Skip to content
PatentBrief
Get alertsTop ↑

Smart Ranking of Emails and Files Based on How You Click

IBM's 1999 patent on automatically sorting lists of items, like emails, by watching which ones you click first and updating a mathematical model of your preferences in the background.

Granted 2002ExpiredExpired 2019Owned by International Business Machines CorpInvented by Roland Seiffert, Ramakrishnan Srikant, Andreas Arning + 1 more

Original patent title: “Self-adaptive method and system for providing a user-preferred ranking order of object sets

Plain-English explanation by SahiLast reviewed · June 13, 2026

IBM's 1999 patent on automatically sorting lists of items, like emails, by watching which ones you click first and updating a mathematical model of your preferences in the background. Granted to International Business Machines Corp in 2002 with 38 claims and 135 forward citations, and it is now in the public domain.

Coverage

What does this patent actually cover?

The system observes the order in which a user accesses a first set of objects, such as opening emails in an inbox, and compares this sequence to an 'access hypothesis'—a baseline expectation of how the user would normally browse them (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). If the user deviates from this baseline (for example, skipping the top three emails to click a receipt further down), the system adapts a 'preference model' (Claim 1). It does this by applying a 'bonus value' to the features of the early-accessed item (Claim 4) and a 'penalty value' to the skipped items (Claim 9). These updated weights, stored in feature vectors, are then used to calculate preferences and re-rank a second set of incoming items (Claim 1).

The gap

What does this patent NOT cover?

  • Does not cover ranking systems that rely purely on explicit user feedback, such as star ratings, likes, or manual folder sorting.
  • Does not cover static ranking systems that do not update their underlying preference models dynamically based on user behavior.
  • Does not cover systems where the baseline expectation (access hypothesis) is not compared against the actual sequence of user interactions.
  • Does not cover ranking methods that do not use feature vectors to represent the attributes of the items being sorted.

These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.

Key facts

Patent numberUS 6370526
StatusExpired
FieldSoftware & Internet
AssigneeInternational Business Machines Corp
InventorsRoland Seiffert, Ramakrishnan Srikant, Andreas Arning and 1 other
Filed1999
Granted2002
Expires2019 (expired)
Claims38
Times cited135
LitigationNone on record
Value · $96K$307KModest

What made this novel

Instead of just tracking what you click, the system compares your actions to an 'access hypothesis' (like assuming you will read top-to-bottom). By measuring how much you deviate from this baseline, it filters out the bias of screen layout.

The Patent Drawing

Representative patent drawing for Self-adaptive method and system for providing a user-preferred ranking order of object sets (US 6370526)
Representative figure · US 6370526All figures on Google Patents →
Self-adaptive method and syste…(Primary claim)softwareconsumer electronicsecommerce

Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.

Where you've seen this

Real-world examples

01

Gmail's Priority Inbox sorting

02

Microsoft Outlook's Focused Inbox

03

Algorithmic sorting of search results in enterprise databases

Why it matters

The bigger picture

This patent represents an early foundation for algorithmic feeds and smart inboxes. Long before modern AI-driven social media feeds, IBM patented the core loop of implicit feedback: watching what a user ignores or clicks to silently re-order their view. It directly relates to features like Gmail's Priority Inbox or Outlook's Focused Inbox.

Filed

May 18, 1999

Granted

April 9, 2002

Market context

Who's building on this

Companies in this space

IBM originally patented this for enterprise databases and email. Today, major email providers like Google and Microsoft, alongside search engine developers, use similar implicit feedback loops to train their ranking algorithms.

Market impact

This patent helped establish the intellectual property landscape for implicit feedback loops. It moved the industry away from manual rules (like 'always put boss's email on top') toward dynamic, self-learning user interfaces that adapt without user intervention.

Claim 1 — Plain English

What this patent covers

The system observes the order in which a user accesses a first set of objects, such as opening emails in an inbox, and compares this sequence to an 'access hypothesis'—a baseline expectation of how the user would normally browse them (Claim 1). If the user deviates from this baseline (for example, skipping the top three emails to click a receipt further down), the system adapts a 'preference model' (Claim 1). It does this by applying a 'bonus value' to the features of the early-accessed item (Claim 4) and a 'penalty value' to the skipped items (Claim 9). These updated weights, stored in feature vectors, are then used to calculate preferences and re-rank a second set of incoming items (Claim 1).

The clever bit

Instead of just tracking what you click, the system compares your actions to an 'access hypothesis' (like assuming you will read top-to-bottom). By measuring how much you deviate from this baseline, it filters out the bias of screen layout.

