Ex Parte Velipasaoglu et al

Patent Trial and Appeal Board

Nov 29, 2017

13012795 (P.T.A.B. Nov. 29, 2017)

United States Patent and Trademark Office
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O.Box 1450
Alexandria, Virginia 22313-1450
www.uspto.gov
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
YAHOP117 7523
EXAMINER
TRAN, BAO G
ART UNIT PAPER NUMBER
2158
MAIL DATE DELIVERY MODE
13/012,795 01/24/2011
149838 7590 11/29/2017
MPG, LLP and EXCALIBUR IP, LLC
Albert S. Penilla
710 Lakeway Drive
Suite 200
Sunnyvale, CA 94085
Emre Velipasaoglu
11/29/2017 PAPER
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
PTOL-90A (Rev. 04/07)
UNITED STATES PATENT AND TRADEMARK OFFICE
BEFORE THE PATENT TRIAL AND APPEAL BOARD
Ex parte EMRE VELIPASAOGLU, ALPA JAIN, and
UMUT OZERTEM
Appeal 2017-007607
Application 13/012,7951
Technology Center 2100
Before DEBRA K. STEPHENS, DANIEL J. GALLIGAN, and
DAVID J. CUTITTAII, Administrative Patent Judges.
STEPHENS, Administrative Patent Judge.
DECISION ON APPEAL
Appellants appeal under 35 U.S.C. § 134(a) from a final rejection of
claims 1—20, which are all of the claims pending in the application. We
have jurisdiction under 35 U.S.C. § 6(b).
We AFFIRM.
1 According to Appellants, the real party in interest is Yahoo! Inc. App.
Br. 1.
Appeal 2017-007607
Application 13/012,795
CLAIMED SUBJECT MATTER
According to Appellants, the claims are directed to a system that
suggests candidate search queries based on an original user search query; the
suggested candidate search queries are generated by adding terms to the
original user search query (Abstract). Claim 1, reproduced below, is
exemplary of the claimed subject matter:
1. A method for synthesizing suggestions for web-search
queries, comprising the operations of:
receiving a user query as an input and segmenting the user
query into a plurality of units;
dropping at least one term from a unit using a labeling
model that combines a plurality of features, wherein at least one
of the features is derived from query logs and at least one of the
features is derived from web documents;
generating one or more candidate queries by adding at
least one term to the unit, wherein the added term results from a
hybrid method based at least in part on co-occurrence of terms in
query sessions, distributional similarity of terms in web
documents, and term substitutions from other user queries that
lead to a common uniform resource locator (URL);
scoring each candidate query based at least in part on well-
formedness of the candidate query, utility, and relevance to the
user query, wherein the relevance depends at least in part on a
similarity measure; and
storing at least one of the scored candidate queries in a
database for subsequent display in a graphical user interface for
a search engine, wherein each operation of the method is
executed by a processor.
REFERENCES
The prior art relied upon by the Examiner in rejecting the claims on
appeal is:
2
Appeal 2017-007607
Application 13/012,795
Kapur
Bailey
Ntoulas
Cucerzan
Ju
US 7,051,023 B2 May 23, 2006
US 2006/0230035 A1 Oct. 12, 2006
US 2010/0241647 A1 Sept. 23, 2010
US 7,818,315 B2 Oct. 19,2010
US 2011/0314003 A1 Dec. 22,2011
REJECTIONS
Claims 1,3,4, 7—11, 13, 14, and 17—20 stand rejected under 35 U.S.C.
§ 103(a) as being unpatentable over Kapur, Cucerzan, and Bailey (Final Act.
10-20).
Claims 2 and 12 stand rejected under 35 U.S.C. § 103(a) as being
unpatentable over Kapur, Cucerzan, Bailey, and Ju (id. at 20—22).
Claims 5, 6, 15, and 16 stand rejected under 35 U.S.C. § 103(a) as
being unpatentable over Kapur, Cucerzan, Bailey, and Ntoulas (id. at 22—
23).
Our review in this appeal is limited only to the above rejections and
the issues raised by Appellants. Arguments not made are waived (see MPEP
§ 1205.02; 37 C.F.R. §§ 41.37(c)(l)(iv), 41.39(a)(1)).
