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 →17 patent families cover semantic natural language interfaces for API/function-call invocation.
27 published records collapse into 17 simple (DOCDB) families; the difference is the same invention filed in more than one country. In force = 12 of 27 records still granted and maintained at the data cut-off; the rest are pending, withdrawn, refused or lapsed.
This landscape draws on a search string combining natural language interface or natural language command terms with semantic and either function call, function invocation, or API across title, abstract and claims. It returns 27 published records that de-duplicate to 17 simple patent families. The search string sets no date limit, so the result covers every matching record the database holds, not a fixed span of years.
17 families is a small pool. The figures below describe exactly what this search returned, they are a starting point for further research, not a map of a field or an industry.
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 (13 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 12 of the 12 filers returned for this search; the data endpoint returns at most 100 entities, so even that 12 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.
Pick a task. Every answer cites the patents behind it.
Two views of the same 17 families and 27 records: when the matching records were filed, and which IPC subclasses they carry.
Counted in published records by earliest filing year, from 2017 (3 records) to 2026 (5 records), with a peak of 5 reached in 2018, 2025 and 2026. Records from 2022 onward are still filling in as later filings publish, so that stretch understates its eventual count and should not be read as a drop-off.
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 2017-2026 (26 records); the 27 total quoted above includes earlier filings outside the window.
G06F (electric digital data processing) is carried by 14 of the 17 families (82.4%), G06N (computing based on AI models) by 5 (29.4%), and G10L (speech & audio analysis/synthesis) by 3 (17.6%). A family can carry more than one class, so these shares add to more than 100%.
Shares are the percentage of the 17 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 semantic natural language interface for api function invocation patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaA multimodal natural language interface interprets user requests combining natural language input from the user with information selected from a current application and sends the request in the proper form to an appropriate auxiliary application for processing. The interface lets users combine natural language (spoken, typed or handwritten) input with a selection from the application they are running to perform a task in another application, without leaving the current application, opening new windows, or pre-determining the available actions.This is the first record the search returns under the database's default order, not the most cited, newest, or broadest filing. What its granted claims actually require has to be read from the claim set itself; an abstract and a family count cannot establish that.


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 worth sitting with before treating this set as representative of anything beyond its own 17 families.
TABLEAU SOFTWARE INC is named on 2 of the 17 simple patent families in scope (11.8%). Twelve listed filers each hold 2 or fewer families; filer rows are not summed here because one family can name more than one filer, which would overlap and inflate any combined figure.
G06F (electric digital data processing) appears on 14 of the 17 families (82.4%), ahead of G06N at 5 families (29.4%) and G10L at 3 families (17.6%). A family can carry more than one IPC class, so these percentages add to more than 100% and are not mutually exclusive groupings.
12 of the 27 published records (44%) were granted and in force as of the 2026-10-21 retrieval date. The remaining records are pending, withdrawn, refused, lapsed or not determinable, and that breakdown is not separated out here; legal status changes continuously and is not a measure of claim strength.
Of the 27 published records, 15 were filed at the United States receiving office, 5 at India, 3 at Australia, 2 at WIPO (PCT), and 1 each at Canada and the EPO. This counts where applications were filed, not where any filer is based.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to semantic natural language interface for api function invocation patent landscape, with the prior art for and against each one.
A 17-family pool supports a quick read, not a full freedom-to-operate or white-space assessment. These are reasonable next moves.
12 of the 27 published records are in force at retrieval. Reading their granted claims directly is the only way to know what they actually require, since this page works from abstracts and counts.
Explore claim scope in EurekaA 17-family result from one string is sensitive to wording. Running variant phrasing in Eureka can surface records this exact string missed.
Run a variant search in EurekaThe listed filers here are capped at the top entries the search returns. Revisiting the same search periodically shows whether new filers or filings enter the list.
Set up monitoring in EurekaThis particular search string returns 27 published records that de-duplicate to 17 simple patent families. The search sets no date limit, so this is every matching record the database holds for that exact phrasing, not a fixed year range. A different combination of search terms would very likely return a different count, so this figure describes this search, not a fixed total for the underlying technology.
Among the filers the search returned, TABLEAU SOFTWARE INC is named on the most families at 2 of the 17 in scope (11.8%). Twelve listed filers each hold 2 or fewer families, so no single row accounts for a large share of the pool. The filer list excludes filings held by named individuals, who are still counted in the totals but not shown as rows, and names are not rolled up to a corporate parent, so related entities appear as separate rows.
IPC subclass tagging shows G06F (electric digital data processing) on 14 of the 17 families (82.4%), G06N (computing based on AI models) on 5 (29.4%), and G10L (speech & audio analysis/synthesis) on 3 (17.6%). Because a single family can carry more than one classification, these shares add to more than 100% and are not a strict breakdown of the pool. Other subclasses appear in the chart at lower shares and are not detailed here.
Counting published records by receiving office, the United States appears most often at 15 of 27 records, followed by India at 5, Australia at 3, WIPO (PCT) at 2, and Canada and the EPO at 1 each. This reflects where applications were filed, not where any filer is headquartered or incorporated, since no nationality data is available in this dataset. One invention can appear at more than one office, which is why these figures sum to the record total rather than the family total.
12 of the 27 published records (44%) were granted and in force as of the 2026-10-21 retrieval date. The rest fall into pending, withdrawn, refused, lapsed or not-determinable status, and that breakdown is not separated out in this dataset. In-force status reflects legal standing at a point in time rather than a measure of how broad, strong or commercially useful any given claim set is, and it will keep changing as records move through prosecution or expire.
Go past this page: query the whole semantic natural language interface for api function invocation 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:(("natural language interface" OR "natural language command*") AND semantic AND ("function call*" OR "function invocation" OR API))
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. One subclass (G06F) carries 82.4% of the patent families, so this search returned a classification-tight set.
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 27 records and 17 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 (13 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 12 of the 12 filers returned, ordered by count alone; the data endpoint returns at most 100 entities, so even that 12 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. The data behind this page was retrieved on 2026-10-21.
Legal status. "In force" counts documents whose legal status at retrieval was granted and maintained (12 of 27). 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