Machine Learning Service

8/12/2019 Machine Learning Service

1/65

US008429103B1

( 1 2 ) United States Patent ( 1 0 ) P a t e n t N 0 . : U S 8 , 4 2 9 , 1 0 3 B1Aradhye t a 1 . ( 4 5 ) D a t e o f P a t e n t : A p r . 2 3 , 2 0 1 3

(54) NATIVEMACHINE LEARNINGSERVICE 7,725,419 B2 5/2010 Lee e t a 1 . . . . . . . . . . . . . . . . . . . . . . . 706/60FORUSERADAPTATIONON AMOBILE 7 , 9 0 4 , 3 9 9 B2 3 / 2 0 1 1 Subramaniam t a l .7 , 9 9 1 , 7 1 5 B2 8 / 2 0 1 1 S c h i f f e t a l .PLATFORM 8 , 0 8 5 , 9 8 2 B1 1 2 / 2 0 1 1 Kim t a 1 .8 , 0 9 5 , 4 0 8 B2 l / 2 0 1 2 S h ' l t l .( 7 5 ) I n v e n t o r s : H r i s h i k e s h A r a d h y e , S a n t a C l a r a , CA 3 , 1 3 9 , 9 0 0 B 2 3 / 2 0 1 2 G i l i f ? k e e t a a l ,

( U S ) ; Wei H u a , P a l o A l t o , CA U S ) ; ( C o n t i n u e d )R u e i - s u n g L i n , R e d w o o d C i t y , CA U S )_ _ _ FOREIGN PATENTDOCUMENTS

( 7 3 ) A s s l g n e e . Google I n c . , Mounta1n 1 e W , CA U S ) EP 2 0 4 8 6 5 6 B 1 2 0 0 1 0( * ) N o t i c e : S u b j e c t t o any d i s c l a i m e r , t h e term o f t h i s WO 2 0 1 2 / 0 0 6 5 8 0 Al V2012

p a t e n t i s e x t e n d e d o r a d j u s t e d u n d e r 3 5 OTHER UBLICATIONSU ' S ' C ' 1 5 4 ( 1 ) ) b y 0 d a y s A n o n y m o u s , W h a t s I n c r e m e n t a l L e a r n i n g andWhy s i t U s e f u l ? ,

M a r . 1 2 , 2 0 0 9 , B a i d u . c o m .( 2 1 ) A p p l ' No 13/565508 Amazon Web S e r v i c e s , C l o u d 1305iMachine L e a r n i n g o n( 2 2 ) F i l e d A u g 2 2012 D e m a n d , J a n . 1 , 2 0 1 2 , Amazon Web S e r v i c e s L L C .

. . , ( C o n t i n u e d )R e l a t e d US. A p p l i c a t i o n Data_ _ _ _ Primary Examiner*effreyA af?n

( 6 0 ) 5 2 0 3 1 3 1 1 0 2 1 1 8 1 a p p l 1 c a t 1 o n N o . 6 1 / 6 6 3 , 3 8 1 , ? l e d o n J u n . A s s i s t a n t E x a m i n e r i l a O l u d e A f o l a b i (74) Attorney, Agent, o r Firm*cDonnell Boehnen

H u l b e r t e h o f f LLP( 5 1 ) I n t . C l . r gG 06F 1 5 / 1 8 ( 2 0 0 6 . 0 1 )G 09B 1 9 / 0 0 ( 2 0 0 6 . 0 1 ) ( 5 7 ) ABSTRACT

( 5 2 ) U S , C l , D i s c l o s e d a r e a p p a r a t u s and e t h o d s f o r p r o v i d i n g machineUSPC . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 6/12 l e a r n i n g s e r v i c e s . A achine-learning s e r v i c e executing o n a

mobile latforrn can receive data related to a l u r a l i t of( 5 8 ) Field o f Classi?cation Search . . . . . . . . . . . . . . . . . . . . 7 0 6 / 1 1 , P P y7 0 6 / 1 2 60 f e a t u r e s . I n some c a s e s , t h e r e c e i v e d d a t a can i n c l u d e d a t aS e e a p p l i c a t i o n ? l e f o r C o m p l e t e S e a r c h h i s t o r y r e l a t e d t o f e a t u r e s r e c e i v e d f r o m a n a p p l i c a t i o n a n d d a t a

r e l a t e d t o f e a t u r e s r e c e i v e d from t h e m o b i l e p l a t f o r m . The( 5 6 ) References Cited m a c h i n e - l e a r n i n g s e r v i c e can d e t e r m i n e a t l e a s t one f e a t u r e

U . S . PATENTDOCUMENTSbased o n h e r e c e i v e d d a t a . The a c h i n e - l e a r n i n g s e r v i c e cang e n e r a t e a n o u t p u t b y p e r f o r m i n g a m a c h i n e - l e a r n i n g o p e r at i o n o n h e a t l e a s t one f e a t u r e . The m a c h i n e - l e a r n i n g o p e r a5 , 9 7 4 , 4 5 7 A 1 0 / 1 9 9 9 Waclawsky t a l . _ _ _6 , 2 3 3 , 4 4 8 B1 5 / 2 0 0 1 A l p e r o v i c h e t a l . t 1 o n can be s e l e c t e d fro m am ong an o p e r a t 1 o n of a n k l n g t h e2 , 3 2 2 , ; g ; k / e n g l a t l e a s t o n e f e a t u r e , a n o p e r a t i o n o f l a s s i f y i n g t h e a t l e a s t o n e

