Implicitly adaptive eye-tracking user interface

US 20170212583A1
(19) United States
(12) Patent Application Publication (10) Pub. No.: US2017/0212583 A1
Krasadakis (43) Pub. Date: Jul. 27, 2017
(54) IMPLICITLY ADAPTIVE EYE-TRACKING (52) U.S. Cl.
USER INTERFACE CPC ............ G06F 3/013 (2013.01); G06F 3/0482
(2013.01); G06F 3/0485 (2013.01); G06F
(71) Applicant: Microsoft Technology Licensing, LLC, 3/04883 (2013.01); G06K 9/00302 (2013.01)
Redmond, WA (US) (57) ABSTRACT
eV1ce 1S d1SCIOSed Or enabl1ng a user to naV1gate between(72) Inventor: Georgios Krasadakis, Redmond, WA Adeviceis disclosed f bling igateb
(US) content using gaze tracking. The device includes a presen
tation component for presenting a plurality of content to a
user in user interface (UI) windows. A camera captures the
gaze of the user, and components described herein control
focus ofthe UI windows presented to the user based on the
(22) Filed: Jan. 21, 2016 gaze. Multiple UI windows of varying content may be
displayed to the user. A processor determines, from the
captured gaze, wherethe user is looking, and the UI window
located at the users gaze point is brought into focus and
(21) Appl. No.: 15/003,781
Publication Classification
(51) Int. Cl. controlled by the user's gaze. As the user looks to other UI
G06F 3/0 (2006.01) windows, focus is seamlessly moved from one UI window
G06K 9/00 (2006.01) to the next to correspond with what the user is looking at,
G06F 3/0488 (2006.01) providing an implicit way to control digital content without
G06F 3/0482 (2006.01) conventional computer commands, actions, or special
G06F 3/048.5 (2006.01) requests.
-300
318 320 322

Patent Application Publication Jul. 27, 2017 Sheet 1 of 7 US 2017/0212583 A1
100.
Client Computing Device
SS- 112-N
110
106
Network 2 s
User interface
Component
134
GaZe Detector
FG.

-200
202 - 1 N
/ PublicNetwork
DataCenter(2) 230
71 Fabric T
N.Controlle/
-N (206
DedicatedNetwork'-22
ServicePOWider
208
F.G. 2

318 320 322
FG. 3

y -400A
ors
s
308.310N is...?312 rs
S
:rf --- - - - -
i;
FG. 4A
FG. 4B

W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. <eaves U window)
1 Gaze NC
1timeon U windoWN
N exceeds /
F.G. 5

W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. W. 3 leaves U Window)
N ? e
received at a
NU window 1.

1 Eye N
movement
g indicates
N auto-scrolling
Noo?as"1 -SE
1 Eye N
movement N
indicateS YeS.
auto-SCrolling /
N too slow 1.r ”
F.G. 7

US 2017/0212583 A1
IMPLICTLY ADAPTIVE EYE-TRACKING
USER INTERFACE
BACKGROUND
0001 Computers have traditionally incorporated user
interfaces that utilize input devices. Such as a mouse and
keyboard. As computers have become more portable, how
ever, theuse ofSuch input devices becomes less practical for
users. One way to provide easier portable usage has been
with touch screens. At the same time, the amount ofcontent
available to users online has increased dramatically, which
has increased the difficulty for users to discover and con
Sume desired content.
0002 While modern portable computers, such as tablets
and Smart phones, now commonly incorporate touch
screens, other types ofhardware and Software are emerging
to enhance portability and usability. For example, built-in
cameras are commonly included in portable computers for a
variety ofpurposes. For example, built-in cameras provide
Video conferencing, which is now apopularway for users to
communicate. In addition to communicating with other
users, cameras are also increasingly used for authentication.
SUMMARY
0003. The disclosed examples are described in detail
below with reference to the accompanying drawing figures
listed below. The following summary is provided to illus
trate some examples disclosed herein, and is not meant to
necessarily limitall examples to anyparticularconfiguration
or sequence of operations.
0004 Some examples are directed to controlling the
display of content on a computing device through tracking
of a user gaze. In some examples, a collection of digital
content is presented to a user in userinterface (UI) windows
on a screen. Additionally, the gaze ofthe user is monitored
and gaze points are tracked with respect to the content
collection presented to the userbased on the monitored gaZe
ofthe user. Some examplesalso display the UI windows that
coverthe gaze points in a focused manner. UI windows that
are outside of the gaze points may also be presented in an
unfocused manner. The users focus may betracked, andUIs
may correspondingly be brought into and out of focus in a
seamless manner that creates a userexperience in which the
user does not notice the unfocused UIs. For example, a
user's gaze shifts from a first UI window to a second UI
window. Prior to the gaze shift, the first UI window appears
active to the user, such as being in color and/or in-focus,
while the second window is grayscale and/or out-of-focus.
With the gaze shift, the first UI window becomes grayscale
and/or out-of-focus, while the second window comes into
focus and/or is brought into color. In this example, the user
is presented a seamless experience, where whatever is
viewed becomes active, while UI windows not currently
being viewed are inactive, and may thus be less distracting
to the user.
0005. In some examples, an in-focus UI window
becomes active in promoting highly-related content to a
user, which may include using animation techniques and
optimal timings. The UI may advantageously adapt by
becoming less distracting for the user and/or more interac
tive given specific item(s) of interest.
Jul. 27, 2017
BRIEF DESCRIPTION OF THE DRAWINGS
0006. The disclosed examples are described in detail
below with reference to the accompanying drawing figures
listed below:
0007 FIG. 1 is an exemplary block diagram illustrating
a computing device for receiving user gaze input data.
0008 FIG. 2 is an exemplary block diagram illustrating
a networking environment for distributing and utilizing user
gaze input data.
0009 FIG. 3 is an exemplary diagram depicting an over
the-shoulder view of a device receiving user input gaze.
0010 FIG. 4A is an exemplary diagram depicting user
gaze input being received to interact with an interface
window.
0011 FIG. 4B is an exemplary diagram depicting user
gaze input being received to activate another interface
window.
0012 FIG. 5 is an exemplary flow chart illustrating
operation of a computing device to bring an interface
window into focus.
operation of a computing device to change the interface
window in focus.
operation ofa computing device to auto-scroll an interface
window.
0015 Corresponding reference characters indicate corre
sponding parts throughout the drawings.
DETAILED DESCRIPTION
0016 Referring to the figures, examples ofthe disclosure
enable a seamless and interactive eye-driven user experi
ence. In some examples, one or more user interface (UI)
windows are controllable by a user's gaze through tracking
by a camera on a computing device. By continuously
monitoring where the user is looking on a screen (for
example), the location ofthe user's gaze may be estimated
and/or determined. For example, a UI window may enteran
active state once the user starts looking at it, and once the
user looks away, the UI window may become inactive, at
least unless/until the user looks at the UI window again.
0017 While various examples dealing with UI windows
coming into focus are provided, the disclosed examples are
not limited to just activating and deactivating UI windows.
Gaze analytics enable very useful data in analyzing the
user's experience. For example, by displaying multiple UI
windows related to a variety oftopics, the topic(s) of most
interest to the user may be determined by analyzing which
UI windows are viewed, the duration of each view, the
repetition ofviews, etc.
0018 Whilehistorical data may be used to builda profile
ofa user's interests over time, targeted content may also be
delivered without knowing anything about the user, Such as
a user's past sessions (if any). The interface may start
tailoring content to an unknown user simply based upon the
current selections the user is making. For example, a user's
current viewinghabits may notonly reveal that the userlikes
sports content, but that when another UI window (even if
inactive) displays a story about a particular football team,
the user takes an interest in related topics (such as a type of
car driven by a particular player on the football team
displayed on another UI window) The interface may also

