Fastest
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 →https://eureka.patsnap.com/resources/blog/rd-blog/software-defect-prediction-using-machine-learning-models-patent-landscape/ · Patsnap · data cut-off 2026-10-20 · downloaded from the live page
Patent Landscape · Software & AISoftware Defect Prediction Using Machine Learning: Patent Landscape
176 patent families on software defect prediction with machine learning, with filings led by Beihang University and no single filer holding a large share.
194
Published Records
176
Simple Patent Families
7%
Families Naming the Largest Filer
41%
In Force at Cut-off
194 published records collapse into 176 simple (DOCDB) families; the difference is the same invention filed in more than one country. BEIHANG UNIV is named on 12 of the 176 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 In force = 79 of 194 records still granted and maintained at the data cut-off; the rest are pending, withdrawn, refused or lapsed.
- 176 simple patent families sit behind 194 published records on software defect prediction using machine learning, with no date limit applied to the search.
- Beihang University holds the largest single share, named on 12 of the 176 families (6.8%), while 57 of the 68 listed filers hold 2 or fewer families each.
- G06F appears on 96.0% of families, with G06N (AI models) on 73.3% and G06K (data recognition) on 29.0%, the three subclasses that carry this dataset.
Published byPatsnap Research··6 min readSourced from Patsnap Eureka
Overview
What this search covers
This landscape draws on a search for "defect prediction" or "bug prediction" combined with machine learning, neural network or classifier terms, restricted to software. It returns 194 published records, which de-duplicate to 176 simple patent families once filings for the same invention across jurisdictions are merged. No start or end date was applied to the search string, so the set reflects whatever has been filed and indexed under these terms to date, not a fixed historical window.
At retrieval, 79 of the 194 records (41%) were granted and still in force; the remainder are pending, withdrawn, refused, lapsed or not determinable, and that breakdown is not available at finer detail. The filer list returned 68 organisations, with individual inventors stripped out of that list but still counted in every total and share on this page.
Records vs. families in scope
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 (32 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 68 filers returned for this search; the data endpoint returns at most 100 entities, so even that 68 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.
Source: Patsnap Eureka. Assignee ranking and totals. Derived from one Patsnap search for Software Defect Prediction Using Machine Learning Models Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
10,000 free credits to start
Data
Filing trend and technology composition
The chart below counts published records by earliest filing year; the IPC view counts simple patent families, so its shares can add to more than 100% where a single family carries more than one classification.
Filing trend, 2009–2026 (published records)
Published records rose from 2 in 2009 to a peak of 29 in 2023. The chart shows a recent window only; 2022 onward is still filling in as later filings publish, so the last few years understate eventual totals and should not be read as a decline.
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 2009-2026 (191 records); the 194 total quoted above includes earlier filings outside the window.
Technology composition by IPC subclass
G06F (electric digital data processing) appears on 96.0% of the 176 families in scope, G06N (computing based on AI models) on 73.3%, and G06K (data recognition & presentation) on 29.0%. The remaining subclasses in the 17-subclass spread each carry a smaller share and are shown on the chart but not characterised here.
Shares are the percentage of the 176 patent families in scope. One patent family can carry several IPC classes, so the shares add up to more than 100%.
Source: Patsnap Eureka. Filing trend and technology composition. Derived from one Patsnap search for Software Defect Prediction Using Machine Learning Models Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.
Go deeper on Software Defect Prediction Using Machine Learning Models Patent Landscape with Eureka
This page is one run against one query. Ask Eureka your own question about software defect prediction using machine learning models patent landscape and every answer comes back with the patent numbers behind it.
Try EurekaExample record
A record from the result set
First record returned, default database order
Devops driven cognitive cost function for software defect prediction
INTERNATIONAL BUSINESS MACHINES CORPORATION
Approaches presented herein enable domain knowledge-based software defect prediction. A cost function configured to train a machine learning model to predict a defect in a software version is obtained, and a domain knowledge penalty metric is determined for a software development team associated with the version. A linear combination of that penalty metric is applied to the cost function to create a domain knowledge-modified cost function, which is then used to train the machine learning model via minimization.Abstract truncated as returned by the database; granted claims are not reproduced here.
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.
Source: Patsnap Eureka. The first record the search returned, shown in full. Derived from one Patsnap search for Software Defect Prediction Using Machine Learning Models Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Run it yourself
Put your own technology through the same analysis
Where to run it
For builders
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 →Patterns in the data
What the filer and technology figures show
These cards report individual figures from the dataset. None of them should be read as a ranking of quality, strategy or market position.
Largest filer
12 of 176
simple patent families
Beihang University's single-row share
Beihang University is named on 12 of the 176 simple patent families in scope, a 6.8% share. This is the single largest row in the filer list; it says nothing about claim scope or portfolio strength beyond the count.
Filer list, top row
Long tail
57 of 68
listed filers
Most listed filers hold 2 or fewer families
Of the 68 organisations returned in the filer list, 57 hold 2 or fewer simple patent families each. The list excludes individual inventors, who are still counted in the 176-family total.
