Ex Parte Kreulen et al

Board of Patent Appeals and Interferences

May 14, 2008

09629831 (B.P.A.I. May. 14, 2008)

UNITED STATES PATENT AND TRADEMARK OFFICE
____________________

BEFORE THE BOARD OF PATENT APPEALS
AND INTERFERENCES
____________________

Ex parte JEFFREY THOMAS KREULEN
and WILLIAM SCOTT SPANGLER
____________________

Appeal 2007-3786
Application 09/629,8311
Technology Center 2100
____________________

Decided: May 14, 2008
____________________

Before: JAY P. LUCAS, ST. JOHN COURTENAY III, and STEPHEN C.
SIU, Administrative Patent Judges.

LUCAS, Administrative Patent Judge.

DECISION ON APPEAL

1 Application filed July 31, 2000. The real party in interest is International
Business Machines Corp.

Appeal 2007-3786
Application 09/629,831
2
STATEMENT OF CASE
Appellants appeal from a final rejection of claims 1 to 17 under
authority of 35 U.S.C. § 134. The Board of Patent Appeals and Interferences
(BPAI) has jurisdiction under 35 U.S.C. § 6(b).

Appellants’ invention relates to a method for creating a dictionary of
the terms of a document in an efficient manner. In the words of the
Appellants:
It is, therefore, an object of the present invention to provide a structure
and method for automatically creating a dictionary for clustering text
documents, including performing a first pass for each of the
documents to determine a frequency of each word in each of the
documents, creating a Hashtable of most frequently occurring words
in the documents, performing a second pass for each of the documents
to determine a frequency of phrases in each of the documents that
contain only words in the Hashtable and adding the most frequently
occurring phrases to the Hashtable, and outputting the most frequently
occurring words and the most frequently occurring phrases as the
dictionary. The determination of the frequency of each word can
include removing punctuation and case from the documents, removing
stop words from the document, replacing words in the documents with
synonyms, removing duplicate words from the documents, adding
remaining words to the Hashtable, determining the frequency of each
word remaining in the Hashtable, and removing words below a
frequency level from the Hashtable.

(Specification, page 2)
Claim 1 is exemplary:
1. A method of automatically creating a dictionary for clustering text
documents comprising:

Appeal 2007-3786
Application 09/629,831
3
inputting a maximum dictionary size;

determining a frequency of each word in each of said documents;

creating a dictionary of most frequently occurring words in said
documents as limited by said maximum dictionary size, such that said
dictionary contains less than all words in said documents;

after creating said dictionary, determining a frequency of phrases in
each of said documents that contain only words in said dictionary;

adding most frequently occurring phrases to said dictionary; and

outputting said most frequently occurring words and said most
frequently occurring phrases as said dictionary, wherein said dictionary size
limits the number of words and phrases maintained in said dictionary.

The prior art relied upon by the Examiner in rejecting the claims on
appeal is:
Kostoff US 5,440,481 Aug. 8, 1995
Kobayashi US 5,742,834 Apr. 21, 1998
Kirsch US 6,070,158 May 30, 2000
Turney US 6,470,307 B1 Oct. 22, 2002
Rejections:
R1: Claims 1, 6 and 11 stand rejected under 35 U.S.C. § 103(a) for being
obvious over Kostoff.
R2: Claims 2 to 5, 7 to 10 and 12 to 17 stand rejected under 35 U.S.C.
§ 103(a) for being obvious over Kostoff in view of Kirsch, Kobayashi and
Turney.

Appeal 2007-3786
Application 09/629,831
4

Appellants contend that the claimed subject matter is not rendered
obvious by Kostoff alone, or in combination with Kirsch, Kobayashi and
Turney for failure of the reference(s) to teach the claimed limitations. The
Examiner contends that each of the claims is properly rejected.
Rather than repeat the arguments of Appellants or the Examiner, we
make reference to the Briefs and the Answer for their respective details.
Only those arguments actually made by Appellants have been considered in
this opinion. Arguments which Appellants could have made but chose not to
make in the Briefs have not been considered and are deemed to be waived.
See 37 C.F.R. § 41.37(c)(1)(vii) (2004).2
We reverse the rejections.
ISSUE
The issue is whether Appellants have shown that the Examiner erred
in rejecting the claims under 35 U.S.C. § 103(a). The issue turns on whether
Kostoff teaches the limitation of “inputting a maximum dictionary size” and
“wherein said dictionary size limits the number of words and phrases
maintained in said dictionary.”