US 2017/0212583 A1
make decisions about content based on data from other
users, such as users whose profile have certain similarities.
0019 Content may also be queued based on the user's
actions. Forexample, while the user may see a collection of
UI windows, each UI window may have a queue ofcontent
behind it, which may or may not be at least partially visible
to the user. A UI windows content queue may be changed
and updatedatanytimebased upon theuser'sactions, which
may be interpreted in view of previous actions, sessions,
and/orhistorical data. The queuing ofUI window content in
some examples need notbe noticeableby the userat all. The
user may not notice that the content ofthe UI windows, as
the user's gaze moves around over time, becomes more
appealing and/or relevant according to the user's tastes and
preferences.
0020. Another feature provides auto-scrolling ofcontent
within a UI window. For example, a news story in a UI
window captures the users attention, who then starts read
ing the text. As the user's reading progresses, the text
auto-scrolls, the speed ofwhich maybebased upon a variety
of possible factors, such as the user's historical reading
speed (including looking at how similarthe content may be)
and/orthe actual current reading speed. Ifthe user increases
or decreases their reading speed, as discussed in more detail
below, the UI window's auto-scrolling speed may adapt in
real-time. Additionally, other media such as pictures and
video, even ifembedded with text, may become activated.
For example, a picture may be enlarged if the user gazes
upon it,a Video may begin playing ifit attracts a usersgaze,
an audio file may begin playing upon viewing, an animation
may start upon viewing, or the like. In some examples, as
Soon as content reaches the end, additional content shows
up, partofthequeue: navigation among content items. Some
examples may utilize a fixed or variable time threshold to
determine when additional content shows up, such as with a
delay.
0021. Anotherfeature allows analysis ofa user's reaction
to content. Forexample, a userthat is Surprised or has some
other emotional reaction may decrease their reading speed.
The reading speed change may be in comparison to not only
thecurrent reading speed, but also forhistorical trends in the
user's reading speed, which may also be known to vary by
content category. This may allow particular passages or
words to be associated with the user based on their interac
tion with text (or images orvideos orothertypes ofcontent).
Otheraspects foranalysis include whether there is repetition
(whether the user re-reads a particular word or portion of
text) and patterns in the user's reading of various content.
Such analysis may reveal the relevancy ofthe content being
displayed or the reading skills of a particular user. For
example, multiple users constantly re-readingan article may
imply that the article is written in an advanced Vernacular
and thus would be better consumed ifpresented in simpler
language. Some examples may be equipped to change the
language of the article based on the implied re-reading of
contentdetermined from usergazes, eitherfora multitude of
users (e.g., thearticle can be dynamically re-written forlater
consumption by all users) or for a specific user who is
constantly re-reading the content. In this vein, textual con
tent being presented to the users may be modified based on
detected user(s) gaze movements. For example, an article
may be presented in a modular fashion, such as on a
per-paragraph (or any other Suitable) basis. In turn, statistics
(such as viewing/reading speed, re-reading, etc.) may be
Jul. 27, 2017
tracked not only for the article as a whole, but any Subcom
ponent, such as separate statistics for different paragraphs.
Someexamples may trackand/or deliver simplerparagraphs
served to the user (quick titles and Summaries) rather more
detailed and complex paragraphs that are delivered to other
users, depending on a user's engagement history, current
reading statistics, patterns, etc.
0022 Aspects ofthe disclosure further enable numerous
technical advantages. For example, bypassing a user's
hands/arms entirely provides a fasterexperience, fasterinput
ofdata, and faster output based upon the user's faster input.
Further, by eliminating the need for various input devices
(mouse, keyboard, touchscreen), system memory may be
conserved which would otherwise be required to run such
devices and/or features, which may also improve perfor
mance ofthe operating system itself. In turn,eliminating the
need for Such devices also frees up processor resources, as
a processor need no longer interact with Such devices.
0023. Anotheradvantage provides forimproved userand
data security. In addition to providing biometric security
through retinal scanning or other eye-recognition tech
niques, a user may more securely input data without typing
on keys, which other individuals could watch to learn what
is being input. For example, combining gaze control with a
privacy screen, whereby others cannot view the screen from
side angles, could further enhance the user's security and
privacy.
0024. Another advantage is improved accuracy, where
many users would benefit from the accuracy of inputting
information via their gaze, in contrast to typing on a key
board (particularly if the user is not skilled at typing) or
using a mouse. In addition, users struggling with a touch
screen (such as with a small touch screen on a Smartphone)
may benefit from improved accuracy. In some areas, such as
with Smart phones, the ability to make selections via gaZe
will greatly increase the ability to communicate with others
phone-to-phone. Further still, removing the need for tradi
tional input mechanisms may allow hardware to become
miniaturized where they may then utilize a camera for gaZe
tracking over traditional input mechanisms. Additionally,
gaze tracking may be utilized in combination with Voice
commands, which maybe implemented/interpreted via natu
ral language processing (NLP).
0025 Referring again to FIG. 1, an exemplary block
diagram illustratesa clientcomputing device 100 configured
to capture and transmit user and environmental data. The
clientcomputing device 100 represents any deviceexecuting
instructions (e.g., as application programs, operating System
functionality, or both) to implement the operations and
functionality described herein associated with the comput
ing device 100. In some examples, the client computing
device 100 has at least one processor 108, one or more
presentation components 110, a transceiver 112, one ormore
input/output (I/O) ports 116, one or more I/O components
118, and computer-storage memory 120. More specifically,
the computer-storage memory 120 is embodied with
machine-executable instructions comprising a communica
tions interface component 130, a user interface component
132, and a gaze detector 134 thatare each executable by the
processor 108 to carry out disclosed functions below.
0026. Theclientcomputing device 100 may take the form
ofa mobile computing device or any other portable device,
such as, for example but without limitation, a mobile tele
phone, laptop, tablet, computing pad, netbook, gaming

