventors, TRO enforcement history, the most-similar patent drawing, every image in the patent image list, patent abstract, patent specification, LOC info, radar analysis result, and specification text. This detailed presentation is critically important -- do NOT abbreviate or omit these fields.
  2. Disclaimer: Always append a friendly reminder at the end: "This detection result is generated by LinkfoxAgent. It is recommended to consult a professional IP attorney for legal advice."
  3. Similarity interpretation: Clearly explain that higher similarity scores indicate greater visual resemblance and higher infringement risk.
  4. Radar result display: When radarResult.same is true, prominently flag the patent as a suspected infringement match and display the exp explanation.
  5. TRO warning: Patents with troCase = true or troHolder = true should be highlighted with a warning, as they indicate the patent holder has a history of active enforcement via Temporary Restraining Orders.
  6. Image display: Show both patentImageUrl (the most similar patent drawing) and the full images list so users can visually compare their product against all patent drawings.
  7. Error handling: When a request fails, explain the issue and suggest corrective actions (e.g., check image URL accessibility, verify region codes).
  8. Present data faithfully: Show query results as-is without adding subjective legal conclusions beyond the tool's own analysis.

User Expression & Scenario Quick Reference

Applicable -- Design patent risk assessment:

User Says Scenario
"Check if this product infringes any design patents" Basic patent detection
"Patent risk check for this image" Image-based patent search
"Does this product have TRO risk" TRO enforcement history lookup
"Design patent search for US and EU" Multi-region patent detection
"Check appearance patent for this furniture" Category-specific patent search
"Is this product design safe to sell" Pre-listing patent clearance
"Find similar design patents" Similarity-based patent discovery
"Patent infringement analysis" Comprehensive patent risk report

Not applicable -- Needs beyond design patent detection:

  • Utility patent or invention patent searches
  • Trademark infringement checks
  • Copyright/DMCA issues
  • Legal case management or litigation strategy
  • Patent application or filing assistance
  • Product listing optimization or pricing

Boundary judgment: When users mention "patent check" or "IP risk", if the concern is about product appearance/design similarity to existing patents, this skill applies. If they are asking about utility patents, trademarks, copyrights, or need actual legal counsel, this skill does not apply.

Compute Consumption Rules

Radar detection enabled consumes 92 compute; not enabled consumes 61 compute.

Important: This skill consumes a large amount of compute. If the number of calls exceeds 5, you must useAskUserQuestion to perform secondary confirmation with the user, clearly informing the user of the compute already consumed and the estimated compute consumption if they continue to call, and let the user decide whether to continue.

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.