bigquery-patent-search
关于
This skill enables developers to perform fast, cloud-based searches across over 76 million worldwide patents using Google BigQuery. It supports keyword searches across titles and abstracts, filtering by CPC classification codes, and retrieving detailed patent information. Use it for prior art searches, patent landscape research, or looking up specific patent details by publication number.
快速安装
Claude Code
推荐/plugin add https://github.com/RobThePCGuy/Claude-Patent-Creatorgit clone https://github.com/RobThePCGuy/Claude-Patent-Creator.git ~/.claude/skills/bigquery-patent-search在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
BigQuery Patent Search Skill
Fast, cloud-based patent searching across 76 million+ worldwide patents using Google BigQuery.
When to Use
Invoke this skill when users ask to:
- Search for prior art patents
- Find patents in a specific technology area
- Search by CPC classification code
- Look up patent details by publication number
- Conduct freedom-to-operate searches
- Research patent landscapes
What This Skill Does
Provides access to Google's public patent dataset:
-
Keyword Search across 76M+ patents:
- Full-text search of titles, abstracts, claims
- Filter by country (US, EP, JP, CN, etc.)
- Filter by filing/grant date ranges
- Fast cloud-based queries (< 5 seconds)
-
CPC Classification Search:
- Search by CPC code (e.g., "G06F16/", "H04L29/06")
- Browse patent classifications
- Find patents in specific technical domains
-
Patent Details Retrieval:
- Get full patent text by publication number
- Access title, abstract, claims, description
- View CPC codes, inventors, assignees
- See filing and grant dates
Required Setup
This skill requires Google Cloud authentication:
Prerequisites:
- Google Cloud Project (free to create)
- BigQuery API enabled (free for reasonable usage)
- Application Default Credentials configured
Setup Commands:
# Install Google Cloud SDK (if not installed)
# Visit: https://cloud.google.com/sdk/docs/install
# Authenticate
gcloud auth application-default login
# Set project (get ID from console.cloud.google.com)
export GOOGLE_CLOUD_PROJECT=your-project-id
Environment Variable:
Set in .env file: GOOGLE_CLOUD_PROJECT=your-project-id
How to Use
When this skill is invoked:
-
Initialize BigQuery searcher:
import sys sys.path.insert(0, os.path.join(os.environ.get('CLAUDE_PLUGIN_ROOT', '.'), 'python')) from python.bigquery_search import BigQueryPatentSearch searcher = BigQueryPatentSearch() -
Search by keywords:
results = searcher.search_patents( query="blockchain authentication", limit=20, country="US", # Optional: filter by country start_year=2020, # Optional: filter by year end_year=2024 ) -
Search by CPC code:
results = searcher.search_by_cpc( cpc_code="G06F16/", # CPC prefix limit=20, country="US" ) -
Get patent details:
patent = searcher.get_patent( patent_number="US10123456B2" # Publication number )
BigQuery Dataset
Uses patents-public-data.patents on Google BigQuery:
- 76M+ worldwide patents
- 12M+ US patents with full text
- Updated weekly
- Free to query (no billing for reasonable usage)
Search Result Format
Each result includes:
{
"publication_number": "US10123456B2",
"title": "Method and system for...",
"abstract": "A system for...",
"filing_date": "2019-01-15",
"grant_date": "2020-06-30",
"country": "US",
"cpc_codes": ["G06F16/245", "H04L29/06"],
"inventors": ["John Doe", "Jane Smith"],
"assignee": "Example Corp"
}
Full patent details also include:
claims: Full text of all claimsdescription: Complete description sectionpriority_date: Earliest priority datefamily_id: Patent family ID
Presentation Format
Present search results as:
PATENT SEARCH RESULTS
====================
Query: "blockchain authentication"
Found: 247 patents (showing top 20)
Date Range: 2020-2024
Country: US
[1] US10123456B2 - System for blockchain-based authentication
Assignee: Example Corp
Filed: 2019-01-15 | Granted: 2020-06-30
CPC: G06F16/245, H04L29/06
Abstract: A system for authenticating users using blockchain
technology with distributed ledger verification...
[2] US10234567B1 - Method of secure authentication using blockchain
...
---
Top 5 Most Relevant:
1. US10123456B2 (95% relevance)
2. US10234567B1 (92% relevance)
...
Advanced Search Techniques
-
Boolean Operators in queries:
- "blockchain AND authentication"
- "encryption OR cryptography"
- "(mobile OR wireless) AND security"
-
Phrase Search:
- "distributed ledger technology"
- "public key infrastructure"
-
CPC Code Hierarchies:
- "G06F" = Computing
- "G06F16/" = Information retrieval
- "G06F16/245" = Structured query language
Common CPC Codes
- G06F: Computing, calculating, counting
- H04L: Digital communication
- G06Q: Business methods
- H04W: Wireless communication
- G06N: Computer systems based on specific models
- G06T: Image processing
Error Handling
If BigQuery is not configured:
- Check if
google-cloud-bigqueryis installed - Verify authentication:
gcloud auth application-default login - Confirm project ID in environment:
GOOGLE_CLOUD_PROJECT - Test with:
python scripts/test_bigquery.py
Cost Considerations
BigQuery pricing:
- First 1TB/month: FREE
- After 1TB: $5 per TB queried
- Typical query: 10-50 MB per search
- ~20,000 searches free per month
Tools Available
- Bash: To run Python BigQuery searches
- Read: To load saved search results
- Write: To save patent search results
- Grep: To search through saved results
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
sglang
元SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。
evaluating-llms-harness
测试该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。
langchain
元LangChain是一个用于构建LLM应用程序的框架,支持智能体、链和RAG应用开发。它提供多模型提供商支持、500+工具集成、记忆管理和向量检索等核心功能。开发者可用它快速构建聊天机器人、问答系统和自主代理,适用于从原型验证到生产部署的全流程。