US 2017/0212583 A1
device, HoloLens, virtual reality (VR) device, and/or por
table media player. The client computing device 100 may
also include less portable devices such as desktop personal
computers, kiosks, tabletop devices, industrial control
devices, wireless charging stations, automated teller
machines (ATMs), electric automobile charging stations, an
electronic component ofa vehicle (e.g., a vehicle computer
equippedwith cameras orothersensors disclosedherein),an
electronically equipped toy (e.g., a stuffed animal, doll, or
other child character equipped with the electrical compo
nents disclosed herein), or the like. Other examples may
incorporate the client computing device 100 as part of a
multi-device system in which two separate physical devices
share or otherwise provide access to the illustrated compo
nents ofthe computing device 100.
0027. The processor 108 may include any quantity of
processing units, and is programmed to execute computer
executable instructions for implementing aspects of the
disclosure. The instructions may be performed by the pro
cessor or by multiple processors within the computing
device, or performed by a processor external to the com
puting device. In some examples, the processor 108 is
programmedto execute instructions such as those illustrated
in accompanying FIGS. 5-7. Additionally or alternatively,
Some examples may program the processor 108 present a
seamless experience in a user interface (“UI), e.g., the UI
shown in FIGS. 3-4B. Moreover, in some examples, the
processor 108 represents an implementation ofanalog tech
niques to perform the operations described herein. For
example, the operations may be performed by an analog
client computing device 100 and/or a digital client comput
ing device 100.
0028. The presentation components 110 visibly or audi
bly present information on the computing device 100.
Examples ofdisplay devices 110 include, without limitation,
computer monitors, televisions, projectors, touch screens,
phone displays, tablet displays, wearable device Screens,
televisions, speakers, vibrating devices, and any other
devices configured to display, Verbally communicate, or
otherwise indicateoutput to a user. The transceiver 112 is an
antenna capable of transmitting and receiving radio fre
quency (“RF) signals. One skilled in the art will appreciate
and understand that various antennae and corresponding
chipsets may be used to provide communicative capabilities
between the client computing device 100 and other remote
devices. Examples are not limitedto RF signaling, however,
as various other communication modalities may alterna
tively be used.
0029 I/O ports 116 allow the client computing device
100 to be logically coupled to other devices and I/O com
ponents 118, some of which may be built in to client
computing device 100 while others may be external. Spe
cific to the examples discussed herein, I/O components 118
include a microphone 122, a camera 124, one or more
sensors 126, and a touch device 128. The microphone 1224
captures audio from the user 102. The camera 124 captures
images or video of the user 102. The sensors 126 may
include any number ofsensors on or in a mobile computing
device, electronic toy, gaming console, wearable device,
television, vehicle, or other computing device 100. Addi
tionally, the sensors 126 may include an accelerometer,
magnetometer, pressure sensor, photometer, thermometer,
global positioning system (“GPS) chip or circuitry, bar
scanner, biometric scanner (e.g., fingerprint, palm print,
Jul. 27, 2017
blood, eye, or the like), gyroscope, near-field communica
tion (“NFC) receiver, or any other sensor configured to
capture data from the user 102 or the environment. The
touch device 128 may include a touchpad, track pad, touch
screen, other touch-capturing device capable oftranslating
physical touches into interactions with Software being pre
sented on, through, or by the presentation components 110.
The illustrated I/O components 118 are but one example of
I/O components that may be included on the client comput
ing device 100. Other examples may include additional or
alternative I/O components 118, e.g., a Sound card, a vibrat
ing device, a scanner, a printer, a wireless communication
module, or any other component for capturing information
related to the user or the user's environment.
0030 The computer-storage memory 120 includes any
quantity of memory associated with or accessible by the
computing device 100. The memory area 120 may be
internal to the client computing device 100 (as shown in
FIG. 1), external to the client computing device 100 (not
shown), or both (not shown). Examples of memory 120 in
include, without limitation, random access memory (RAM);
read only memory (ROM); electronically erasable program
mable readonly memory (EEPROM); flash memory orother
memory technologies; CDROM, digital versatile disks
(DVDs) or other optical or holographic media; magnetic
cassettes, magnetic tape, magnetic disk storage or other
magnetic storage devices; memory wired into an analog
computing device; or any other medium for encoding
desired information and for access by the client computing
device 100. Memory 120 may also take the form ofvolatile
and/or nonvolatile memory; may be removable, non-remov
able, or a combination thereof, and may include various
hardware devices (e.g., Solid-state memory, hard drives,
optical-disc drives, etc.). Additionally or alternatively, the
memory 120 may be distributed across multiple client
computing devices 100, e.g., in a virtualized environment in
which instruction processing is carried out on multiple
devices 100. For the purposes ofthis disclosure, “computer
storage media,” “computer-storage memory,” and
“memory do not include carrier waves or propagating
signaling.
0031. The computer-storage memory 120 stores, among
other data, various device applications that, when executed
by the processor 108,operate toperform functionality on the
computing device 100. Examples of applications include
gaZe detector applications, instant messaging applications,
electronic-mail application programs, web browsers, calen
dar application programs, address book application pro
grams, messaging programs, media applications (e.g., con
tentbrowsingapplications, news sites/portals, various media
types), location-based services, search programs, and the
like. The applications may communicate with counterpart
applications or services such as web services accessible via
the network 106. Forexample, the applications may include
client-operating applications that correspond to server-side
applications executing on remote servers or computing
devices in the cloud.
0032 Specifically, instructions stored in memory 120
comprisea communications interface component 130, a user
interface component 132, and a gaze detector 134. In some
examples, the communications interface component 130
includes a network interface card and/or a driver for oper
ating the network interface card. Communication between
the client computing device 100 and other devices may

US 2017/0212583 A1
occur using any protocol or mechanism over a wired or
wireless connection, or across the network 106. In some
examples, the communications interface component 130 is
operable with RF and short-range communication technolo
gies using electronic tags, such as NFC tags, BLU
ETOOTHR) brand tags, or the like. In some examples, the
communications interface component 130 communicates
with a remote content store, which may be in a remote
device (such as a server) or cloud infrastructure. The remote
content store, forexample, may receive, store, and send data
related to content analytics, user analytics, and/or pattern
data (which may relate to one or more users).
0033. In some examples, the user interface component
132 includes a graphics card for displaying data to the user
and receiving data from the user. The user interface com
ponent 132 may also include computer-executable instruc
tions (e.g., a driver) for operating the graphics card to
display gaze detector responses (which may include updat
ing the UI context) and corresponding images oraudio on or
through the presentation components 110. The user interface
component 132 may also interact with the various sensors
126 to both capture and present information through the
presentation components 110.
0034. The gaze detector 134, when executed, receives
visual data through the camera 124 and/or sensors 126,
where the visual data may include a user's gaze. The terms
"gazedetector” and "gazelocator” maybeusedinterchange
ably throughout. The gaze detector 134 detects the user's
eyes (shown below in 103 FIG. 3) or a particular portion
thereof. Such as the pupil, cornea, iris, Sclera, etc. Other
examples use the camera 124 and/or 126 Sensors to capture
the user's 102 body position, motions, and/or facial expres
S1O.S.
0035. The camera 124 may estimate the exact area ofthe
presentation component 110 (hereascreen, forexample,and
referred to below as screen 110) at which the user 102 is
looking. In some examples, the gaze detector 134 extrapo
lates the user's gaze to position coordinates with respect to
the screen 110. The terms coordinates, pixels, and gaZe
points may be used interchangeably throughout. In this
example the gaze detector 134 receives and updates gaZe
information in a continuous and real-time manner. Other
examples utilize the gaze detector 134 to obtain gaze infor
mation continually, periodically, aperiodically, intermit
tently, at intervals, and/or in a delayed manner.
0036. In some examples, the gaze data is processed
within the client computing device 100. Other examples
may provide forgazedata (orany otherdata)to beprocessed
remotely, such as overthe network 106. Based upon thegaze
data, as discussed below in more detail, the user interface
component 132 displays data (such as web content)and may
communicate the retrieved userand environmental data over
the network 106 to remote devices, such as devices that host
the content store, which in turn may communicate data back
to the client computing device 100 or presentation compo
nent 110.
0037. In some examples, the user interface component
includes a graphics processor for displaying data to the user
and receiving data from the user. The user interface com
ponent may also include computer-executable instructions
(e.g., a driver) for operating the graphics card. Further, the
user interface component may include a display (e.g., a
touch screen display or natural user interface) and/or com
puter-executable instructions (e.g., a driver) for operating
Jul. 27, 2017
the display. The user interface component may also include
and/orinterfacewithone or moreofthe followingto provide
data to the user or receive data from the user: Speakers, a
Sound card, a camera, a microphone, a vibration motor, one
or more accelerometers, a BLUETOOTHR) communication
module, global positioning system (GPS) hardware, and a
photoreceptive light sensor. Forexample, the usermay input
commands or manipulate data by moving the computing
device in a particular way.
0038. The term “Wi-Fi as used herein refers, in some
examples, to a wireless local area network using high
frequency radio signals for the transmission of data. The
term BLUETOOTHR as used herein refers, in some
examples, to a wireless technology standard for exchanging
data over short distances using short wavelength radio
transmission. The term “cellular as used herein refers, in
Some examples, to a wireless communication system using
short-range radio stations that, when joined together, enable
the transmission of data over a wide geographic area. The
term “NFC as used herein refers, in some examples, to a
short-range high frequency wireless communication tech
nology for the exchange of data over short distances.
0039 Turning now to FIG. 2, an exemplary block dia
gram illustrates a cloud-computing environment for pulling
content from client devices and sending data to client
devices, such as for an adaptive eye-tracking user interface.
Architecture 200 illustrates an exemplary cloud-computing
infrastructure, Suitable for use in implementing aspects of
the disclosure.Architecture 200 should not be interpreted as
having any dependency or requirement related to any single
component or combination of components illustrated
therein. In addition, any number ofnodes, virtual machines,
data centers, role instances, or combinations thereofmay be
employed to achieve the desired functionality within the
Scope of examples ofthe present disclosure.
0040. The distributed computing environment ofFIG. 2
includes a public network 202, a private network 204, and a
dedicated network 206. Public network 202 may be a public
cloud, for example. Private network 204 may be a private
enterprise network or private cloud, while dedicated net
work 206 may be a third party network or dedicated cloud.
In this example, private network 204 may host a customer
data center 210, and dedicated network 206 may host an
internet service provider212. Hybridcloud 208 may include
any combination of public network 202, private network
204, and dedicated network 206. For example, dedicated
network 206 may be optional, with hybrid cloud 208 com
prised ofpublic network 202 and private network 204.
0041 Public network 202 may include data centers con
figured to host and Support operations, including tasks ofa
distributed application, according to the fabric controller
218. It will be understood and appreciated that data center
214 and data center 216 shown in FIG. 2 is merely an
example ofone suitable implementation foraccommodating
one or more distributed applications and is not intended to
Suggestany limitation as to the scope ofuse or functionality
of examples of the present disclosure. Neither should data
center 214 and data center 216 be interpreted as having any
dependency or requirement related to any single resource,
combination of resources, combination of servers (e.g.
server 220, server 222, and server 224) combination of
nodes (e.g., nodes 232 and 234), or set ofAPIs to access the
resources, servers, and/or nodes.