ISSUE 1
35 U.S.C. § 103(a): Claims 1-19
Appellants contend their invention as recited in claims 1 and 11 is
patentable over Kapur, Cucerzan, and Bailey (App. Br. 7—15). The issues
presented by the arguments are:
Issue la: Has the Examiner shown Cucerzan teaches or suggests an
“added term results from a hybrid method based at least in part on . . .
distributional similarity of terms in web documents,” as recited in claim 1
and similarly recited in claim 11?
3
Appeal 2017-007607
Application 13/012,795
Issue lb: Has the Examiner shown Cucerzan teaches or suggests an
“added term results from a hybrid method based at least in part on . . . term
substitutions from other user queries that lead to a common uniform resource
locator (URL),” as recited in claim 1 and similarly recited in claim 11?
Issue lc: Has the Examiner shown Cucerzan teaches or suggests
“scoring each candidate query based at least in part on well-formedness of
the candidate query,” as recited in claim 1 and similarly recited in claim 11?
ANALYSIS
Issue la
Appellants contend the Examiner erred in finding Cucerzan teaches or
suggests an “added term results from a hybrid method based at least in part
on . . . distributional similarity of terms in web documents,” as recited in
claim 1 and similarly recited in claim 11 (App. Br. 7—11; Reply Br. 3—5).
Specifically, Appellants argue Cucerzan’s added term “extensions are not
substituted terms” (Reply Br. 5 (emphasis omitted)). Further, Appellants
argue “[i]f [Cucerzan’s] extensions show[ed] ‘distributional similarity of
terms[,]’ then each of the extensions would tend to be synonyms,
hypemyms, siblings, etc.” (id (italics emphasis added and underline
emphasis omitted)).
We are not persuaded. The Examiner finds (Ans. 3^4; Final Act. 3—4,
15), and we agree, Cucerzan “generate^] the popular extensions,” i.e.,
distributionally similar terms, for a user’s search query (Cucerzan 6:18—30).
For example, the “user submits the query ‘hard disk case,”’ which
“generate^] the popular extension[] . . . ‘enclosure’” (id. ).
4
Appeal 2017-007607
Application 13/012,795
Appellants’ argument that Cucerzan’s term extensions are not
distributionally similar terms because those “extensions are not substituted
terms” (Reply Br. 5 (emphasis omitted)) is not commensurate with the scope
of the claim. Neither the claims nor the Specification define explicitly
“distributional similarity of terms in web documents,” or even that
“distributionally similar terms” are substituted terms. Appellants point to
their Specification as “describ[ing] in detail” “distributional similarity of
terms in web documents” (App. Br. 8—9); however, the Specification
provides examples without specifics as to how each variable is determined.
As such, Appellants have not persuaded us the Examiner’s findings are in
error and, specifically, that the claims require the Examiner to demonstrate
Cucerzan’s extensions are substituted terms.
Cucerzan teaches “a user submits the query ‘hard disk case’ although
a better or more accurate description (e.g., generally accepted and more
frequently used on the web) is ‘hard drive enclosure’” (Cucerzan 6:18—30).
Cucerzan “identif[ies] ‘hard disk’ as a relevant prefix” and substitutes the
extension term “case” for the previous term “drive,” resulting in the “hard
drive enclosure” candidate query (id. ). Id.
Further, Appellants’ argument that the term extensions “case” and
“enclosure” do not teach “distributional similarity of terms” because other
term extensions in Cucerzan are not each themselves synonyms (Reply Br.
5) is unpersuasive. Neither the claims nor the Specification require that a
“distributional similarity of terms in web documents” requires the terms be
synonymous (Spec. 131 (“terms that are distributionally similar tend to be
synonyms, hypemyms, siblings, etc.”) (emphasis added)). Moreover, the
Examiner does not rely on the other, non-synonym term extensions to teach
5
Appeal 2017-007607
Application 13/012,795
“distributional similarity of terms”. Rather, the Examiner finds Cucerzan
teaches a pair of synonyms, “case” and “enclosure” (Ans. 4—5 (citing
Cucerzan 6:18—37); Final Act. 4, 15), and Appellants do not proffer
sufficient persuasive evidence or arguments as to why those synonymous
terms do not teach “distributional similarity of terms in web documents.”