, , oss ta ~ ~ -6 , 7 0 1 , 1 4 4 B 3 / 2 0 0 4 K i r b a s e t a 1 f e a t u r e , a n o p e r a t 1 o n o f p r e d 1 c t 1 n g t h e a t l e a s t o n e f e a t u r e , a n d6 , 8 1 3 , 5 0 1 B2 1 1 / 2 0 0 4 Kinnunen t a 1 an o p e r a t 1 o n of c l u s t e r i n g t h e a t l e a s t one f e a t u r e . The7 , 0 7 6 , 2 5 5 B2 7 / 2 0 0 6 P a m p u d j e t a 1 , m a c h i n e - l e a r n i n g s e r v i c e can s e n d t h e o u t p u t .7 , 1 7 1 , 3 6 0 B2 l / 2 0 0 7 Huang t a l .7 , 2 8 6 , 8 3 4 B2 l 0 / 2 0 0 7 W a l t e r 3 0 C l a i m s , 29 Drawing S h e e t s

M o b i l e P l a t f o r mmI S y s t e m A p p l i c a t i o n 2 3 0 U s e r A p p l i c a t i o n 2 4 0 IhFRD 2 3 2 MLOO 2 3 4 FRD 2 4 2 MLOO 2 4 4

I M a c h i n e L e a r n i n g a n d A d a p t a t i o n S e r v i c e 31l l M a c h i n e - L e a r n i n g O p e r a t i o n. \ Out ut 224Mobile Feature-Related Data 222 p

Platform _System O p e r a t i n g System S o f t w a r e 2 1 4210 Mobile Platform Hardware 1


2/65

U S 8 , 4 2 9 , 1 0 3 B1P a g e 2

US. PATENTDOCUMENTS8 , 1 9 9 , 9 7 9 B2 6 / 2 0 1 2 S t e i n b e r g e t a l .2003/0118015 A1 6/2003 Gunnarsson e t a l .2 0 0 3 / 0 1 6 7 1 6 7 A1 9 / 2 0 0 3 Gong

2007/0032225 A1 2/2007 Konicek e t a l .2 0 0 8 / 0194270 A1 8 / 2 0 0 8 G r e e n b e r g2009/0163183 A1 6 / 2 0 0 9 ODonoghue t a l .2009/0224867 A1 9 / 2 0 0 9 OShaughnessy t a l .2009/0298511 A1 1 2 / 2 0 0 9 P a u l s o n2010/0138416 A1 6 / 2 0 1 0 B e l l o t t i2 0 1 0 / 0 1 5 3 3 1 3 A1* 6 / 2 0 1 0 Baldwin t a l . . . . . . . . . . . . . . . . . . 706 /112010/0278396 A1 1 1 / 2 0 1 0 M i t s u h a s h i e t a l .2011/0026853 A1 2 / 2 0 1 1 Gokturk e t a l .2011/0070863 A1 3 / 2 0 1 1 Ma t a l .2011/0125783 A1 5 / 2 0 1 1 Whale e t a l .2011/0161276 A1 6 / 2 0 1 1 Krumm t a l .2011/0184730 A1 7 / 2 0 1 1 Lebeau e t a l .2011/0264528 A1 1 0 / 2 0 1 1 Whale2011/0314367 A1 1 2 / 2 0 1 1 Chang t a l .2012/0011119 A1 1 / 2 0 1 2 B a h e t i e t a l .2012/0269436 A1 1 0 / 2 0 1 2 Mensink e t a l .2012/0308124 A1 1 2 / 2 0 1 2 Belhumeur e t a l .

