Patent Signals (Inventor)

Overview

Inventor-level US patent signals — one record per named inventor on a newly granted US patent.
Same weekly USPTO grant source as Patent Signals (Company), delivered
under signal_type: patents, association: contact. Only the patentGrant subtype produces
contact records (velocity, challenges, and law-firm signals are company-only). Each record carries
both the enriched contact and the assignee company, so you can act on the person and their
employer together.

📘
High-confidence contacts only
Common inventor names make person resolution error-prone, so we resolve each inventor to a
LinkedIn profile and deliver only matches at confidence 9–10. Lower-confidence and
unresolved inventors are dropped, not delivered — the contact you receive is one we stand behind.
Patent signals never carry relevance, confidence, or sentiment fields.

Available Subtypes

Subtype (`signal_subtype`)	Description
`patentGrant`	A named inventor on a newly granted US patent

Schema

Top-Level Fields

Field	Type	Description
`signal_id`	string	Stable ID (upsert on this)
`batch_id`	string	Delivery batch
`signal_type`	string	Always `patents`
`signal_subtype`	string	`patentGrant`
`detected_at`	string (ISO 8601)	When the signal was produced
`association`	string	`contact`

Contact Object

Enriched from Autobound's contact truth data on the resolved LinkedIn URL. Unknown → null.

Field	Type	Description
`first_name`	string \| null	Enriched
`last_name`	string \| null	Enriched
`full_name`	string	Inventor name from the grant
`email`	string \| null	Enriched
`job_title`	string \| null	Enriched
`linkedin_url`	string	Resolved inventor profile (confidence 9–10)

Company Object

The assignee company — same shape as Patent Signals (Company)
(name, domain, linkedin_url, industries[], employee_count_low/high, description).

Data Object

Prose: summary, detail, invention_explanation, technologies_mentioned[], tags[].
Grant facts: patent_number, patent_title, patent_abstract, grant_date, cpc_primary,
tech_area, uspto_assignee, source_url, event_at, event_kind (grant_date).
Inventor placement: inventor_is_primary (bool), inventor_sequence (int),
co_inventor_count (int).

Example

{
  "signal_id": "9ac2…",
  "batch_id": "patents-2026-09-06",
  "signal_type": "patents",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-06T07:03:11Z",
  "association": "contact",
  "contact": {
    "first_name": "Dana",
    "last_name": "Ng",
    "full_name": "Dana Ng",
    "email": null,
    "job_title": "Principal Robotics Engineer",
    "linkedin_url": "https://www.linkedin.com/in/dana-ng"
  },
  "company": {
    "name": "Acme Robotics",
    "domain": "acmerobotics.com",
    "linkedin_url": "https://www.linkedin.com/company/acme-robotics",
    "industries": ["Robotics"],
    "employee_count_low": null,
    "employee_count_high": null,
    "description": "Autonomous warehouse robotics."
  },
  "data": {
    "summary": "Dana Ng is a named inventor on Acme Robotics' newly granted gripper-control patent.",
    "patent_number": "US11987654",
    "patent_title": "Adaptive gripper control for variable-geometry payloads",
    "grant_date": "2026-09-01",
    "tech_area": "Robotics & Automation",
    "inventor_is_primary": true,
    "inventor_sequence": 1,
    "co_inventor_count": 2,
    "event_at": "2026-09-01",
    "event_kind": "grant_date",
    "source_url": "https://patents.google.com/patent/US11987654"
  }
}

Coverage

Bucket: autobound-patents-contact (mirrored to your S3 delivery bucket where configured)
Refresh: weekly (USPTO grants publish Tuesdays)
Association: contact (inventor)
Subtypes: 1 (patentGrant); confidence 9–10 matches only