Event Driven Accelerator Patents: Leaders, Trends & White Space 2026
A data-backed view of event-driven accelerator patents for neuromorphic computing: filing trends, leading assignees, technology composition and where claim space remains open through 2026.
Filing growth = 2021 (2 records) → 2024 (3); 2024 is the last year we treat as complete. Top-5 share = the 5 largest assignees ÷ all 94 records in scope (CR5), not the ranked leaders only.
What the event-driven accelerator patent record actually covers
Event-driven accelerator patents describe processing circuitry that acts only when a triggering event occurs, rather than on a fixed clock cycle — the architectural premise behind much of neuromorphic computing. The 94 records captured under this search span 2015 through the current data cut-off, with publication naturally lagging filing by roughly 18 months, so the most recent years understate real activity. The assignee base is broad: 67 companies appear in the ranking, and no single filer dominates the field outright.
The technology classes attached to these records are unusually dispersed for a single search string, running from digital data processing and AI computing through to engine control, gearing, and nuclear plant control — evidence that 'event-driven accelerator' claim language has migrated well beyond its neuromorphic-chip origin into automotive and industrial control filings.
Filing trend and technology composition
Two views of the same 94-record dataset: how filing activity has moved year over year, and which IPC subclasses the claims actually sit in.
Filing trend, 2017-2026
Filings rose from 1 record in 2017 to a peak of 13 in 2019, before settling into a smaller but growing base — 2 records in 2021 climbing to 3 in 2024, a +50% increase over that span. 2025 and 2026 figures will rise as publication catches up with filing.
Publication lags filing by roughly 18 months, so 2025 onwards are still filling in. Growth rates on this page therefore end at 2024; running them to the last bar would understate the field.
IPC subclass distribution
G06F (electric digital data processing) leads at 12.8% of the 94 records, followed by H04N (pictorial communication) at 10.6% and F02D (engine control) at 9.6%. Because records can carry multiple IPC codes, these shares sum to more than 100% and should be read against the 94-record total, not against each other.
Shares are the percentage of the 94 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Neuromorphic Computing: Event Driven Accelerator Patent Landscape with Eureka
This page is one run against one query. Ask Eureka your own question about neuromorphic computing: event driven accelerator patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaA representative event-driven accelerator patent
US10379907B2 — Event-driven system and method for selectively performing computations
An event-driven system, method and computer program product are provided to selectively generate events in response to receipt of data elements. The event-driven system includes processing circuitry configured to identify, in response to receipt of one or more data elements, an event that is impacted by the one or more data elements. The processing circuitry is also configured to determine whether at least a threshold number of consumers are currently listening for the event, and if so, to perform one or more computations based upon the one or more data elements.Filed by Change Healthcare Holdings; published 2019-08-13.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US5196775A | Switched reluctance motor position by resonant signal injection | 83 |
| 2 | US5040508A | Throttle valve actuator | 54 |
| 3 | US20150304875A1 | Method and Apparatus for Controlling Cell Aggregation | 31 |
| 4 | WO1995012203A1 | An energy amplifier for "clean" nuclear energy production driven by a particle beam accelerator | 21 |
| 5 | US8355517B1 | Hearing aid circuit with feedback transition adjustment | 20 |
| 6 | US20260050860A1 | System and method for comprehensive ESG performance management with multi-dimensional business value quantifi… | 18 |
| 7 | US20200311698A1 | Vehicle value as a token | 18 |
| 8 | US4412290A | Electronic control device for changing the speed ratios in an automatic transmission of an automotive vehicle | 17 |
| 9 | EP0500295A1 | Switched reluctance motor position by resonant signal injection | 15 |
| 10 | US2193304A | Change-speed mechanism and control | 15 |
Citation counts favour older records in a searched corpus and should be read as a signal of influence, not current relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Put your own technology through the same analysis
Eureka on the web
When you want the answer in the next five minutes.
The agent works the prompt against patents and technical literature, citing every source.
Run your analysis now →MCP server & REST API
When it has to run inside your own pipeline.
Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.
Browse MCP servers →What the concentration and citation data mean for filing strategy
The ranking, the concentration figures and the most-cited records point to a field that is active but not yet locked down by a small group of holders.