US 2017/0212583 A1
0042 Data center 214 illustrates a data centercomprising
a plurality of servers, such as server 220, server 222, and
server 224. A fabric controller 218 is responsible for auto
matically managing the servers and distributing tasks and
other resources within the data center 214. By way of
example, the fabric controller 218 may rely on a service
model (e.g., designed by a customer that owns the distrib
uted application) to provide guidance on how, where, and
when to configure server 222 and how, where, and when to
place application 226 and application 228 thereon. In one
example, one or more role instances of a distributed appli
cation, may be placed on one or more ofthe servers ofdata
center 214, where the one or more role instances may
represent the portions ofSoftware, component programs, or
instances ofroles that participate in the distributed applica
tion. In another example, one or more ofthe role instances
may representstored data thatis accessible to the distributed
application. In someexamples, one or more data centers 214
may act as a content store by storing content in various
forms and/or content metadata, including gaZe analytics at
the content level to generate personalized user experiences.
0043. In some examples, application 226 on server 222
may build a user profile based upon the activity ofthe user
ofthe client 100. For example, the gaze ofthe user may be
tracked, as discussed in more detail below. In various
examples, eye movement of a user may be tracked, along
with a variety ofrelated data, Such as gaze duration, speed
of eye movement, how quickly attention is shifted, and so
on. Gaze analytics based upon eye movement may be added
to a user'sprofile. Additionally, the context ofgaze data may
also be interpreted and/or added to a user's profile, such as
analyzing the context of the content. For example, the
application 226 may aggregate data for a user's profile that
the user gazed upon a window for a particular duration of
time, andthen Switchedto anotherwindow. Continuing with
this example, context data may also be added to the user's
profile based upon the userhaving first viewed a news story
that mentions a type of car, and then having viewed the
second window which also features a car ofthe same brand.
Additionally, content queued forthe user may be updated at
any time based upon Such information, which may be stored
and/or received at the application 226.
0044) When a user is looking at an image, gaZe analytics
may be associated with specific image properties (size,
landscape, contrast, palette, etc.) along with the entities
appearing in the image (persons, named/famous persons,
locations, landmarks, etc.), as well as with any other meta
data associated with the image, and may also apply to
VideoS/animations as well. In this example, accumulated
metrics (gaZe analytics) may empower statistical analysis
which may then used for advanced personalization and
adaptation to user needs. Additionally, telemetry data may
be captured/analyzed from any user's session. Examples
include what a user is looking at, what Succeeds to attract a
user's attention, what fails (both UI elements within a UI
window and ata content level. Such as specific contentitems
presented through the UI). Additionalexamples oftelemetry
data include how many times, how fast, and/or what pattern
a user used to read through a specific sentence (or other
portions ofcontent). Continuing with thatexample, this data
couldbetranslated in to readability score (regardingthe user
and/or the text). In another example, cross-page and/or
Jul. 27, 2017
cross-session content (Such as news and/or fiction stories)
may be formulated based on specific attention-received
patterns.
0045. In some examples, application 228 on server 222
may generate and/or queue content for the user ofclient 100
based upon a comparison of the user's profile with the
profiles ofother users stored in, or accessed by, application
222. Forexample, the user's demographic data (age, gender,
race, location, etc.) may be compared to theprofiles ofother
users whose profiles share similar characteristics. In various
examples, any Suitable criteria may be utilized to determine
what content may be most relevant and/or desirable for the
user based upon the profiles of similar users. For example,
if the user gazes upon content featuring certain types of
stocks, then othercontent (even ifseemingly unrelated) Such
as political articles or technology gadget updates may be
delivered and/or queued. A relation may used, being based
upon users in thesameage rangeand geographic region who
have expressed an interest in Such stocks, havingprofileand
relational data that indicates a tendency to have an interest
in politics or technology gadget updates. Relational data
may be store and/or utilized in the application 228 (or any
other remote location/device) and/or on the client 100. In
Some examples, non-relational data can be stored as well in
the form of serialized objects, document objects, binary
data, XML, JSON, BLOBS etc.
0046 Data center 216 illustrates a data centercomprising
a plurality ofnodes, such as node 232 and node 234. One or
more virtual machines may run on nodes ofdata center 216,
such as virtual machine 236 of node 234 for example.
Although FIG. 2 depicts a single virtual node on a single
node ofdata center216,any numberofvirtual nodes may be
implemented on any number of nodes ofthe data center in
accordance with illustrative examples of the disclosure.
Generally, virtual machine 236 is allocated to role instances
ofa distributed application, or service application, based on
demands (e.g., amount of processing load) placed on the
distributed application. As used herein, the phrase “virtual
machine' is not meant to be limiting, and may refer to any
Software, application, operating system, or program that is
executed by aprocessing unitto underlie the functionality of
the role instances allocated thereto. Further, the virtual
machine 236 may include processing capacity, storage loca
tions, and otherassets within the data center 216 to properly
Support the allocated role instances.
0047. In operation, the virtual machines are dynamically
assigned resources on a first node and second node of the
data center, and endpoints (e.g., the role instances) are
dynamically placed on the virtual machines to satisfy the
current processing load. In one instance, a fabric controller
230 is responsible for automatically managing the virtual
machines running on the nodes of data center 216 and for
placing the role instances and other resources (e.g., software
components)within the data center216. By way ofexample,
the fabric controller 230 may rely on a service model (e.g.,
designed by a customerthat owns the service application) to
provide guidance on how, where, and when to configure the
virtual machines, such as virtual machine 236, and how,
where, and when to place the role instances thereon.
0048. As discussed above, the virtual machines may be
dynamically established and configured within one or more
nodes ofa data center. As illustrated herein, node 232 and
node 234 may be any form ofcomputing devices, such as,
for example, a personal computer, a desktop computer, a

