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 →Filing growth compares 2021 (6 records) with 2024 (5) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 88 records in scope (CR5), not by the ranked leaders only.
Inline process control and virtual metrology sit at the intersection of semiconductor fab control loops and statistical modelling: run-to-run adjustment, chamber fingerprinting, drift and excursion detection, and the sampling-plan logic that decides which wafers actually get measured. The scope tracked here spans 88 published records filed between 2015 and mid-2026, drawn from a search string that pairs advanced-process-control and virtual-metrology terms with the specific mechanics — sensor data fusion, drift detection, sampling optimisation, model retraining, chamber fingerprinting and excursion detection — that separate a working system from a general control-theory claim.
Because publication lags filing by roughly 18 months, the most recent one or two years in any trend understate real filing activity; treat 2025 and 2026 as still filling in rather than as a genuine slowdown.
Pick a task. Every answer cites the patents behind it.
Two views of the same 88-record dataset: how filing volume moved year over year, and which IPC subclasses carry the claims.
Annual filings rose from 4 records in 2017 to a peak of 22 in 2023, then eased to 5 by 2024 — a -17% move across the 2021-to-2024 window that is the last span the data can call complete. Readings for 2025 and 2026 are still incomplete due to publication lag and should not be read as a further decline.
G05B (control and regulating systems) appears in 40.9% of the 88 records, ahead of H10P at 26.1%, H01L semiconductor devices at 23.9%, G06N AI-based computing at 22.7% and G03F photolithography at 21.6%. Because records can carry multiple IPC classes, these shares add up to more than 100% of the record total — the pattern shows where claim density sits, not a partition of the field.
Shares are the percentage of the 88 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
This page is one run against one query. Ask Eureka your own question about inline process control and virtual metrology and every answer comes back with the patent numbers behind it.
Try EurekaFiled by Honeywell International, this application addresses advanced process control by comparing a current operating condition digital signature against historical signatures for the same asset, then adjusting real-time settings based on the insights that comparison produces. It targets the recommendation layer that sits above raw sensor fusion — deciding what to do with a detected drift rather than just detecting it.Published 2023-12-21


| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US20080286885A1 | Methods and systems for creating or performing a dynamic sampling scheme for a process during which measureme… | 91 |
| 2 | US20210236020A1 | Wearable device to monitor musculoskeletal loading, estimate tissue microdamage and provide injury risk biofe… | 83 |
| 3 | US20120208301A1 | Methods and Systems for Creating or Performing a Dynamic Sampling Scheme for a Process During Which Measureme… | 73 |
| 4 | US8175831B2 | Methods and systems for creating or performing a dynamic sampling scheme for a process during which measureme… | 46 |
| 5 | EP3312693A1 | Methods & apparatus for controlling an industrial process | 36 |
| 6 | US20210397172A1 | Method of manufacturing devices | 29 |
| 7 | US6905895B1 | Predicting process excursions based upon tool state variables | 26 |
| 8 | US20230259112A1 | Diagnostic tool to tool matching and comparative drill-down analysis methods for manufacturing equipment | 20 |
| 9 | WO2018072962A1 | Methods & apparatus for controlling an industrial process | 19 |
| 10 | US20200050180A1 | Methods & apparatus for controlling an industrial process | 18 |
Citation counts favour older filings in any searched corpus — read them as a signal of influence on later work, not as a measure of current relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
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 →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 →Three read-throughs from the concentration, trend and technology-class figures above.
With the top five assignees holding 77.3% of all 88 records in scope and the leader alone attached to 32, this is not a fragmented field where a new filer can stake a broad claim unopposed. The tenth-ranked assignee holds only 2 records, meaning the drop-off from leader to long tail is steep rather than gradual.
Filing rose unevenly from 4 records in 2017 to a peak of 22 in 2023, then declined to 5 by 2024 -- a -17% move across that three-year span. The 2025-2026 counts are still incomplete because of publication lag and should not be read as evidence the field is shrinking further.
