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 →4,675 families and 10,625 records on SVM kernel optimization, with filing trends, filer concentration and IPC splits.
10,625 published records collapse into 4,675 simple (DOCDB) families; the difference is the same invention filed in more than one country. INTERNATIONAL BUSINESS MACHINE CORPORATION is named on 62 of the 4,675 patent families in scope. One patent family can name several filers, so these figures are not slices of a divided whole and do not add up. In force = 3,978 of 10,625 records still granted and maintained at the data cut-off; the rest are pending, withdrawn, refused or lapsed.
This landscape reports every record matched by TAC:("support vector machine") AND (kernel OR "kernel function" OR "kernel selection"), with no date limit applied in the search string itself. That returns 10,625 published records, which de-duplicate to 4,675 simple patent families once filings for the same invention across different countries are collapsed. The filing-trend chart on this page shows a recent window only and should not be read as the full span of the dataset.
Of the 10,625 records, 3,978 (37%) were granted and still in force at retrieval; the remainder covers everything else a record can be, pending, withdrawn, refused, lapsed or simply not determinable from the data available, and that breakdown is not split out further here.
Counted over all 10,625 published records, including filings from before 2007; the filing-trend chart below covers only the 9,722 records from 2007 onward, so the two charts are not the same set of documents. Ordered by volume only, not by importance or claim strength. Counted in simple (DOCDB) patent families, so one invention filed in several countries counts once. Names come from Patsnap's standardised assignee field as recorded on each document; subsidiaries and group companies are not merged. The icon before each name is read from the name itself (words such as University, Institute or Ltd); the data carries no organisation-type field, so treat it as a reading aid rather than a classification. Filings held by named individuals rather than organisations are removed where they can be identified (1 here); that identification is not exhaustive, so an individually held filing can still appear below. Either way those filings stay inside the totals above. This table shows the top 30 of the 99 filers returned for this search; the data endpoint returns at most 100 entities, so even that 99 is not the complete set of filers. A single family can name more than one filer, so these counts overlap and do not add up to the total.
The two views below use different units, published records by earliest filing year for the trend, and simple patent families for the technology split, so read each figure against the unit named with it.
Records filed from 2007 (210) run through 2026 (221), with a peak so far of 829 in 2019. Records filed from 2018 to 2021 rose from 701 to 799, a 14% increase; years from 2022 onward are still filling in as later-filed applications continue to publish, so no decline should be read into that final stretch.
Counted in published records by earliest filing year, not de-duplicated into families. A filing is counted in the year it was filed, but it only becomes visible after it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. 2022 onwards are therefore still filling in and are shaded; no growth figure on this page uses them. Because this series counts documents rather than inventions, a rise can mean more inventions or the same inventions filed in more countries; this dataset cannot separate the two. This chart covers 2007-2026 (9,722 records); the 10,625 total quoted above includes earlier filings outside the window.
G06N (computing based on AI models) appears on 35.8% of the 4,675 families, G06F (electric digital data processing) on 33.9%, and G06K (data recognition & presentation) on 26.9%. A family can carry more than one of these classes, so the three shares add up to more than 100%.
Shares are the percentage of the 4,675 patent families in scope. One patent family 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 support vector machine kernel function optimization patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaA feature selection technique for support vector machine (SVM) classification makes use of a fast Newton method that suppresses input space features for a linear programming formulation of a linear SVM classifier, or suppresses kernel functions for a linear programming formulation of a nonlinear SVM classifier. The technique may be implemented with a linear equation solver, without the need for specialized linear programming packages, and is described as applicable to linear or nonlinear SVM classifiers.Shown because it is the first record returned under the database's default ordering for this search, not because it is the most cited or most recent filing in scope.


Selected as the first record the search returns under the database default order, then shown in full. It is not ranked by citations, claim breadth or commercial importance, and it is not a judgement about which filing in this space matters most.
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 figures from this dataset are worth holding in mind before drilling into the full tables.
International Business Machine Corporation is named on 62 of the 4,675 simple patent families in scope (1.3%), the largest single row in a list of 100 listed filers. Filer rows are not rolled up to corporate group and one family can name several filers, so rows cannot be added together to produce a combined share.