US 2017/0212583 A1
laptop computer, a mobile device, a consumer electronic
device, server(s), the computing device 100 ofFIG. 1, and
the like. In one instance, the nodes host and Support the
operations of the virtual machines, while simultaneously
hosting other virtual machines carved out for Supporting
othertenants ofthe data center216, such as internal services
238 and hosted services 240. Often, the role instances may
include endpoints ofdistinct service applications owned by
different customers.
0049. Typically, each ofthe nodes include, oris linked to,
Some form ofa computing unit (e.g., centralprocessing unit,
microprocessor, etc.)to Support operations ofthe component
(s) running thereon. As utilized herein, the phrase “comput
ing unit' generally refers to a dedicated computing device
with processing powerand storage memory, which Supports
operating software that underlies the execution ofsoftware,
applications, and computer programs thereon. In one
instance, the computing unit is configured with tangible
hardware elements, or machines, that are integral, or oper
ably coupled, to the nodes to enable each device to perform
a variety of processes and operations. In another instance,
the computing unit may encompass a processor (not shown)
coupled to the computer-readable medium (e.g., computer
storage media and communication media) accommodated
by each ofthe nodes.
0050. The role instances that reside on the nodes support
operation ofserviceapplications,and may be interconnected
via application programming interfaces (APIs). In one
instance, one or more of these interconnections may be
establishedviaa networkcloud, such aspublic network 202.
The network cloud serves to interconnect resources, such as
the role instances, which may be distributably placed across
various physical hosts, such as nodes 232 and 234. In
addition, the network cloud facilitates communication over
channels connecting the role instances ofthe service appli
cations running in the data center 216. By way ofexample,
the network cloud may include, without limitation, one or
more local area networks (LANs)and/or widearea networks
(WANs). Such networking environments are commonplace
in offices, enterprise-wide computer networks, intranets, and
the Internet. Accordingly, the network is not further
described herein.
0051 Although described in connection with an exem
plary computing system environment, examples ofthe dis
closure are capable ofimplementation with numerous other
general purpose or special purpose computing system envi
ronments, configurations, or devices.
0052 Examples ofwell-known computing systems, envi
ronments, and/or configurations that may be suitable foruse
with aspects ofthe disclosure include, butare not limited to,
mobile computing devices, personal computers, servercom
puters, hand-held orlaptop devices, multiprocessor Systems,
gaming consoles, microprocessor-based systems, set top
boxes, programmable consumer electronics, mobile tele
phones, mobile computingand/orcommunication devices in
wearable or accessory form factors (e.g., watches, glasses,
headsets, or earphones), network PCs, minicomputers,
mainframe computers, distributed computing environments
that include any of the above systems or devices, and the
like. Such systems ordevices may acceptinput from theuser
in any way, including from input devices such as a keyboard
or pointing device, via gesture input, proximity input (Such
as by hovering), and/or via Voice input.
Jul. 27, 2017
0053 Examples ofthe disclosure may be described in the
general context ofcomputer-executable instructions, such as
program modules, executed by one or more computers or
other devices in software, firmware, hardware, or a combi
nation thereof. The computer-executable instructions may
be organized into one or more computer-executable com
ponents or modules. Generally, program modules include,
but are not limited to, routines, programs, objects, compo
nents, and data structures that perform particular tasks or
implement particular abstract data types. Aspects of the
disclosure may be implemented with any number and orga
nization of Such components or modules. For example,
aspects of the disclosure are not limited to the specific
computer-executable instructions orthe specific components
or modules illustrated in the figures and described herein.
Other examples of the disclosure may include different
computer-executable instructions or components having
more or less functionality than illustrated and described
herein.
0054. Inexamples involvingageneral-purpose computer,
aspects of the disclosure transform the general-purpose
computer into a special-purpose computing device when
configured to execute the instructions described herein.
0055 FIG. 3 illustrates a block diagram 300 where a
device 302 utilizes a camera 304 to track a user's gaze 306
by monitoring the eyes 103 of the user 102. Any part of a
user's eyes (pupil, retina, iris, Sclera, etc.) may be moni
tored. Any number ofeyes 103, such as one or both, may
serve to represent a user's gaze306. In some examples, eyes
103 from different individuals or entities may be monitored
together, Such as forcollaborativegazing. Additionally, gaZe
points may be based on gaze direction determined through
facial recognition, either in conjunction with the eye detec
tion or independent thereof.
0056. As discussed above, any type ofcamera 304 (web
cam, light-field camera, Zoom-lens, 3-d camera, Kinect(R),
RealSense, etc.) or sensor (infrared, etc.) may be used to
monitor a gaze 306. The gaze 306 may be captured in
real-time, delayed, archived, etc. Fordigital video examples,
Some or all of the frames of the gaze monitoring may be
utilized. Blinking may be ignored based upon any type of
suitable threshold of blink time occurring at an interval.
Additionally, the device 302 may be any type of display,
Such as a touch screen, holographic display, or virtual
display.
0057. In someexamples, UI windows 308,310,312,314,
316,318,320, and322 are displayed on the device302. The
camera 304 detects the gaze 306 from the eyes 103 ofthe
user 102. Here, the user 102 has a gaze 306 fixed upon UI
window 310, depicted as containing a report. Continuing
with this example, the gaze 306 causes the UI window to
come into focus. By contrast, the other UI windows 308,
312,314,316,318,320, and 322 arenot in focus (i.e., focus
is suspended). In this example, these UI windows are
depicted in a blurred manner (i.e., being out-of-focus). In
other examples, the UI windows not being gazed upon may
utilize any type ofindicator that they are not in focus (such
asbeing in grayscale, shrunk, static/inanimate,etc.). In some
examples, initially there are no UI windows in focus;
whereas, other examples may automatically bring one or
more UI windows into focusbased upon random selection or
any suitable factors such as a user's 102 history or news
worthiness. When a gaze 306 shifts to a UI window (also
known as an on-focus event), the interface may smoothly