OTHERPUBLICATIONSCCNA r a i n i n g , W i r e l e s s T u t o r i a l , A u g . 1 2 , 2 0 1 1 , CCNA r a i ni n g .S . D a s g u p t a , CSE 9 1 : T o p i c s i n U n s u p e r v i s e d L e a r n i n g i L e c t u r e sa n d R e a d i n g s , S p r i n g 2 0 0 8 , U n i v e r s i t y o f C a l i f o r n i a S a n D i e g o ,C o m p u t e r S c i e n c e a n d E n g i n e e r i n g D e p a r t m e n t .I . F r i e d , Coming S o o n : P h o n e s T h a t L e a r n t o R e s t When Y ou D o ,F e b . 2 9 , 2 0 1 2 , A l l T h i n g s D . c o m , D o w o n e s ompany n c .J . H . G e n n a r i e t a l . , M o d e l s o f I n c r e m e n t a l C o n c e p t F o r m a t i o n ,J o u r n a l o f A r t i ? c i a l I n t e l l i g e n c e , S e p . 1 9 8 9 , p p . l l - 6 l , v o l . 4 0 , I s s u el - 3 , E l s e v i e r S c i e n c e P u b l i s he r s L t d , E s s e x , U n i t e d K i n g d o m ,G o o g l e I n c . , G o o g l e P r e d i c t i o n A P I i D e v e l o p e r G u i d e , J u n . 2 6 ,2 0 1 2 , G o o g l e I n c .Google n c , P u b l i c C l a s s Noti?cationiAndroid e v e l o p e r s , M a r .2 2 , 2 0 1 2 , V e r s i o n A n d r o i d 4 . 0 r l , G o o g l e I n c .J . L u o , I n c r e m e n t a l L e a r n i n g f o r A d a p t i v e V i s u a l P l a c e R e c o g n i t i o ni n Dynamic I n d o o r E n v i r o n m e n t s , O c t . 2 0 0 6 , M a s t e r s T h e s i s ,S c h o o l o f C o m p u t e r S c i e n c e a n d C o m m u n i c a t i o n , R o y a l I n s t i t u t e o fT e c h n o l o g y , S E - l 0 0 4 4 S t o c k h o l m , S w e d e n .A . M a r k i t a n i s , L e a r n i n g M o b i l e U s e r B e h a v i o u r s , J u n . 2 1 , 2 0 1 1 ,M a s t e r s I n d i v i d u a l P r o j e c t , I m p e r i a l C o l l e g e L o n d o n , D e p a r t m e n to f C o m p u t i n g , S o u t h K e n s i n g t o n C a m p u s , London S W 7 2AZ n i t e dK i n g d o m .D . M c F a d d e n , C h a p t e r 5 . S y s t e m s o f R e g r e s s i o n E q u a t i o n s i L e ct u r e N o t e s f o r Economics 2 4 0 B , J a n . 1 , 1 9 9 9 , D e p a r t m e n t o f Econ o m i c s , U n i v e r s i t y o f C a l i f o r n i a , B e r k e l e y , E v a n s H a l l , B e r k e l e y ,CA.P i o t r e t . a l , D e t e c t i n g Unknown C l a s s i n a Bayes C l a s s i ? e r , M a r .9 - 1 0 , 2 0 1 0 , s t a c k o v e r ? o w . c o m Web i t e , S t a c k E x c h a n g e I n c .W. S h e n , E f ? c i e n t I n c r e m e n t a l I n d u c t i o n o f D e c i s i o n ListsiCanI n c r e m e n t a l L e a r n i n g O u t p e r f o r m N o n - I n c r e m e n t a l L e a r n i n g ? ,J a n . 1 9 9 6 , U S C / I n f o r m a t i o n S c i e n c e s I n s t i t u t e R e p o r t N o . I S I / R R9 6 - 4 3 3 , I n f o r m a t i o n S c i e n c e s I n s t i t u t e , U n i v e r s i t y o f S o u t h e r n C a l if o r n i a , M a r i n a D e l R e y , CA.A . S t y o p k i n , A u t o m a t i c P h o t o S e r v e r f o r Windows4One-clickP h o t o S o r t i n g S o f t w a r e , J a n . 1 , 2 0 1 0 , S t y o p k i n S o f t w a r e .G . Widmer e t a l . , L e a r n i n g F l e x i b l e C o n c e p t s f r o m S t r e a m s o fE x a m p l e s : F L O R A 2 : , A u g . 3 - 7 , 1 9 9 2 , p p . 4 6 3 - 4 6 7 , P r o c e e d i n g s o ft h e 1 0 t h E u r o p e a n C o n f e r e n c e o n A r t i ? c i a l i n t e l l i g e n c e (ECAI 9 2 ) ,V i e n n a , A u s t r i a , p u b . b y J o h n W i l e y o n s , I n c . , New o r k , N Y .W i k i p e d i a , L e a r n i n g t o R a n k , F e b . 1 6 , 2 0 1 2 , W i k i m e d i a F o u n d at i o n .W i k i pe d i a , L i n e a r R e g r e s s i o n , A p r . 4 , 2 0 1 2 , W i k i m e d i a F o u n d at i o n .Xiam T e c h n o l o g i e s L i m i t e d , Qualcomm A n n o u n c e s ConsiaTMS o f t w a r e S o l u t i o n f o r H i g h l y O p t i m i z e d D e v i c e O p e r a t i o n , F e b . 2 8 ,2 0 1 2 , Xiam e c h n o l o g i e s L i m i t e d .Xiam e c h n o l o g i e s L i m i t e d , S o l u t i o n s , M a r . 2 0 , 2 0 1 2 , Xiam e c hn o l o g i e s L i m i t e d .