G05B control and regulating systems claims appear in 40.9% of records, ahead of the AI-modelling class G06N at 22.7% and material-analysis class G01N at just 10.2%. That gap suggests the control-loop mechanics are more heavily claimed than the underlying measurement or AI-inference methods feeding them.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to inline process control and virtual metrology, with the prior art for and against each one.
The ranking below covers all 39 companies the data endpoint returns for this search — not a top-50 or top-100 cut. It is heavily front-loaded: the leader holds 32 records against 6 at fifth place and 2 at tenth.
The leading assignee's 32 records are more than five times the count at fifth place, a gap wide enough that its published applications are a reasonable proxy for where the field's boundary claims currently sit.
Beyond the top ten combined 90.9% of all 88 records, the remaining assignees in the 39-company ranking hold only a handful of filings each, consistent with universities, single-inventor filers and smaller toolmakers testing narrow claims rather than building portfolios.
Only 10 co-assignee pairs appear across the dataset, and the strongest recurring pairs involve the same lead entity working with named individual inventors rather than a network of corporate partners — this field is largely filed solo.
| Assignee | Recent year | YoY |
|---|---|---|
| Applied Materials, Inc. | 0 | -100% |
| ASML Netherlands B.V. | 0 | — |
| Vanderbilt University | 0 | — |
| KLA Corporation | 0 | — |
| Honeywell International Inc. | 0 | — |
| Ludovico Technologies | 0 | — |
| Nova Measuring Instruments Ltd. | 0 | — |
| United Microelectronics Corporation | 0 | — |
The dataset points to a concentrated field with a narrow but active set of under-claimed branches. Two practical next steps follow from that.
With one assignee holding 32 of 88 records, checking any planned filing against that portfolio first avoids the most likely collision before drafting goes further.
Run a freedom-to-operate check in Eureka →Sampling-plan optimisation and cross-tool fingerprint transfer show thinner coverage now; watching these branches over the next few publication cycles shows whether they stay open.
Set up monitoring in Eureka →One assignee leads the ranked field with 32 of the 88 records in scope, more than five times the count held by the fifth-placed company at 6. The top five assignees combined account for 77.3% of all 88 records, so filing activity is concentrated rather than spread evenly across the 39 companies in the ranking. Anyone assessing this space should treat the leader's published applications as the closest thing to a boundary map of current claims.
Filing peaked at 22 records in 2023, then declined to 5 by 2024, a -17% move measured from 2021 to 2024 — the last window the dataset can treat as complete. Counts for 2025 and 2026 look lower still, but that reflects the roughly 18-month lag between filing and publication rather than a genuine drop-off. Judging the field's current trajectory on the two most recent years alone would be misleading.
Control and regulating systems, IPC class G05B, appear in 40.9% of the 88 records in scope, ahead of H10P at 26.1%, semiconductor devices (H01L) at 23.9%, AI-based computing methods (G06N) at 22.7% and photolithography (G03F) at 21.6%. Because a single record can carry several IPC classes, these percentages add up to more than 100% of the record total — they describe where claim density concentrates, not a clean split of the field. Material-analysis and testing claims (G01N) are comparatively thin at 10.2%.
The dataset points to sub-areas that sit adjacent to the dense G05B and H01L clusters but show thinner direct coverage, including cross-tool chamber fingerprint transfer, sampling-plan optimisation under model drift, and instance-based retraining triggers. These are not guarantees of a clear field — they are areas where the concentration seen elsewhere in the ranking is less pronounced. A proper freedom-to-operate search against the leading assignees' specific claims is still the necessary next step before drafting.
US20230408989A1, filed by Honeywell International and published 2023-12-21, claims a recommendation system for advanced process control limits that compares a current operating condition digital signature against historical signatures for the same asset, then adjusts real-time settings based on the resulting insights. It sits at the recommendation and adjustment layer above raw sensor fusion or drift detection — it assumes an event indicator already exists and focuses on what to do about it. Anyone building an instance-based or signature-comparison approach to process-limit recommendation should read its claim set closely before proceeding.
Go past this page: query the whole inline process control and virtual metrology 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.
Help us improve
Something wrong, out of date, or missing on this page? Tell us and it goes straight to the team that maintains it.
This page