メニュー
Assists R&D teams with patent technical disclosure drafting and patent/novelty search analysis; use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/ThomasMoreAI/legal-skills-open --skill patent-assistantコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Use when retrieving arbitration institutional rules (ICC, LCIA, SCC, SIAC, HKIAC, VIAC, МКАС/МАК при ТПП України, UNCITRAL) — fetching current version, verifying redaction applicable to the date of arbitration agreement, constructing URLs for official rule texts
Use when choosing the Polish legal regime for letters, requests, applications, complaints, petitions, public-information requests, KPA filings, PPSA complaints, RODO access requests, registry extracts, court-file access, tax/ZUS/cudzoziemcy/USC procedures, or professional lawyer letters. Prevents mixing UDIP, KPA, PPSA, RODO, registry, special-procedure, and advocate/radca letter regimes.
Use when preparing applications for recognition and enforcement of foreign arbitral awards in Poland, applications for setting aside arbitral awards under KPC art. 1205–1211, or opposing such applications — mapping Article V of the 1958 New York Convention to art. 1214–1215 of the Polish KPC, identifying grounds for refusal, structuring public policy arguments
SOC 職業分類に基づく
SKILL.md を表示中
| name | patent-assistant |
| title | Patent Technical Disclosure Document |
| description | Assists R&D teams with patent technical disclosure drafting and patent/novelty search analysis; use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty. |
| author | aipoch |
| author_url | https://github.com/aipoch/medical-research-skills/tree/main/scientific-skills/Academic Writing/patent-assistant |
| license | MIT |
| version | 0.1.0 |
| execution_mode | open |
| jurisdiction | general |
| practice | ip |
| language | en |
Use this skill in the following scenarios:
>= 3.9requests >= 2.28beautifulsoup4 >= 4.11lxml >= 4.9Note: Exact runtime dependencies may vary depending on how
scripts/patent_search.pyis implemented in your repository.
User prompt
Help me write a patent disclosure document:
I designed a system that uses an on-device model to detect abnormal vibration patterns in industrial motors.
It compresses sensor streams, runs anomaly detection locally, and only uploads event snippets to reduce bandwidth.
Expected output (Markdown disclosure template)
# Patent Technical Disclosure Document
## I. Title of Invention
A method and system for on-device vibration anomaly detection and event-based uploading for industrial motors
## II. Technical Field
The present invention relates to the technical field of industrial equipment monitoring, and specifically relates to on-device vibration signal processing and anomaly detection.
## III. Background Art
### 3.1 Description of Existing Technology
Existing solutions typically stream high-frequency vibration data to a cloud platform for centralized analysis, or use threshold-based alarms on edge devices.
### 3.2 Defects of Existing Technology
The existing technology has the following problems:
1. High bandwidth and storage costs due to continuous raw data uploading.
2. High latency for cloud-based detection, which may delay fault response.
3. Threshold-based edge alarms have poor adaptability across different motor types and operating conditions.
## IV. Summary of Invention
### 4.1 Technical Problem to be Solved
The technical problem to be solved by the present invention is reducing bandwidth and latency while maintaining reliable anomaly detection for motor vibration monitoring.
### 4.2 Technical Solution
To solve the above technical problem, the present invention adopts the following technical solution:
- Collect vibration sensor data from an industrial motor using an edge device.
- Perform stream compression/feature extraction on the edge device to obtain compact representations.
- Execute an on-device anomaly detection model to identify abnormal vibration patterns.
- When an anomaly is detected, generate an event snippet containing a time window of raw/feature data and metadata (timestamp, motor ID, operating state).
- Upload only the event snippet (and optionally periodic summaries) to a remote server for storage, visualization, and further diagnosis.
### 4.3 Beneficial Effects
By adopting the technical solution of the present invention, the following beneficial effects are achieved:
1. Significantly reduced network bandwidth usage by avoiding continuous raw data uploads.
2. Faster anomaly response due to local inference and event-triggered reporting.
3. Improved detection robustness compared with fixed thresholds by using a learned model.
## V. Detailed Description
### 5.1 Embodiment 1
An edge device connected to an accelerometer samples vibration at a preset rate, computes spectral features, and runs an anomaly model. Upon detection, it uploads a 5-second window around the event plus operating metadata.
### 5.2 Embodiment 2 (Optional)
The anomaly model is periodically updated using federated or scheduled offline training, while inference remains on-device.
## VI. Description of Drawings
Suggestions for drawing the following figures:
- Figure 1: System architecture (sensor, edge device, network, server).
- Figure 2: On-device processing pipeline (sampling → compression/features → anomaly detection → event packaging → upload).
## VII. Keywords
vibration monitoring; anomaly detection; edge computing; event-based upload; industrial motor; signal compression
Basic search (default platform: Google Patents)
python scripts/patent_search.py "vibration anomaly detection edge event-based upload" --limit 20
Parallel search across all supported platforms (recommended)
python scripts/patent_search.py "vibration anomaly detection edge event-based upload" -s all -p
Search specific platforms
python scripts/patent_search.py "vibration anomaly detection edge event-based upload" -s google,cnipa,innojoy
Search with similarity analysis
python scripts/patent_search.py "vibration anomaly detection edge event-based upload" -s all -p -a
Expected search output (conceptual)
Information collection (ask if missing)
Document synthesis
Optimization suggestions
Keyword extraction
Search execution
scripts/patent_search.py to query one or multiple platforms.google, lens, innojoy, baidu, espacenet, cnipa, allResult analysis
| Field | IPC Classification |
|---|---|
| Computer Software | G06F |
| Artificial Intelligence | G06N |
| Image Processing | G06T |
| Communication | H04L, H04W |
| Database / Information Retrieval | G06F 16/ |
| Internet of Things | H04L 67/ |
| Blockchain / Cryptographic protocols in networks | H04L 9/, G06Q |