B e a c h , A . e t a l . , F u s i n g M o b i l e , S e n s o r , a n d S o c i a l D a t a t o F u l l yE n a b l e C o n t e x t - A w a re C o m p u t i n g , H o t m o b i l e 2 0 1 0 P r o c e e d i n g s o ft h e E l e v e n t h Workshop o n M o b i l e C o m p u t i n g S y s t e m s p p l i c at i o n s , F e b . 2 2 - 2 3 , 2 0 1 0 , A n n a p o l i s , M a r y l a n d , p p . 6 0 - 6 5 , ACM, NewY o r k , New o r k .B e l l a v i s t a , P . e t a l . , Context-aware m iddleware f o r r e s o u r c e management i n t h e w i r e l e s s I n t e r n e t , IEEE T r a n s a c t i o n s on S o f t w a r eE n g i n e e r i n g , 2 0 0 3 , v o l . 2 9 , N o . 1 2 , p p . 1 0 8 6 - 1 0 9 9 .D a v i d y u k , O . e t a l . , C o n t e x t - A w a r e M i d d l e w a r e f o r M o b i l e M u l t imedia A p p l i c a t i o n s , 3 r d I n t e r n a t i o n a l C o n f e r e n c e on Mobile andU b i q u i t o u s M u l t i m e d i a (MUM2004), c t . 2 7 - 2 9 , 2 0 0 4 , p p . 2 1 3 - 2 2 0 ,C o l l e g e P a r k , M a r y l a n d , U S A .D e v a n t i e e t a l . , S m a r t P l a y l i s t : a C o n t e x t - a w a r e S y s t e m ,s u b m i t t e df o r P e r v a s i v e C o m p u t i n g C o u r s e , F a l l 2 0 1 0 , I T U n i v e r s i t y o fC o p e n h a g e n , D e c . 1 5 , 2 0 1 0 , p p . l - l 0 .H a i l p e r n , J o s h u a e t a l . . On i m p r o v i n g a p p l i c a t i o n u t i l i t yp r e d i c t i o n , P r o c e e d i n g s o f t h e 2 8 t h ACM o n f e r e n c e on HumanF a c t o r s i n C o m p u t i n g S y s t e m s ( C H I 2 0 1 0 ) , W o r k - i n - P r o g r e s s ( S p o tl i g h t o n P o s t e r s D a y s 1 & 2 ) , A p r . 1 2 - 1 3 , 2 0 1 0 , p p . 3 4 2 1 - 3 4 2 6 . ACM,A t l a n t a , GA.H e r b o r n , S . e t a l . , P r e d i c t i v e c o n t e x t a w a r e m o b i l i t y h a n d l i n g , I n t e r n a t i o n a l C o n f e r e n c e on Telecommunications 2 0 0 8 , J u n . 1 6 - 1 9 ,2 0 0 8 , p p . 1 - 6 , I E E E .J o n e s e t a l . , C o n t e x t - A w a r e R e t r i e v a l f o r U b i q u i t o u s C o m p u t i n gE n v i r o n m e n t s , M o b i l e a n d U b i q u i t o u s I n f o . A c c e s s W o r k s h o p2 0 0 3 , U d i n e , I t a l y , S e p . 8 , 2 0 0 4 , LNCS 9 5 4 , p p . 2 2 7 - 2 4 3 , S p r i n g e rV e r l a g , B e r l i n H e i d e l b e r g G e r m a n y .K h a l i l , A . e t a l . , I m p r o v i n g c e l l p h o n e a w a r e n e s s by s i n g c a l e n d a ri n f o r m a t i o n , P r o c e e d i n g s o f n t e r a c t 0 5 , S e p . , 2 0 0 5 , LNCS 3 5 8 5 , p .5 8 8 - 6 0 0 , S p r i n g e r - V e r l a g , B e r l i n H e i d e l b e r g G e r m a n y .M i r a o u i , M. e t a l . , C o n t e x t M o d e l i n g a n d C o n t e x t - A w a r e S e r v i c eA d a p t a t i o n f o r P e r v a s i v e C o m p u t i n g S y s t e m s , I n t e r n a t i o n a l J o u r n a lo f C o m p u t e r a n d I n f o r m a t i o n S c i e n c e a n d E n g i n e e r i n g , Summer2 0 0 8 , v o l . 2 , I s s u e 3 , p p . 1 4 8 - 1 5 7 .M i Z r a , Mariyam e t a l . , A m a c h i n e l e a r n i n g a p p r o a c h t o TCPt h r o u g h p u t p r e d i c t i o n , SIGMETRICS 0 7 P r o c e e d i n g s o f t h e 2 0 0 7ACM IGMETRICS n t e r n a t i o n a l Conference on Measurem ent andM o d e l i n g o f C o m p u t e r S y s t e m s , J u n . 1 2 - 1 6 2 0 0 7 , p p . 9 7 - 1 0 8 .N a g e l , K . S . e t a l . P r e d i c t o r s o f A v a i l a b i l i t y i n H o m e L i f e C o n t e x tM e d i a t e d C o m m u n i c a t i o n , ACM o n f e r e n c e o n Computer Supp o r t e d C o o p e r a t i v e Work C S W C 0 4 ) , N o v . 6 - 1 0 , 2 0 0 4 , C h i c a g o , I L ,p p . 4 9 7 - 5 0 6 , v o l . 6 , I s s u e 3 , A s s o c ia t i o n o f C o m p u t i n g M a c h i n e r y .Van H a l t e r e n e t a l . , Mobile S e r v i c e P l a t f o r m : A iddleware f o rNomadic M o b i l e S e r v i c e P r o v i s i o n i n g , IEEE I n t e r n a t i o n a l C o n f e re n c e on W i r e l e s s and Mo bile Computing, Networking and Commun i c a t i o n s ( W i M o b 2 0 0 6 ) , J u n . 1 9 - 2 1 , 2 0 0 6 , p p . 2 9 2 - 2 9 9 .Q i n , C . e t a l . , T a g s e n s e : a s m a r t p h o n e - b a s e d a p p r o a c h t o a u t o m a t i ci m a g e t a g g i n g , P r o c e e d i n g s o f t h e 9 t h I n t e r n a t i o n a l C o n f e r e n c e o nM o b i l e S y s t e m s , A p p l i c a t i o n s a n d S e r v i c e s ( M o b i S y s 2 0 1 1 ) , J u n .2 8 - J u l . 1 , 2 0 1 1 , B e t h e s d a , MD , USA.R o y , N . , A C o n t e x t - A w a r e L e a r n i n g , P r e d i c t i o n , a n d M e d i a t i o nFramework f o r R e s o u r c e Management n S m a r t P e r v a s i v e E n v i r o nm e n t s , J u l . 1 8 , 2 0 0 8 , P h . D . T h e s i s , C o m p u t e r S c i e n c e a n d E n g in e e r i n g D e p a r t m e n t , U n i v e r s i t y o f T e x a s a t A r l i n g t o n .S h a n k a r , P . e t a l . , CARS: C o n t e x t - A w a r e R a t e S e l e c t i o n f o r V e h i c ul a r N e t w o r k s , P r o c e e d i n g s o f t h e 1 6 t h IEEE I n t e r n a t i o n a l C o n f e re n c e on Network P r o t o c o l s ( I C N P ) , O r l a n d o , F L , O c t . 1 9 - 2 2 , 2 0 0 8 ,p p . 1 - 1 2 , I E E E .Wang, . e t a l . , M u s i c Recommender s y s t e m f o r W i - F i Walkman,S e p . 3 , 2 0 0 3 , T e c h n i c a l R e p o r t I C T - 2 0 0 3 - 0 1 , F a c u l t y o f E l e c t r i c a lE n g i n e e r i n g , M a t h e m a t i c s , a n d C o m p u t e r S c i e n c e , D e l f t U n i v e r s i t yo f T e c h n o l o g y , D e l f t , N L .Z i e b a r t e t a l . , L e a r n i n g a u t o m a t i o n p o l i c i e s f o r p e r v a s i v e c o m p u t i n ge n v i r o n m e n t s P r o c e e d i n g s o f t h e Second n t e r n a t i o n a l C o n f e r e n c eon Autonomic C o m p u t i n g , ICAC 2 0 0 5 , J u n . 1 3 - 1 6 , 2 0 0 5 , p p . 1 9 32 0 3 , I E E E , S e a t t l e , WA.Pawar t a l . , C o n t e x t - A w a r e Middleware S u p p o r t f o r t h e NomadicMobile S e r v i c e s on Mu lti-homed Handheld Mob ile D e v i c e s , 1 2 t hIEEE n t e r n a t i o n a l Symposium n C o m p u t e r s a n d C o m m u n i c a t i o n s ,J u l . 1 - 4 , 2 0 0 7 , p p . 3 4 1 - 3 4 8 .E . A l t m a n , C a p a c i t y o f M u l t i - S e r v i c e C e l l u l a r N e t w o r k s w i t hT r a n s m i s s i o n - R a t e C o n t r o l : A u e u e i n g A n a l y s i s , P r o c e e d i n g s o f