What it does not cover

  • Does not cover ranking systems that rely purely on explicit user feedback, such as star ratings, likes, or manual folder sorting.
  • Does not cover static ranking systems that do not update their underlying preference models dynamically based on user behavior.
  • Does not cover systems where the baseline expectation (access hypothesis) is not compared against the actual sequence of user interactions.
  • Does not cover ranking methods that do not use feature vectors to represent the attributes of the items being sorted.

Patent timeline

Filing

Application submitted to the patent office

Publication

Application published, typically 18 months after filing

Grant

Patent officially issued

Expiration

Patent enters public domain

This patent is in the public domain

See the Freedom to Build guide — what is free to use, what is not, and how to cite this patent.

View guide →

PatentBrief Score

Impact Score

Strong

Citation count

40/40

Highly cited

Claim breadth

20/20

Very broad protection

Recency

0/20

Older than 20 years

Assignee scale

0/20

Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →

PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.

Heuristic Value Estimate

What this patent might be worth

Modest

$96K$307K

Midpoint $192K · expired or expiring · industry ×1.6

Adjust inputs →

Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.

Claim text not yet imported for this patent

The original legal language

Original claims

38 claims as filed with the patent office.

Concepts involved

ClaimPrior artNon-obviousnessNoveltySpecificationAssigneePatent term

Citations

Patent lineage

Cites earlier patents

3

earlier patents this invention cites as foundations

View prior art →

Cited by later patents

135

later patents that build on this invention

View patents →

Cite this patent

Seiffert, R., Srikant, R., Arning, A., & Agrawal, R. (2002). Smart Ranking of Emails and Files Based on How You Click (U.S. Patent No. 6,370,526). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/6370526/google-adwords-pay-per-click

Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.

Embed

Add this patent to your site

Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.

<div data-patentlens-widget data-patent-number="US6370526"></div>
<script src="https://patentbrief.org/embed.js" async></script>

Stay in the loop

Get a weekly digest of new patents.

One email per week. No spam. Unsubscribe anytime.

Keep exploring

Related patents you should know

US 4683195 · 1987

How to Make Billions of Copies of a DNA Segment

This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.

Cetus Corp

US 8697359 · 2014

How to Edit Genes in Human Cells Using an Engineered CRISPR System

This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.

Massachusetts Institute of Technology

US 7657849 · 2010

How the iPhone's Slide-to-Unlock Gesture Works

Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.

Apple Inc

US 4733665 · 1988

How Doctors Implant a Permanent Stent Using a Balloon

This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.

Expandable Grafts Partnership

US 4965188 · 1990

How to Make Many Copies of a DNA Piece with Heat

This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.

Cetus Corp

US 4235871 · 1980

How to Encapsulate Active Materials in Lipid Bubbles Efficiently

This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.

Individual

Semantically similar

You might also find these interesting

SEARCH ALL

More to explore

More in Software & Internet

Browse all Software & Internet

New to patents?

What is a patent?How to read a patentAnatomy of a claimHow strong is this patent?What the citations meanWhat it doesn't coverSoftware PatentsPatent glossary
Explore the landscape:software patents →consumer electronics patents →ecommerce patents →

Common Questions

Frequently Asked Questions

What does Smart Ranking of Emails and Files Based on How You Click cover?

IBM's 1999 patent on automatically sorting lists of items, like emails, by watching which ones you click first and updating a mathematical model of your preferences in the background.

Who owns patent US 6370526?

International Business Machines Corp owns this patent, granted in 2002.

When does this patent expire?

This patent has expired and is now in the public domain — anyone can use the invention freely.

What is patent US 6370526 cited by?

This patent has been cited by 135 later patents that build on its ideas.

What problem does this patent solve?

This patent represents an early foundation for algorithmic feeds and smart inboxes. Long before modern AI-driven social media feeds, IBM patented the core loop of implicit feedback: watching what a user ignores or clicks to silently re-order their view. It directly relates to features like Gmail's Priority Inbox or Outlook's Focused Inbox.

What does this patent NOT cover?

Does not cover ranking systems that rely purely on explicit user feedback, such as star ratings, likes, or manual folder sorting.

View all →
US 11645473·2023

How AI Predicts Who Will Speak Next in a Conversation

US 10318876·2019

How AI Systems Adjust Their Behavior Based on User Mood

US 10140638·2018

How Cloud Services Automatically Switch Providers When One Fails

US 9959544·2018

How a Server Updates Smart Card Apps and Shows Ads

Patent monitoring

Get notified when International Business Machines Corp files a new patent

Get notified when this company files a new patent. Weekly digest · Confirm via email · Unsubscribe anytime.

Last reviewed: June 13, 2026 · PatentBrief is not a law firm and this is not legal advice.