SuperAPI AI Directory

linkfox-zhihuiya-patent-cited

Data & analytics

View repository

Updated 10-16 00:00

About this skill

Zhihuiya Patent Citations Explorer

This skill guides you on how to query patent citation data from Zhihuiya (PatSnap), helping users understand the citation landscape of specific patents.

Core Concepts

Patent citation analysis reveals how influential a patent is within its technology domain. When Patent B references Patent A in its prior art section, Patent A is said to be "cited by" Patent B. A higher citation count generally indicates greater technological significance and broader industry influence.

Key metrics:

  • 3-year citations (citedBy3y): Number of times the patent was cited within 3 years of publication. Indicates early-stage impact.
  • 5-year citations (citedBy5y): Number of times the patent was cited within 5 years. Indicates medium-term influence.
  • Simple family citations (citedBySimpleFamily): Count of simple patent family members that cite the patent.
  • INPADOC family citations (citedByInpadocFamily): Count of INPADOC patent family members that cite the patent.
  • PatSnap family citations (citedByPatsnapFamily): Count of PatSnap-defined patent family members that cite the patent.

Parameter Guide

You must provide at least one of the following identifiers. If both are supplied, patent ID takes priority.

Parameter Description Example
patentId Zhihuiya internal patent ID. Multiple IDs separated by commas (max 100). abc123def456
patentNumber Publication / announcement number. Multiple numbers separated by commas (max 100). US10123456B2, CN112345678A

Important: At least one of patentId or patentNumber is required. When the user provides a publication number (e.g., "US10123456B2"), use patentNumber. When they provide internal IDs, use patentId.

Usage Examples

1. Single patent citation lookup by publication number Query: "How many citations does patent US10123456B2 have?"

{
  "patentNumber": "US10123456B2"
}

2. Multiple patents citation comparison Query: "Compare citations for CN112345678A and CN113456789B"

{
  "patentNumber": "CN112345678A,CN113456789B"
}

3. Lookup by patent ID Query: "Get citation data for patent ID abc123def456"

{
  "patentId": "abc123def456"
}

4. Batch query with multiple IDs Query: "Citation info for these patent IDs: id001, id002, id003"

{
  "patentId": "id001,id002,id003"
}

Display Rules

  1. Present data in tables: Show citation results in clear, structured tables. Include the publication number, 3-year citations, 5-year citations, and family citation counts.
  2. Highlight key metrics: When comparing multiple patents, highlight the one with the highest citation counts.
  3. Explain family types: If the user is unfamiliar with patent families, briefly explain the difference between Simple, INPADOC, and PatSnap family definitions.
  4. Citing patent details: If the response includes a citedByPatents array with details of citing patents, present them in a sub-table or expandable list.
  5. Error handling: When a query fails, explain the reason based on the response and suggest checking whether the patent number or ID is correct.
  6. No subjective advice: Present factual citation data without making judgments about patent value or investment decisions.

How to call

  • API endpoint:POST /zhihuiya/patentCited(for complete parameters/responses/error codes, see references/api.md)
  • Python script:python scripts/zhihuiya_cited_by.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 try different keywords, paginate, or change the postal 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 complete response to <cwd>/linkfox/<YYYY-MM-DD>/<session>/data/linkfox-zhihuiya-patent-cited-<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 complete 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 problem resolution:

Abnormal situations

  • API Key not configured: The environment variable is not configured 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.

User Expression & Scenario Quick Reference

Applicable -- Patent citation analysis scenarios:

User Says Scenario
"How many times has this patent been cited" Basic citation count
"Which patents cite this one" Citing patent list
"Patent influence analysis" Citation-based impact
"Compare citations between patents" Multi-patent comparison
"3-year / 5-year citation count" Time-windowed citation metrics
"Patent family citation data" Family-level citation analysis
"Forward citations for patent X" Synonym for cited-by lookup

Not applicable -- Needs beyond patent citation data:

  • Patent full-text search or semantic search
  • Patent legal status or prosecution history
  • Patent valuation or licensing recommendations
  • Backward citations (references made by a patent)

Compute consumption rules

Billed according to dynamic rules: compute consumed = 81 × number of returned data entries. Each entry is 1 patent citation result

Important: The service of this skill is dynamically calculated by a multiplier and may consume a large amount of compute at once. The user must be reminded, and the user decides 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.