3/65

U S 8 , 4 2 9 , 1 0 3 B1P a g e 3

t h e 8 t h Annual I n t e r n a t i o n a l C o n f e r e n c e on Mobile Computing andN e t w o r k i n g ( M o b i C o m 0 2 ) , S e p . 2 3 , 2 0 0 2 , p p . 2 0 5 - 2 1 4 , ACM,A t l a n t a , GA.J . G u o t a l . , E s t i m a t e t h e C a l l D u r a t i o n D i s t r i b u t i o n P a r a m e t e r s i nGSM ystem Based n K-L D i v e r g e n c e M e t h o d , I n t e r n a t i o n a l Conf e r e n c e o n W i r e l e s s C o m m u n i c a t i o n s , N e t w o r k i n g , and M o b i l eC o m p u t i n g (WiCom 0 0 7 ) , S e p . 2 1 , 2 0 0 7 , p p . 2 9 8 8 - 2 9 9 1 , I E E E .

A . Hac t a l . , R e s o u r c e A l l o c a t i o n Scheme f o r Q o S P r o v i s i o n i n g i nM i c r o c e l l u l a r N e t w o r k s C a r r y i n g M u l t i m e d i a T r a f ? c , I n t e r n a t i o n a lJ o u r n a l o f N e t w o r k M a n a g e m e n t , S e p . 2 0 0 1 , p p . 2 7 7 - 3 0 7 , v o l . 1 1 ,i s s u e 5 , J o h n W i l e y o n s , L t d . , NewYork, N Y .

* c i t e d b y examiner


4/65

US. atent A p r . 2 3 , 2 0 1 3 S h e e t 1 0 1 2 9 U S 8 , 4 2 9 , 1 0 3 B1

r 1 0 0r110

R e c e i v i n g d a t a r e l a t e d t o a p l u r a l i t y o f f e a t u r e s b y a m a c h i n e - 1l e a r n i n g s e r v i c e e x e c u t i n g on a mobile p l a t f o r m[ - 1 2 0 v

[ D e t e r m i n i n g a t l e a s t o n e f e a t u r e i n t h e p l u r a l i t y o f f e a t u r e s b a s e d o nt h e d a t a u s i n g t h e m a c h i n e - l e a r n i n g s e r v i c er1 3 o vG e n e r a t i n g an o u t p u t by t h e m a c h i n e - l e a r n i n g s e r v i c e p e r f o r m i n g amachine-learning o p e r a t i o n on t h e a t l e a s t one f e a t u r e o f t h ep l u r a l i t y o f f e a t u r e s , where t h e m a c h i n e - l e a r n i n g o p e r a t i o n i ss e l e c t e d f r om among: an operation o f ranking t h e a t l e a s t onef e a t u r e , an o p e r a t i o n o f c l a s s i f y i n g t h e a t l e a s t one f e a t u r e , ano p e r a t i o n o f p r e d i c t i n g t h e a t l e a s t one f e a t u r e , and an o p e r a t i o n o fc l u s t e r i n g t h e a t l e a s t one f e a t u r e( - 1 4 0 v[ S e n d i n g t h e o u t p u t f r o m t h e m a c h i n e - l e a r n i n g s e r v i c e ]

F I G . 1 A


5/65

US. atent A p r . 2 3 , 2 0 1 3 S h e e t 2 0 f 2 9 US , 4 2 9 , 1 0 3 B1

( 1 5 0[ - 1 6 0R e c e i v i n g f e a t u r e - r e l a t e d d a t a by a m a c h i n e - l e a r n i n g s e r v i c eexecuting o n a mobile p l a t f o r m , where t h e f e a t u r e - r e l a t e d d a t aincl udes data r e l a t e d t o a f i r s t p l u r a l i t y o f f e a t u r e s received fro m ana p p l i c a t i o n executing o n t h e mobile p l a t f o r m and d a t a r e l a t e d t o asecond p l u r a l i t y o f f e a t u r e s r e c e i v e d from t h e m o b i l e p l a t f o r m , andwhere t h e f i r s t p l u r a l i t y o f f e a t u r e s and t h e second p l u r a l i t y o f

\features d i f f e r ,

T170 vD e t e r m i n i n g , u s i n g t h e m a c h i n e - l e a r n i n g s e r v i c e , among t h e f i r s t p l u r a l i t y o f f e a t u r e s and t h e second p l u r a l i t y o f f e a t u r e s based on t h ef e a t u r e - r e l a t e d d a t a