Accordingly, we are not persuaded the Examiner erred by finding
Cucerzan teaches or suggests an “added term results from a hybrid method
based at least in part on . . . distributional similarity of terms in web
documents,” as recited in claim 1 and similarly recited in claim 11.
Issue lb
Appellants contend the Examiner erred in finding Cucerzan teaches or
suggests an “added term results from a hybrid method based at least in part
on . . . term substitutions from other user queries that lead to a common
uniform resource locator (URL),” as recited in claim 1 and similarly recited
in claim 11 (App. Br. 8—11; Reply Br. 6—8). Specifically, Appellants argue
Cucerzan’s “other queries do not necessarily lead to a common URL” and
“nowhere does [Cucerzan] teach that these listed [other] queries lead to a
common URL” (Reply Br. 7).
We are not persuaded. Specifically, we are not persuaded by
Appellants’ argument that Cucerzan’s substitute queries would not lead to a
common URL (Reply Br. 7). The Examiner finds (Ans. 5—6; Final Act. 4—
6), and we agree, a web page, i.e., a common URL, includes “many of the
frequent words utilized in queries when a term is searched (such as ‘dog’)
may cover many of the related topics that a user may be interested in (e.g.,
adoption, sale, breeds, puppy, ...)” (Cucerzan 7:5—9; see also Cucerzan
6
Appeal 2017-007607
Application 13/012,795
5:41—52). The Examiner further finds (Ans. 5—6; Final Act. 4—6), and we
agree, Cucerzan teaches “a query such as ‘dog’ . . . retrieve[s]” related
substitute queries, “e.g., dog breeds . . . dog adoption, dogs for sale” and
“puppy” (Cucerzan 5:41—52). Because Cucerzan’s webpage includes
information responsive to Cucerzan’s substitute queries, Cucerzan teaches,
or at least suggests, those substitute queries lead to that same webpage.
Accordingly, we are not persuaded the Examiner erred by finding
Cucerzan teaches or suggests an “added term results from a hybrid method
based at least in part on . . . term substitutions from other user queries that
lead to a common uniform resource locator (URL),” as recited in claim 1
and similarly recited in claim 11.
Issue lc
Appellants contend the Examiner erred in finding Bailey teaches or
suggests “well-formedness of the candidate query,” as recited in claim 1 and
similarly recited in claim 11 (App. Br. 11—15). Specifically, Appellants
argue Bailey “nowhere explicitly or inherently teach[es] well-formedness of
the candidate query” (App. Br. 15).
We are not persuaded. The Examiner finds (Final Act. 7—9, 16—17;
Ans. 7), and we agree, Bailey teaches a “syntactical reviser 108.2 can revise
queries by making various types of syntactic changes to the original query”
(Bailey 148). The Examiner finds that Bailey’s revised queries “produce
better queries” and so Bailey teaches that revised queries are better formed
than non-revised queries, i.e., “well-formedness of the candidate query”
(Final Act. 8—9, 16—17; Ans. 7).
7
Appeal 2017-007607
Application 13/012,795
Appellants’ argument that Bailey does not “explicitly or inherently
teach well-formedness of the candidate query” (App. Br. 15) is
unpersuasive. Appellants’ description of the “well-formedness of the
candidate query” {id.), discusses “an example embodiment” of the “well-
formedness of the candidate query” (Spec. 138), rather than a limiting
definition. Furthermore, Appellants’ reproduction of cited portions of
Bailey (App. Br. 14—15), does not provide any elaboration or explanation
persuading us the Examiner erred in finding that Bailey teaches revised
queries have a well-formedness, compared to non-revised queries (Final Act.
8—9, 16—17 (citing Bailey Tflf 46, 48); Ans. 7). Accordingly, we are not
persuaded the Examiner erred by finding Bailey teaches or suggests a “well-
formedness of the candidate query,” as recited in claim 1 and similarly
recited in claim 11.
Therefore, we sustain the rejection of claims 1 and 11 under 35 U.S.C.
§ 103(a) as being unpatentable over Kapur, Cucerzan, and Bailey. We also
sustain the Examiner’s rejection of claims 3, 4, 7—11, 13, 14, and 17—19, and
we further sustain the rejections of claims 2 and 12 under 35 U.S.C. § 103(a)
as being unpatentable over Kapur, Cucerzan, Bailey, and Ju and claims 5, 6,
15, and 16 under 35 U.S.C. § 103(a) as being unpatentable over Kapur,
Cucerzan, Bailey, and Ntoulas, for which Appellants offer no additional
persuasive arguments for patentability (see App. Br. 15).