US 2017/0212583 A1
Suspend any other content and/oractivity (such as animation
to promote content or navigate through content) previously
active in a different UI window (orelsewhere on the screen).
Continuing with this example, the interface may smoothly
initiate animation for the on-focus event, along with serving
related contentsequentially whileuserinteractions arebeing
captured.
0.058. In some examples, gaZe analytics may be gener
ated, either on the client device itselfor by a remote device
(e.g., a backend server), and used to personalize the user
experience. Gaze analytics may be generated, for example,
by analyzing the time a user spends on a particular portion
ofa UI window, Such as a pause or slow-down for specific
text ora graphic. The pause or slow-down may be measured
against other Such instances to build associations with
respect to a profile associated with the user profile, regard
less of whether there may already be historical data from
previous sessions or not. For example, a users interest in
automobiles (e.g., a particular car or a car brand) may be
reflected with an update to the user's profile based upon this
information, such as where a user slows their content
viewing upon seeing a particular car mentioned, photo
graphed, or appearing in a video. Videos or audio may be
paused or removed if a user gazes away, although some
examples provide that the video or audio resumes upon the
gaze returning. In some examples, advertisements may also
be provided using any of the techniques provided herein.
0059 Another example utilizes gaze analytics for the UI
arrangement itself, such as where the interface may know
that the specific user tends to focus on top-right corner (for
any reason independent ofthe content served to the user). In
this example, the interface may promote the most relevant
andpotentially valuablecontent forthe specific user, Such as
to the top-rightmost elements ofthe UI. In anotherexample,
the interface may test (A/B testing) specific structural alter
natives of the overall UI (for instance, how many UI
windows fit a screen/display area, UI window size, vertical
vs. horizontal, etc). Testing may also be executed to deter
mine from a number ofUI alternatives which one(s) may (or
are most likely to) attract higher levels of user attention/
engagement, Such as through gaze-driven content experi
CCCS.
0060. In someexamples, gaze data may betranslated into
interestlevels in content (regarding specific and/orgroups of
content). For example, a longer gaze on a piece of content
may translate into a higher content interest level than a
shortergaze. Additionally, various weighting criteria may be
utilized. Forexample, a user whose profile is deemed highly
relevant may be afforded more weight in affecting the
interest profile of a content item as compared with a user
whose profile is deemed less relevant. Continuous measure
ment of interest may be performed across a user's session
and/or with respect to specific UI elements and/or content
items, including (but not limited to) sentiment capture/
analysis/modeling.
0061 Additionally, a user profile, including but not lim
ited to historical and/or session data, may include data
derived across other platforms, software, and input mecha
nisms (such as mouse, keyboards, touch screen, etc.) to
develop a more accurate and robust user profile. For
example, a user's prior keyboard/mouse and touch screen
profile data may be used to display tailored content in UI
windows and/or place tailored content in the UI windows
queues, and/or vice versa.
Jul. 27, 2017
0062. The content of UI windows 308, 310, 312, 314,
316, 318,320, and322 may changeor rotatebased upon any
number of factors. As discussed below, content in a UI
window may auto-scroll upon receiving a gaze. Addition
ally, media (Such as videos or audio files) may await a gaZe
in order to begin playing, or may play without sound, and/or
ata Smaller size. Intheseexamples,agaze couldactivate the
Video playing, initiatethe video's Sound, and/orincrease the
video's size. In other examples, a web link (or uniform
resource locator (URL) or similar resources) may be
selected and/or visited upon receiving a gaze, which may
include additional logic, Such as at least X milliseconds of
duration and/or combined with a voice command (such as
with NLP). For example, a URL/hyperlink that receives a
gaze for a particular content item may be utilized to trigger
specialized prompts (micro-animated, inline panels, etc.)
that provide the user with the ability to view more informa
tion regarding the content item that was or is still being
gaZed.
0063. TheUI windows 308,310,312,314,316,318,320,
and 322 may have additional content queued behind the
current content being displayed in the UI window. For
example, while UI window 310 may currently display a
financial report, content from additional categories ortopics
(sports, news, cars, etc.) may be queued up behind the
current content, such as in UI window 310. The content of
one or more UI windows (including queued content) may be
stored locally or obtained remotely, such as from the cloud
ora server (orgroup ofservers). Auser's gaze, even without
historical data, may be used to begin customizing the user
experience. Forexample, a new user with no data may gaZe
upon a news story, and when the story ends, the gaze shifts
to a UI window with contentabout a particularcar. Aprofile
may bebuilt as soon as the userbegins gazing upon content.
Additionally, gaze data relative to the location of updated
content may be analyzed. Content in the queue may be
brought to the forefront ofa UI window, removed from the
forefront, moved forward or backward in the queue, and/or
removed entirely from the queue. The content within a
queue may be adapted in real-time as the user interacts with
one or more UI windows. In addition, just-in-time opera
tions among queues may be implemented. For example,
where a user focuses on specific type ofcontent, the overall
set of content across queues may self-organize to better
satisfy the implied preferences of the user.
0064. Additionally, if content the user was previously
viewing (but the user's gaze shifted away) is suddenly
obscured, the gaze location may be stored for future use
should the gaze return to the UI window. The interface
described herein may be implemented at the operating
system level, built into web browsers, apps for smart
devices, stand-alone software, or built-in with respect to
hardware (such as a camera).
0065 FIG. 4A illustrates a block diagram 400A of the
device 302 whose camera 304 monitors the location of the
user'sgaze306. Here, the user'sgaze306 has switched from
UI window 310 displayinga report to UI window 314 where
a text document is being accessed. The previously-gazed UI
window 310 is no longerin focus. In this example, the report
in UI window 310 may animate, such as showing compu
tations and a graph being updated (upon coming into focus)
to show the evolution of the data. Some examples may
restrict the animation to only data that was updated since
previously going out-of-focus.

US 2017/0212583 A1
0066. In some examples, if the gaze is removed, the
report may instantly revert to an out-of-focus state. In other
examples, ifthe gaze is removed, the report may regress to
an out-of-focus state in an animated fashion. In some
examples, a confirmation indicator may also be displayed to
warn the user that UI window 310 will revert to an out-of
focus state within a certain amount oftime. Additionally, a
warning may be displayed that the previous state ofthe UI
window may be lost if the windows goes out-of-focus.
0067 FIG. 4B illustrates a block diagram 400B utilizing
the device 302 whose camera 304 monitors a user's shifted
gaze 306 where the user's gaze 306 has switched to UI
window 314 where a text document is accessed, while the
previously-gazed UI window 314 Window is no longer in
focus. Additionally, UI window 314 may retain the last
location within the document if the window goes out-of
focus.
0068. Upon comingback into focus, UI window 314 may
resume the last location within the document ifthe window
comes back into focus again, upon receiving the user's gaZe
again. Other examples may revert UI window 314 back to
the beginning of the document, or some other default
location. Otherexamples may revert UI window 314 to one
of one or more checkpoint locations based upon a previ
ously-viewed location within the document, or at a location
close to where the gaze ended (even if the checkpoint
location is further than the user's gaze had previously
reached).
0069 FIG. 5 is a flow chart diagram that illustrates
utilizing a user's gaze to bring a UI window into focus. As
shown at block 502, a collection of UI interfaces are
displayed or refreshed. A user's gaze is tracked by the gaZe
detector 134. Agaze upon oneofthe UI windows is awaited
until a gaze is received, as shown at block 504. The gaze
detector 134 checks—either periodically or conditionally—
to see whether a gaze has been received. If not, the gaZe
detector 134 continues to wait, as shown atblock504. Once
a gaze has been received on a UI window, as shown at block
506, a check is performed to see whether the user gaze has
left the UI window, as shown atblock508. The length ofthe
user's gaze may be used, for example, to differentiate a
quick glance from a longer gaze.
0070 If the gaze leaves the UI window, the interface
returns to awaiting a gazebackatblock504. Ifthegaze does
not leave the UI window, the gaze detector 134 performs a
checkto see whethera thresholdamount oftimehas elapsed,
as shown at block 510. If the threshold amount of time has
not yet been met, the gaze detector 134 returns to block 506
to make sure that the gaze does not leave the UI window
prior to the threshold amount of time. If the threshold
amountoftimehas been met, the UI window is brought into
focus or activated. For example, the threshold amount of
time may be utilized to make sure the UI window is not
taken out of focus due to, for example, blinking or an
inadvertent dart of the eyes.
changingthe focus among UI windows based upon a change
in user gaze. As shown at block 602, a UI window is in
focus. As shown at block 604, a check is performed to see
whether the gaze has left the card in focus. If the gaze has
not left the UI window, the interface returns to analyzing the
UI window in focus as shown atblock 602. Ifthe gaze leaves
the UI window at 604, the UI window is taken out offocus
as shown at block 606. As shown at block 608, a gaze is
Jul. 27, 2017
awaited. As shown at block 610, if no gaze has yet been
received, the interface returns to 608. Ifa gaze is received
upon a UI window, as shown at block 610, the UI window
receiving the gaze is brought into focus as shown at block
612.
auto-scroll speed adjustment based upon a user eye move
ment. As shown at block 702, a UI window is in focus. As
shown at block 704, the UI window begins an auto-scroll
movement. The auto-scroll may be (for example) a vertical,
horizontal, or any other type of content advancement that
automatically advances for a user's reading. In addition to
text, other content such as images and videos may be
displayed and auto-scrolled. A user's historical data, if
available, may be used to determine the auto-scroll rate.
Other ways to determine an initial auto-scroll rate may
include, for example, a default auto-scroll rate or session
data. Auto-scroll logic may also include a predefined value
for quick independent stops in the scrolling experience.
Scrolling, for example, may be vertical, horizontal, forward
and/or backward. Session data may include, for example,
any actions the user has performed since the current inter
active session.
0073. As shown atblock 706, a check is performed to see
whether the auto-scroll is moving too fast relative to the
user's reading speed. For example, the check determines if
the user's reading speed is movingtoo close to the top ofthe
auto-scrolling text (ifthe text is scrolling downward). Ifthe
user's eye movement indicates at 706 auto-scrolling text is
movingtoo fast(e.g.,theuser'sgazegets too close ofthetop
of the auto-scrolling text), as shown at block 708 the
auto-scroll speed is reduced.Theauto-scroll speed reduction
may be adjusted to match the current read speed, user
historical data, and/or any other suitable criteria. The inter
face then returns to 704.
0074. If the auto-scroll at 706 is not too fast, then as
shown at block710, a checkis performed to see whetherthe
auto-scroll is moving too slow relative to the user's reading
speed. For example, the check determines if the user's
reading speed is moving too close to the bottom of the
auto-scrolling text (ifthe text is scrolling downward). Ifthe
user's eye movement indicates at 706 auto-scrolling text is
movingtoo slow, theauto-scroll speed is increasedas shown
atblock 712. Theauto-scroll speed increase may beadjusted
to match the current read speed, user historical data, and/or
any other suitable criteria. The interface then returns to 704.
If the auto-scroll at 706 is not too fast, then at 714 the
auto-scroll speed is maintained.
0075. The interface may automatically adjust the auto
scroll experience using data gathered from multiple users
across different types of content, languages, etc. For
example, the initial values (speed, duration ofbreaks, etc.)
may be based on 'optimal values derived from usage data
from highly engaged users. In another example, automatic
experimentation (A/B, multivariate testing, etc.) may be
used to test different auto-scroll values for different users
and then pick any desired values, such as optimal values
having statistical significance.
0076. Additionally, sentiment and/or emotion capture/
analysis may be performed. For example, in-document sen
timent analysis and readability analysis may help determine
the way content is prepared and packaged. This metadata
may lead to more effective ways to present and package
content (such as making content more readable, possibly