G e n e r a t i n g a n o u t p u t b y t h e m a c h i n e - l e a r n i n g s e r v i c e p e r f o r m i n g amachine-learning operation o n t h e a t l e a s t one f e a t u r eK190 VSending t h e o u t p u t from t h e m a c h i n e - l e a r n i n g s e r v i c e t o t h e

application 1

F I G . 1B


6/65


M o b i l e P l a t f o r mmS y s t e m A p p l i c a t i o n 2 3 U s e r A p p l i c a t i o nwaF R D 2 3 2 MLOO 2 3 4 i F R D 242F100 2 4 4V V| M a c h i n e L e a r n i n g a n d A d a p t a t i o n S e r v i c e _ 2 _ . _ 2 _ Q I@ a c h i n e - L e a r n i n g O p e r a t i o n

M o b i l e F e a t u r e - R e l a t e d Data 222 Output 224P l t fS i g n " ? O p e r a t i n g S y s t e m S o f t w a r em

210 Mobile P l a t f o r m Hardware3F I G . 2

Machine L e a r n i n g and A d a p t a t i o n S e r v i c e ggg

Machine L e a r n i n g and A d a p t a t i o n S e r v i c e APl 11gr H r

Machine DataL e a r n i n g A g g r e g a t i o n S e r v i c eA d a p t a t i o n a n d ManagerE n g i n e R e p r e s e n t a t i o n _ _ l _ _ 6 _Q 1 2 E n g i n e 3 1 5a H a

M L A S Network S u p p o r tM

F I G . 3


7/65


(0 0A p p l i c a t i o n 4 0 2 a A p p l i c a t i o n 4 0 2 b A p p l i c a t i o n 4 0 2 c

B u i l t - i n F e a t u r e s S e r v i c e m a n f l g e "m S e s s i o nm g e t s e l ' v l c e l l i n f o r m a t i o n@R a n k e r l n t e r f a c e ( )L e a r n i n g A P lm r e d i c t i o n l n t e r f a c e oC l a s s i f i c a t i o n l n t e r f a c e oC l u s t e r i n g l n t e r f a c e ( )l | D A R E 3 1 4 a | | D A R E 3 1 4 b |i TL e a r n i n g S e s s i o n L e a r n i n g S e s s i o n L e a r n i n g S e s s i o n

Thread 432a Thread 432b Thread 4320] M L A E 3 1 2 a | | M L A E 3 1 2 b ] IM]

F e a t u r e B u f f e r Feature B u f f e r Feature B u f f e r4 4 a 44Q 4 3 4 c

Context 436a Context 43G b Context 436a

B u i l t - I n F e a t u r e s ?QLocation ~ o c a t i o n o f mobile p l a t f o r mL o c a t i o n L a b e l - l a b e l o f l o c a t i o n (Home, Work, e t c . )A p p l i c a t i o n S t a t s - , l o c , P ( A p p l T ) , P ( A p p | l o c ) , P ( A p p l l o c & T )P e o p l e name, a d d r e s s , t i t l e , p h o n e , e m a i l , s o c i a l n e t w o r k i n gC a l l i n g i n f o r m a t i o n a l l i n g p a r t y , c a l l e d p a r t y , d i g i t sBattery/Power - l e v e l s , c h a r g i n g s t a t u sNetwork ommunication, addresses, network i n f oH i s t o r i c a l / U s a g e l n f o r m a t i o n e P u s h e s ( ) , P u l l s ( ) , l a s t save

L e a r n i n g i n t e r f a c e 5 1 1P u s h ( ) p r o v i d e d a t a t o l e a r n i n g s e s s i o nP u l l ( ) r e q u e s t i n f e r e n c e s / p r e d i c t i o n s f r o m l e a r n i n g s e s s i o nN o t i f y ( p ) ~ p r o v i d e i n f e r e n c e s / p r e d i c t i o n s t o a p p l i c a t i o nSave(M) save l e a r n i n g session t o MLoad(M) ~ l o a d model from M o l e a r n i n g s e s s i o n

F I G . 4


8/65


( ' 0 0Mobile P l a t f o r m

502User

i n t e r f a c e510 Phone D i a l e r S e t t i n g s

D i a l i n g S e t t i n g sC o n t a c t S e t t i n g sM i c r o p h o n e S e t t i n g sM i c r o p h o n e Volume

D i a l e r Change m i c r o p h o n e o u t p u t v o l u m eAppM i c r o p h o n eD i a l o g

522ManualM i c r o p h o n eSetting 1 0 g

5 2 4 ( s o f t ) ( l o u d )S m a r t S m a r t M i c r o p h o n e S e t t i n g

Micwqhme L e a r n a n d S e t M i c r o p h o n e V o l u m e B a s e ds e t t i n g o n C a l l e d P a r t y526 @ n a b l e0 i s a b l e

OK Cancel

F I G . 5 A


9/65


10/65


'/ 0 0Mobile P l a t f o r m

602

Sound S e t u pG e n e r a lM i c r o p h o n e s

M i c r o p h o n e Microphone Volu meC h a n g e m i c r o p h o n e o u t p u t v o l u m e

M i c r o p h o n eD i a l o g622 M i c r o p h o n e Volume

ManualM i c r o p h o n eS e t t i n g624

100( s o f t ) ( l o u d )S m a r t S m a r t M i c r o p h o n e S e t t i n g

MicmQhcme L e a r n a n d S e t M i c r o p h o n e V o l u m e B a s e dS e t t i n g o n C a l l e d P a r t y626 @ n a b l e0 i s a b l e