8
Appeal 2017-007607
Application 13/012,795
ISSUE 2
35 U.S.C. § 103(a): Claim 20
Appellants contend their invention as recited in claim 20, is patentable
over Kapur, Cucerzan, and Bailey (App. Br. 15—17). The issue presented by
the arguments is:
Issue 2: Has the Examiner shown Bailey teaches or suggests
“wherein the relevance depends at least in part on web-based-aboutness
similarity,” as recited in claim 20?
ANALYSIS
Appellants contend the Examiner erred in finding Bailey teaches or
suggests “wherein the relevance depends at least in part on web-based-
aboutness similarity,” as recited in claim 20 (App. Br. 15—17; Reply Br. 9).
Specifically, Appellants argue Bailey does not “explicitly or inherently teach
‘web-based-aboutness similarity’ as described in” the Specification (App.
Br. 15—16 (citing Spec. Tflf 47-48, Fig. 7)).
We are not persuaded. The Examiner finds (see Final Act. 16—17, 20;
see also Ans. 7), and we agree, Bailey teaches “[qjuery revisions that add
synonyms as disjuncts” or “add a related word” (Bailey 146), i.e., a web-
based aboutness similarity.
Appellants’ argument that Bailey does not “explicitly or inherently
teach ‘web-based-aboutness similarity’” (App. Br. 15) is without elaboration
and is therefore unpersuasive. Appellants reproduce portions of the
Specification (App. Br. 16—17 (citing Spec. Tflf 47-48, Fig. 7)) describing
features in “an example embodiment” (Spec. 143) that are not reflected in
the claims. Appellants do not present sufficient explanation as to why
9
Appeal 2017-007607
Application 13/012,795
Bailey’s query revisions, which add synonyms and related words (Bailey
146), do not teach a “web-based-aboutness similarity.” Accordingly, we are
not persuaded the Examiner erred by finding Bailey teaches or suggests
“wherein the relevance depends at least in part on web-based-aboutness
similarity,” as recited in claim 20. Therefore, we sustain the rejection of
claim 20 under 35 U.S.C. § 103(a) as being unpatentable over Kapur,
Cucerzan, and Bailey.
DECISION
The Examiner’s rejection of claims 1,3,4, 7—11, 13, 14, and 17—20
under 35 U.S.C. § 103(a) as being unpatentable over Kapur, Cucerzan, and
Bailey is affirmed.2’3
The Examiner’s rejection of claims 2 and 12 under 35 U.S.C. § 103(a)
as being unpatentable over Kapur, Cucerzan, Bailey, and Ju is affirmed.
2 Determining how “well-formed” a candidate query is encompasses a
relative, subjective judgment of the query; e.g., whether the query is a well-
made query. Although Appellants’ Specification provides “an example”
determination of the “well-formedness of the candidate query” (Spec. H 38—
42, Fig. 6), that example is not reflected by the claim language of claims 1 or
11, and so, claims 1 and 11 encompass relative, subjective judgments when
determining the well-formedness of a candidate query. In the event of
further prosecution, the Examiner may wish to review claims 1 and 11 for
compliance with 35 U.S.C. § 112, second paragraph.
3 Determining an “aboutness similarity” encompasses a relative, subjective
judgment; e.g., about how similar items queries are. Although Appellants’
Specification provides examples of determining the “aboutness similarity”
(Spec. H43, 47—48, Fig. 7), those examples are not reflected in the claim
language recited by claim 20, and so, claim 20 encompasses relative,
subjective judgments when determining the aboutness similarity of queries.
10
Appeal 2017-007607
Application 13/012,795
The Examiner’s rejection of claims 5, 6, 15, and 16 under 35 U.S.C.
§ 103(a) as being unpatentable over Kapur, Cucerzan, Bailey, and Ntoulas is
affirmed.
No time period for taking any subsequent action in connection with
this appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R.
§ 41.50(f).
AFFIRMED
In the event of further prosecution, the Examiner may wish to review claim
20 for compliance with 35 U.S.C. § 112, second paragraph.
11