US 2017/0212583 A1
more compact, using specific high-performance patterns,
etc.). Continuing with the example, this may impact how
content is formed (such as being delivered faster, given the
insights derived from the metadata), and/or how content is
distributed (e.g., more efficiently according to 2-level per
Sonalization. For example, this may result in less bandwidth
being consumed, such as due to the compact nature of the
data/content.
0077. In some examples, as a user interacts with UI
windows (by any means, including gaze) the interface
Submits metadataand adjusts the underlying analytical mod
els serving the user's needs andpreferences. Suchas in terms
of content and content presentation. Continuing with the
example, the data may be aggregated and analyzed within
the context of the specific user, as well as against specific
user profiles, segments, markets and additional dimensions.
The interface may learn and predict which content may be
more appreciated by the userat any given time point, which
may vary over time. Put another way, the same user may
consume different types of content during weekdays VS
weekends, mornings VS evenings, when at home VS on trip,
etc. Moreover, the interface may have the ability to make
associations among different categories of content given a
specific item as an entry point (e.g., ifthe user started the
experience with sports->politics-news then the next best
content to be promoted may be life style). The interface
may use Some or all information (and/or additional infor
mation) provided by the underlying model in order to get
initialized for a specific user. For example, when an initial
personalized experience is provided, the interface may uti
lize information that describes what attracts a user's atten
tion in order to provide a second layer of just-in-time'
personalization, such as when a user looks at a car-themed
UI window for a long time and consumes the content served
through the UI window. Although cars may not be the
favorite category for the specific user, it is determined that
there is strong interest by the user, at least at this particular
moment. The interface may then silently (seamlessly) adapt
by providing more content related to cars and also directly
and/or indirectly related categories (such as car industry car
news, car reviews, etc.). Continuing with this example, the
interface may serve this content via the UI window user is
gazing at, and/orthrough other visible UI windows. In some
examples, such content may be queued in any UI window
(whether the currently in-focus UI window, or not) without
being visible to the user at that time.
Additional Examples
0078 Some examples are directed to systems, methods,
and computer-storage media for enabling a user to navigate
between content using gaZe tracking, through the following.
A presentation component presents a plurality ofcontent to
a user in user interface (UI) windows. A camera captures a
gaze of the user. Memory storing instructions for detecting
thegaze ofthe user and controlling focus ofthe UI windows
are presented to the user based on the gaze. A processor is
programmed fortracking the gaze ofthe userand determin
ing a first gaze point in a first of the UI windows corre
sponding to the gaze ofthe user. Where the first gaze point
is located in the first of the UI windows, the first ofthe UI
windows is displayed in a focused manner.
0079. Some examples are directed to systems, methods,
and computer-storage media for controlling the display of
content on a computing device through tracking of a user
Jul. 27, 2017
gaze, through the following operations. A collection of
digital content is presented in user interface (UI) windows.
The gaze of the user is monitored. Gaze points are tracked
with respect to the contentcollectionbasedon the monitored
gaze of the user. One or more UI windows are displayed
covering the gaze points in a focused manner. One or more
UI windows not coveringthegaze points are displayed in an
unfocused manner.
0080 Some examples are directed to systems, methods,
and computer-storage media for controlling interaction with
content on a computing device, through performing several
executable operations. A collection of digital content is
presented to the user in user interface (UI) windows. A face
ofa user is monitored. Gaze points on the screen are located
corresponding to the monitored face of the user. A UI
window covering the gaze points is displayed in a focused
manner. The content in the UI window displayed in the
focused manner is interacted with as the gaze points move
inside the UI window. User interaction may, forexample, be
measured/observed/differentiated where a user glanced at a
display comprising multiple UI windows, as compared with
a user having three continuous minutes of interaction with
one or more of the UI windows.
I0081 Alternatively or in addition to the other examples
described herein, examples include any combination ofthe
following:
0082 continuing to track the gaze of the user;
0.083 determining a second gaze point in a second of
the UI windows corresponding the gaze ofthe user;
0084 incident to the second gaze point being located
in the second ofthe UI windows, displaying the second
of the UI windows in a focused manner;
0085 differentiating a glance from a gaze by compar
ing gaZe time to a time threshold;
I0086 removing focus froma UI window upon removal
of the gaze from the UI window;
0.087 auto-scrolling content in a UI window being
displayed in a focused manner;
0088 utilizing a scroll rate based upon the gaze ofthe
user,
0089 utilizinga scroll ratethatisbased upon historical
databased upon the user,
0090 storing analytics with respect to a portion of
content based upon a change in the user's viewing
speed with respect to the portion of content;
0.091 switching focus from a first UI window to a
second UI window corresponding to the gaze points
moving from the first UI window to the second UI
window;
0092 tracking eye movements of the user;
0.093 identifying an animation control in at least one
of the UI windows displayed in a focused manner;
0094 automatically starting the animation control in
response to the gaze points being within a specific area
of the at least one of the UI windows;
0.095 playing a video in the at least one of the UI
windows;
0.096 playing audio in the at least one of the UI
windows;
0097 scrolling through content in the at least one of
the UI windows;
0.098 selectinga hyperlinked data in the at leastone of
the UI windows;