OK

F I G . 6 A


11/65


(0 0M i c L e a r n i n gAp p Model B l F s _ 2 , Q 6 3 2 3 . 4 9 .Ee t S e r v i c e ( ) _ ;_2

Q 5 _ 6 _ P r e d i c t i o n l n t e r f a c e ( 2 , MicV o l , MIC_VOL, ->CALLED_PARTY) u s h ( S 2 , M i c V o I , 8 0 ) - > ieqBI(CALLED_PARTY)>4 @I Zw; u s h ( B l 2 , CALLED_PARTY,G r a n d m a )_6? u s h ( S 2 , M i c V o l , 4 0 ) > gag u s h ( B l 2 , CALLED_PARTY, Boss)


12/65


/' 0 0

[ - 7 1 0Receiving data a t a c o n t e x t - i d e n t i f i c a t i o n system executing o n amobile p l a t f o r m , where t h e r e c e i v e d d a t a i n c l u d e s : c o n t e x t - r e l a t e dd a t a a s s o c i a t e d w i t h t h e m o b i l e p l a t f o r m and a p p l i c a t i o n - r e l a t e d d a t ar e c e i v e d from t h e m o b i l e p l a t f o r m

r 7 2 0 li d e n t i f y i n g a t l e a s t one c o n t e x t using t h e c o n t e x t - r e l a t e d d a t aa s s o c i a t e d w i t h t h e m o b i l e p l a t f o r m a n d / o r t h e a p p l i c a t i o n - r e l a t e dL d a t a r e c e i v e d f r o m t h e m o b i l e p l a t f o r mr 7 3 0 l

Based o n a t l e a s t one context i d e n t i f i e d , predicting a t l e a s t onecommunicative a c t i o n a s s o c i a t e d w i t h t h e m o b i l e p l a t f o r m byperforming a m a c h i n e - l e a r n i n g o p e r a t i o n o n t h e r e c e i v e d d a t a

( 7 4 0 lI I wReceiving an i n s t r u c t i o n t o execute a t l e a s t one communicativea c t i o n a s s o c i a t e d w i t h t h e mobile p l a t f o r m .

1

F I G . 7


13/65

US. atent A p r . 2 3 , 2 0 1 3 S h e e t 1 0 0 f 2 9 US , 4 2 9 , 1 0 3 B1

f0 0Mobile P l a t f o r m

802I n t e r f a c e

Context3 / 1 2 / 2 0 1 28:05 AM 8 R a i n yContextI d e n t i f i c a t i o n

806

S u g g e s t e dContact8 0 8 Suggested C o n t a c t

Limo D r i v e rS u g g e s t e d

PhoneNu m be r8 1 0 Suggested Number555-555-5555

i n s t r u c t i o nI n p u t812 Cancel

)

F I G . 8 A


14/65

US. P a t e n t A p r . 2 3 , 2 0 1 3 S h e e t 1 1 0 f 2 9 US , 4 2 9 , 1 0 3 B1

A i r p o r t A r r i v a l Data Record 820WLimo D r i v e r Data 824Phone Contact D ata Context-Relatedumber 828 Data 8 3 0

Data 826

N p u h r g g z r C o n t a c t D a t a C o n t e x t - R e l a t e da t a 8 3 4 8 3 6 D a t a 8 3 8

U s e r s Daughter D a t a 840

N p u h r g s z r C o n t a c t D a t a C o n t e x t - R e l a t e da t a 8 4 2 844 D a t a 8 4 6

U s e r s Wife Data 848

N p u h r g g z r C o n t a c t D a t a C o n t e x t - R e l a t e da t a 8 5 0 8 5 2 D a t a 8 5 4

F I G . 8B


15/65

US. P a t e n t A p r . 2 3 , 2 0 1 3 S h e e t 1 2 0 f 29 US 8 , 4 2 9 , 1 0 3 B1

A p p l i c a t i o n - R e l a t e d ClSf 0 0a t a 915C o n t e x t - R e l a t e d Data

910 912 914 f f - F 9 1 6C P n t e X l > C O Q I B X I |> C l a S S I ? e r R e c o g n i t i o n U s e r M o d e IS i g n a l s I d e n t i f i c a t i o n F u n c t i o n QZQ

F I G . 9 ACCIS

C o n t e x t - R e l a t e d D a t a7/ 0 2

A p p l i c a t i o n - R e l a t e d

C o l l e c t i v eM o d e la

Data 9i8a-918c22a [924a _I C o n t e x t S i g n a l 1 l - > I R e c o g n i t i o n\

F 9 2 2 ) [ 9 2 4 t h. . . C I II C o m e t : S i - g n a l 2 | ~ > I R e c o g - n i - t i o n I _ > 8 8 8 8 5 1 ; ?9 2 2 ( - 9 2 4 1 ;C o n t e x t S i g n a l N I > | R e c o g n i t i o n/

F I G . 9 B

A p p l i c a t i o nR e l a t e d Datam

C o n t e x tR e l a t e d DataQ

User ModelQ 2 9 .

C o l l e c t i v e

FIG

M o d e lm

U s e r - S p e c i ? cComm.

FACIS7/ 0 4Addresses I

940Feedback

Feedback948

G e n e r a lComm.