Among the 99 listed filers (organisations; individual-named filings are excluded from this list where they can be identified but remain in the totals), none holds 2 or fewer families. The listed rows together sum to 30% of the 4,675 families, which reflects overlap between rows rather than a coverage figure.
G06N (computing based on AI models) appears on 1,674 of 4,675 families (35.8%), ahead of G06F at 33.9% and G06K at 26.9%. Because families can carry multiple IPC subclasses, these shares are not mutually exclusive and do not sum to 100%.
At the 2026-10-27 retrieval date, 3,978 of the 10,625 published records (37%) were granted and still in force. The remaining records cover every other status a record can carry, which is not broken out further in this dataset.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to support vector machine kernel function optimization patent landscape, with the prior art for and against each one.
The figures on this page describe what this search returned; they do not establish claim scope, strategy or priority for any single filer or record.
A family count or an abstract cannot establish what a granted claim requires. Anyone evaluating a specific design or route against this space needs to pull the granted claim set for the records that matter to them.
Explore records in Patsnap EurekaThe filer ranking shows which organisations recur across this search, without summing related names or inferring strategy from volume. Use it as a starting list for deeper per-filer review.
Build a filer watchlist in Patsnap EurekaThis search returns 10,625 published records, which de-duplicate to 4,675 simple patent families once the same invention filed in multiple countries is collapsed to one entry. Records and families are different units counting the same underlying field, so a figure quoted in one unit should not be compared directly with a figure quoted in the other. The search string carries no date limit, so this set spans every matching record the database holds, though the most recent few years are still filling in as filings continue to publish.
International Business Machine Corporation is named on 62 of the 4,675 simple patent families in scope, the largest single row among the 99 listed filers (organisations; individually named filers are excluded from this list but remain in the totals). The fifth-ranked filer holds 31 families and the tenth-ranked holds 22, which shows the count tapering gradually rather than concentrating sharply at the very top. Filer rows are not rolled up to corporate group, so a parent and its subsidiaries, if both present, would appear as separate rows and should not be summed.
Published records with an earliest filing year between 2018 and 2021 rose from 701 to 799, a 14% increase over that span, and the peak year observed so far is 2019 with 829 records. Filings from 2022 onward are not yet complete because publication takes roughly 18 months for most routes and up to 30 months where a PCT application enters national phase, so those later years understate the true count and should not be read as a slowdown. The trend counts published records, not inventions, so a rise can also reflect the same invention being filed in more countries rather than more distinct inventions appearing.
Within the IPC subclasses large enough to discuss reliably here, G06N (computing based on AI models) appears on 35.8% of the 4,675 families, G06F (electric digital data processing) on 33.9%, and G06K (data recognition & presentation) on 26.9%. These shares add up to more than 100% because a single family can carry more than one IPC subclass tag. The dataset includes 100 subclasses in total, and only the largest few are discussed here because the smaller ones risk reflecting search-string noise rather than a genuine technical branch.
US7421417B2, assigned to Wisconsin Alumni Research Foundation and published 2008-09-02, describes a feature selection technique for SVM classification that uses a fast Newton method to suppress input-space features or kernel functions within a linear programming formulation, implementable with a standard linear equation solver rather than specialised linear programming packages. This record was returned as the first result under the database's default ordering for this search, not because it is the most cited, the newest, or otherwise representative of the field. Neither an abstract nor a family count can establish what the granted claims actually cover or require; any freedom-to-operate or infringement question has to be answered by reading the granted claim set directly.
Go past this page: query the whole support vector machine kernel function optimization patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
Search. Every figure on this page comes from one Patsnap search, run once and not edited afterwards. This is the exact search string:
TAC:("support vector machine") AND (kernel OR "kernel function" OR "kernel selection")
Reading the field codes: TAC searches the title, abstract and claims of each record, not the full description. The search string sets no date limit, so the scope is every matching record in the database regardless of when it was filed. It is not restricted to recent years. How this string was built matters for how far the counts can be pushed. It was generated in batch from a topic list rather than hand-crafted for this page, and the result set is not manually screened. A keyword search over title, abstract and claims both over-captures (unrelated filings that happen to use the same words) and under-captures (the same invention written in different words). This page cannot measure either effect, so read every figure here as what this particular string returned, not as what exists in the field. No subclass carries much of this set: the most common one is on 35.8% of the patent families and the set spans 100 subclasses in all. That can mean the technology genuinely sits across several areas, or that the search string is also matching adjacent work that happens to use the same words. This page cannot separate the two, and the result set is not screened by hand.