US 2017/0212583 A1
0099
data;
0100 content is delivered to UI windows based upon
historical data;
0101 content targeted to the user is delivered without
being based upon historical data;
0102 monitoring the face of the user through the
camera comprises:
0103 performing facial recognition to determine a
gaze direction ofthe user;
0104 identifying the gaze points based on the gaZe
direction determined through facial recognition;
0105 adding updated content in one or more UI win
dows based upon the gaze location ofthe user; and
0106 analyzing the gaze location relative to the loca
tion of the updated content.
0107 While the aspects of the disclosure have been
described in terms ofvarious examples with theirassociated
operations, a person skilled in the art would appreciate that
a combination ofoperations from any number of different
examples is also within scope of the aspects ofthe disclo
SUC.
content auto-scrolling is based upon session
Exemplary Operating Environment
0108 Exemplary computer readable media include flash
memory drives, digital versatile discs (DVDs), compact
discs (CDS), floppy disks, and tape cassettes. By way of
example and not limitation, computer readable media com
prise computer Storage media and communication media.
Computer storage media include Volatile and nonvolatile,
removable and non-removable media implemented in any
method or technology for storage of information Such as
computer readable instructions, data structures, program
modules or other data. Computer storage media are tangible
and mutually exclusive to communication media. Computer
storage media are implemented in hardware and exclude
carrier waves and propagated signals. Exemplary computer
storage media include hard disks, flash drives, and other
Solid-state memory. Communication media embody data in
a signal. Such as a carrier wave or other transport mecha
nism, and include any information delivery media. Com
puter storage media and communication media are mutually
exclusive.
0109 Although described in connection with an exem
plary computing system environment, examples ofthe dis
closure are capable ofimplementation with numerous other
general purpose or special purpose computing system envi
ronments, configurations, or devices.
0110. Examples ofwell-known computingsystems, envi
ronments, and/or configurations that may be suitable foruse
with aspects ofthe disclosure include, butare not limited to,
mobile computing devices, personal computers, servercom
puters, hand-held orlaptop devices, multiprocessor Systems,
gaming consoles, microprocessor-based systems, set top
boxes, programmable consumer electronics, mobile tele
phones, mobile computingand/orcommunication devices in
wearable or accessory form factors (e.g., watches, glasses,
headsets, or earphones), network PCs, minicomputers,
mainframe computers, distributed computing environments
that include any of the above systems or devices, and the
like. Such systems ordevices may acceptinput from theuser
in any way, including from input devices such as a keyboard
or pointing device, via gesture input, proximity input (Such
as by hovering), and/or via Voice input.
10
Jul. 27, 2017
0111 Examples ofthe disclosure may be described in the
general context ofcomputer-executable instructions, such as
program modules, executed by one or more computers or
other devices in software, firmware, hardware, or a combi
nation thereof. The computer-executable instructions may
be organized into one or more computer-executable com
ponents or modules. Generally, program modules include,
but are not limited to, routines, programs, objects, compo
nents, and data structures that perform particular tasks or
implement particular abstract data types. Aspects of the
disclosure may be implemented with any number and orga
nization of Such components or modules. For example,
aspects of the disclosure are not limited to the specific
computer-executable instructions orthe specific components
or modules illustrated in the figures and described herein.
Other examples of the disclosure may include different
computer-executable instructions or components having
more or less functionality than illustrated and described
herein.
0112 Inexamples involvingageneral-purpose computer,
aspects of the disclosure transform the general-purpose
computer into a special-purpose computing device when
configured to execute the instructions described herein.
0113. The examples illustrated and described herein as
wellasexamples notspecifically described herein but within
the scope ofaspects ofthe disclosure constitute exemplary
means forpresenting an adaptive eye-tracking interface. For
example, the elements illustrated in FIGS. 1 and 2, such as
when encoded to perform the operations illustrated in FIGS.
3-7, constitute exemplary means for presenting a collection
ofdigital content in userinterface (UI) windows, monitoring
the gaze ofthe user, tracking gaze points with respect to the
collection based on the monitored gaze ofthe user, display
ing the UI windows covering the gaze points in a focused
manner, and/or displaying the UI windows not covering the
gaze points in an unfocused manner.
0114. The order of execution or performance of the
operations in examples of the disclosure illustrated and
described herein is not essential, unless otherwise specified.
Thatis,theoperations may beperformed in any order, unless
otherwise specified, and examples of the disclosure may
include additional or fewer operations than those disclosed
herein. For example, it is contemplated that executing or
performing a particular operation before, contemporane
ously with, or after another operation is within the scope of
aspects of the disclosure.
0.115. When introducing elements of aspects of the dis
closure or theexamples thereof, the articles “a,” “an,” “the.'
and "said” are intended to mean that there are one or more
of the elements. The terms “comprising,” “including,” and
“having are intended to be inclusive and mean that there
may be additional elements other than the listed elements.
The term “exemplary” is intended to mean “an example of
The phrase “one or more of the following: A, B, and C
means “at least one ofA and/or at least one of B and/or at
least one of C.’
0116. Having described aspects of the disclosure in
detail, it will be apparent that modifications and variations
are possible without departing from the scope ofaspects of
the disclosure as defined in the appended claims. As various
changes could be made in theabove constructions, products,
media, and methods without departing from the scope of
aspects of the disclosure, it is intended that all matter

US 2017/0212583 A1
contained in the above description and shown in the accom
panying drawings shall be interpreted as illustrative and not
in a limiting sense.
What is claimed is:
1. A device for enabling a user to navigate between
content using gaze tracking, the device comprising:
a presentation component for presenting a plurality of
content to a user in user interface (UI) windows;
a camera for capturing a gaze ofthe user;
memory storing instructions for detecting the gaze ofthe
userand controlling focus ofthe UI windowspresented
to the user based on the gaze; and
a processor programmed for:
tracking the gaze ofthe user;
determining a first gaze point in a first of the UI
windows corresponding to the gaze ofthe user; and
incident to the first gaze point being located in the first
of the UI windows, displaying the first of the UI
windows in a focused manner.
2. The device of claim 1, wherein the processor is
programmed for:
continuing to track the gaze ofthe user;
determining a second gaze point in a second of the UI
windows corresponding the gaze of the user, and
incident to the second gaze point being located in the
second ofthe UI windows, displaying the secondofthe
UI windows in a focused manner.
programmed for differentiating a glance from a gaze by
comparing gaZe time to a time threshold.
programmed for removing focus from a UI window upon
removal of the gaze from the UI window.
programmed for auto-scrolling content in a UI window
being displayed in a focused manner.
6. The device of claim 5, wherein the auto-scrolling
content utilizes a scroll rate based upon the gaze ofthe user.
7. The device of claim 5, wherein the auto-scrolling
contentutilizes a scroll ratethatisbased upon historical data
based upon the user.
programmedforstoringanalytics with respecttoaportion of
content based upon a change in the user's viewing speed
with respect to the portion ofcontent.
9. A method for controlling the display of content on a
computing device through tracking ofa user gaze, compris
ing:
presenting a collection ofdigital content in user interface
(UI) windows;
monitoring the gaze ofthe user;
tracking gaze points with respect to the collection based
on the monitored gaze ofthe user;
displaying the UI windows covering the gaze points in a
focused manner, and
displaying the UI windows not coveringthegaze points in
an unfocused manner.
Jul. 27, 2017
10. The method ofclaim 9, further comprising switching
focus from a first UI window to a second UI window
corresponding to the gaze points moving from the first UI
window to the second UI window.
11. The method ofclaim 9, wherein said monitoring ofthe
gaze of the user comprises tracking eye movements ofthe
USC.
12. The method of claim 9, further comprising:
identifying an animation control in at least one ofthe UI
windows displayed in a focused manner; and
automatically startingtheanimation control in responseto
the gaze points being within a specific area of the at
least one of the UI windows.
13. The method of claim 12, wherein the animation
control comprises:
playing a video in the at least one of the UI windows;
playing audio in the at least one ofthe UI windows;
scrolling through content in the at least one of the UI
windows; or
selecting hyperlinked data in the at least one of the UI
windows.
14.The method ofclaim 9, wherein contentauto-scrolling
is based upon session data.
15. The method ofclaim 9, wherein content is delivered
to UI windows based upon historical data.
16.The method ofclaim9, wherein contenttargeted to the
user is delivered without being based upon historical data.
17. One or more computer-storage media embodied with
executable instructions for controlling interaction with con
tent on a computing device, further comprising:
presenting a collection ofdigital content to a user in user
interface (UI) windows;
monitoring a face of a user;
locating gaze points on the screen corresponding to the
monitored face ofthe user;
displaying a UI window covering the gaze points in a
focused manner; and
interactingwith thecontentin the UI window displayed in
the focused manner as the gaze points move inside the
UI window.
18.Thecomputer-storage mediaofclaim 17, wherein said
monitoring the face of the user comprises:
performing facial recognition to determine a gaze direc
tion of the user; and
identifying the gaze points based on the gaze direction
determined through facial recognition.
19.Thecomputer-storage mediaofclaim 17, wherein said
monitoring the face of the user comprises adding updated
content in one or more UI windows based upon the gaZe
location of the user.
20. The computer-storage media of claim 19, wherein
updating content in one or more UI windows based upon the
gaze location of the user further comprises analyzing the
gaze location relative to the location ofthe updated content.
k k k k k

Implicitly adaptive eye-tracking user interface

More Related Content

Similar to Implicitly adaptive eye-tracking user interface (20)

More from George Krasadakis (20)

Recently uploaded (20)

Implicitly adaptive eye-tracking user interface