CommunicationAddressS u g g e s t i o n

U l

Addresses942


16/65


r 1 0 0 0r 1 0 1 0

Receiving f e a t u r e - r e l a t e d d a t a a t a machine-learning s e r v i c eexecuting o n a mobile p l a t f o r m , where t h e f e a t u r e - r e l a t e d d a t aincludes image-related data r e l a t e d t o one or m ore images receivedfrom an a p p l i c a t i o n e x e c u t i n g on t h e mobile p l a t f o r m and p l a t f o r mr e l a t e d d a t a r e c e i v e d from t h e mobile p l a t f o r m , and where t h ef e a t u r e - r e l a t e d d a t a and t h e p l a t f o r m - r e l a t e d d a t a d i f f e rr 1020 "

r G e n e r a t i n g a t i t l e r e l a t e d t o t h e one o r more images by t h e m a c h i n e - l e a r n i n g s e r v i c e p e r f o r m i n g a m a c h i n e - l e a r n i n g o p e r a t i o n on t h ef e a t u r e - r e l a t e d d a t ar 1 0 3 0 lSending the t i t l e r e l a t e d t o the one o r more images f ro m t h e\ m a c h i n e - l e a r n i n g s e r v i c e t o t h e a p p l i c a t i o n

F I G . 10


17/65

US. atent A p r . 2 3 , 2 0 1 3 S h e e t 1 4 0 f 29 US 8 , 4 2 9 , 1 0 3 B1

P l a t f o r m - R e l a t e d ( - 1 1 0 0ata 1118i m a g e - R e l a t e d D a t a 1112 1 1 1 0 f 1 1 1 4 1 1 1 6@e a t u r e - > | g a s s i ? e r i > { R Q O n l ? o nE x t r a c t i o n 9

F I G . 1 1 AC l l S( - 1 1 0 2

C o l l e c t i v eModel 1 1 Q

FANS( - 1 1 0 4I m a g e / A l b u m

T i t l eS u g g e s t i o nU lM

I m a g e - R e l a t e d D a t a P l a t f o r m - R e l a t e d Data 1118a-1118c1122a [1124a _

I U s e r 1 i m a g e s i > l R e c o g n i t i o n\ 1( 1 1 2 2 1 ) ( 1 1 2 4 b C o l l e c t i v e| U s e r 2 I m a g e s l > i R e c o g n i t i o n i> L e a r n e r

11226 11246 1 1 2 . 5 .F FU s e r N I m a g e s I > I R e c o g n i t i o n

UserS p e c i f i cf T i t l e sP l a t o r m - 1140Related Data User Mde|1113 112g F k1145

| m a g e _ FeedbackRelated Data cnective 11481 1 2 2 , 1 1 2 4 Model 1152 G e n e r a l

T i t l e s1142


18/65


( - 1 2 0 0Mobile Platform

1202U s e r KwI n t e r f a c e

1210Camera

l m a g e> 1224

PhotoA l b u m / T i t l e

S u g g e s t e dA . Album/Titleb u m S u g g e s t p h o t o a l b u m name a n d / o r t i t l e D i a l o g

S u g g e s t i o n1226 P h o t o Album S u g g e s t i o n

T i t l eS u g g e s t i o n S u g g e s t Save1228 P h o t o T i t l e S u g g e s t i o n

C a n c e lJ

F I G . 1 2 A


19/65


1200P h o t o fA l b u mT i t l e L e a r n i n gA p p Model B l F s 81 2 . 2 . 2 BE 3 2 5 2 3 . 2 5 . 1 2 5 2 getService()> ankinglmagePrc c (PHOTO_ALBUM) F A C E S , O B J S , LANDMARKS)_1P 1E_ R e q B I ( S T O R E D _ I M A G E S ) _ >


20/65


f3 0 0Receiving f e a t u r e - r e l a t e d d a t a a t a m a c h i n e - l e a r n i n g s e r v i c eexecuting o n a mobile p l a t f o r m , where t h e f e a t u r e - r e l a t e d d a t aincludes communications-related data r e l a t e d t o one or moresearches f o r e s t a b l i s h i n g e l e c t r o n i c communications r e c e i v e d froman a p p l i c a t i o n e x e c u t i n g on t h e mobile p l a t f o r m and p l a t f o r m - r e l a t e dd a t a r e c e i v e d from t h e mobile p l a t f o r m , and where t h ecommunications-related d a t a and t h e p l a t f o r m - r e l a t e d d a t a d i f f e r

K1320 7D e t e r m i n i n g w h e t h e r t h e m a c h i n e - l e a r n i n g s e r v i c e i s t r a i n e d t o p e r f o r m m a c h i n e - l e a r n i n g o pe r a t i o n s r e l a t e d t o p r e d i c t i n g outcomesof searches f o r establishing electronic c ommunications ,r1330 ,i n response t o d e t e r m i n i n g t h a t t h e m a c h i n e - l e a r n i n g s e r v i c e i st r a i n e d : r e c e i v i n g , a t t h e m a c h i n e - l e a r n i n g s e r v i c e , a r e q u e s t f o r ap r e d i c t e d outcome o f a search f o r e s t a b l i s h i n g an e l e c t r o n i cc o m m u n i c a t i o n , g e n e r a t i n g t h e p r e d i c t e d outcome b y t h e machinel e a r n i n g s e r v i c e p e r f o r m i n g a m a c h i n e - l e a r n i n g o p e r a t i o n on t h ef e a t u r e - r e l a t e d d a t a , and sending t h e p r e d i c t e d outcome t o t h ea p p l i c a t i o n 1

F I G . 13


21/65


22/65


23/65


24/65


25/65


26/65


27/65


28/65


29/65


30/65


31/65


32/65


33/65


34/65


35/65


36/65


37/65


38/65


39/65


40/65


41/65


42/65


43/65


44/65


45/65


46/65


47/65


48/65


49/65


50/65


51/65


52/65


53/65


54/65


55/65


56/65


57/65


58/65


59/65


60/65


61/65


62/65


63/65


64/65


65/65

Machine Learning Service

Documents