What is being counted. Two different units appear on this page and they are not interchangeable. The filer list and the technology split are counted in simple (DOCDB) patent families: one invention counts once however many countries it was filed in. The total, the jurisdiction split and the filing-year chart are counted in published records: the same invention counts once per publication. For this search that is 10,625 records and 4,675 families. Record counts reward filing in many jurisdictions; family counts do not. Shares are only ever taken against a denominator in the same unit, and each one names it.
Who the filers are. Names come from Patsnap's standardised assignee field, as recorded on the documents themselves. They are not rolled up to corporate group: a parent and its subsidiaries appear as separate entries, and a portfolio acquired from another company stays under the name on the document unless the assignment is reflected there. This list is meant to carry organisations, not people. Filings held by a named individual are identified by matching the assignee against the inventors on the same search, and, for names written in Chinese, Japanese or Korean characters, by the name carrying no organisational suffix; those are removed from the list (1 of them here). Neither test is exhaustive: the inventor list it matches against is itself capped, and a personal name written in Latin script with no organisational wording in it cannot be told apart from a short company name by rule. So an individually held filing can still appear in the list. Those filings stay inside every total and share on this page either way, so the listed entries can add up to less than the total. A record shown in full further down still names its assignee exactly as the patent office records it, including where that is a person: that name is how the record is identified and checked. What is left out of the ranking is people as ranked entries, not people as cited sources. The table shows the top 30 of the 99 filers returned, ordered by count alone; the data endpoint returns at most 100 entities, so even that 99 is not every filer. One patent family can name several filers and each is counted separately, so these rows are not slices of a divided whole: adding them together over-counts, and this page deliberately publishes no combined "top five" share for that reason. See every filer, individuals included
Dates. The year chart counts by earliest filing year, not publication year. A filing only becomes visible once it publishes: roughly 18 months for most routes, and up to 30 months where a PCT application enters national phase. Measured across these pages, the year four back from today still holds only about 89% of its eventual count. 2022 onwards are therefore shaded on the chart as still filling in, and the growth figure stops at 2021. The data behind this page was retrieved on 2026-10-27.
Legal status. "In force" counts documents whose legal status at retrieval was granted and maintained (3,978 of 10,625). Everything else is pending, withdrawn, refused, lapsed or not determinable, and those states are not broken out here because the underlying codes do not separate them cleanly. Legal status changes continuously and is reported per document, not per family. Get the status breakdown in Eureka
Classification. The technology split uses IPC subclasses (four characters, for example H01M). A single record usually carries several, so the shares add up to more than 100% and a record can appear in more than one bar. Subclass is a coarse grouping; it describes the field a record was classified into, not what the claims cover. Break the classes down to subgroup level
Who wrote the words. The tables, charts, counts, shares and patent numbers on this page are produced directly from the search result by a program; none of them are written or estimated by a language model. The surrounding prose, headings, FAQ answers and the answers in the question panel are drafted by a language model that is given those same figures and is not permitted to introduce others. Prose can still mis-describe a correct figure, so where the two disagree, the tables and charts are the record.
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 limitations that apply to every figure above. Recent filings are under-counted, because an application is not public until roughly 18 months after filing and database loading adds further delay. The search string defines and constrains everything shown: records that use different terminology, or that sit outside the fields searched, are absent and cannot be counted. Applicant names, classification codes, legal-status codes and citation records are taken as recorded and may contain errors, duplicates, omissions or stale entries. Ordering by volume is not a measure of quality, scope, enforceability or commercial value, and a larger portfolio is not a stronger one. 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, validity or infringement search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. No attorney-client relationship is created by it. Any patent, commercial, or strategic decision should be verified independently against the primary records 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.
The question panel. The answers behind the suggested questions on this page were written when the page was generated, not in response to your click. The progress steps that play before an answer appears are an animation of how that analysis was done; nothing is being searched or computed at that moment. Typing your own question instead opens Patsnap Eureka, which does run it live.
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