The top of the ranking is thin, not dominant
The leading assignee holds 11 records out of 94, and the top 5 combined reach 36.2% of all records in scope. That leaves a long tail across 67 ranked companies, with fifth place at just 4 records and tenth place at 3 — no single entity has cornered the core claim space.
Activity is rebuilding after the 2019 peak
Filings peaked at 13 in 2019, then fell back before recovering: 2021's 2 records grew to 3 by 2024, a +50% increase over that three-year span. Because publication lags filing by around 18 months, 2025-2026 counts will revise upward as more applications publish.
Claim language has spread well outside computing
G06F (digital data processing) leads at 12.8% of the 94 records, but F02D (engine control), F16H (gearing) and G21C/G21D (nuclear reactors and plants) each carry 7.4-9.6% shares. This spread suggests 'event-driven accelerator' phrasing is being reused in automotive and industrial control claims well outside neuromorphic chip design.
Filing is US-anchored with meaningful EPO and India volume
The United States receives the largest share of filings at 33 records, followed by the EPO at 19 and India at 11. The United Kingdom, WIPO/PCT and Canada each carry single-digit counts, indicating most applicants are not yet pursuing broad multi-jurisdiction coverage for this specific claim language.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to neuromorphic computing: event driven accelerator patent landscape, with the prior art for and against each one.
Where to take this analysis
The dataset points to a fragmented ownership structure and claim language that has drifted across domains — both are worth investigating further before filing or licensing decisions.
Map the white space by IPC branch
With classification spread across eight or more subclasses at single-digit percentages each, some combinations of event-driven triggering with specific application domains remain thinly claimed. A branch-by-branch review can surface which combinations are open.
Explore white space in EurekaTrack the long tail of single-filing entrants
67 ranked companies sit behind a leader with only 11 records, meaning most of the field consists of companies with one or two filings. Watching new entrants here can flag emerging competitive moves before they consolidate.
Set up assignee tracking in EurekaCommon questions about event-driven accelerator patents
The dataset used for this analysis contains 94 published records spanning 2015 through the current data cut-off in 2026. This count reflects a specific search built around event-driven accelerator and processing-circuit claim language, not the entire neuromorphic computing field, so a broader search string would return a different total. Because publication lags filing by roughly 18 months, the most recent years in this count will rise as more applications publish.
The ranking covers 67 companies, with the leading assignee holding 11 records and the top 5 combined accounting for 36.2% of all 94 records in scope. Beyond the top 5, holdings drop off quickly — fifth place holds 4 records and tenth place holds 3 — indicating a long tail of companies with only one or two filings rather than a market dominated by a handful of holders. Reviewing the full ranked list is more informative than focusing only on the leader.
Filing activity peaked at 13 records in 2019, dipped afterward, and then grew again: 2021's 2 records increased to 3 by 2024, a +50% rise over that three-year span. That is the most reliable recent trend, because 2025 and 2026 figures are still incomplete due to normal publication lag. Treat any apparent decline in the very latest years as an artefact of that lag rather than a real slowdown.
The leading IPC subclass is G06F (electric digital data processing) at 12.8% of the 94 records, followed by H04N (pictorial communication) at 10.6% and F02D (engine control) at 9.6%. Other classes present include G06N (AI-based computing), H04L (digital information transmission), F16H (gearing), and G21C/G21D (nuclear reactors and plants), each in the 7-9% range. Because a single record can carry multiple IPC codes, these percentages add up to more than 100% and should each be read against the full 94-record total.
US10379907B2, assigned to Change Healthcare Holdings and published in 2019, claims an event-driven system that generates computation only when a threshold number of consumers are actively listening for a triggered event. This is a specific gating mechanism — event detection plus a consumer-threshold check before computation runs — rather than a claim over event-driven processing broadly. Anyone building a similar system should review whether their triggering and consumer-threshold logic differs meaningfully from this specific claim structure before assuming freedom to operate.
Research Neuromorphic Computing: Event Driven Accelerator Patent Landscape in depth with Eureka
Go past this page: query the whole neuromorphic computing: event driven accelerator patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.
Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.
Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.
Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company’s registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.