Filer list, full set
Technology split
96.0%
of 176 families
G06F carries almost the whole set
G06F (electric digital data processing) appears on 169 of the 176 families (96.0%), G06N (AI models) on 129 (73.3%), and G06K (data recognition & presentation) on 51 (29.0%). Families can carry more than one class, so these shares overlap rather than add.
IPC composition
Legal status
41%
of 194 records
79 of 194 records remain in force
At the 2026-10-20 retrieval date, 79 of the 194 published records (41%) were granted and still in force. The rest are pending, withdrawn, refused, lapsed or not determinable, without further breakdown available.
Legal status at retrieval
Eureka AI Agent
Looking for what nobody has claimed yet?
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to software defect prediction using machine learning models patent landscape, with the prior art for and against each one.
Source: Patsnap Eureka. Derived observations on the same dataset. Derived from one Patsnap search for Software Defect Prediction Using Machine Learning Models Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Next steps
Where to go from this landscape
This page reports counts and shares from one search string. Reading claim scope, assessing freedom to operate, or tracking a specific filer's activity over time call for a closer look.
Read the granted claims directly
A family count or an abstract cannot establish what a patent covers. Pull the granted claim set for any record that matters to a specific design before drawing conclusions about it.
Open Patsnap Eureka →Track filers individually, not by name pattern
Rows with similar names are not combined on this page and should not be combined by the reader either; each row's share belongs to that row alone.
Explore filer profiles in Patsnap Eureka →Source: Patsnap Eureka. Suggested next steps. No new data: every figure named here is one of those above. Derived from one Patsnap search for Software Defect Prediction Using Machine Learning Models Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
FAQ
Common questions about this landscape
This search returns 194 published records, which de-duplicate to 176 simple patent families once the same invention filed in multiple jurisdictions is merged into one. The search string combines defect/bug prediction terms with machine learning, neural network or classifier terms, restricted to software, and carries no date limit. Because coverage depends entirely on which terms a record uses, this count should be read as what this specific search string catches, not as a definitive count of all related filings.
Beihang University is named on 12 of the 176 simple patent families in scope, the largest single-row share at 6.8%. The filer list returned 68 organisations in total, with 57 of them holding 2 or fewer families each, so the field is spread across many small filers rather than concentrated in a handful. Filer rows are not rolled up to corporate group and cannot be summed into a combined share, since one family can name more than one filer.
The filing trend, counted in published records, rose from 2 records in 2009 to a peak of 29 in 2023. The chart's most recent years, from 2022 onward, are still filling in as later filings publish, which understates their eventual totals, so a drop in those years should not be read as a decline. No growth rate is available on this page because the dataset and the complete-year window are too thin to support one reliably.
G06F (electric digital data processing) appears on 96.0% of the 176 families in scope, G06N (computing based on AI models) on 73.3%, and G06K (data recognition & presentation) on 29.0%. These shares add to more than 100% because a single family can carry more than one classification. Smaller subclasses also appear in the full 17-subclass spread shown on the chart, but they carry much smaller shares and are not detailed in this summary.
Counted in published records, the largest receiving offices in this set are China with 135, India with 30, and the United States with 18, alongside smaller counts at the European Patent Office, WIPO and Canada. The search returned 8 receiving offices in total; these figures are counts of where applications were filed, not an indication of where any filer is based. One invention can appear more than once if filed in multiple offices, so these figures sum to the record total rather than the family total.
US20200004532A1, assigned to International Business Machines Corporation, describes a cost function for training a machine learning model to predict software defects, incorporating a domain knowledge penalty metric tied to a development team. The abstract describes a linear combination of that penalty metric with the base cost function, used to train the model through minimization. This is simply the first record returned under the database's default order, not a ranking by citations or importance, and its abstract alone cannot establish what its granted claims actually require.
Answers are grounded in the same dataset. Derived from one Patsnap search for Software Defect Prediction Using Machine Learning Models Patent Landscape, covering all matching records regardless of filing date (the search string sets no date limit), retrieved 2026-10-20. Counts cover published records only and move as new filings publish.Run this in Eureka MCP
Research Software Defect Prediction Using Machine Learning Models Patent Landscape in depth with Eureka
Go past this page: query the whole software defect prediction using machine learning models patent landscape corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
How this page was built, and what the numbers do and do not mean
Search. Every figure on this page comes from one Patsnap search, run once and not edited afterwards. This is the exact search string:
TAC:(("defect prediction" OR "bug prediction") AND ("machine learning" OR "neural network" OR classifier) AND software)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 96.0% 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 194 records and 176 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 (32 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 68 filers returned, ordered by count alone; the data endpoint returns at most 100 entities, so even that 68 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 2026-10-20.
Legal status. "In force" counts documents whose legal status at retrieval was granted and maintained (79 of 194). 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.
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.