2 Appellants have not presented any substantive arguments directed
separately to the patentability of the dependent claims or related claims in
each group, except as will be noted in this opinion. In the absence of a
separate argument with respect to those claims, they stand or fall with the
representative independent claim. See In re Young, 927 F.2d 588, 590 (Fed.
Cir. 1991).

Appeal 2007-3786
Application 09/629,831
5
FINDINGS OF FACTS
The record supports the following findings of facts (FF) by a
preponderance of the evidence.
1. Appellants have invented a method for creating a dictionary of the terms
in a document. (Spec, p. 2, l. 5). In this context, a dictionary is a list of
the important words and phrases in a document used for automated
document classification or quick understanding of the subject matter of
the document. (Spec, p. 1, l. 10). A key feature of the independent claims
is the ability of the user to specify a maximum dictionary size which
limits the total number of phrases that will be returned. (Spec, p. 4, ll. 8
to 9).
2. The patent to Kostoff presents a method and system for compiling a
database of the words and phrases in a set of documents. (Col. 3, l. 23).
The steps include assembling the documents that will be analyzed into a
full text database. (Col. 4, ll. 13 to 14). The user then makes a list of
“trivial phrases” such as “it, to, if and but, etc. that the user wishes to
have excluded from the database” and that list is used to eliminate those
words and phrases. (Col 4, ll. 38 to 41). Thereafter the system presents
related words and phrases organized by “pervasive theme areas” (PTAs)
to the user, for selection of the phrases that the user desired to have
included in the dictionary. (Col. 4, l. 65 to col. 5, l. 65).
Appeal 2007-3786
Application 09/629,831
6
PRINCIPLES OF LAW
Appellants have the burden on appeal to the Board to demonstrate
error in the Examiner’s position. See In re Kahn, 441 F.3d 977, 985-86
(Fed. Cir. 2006) (“On appeal to the Board, an applicant can overcome a
rejection [under § 103] by showing insufficient evidence of prima facie
obviousness or by rebutting the prima facie case with evidence of secondary
indicia of nonobviousness.”) (quoting In re Rouffet, 149 F.3d 1350, 1355
(Fed. Cir. 1998)).
“In reviewing the [E]xaminer’s decision on appeal, the Board must
necessarily weigh all of the evidence and argument.” In re Oetiker, 977
F.2d 1443, 1445 (Fed. Cir. 1992).
“What matters is the objective reach of the claim. If the claim extends
to what is obvious, it is invalid under § 103.” KSR Int’l Co. v. Teleflex, Inc.,
127 S. Ct. 1727, 1742 (2007). To be nonobvious, an improvement must be
“more than the predictable use of prior art elements according to their
established functions.” Id. at 1740.

ANALYSIS
From our review of the administrative record, we find that the
Examiner has presented a prima facie case for the rejections of Appellants’
claims under 35 U.S.C. § 103(a). The prima facie case is presented on pages
3 to 15 of the Examiner’s Answer.
Appeal 2007-3786
Application 09/629,831
7
In opposition, Appellants present two main arguments, applied to both
rejections. The one argument is dispositive of the appeal. Specifically,
Appellants argue that Kostoff does not teach “inputting a maximum
dictionary size” (Br. p. 18, bottom) or “creating a dictionary of most
frequently occurring words in said documents as limited by said ‘maximum
dictionary size’… .” (Br. p. 20, bottom).
The Examiner responds by pointing to two sections of Kostoff that he
contends teach or suggest limiting the dictionary size, as claimed. (Ans., p.
15, middle). First, in column 5, line 1 to column 6, line 64, Kostoff teaches
the user selecting the preliminary set of phrases to be included in the
dictionary. The Examiner argues that by selecting some phrases, and
rejecting others, the method inputs a maximum dictionary size. We cannot
agree. The disclosed Kostoff selection method is an act of inclusion, where
the user specifies which PTAs and which phrases are to be put in the
dictionary. There is no limit on the number of PTAs or phrases imposed
either by the system or artificially by the rules under which the user is
operating. We do not feel that this suggests to the person of ordinary skill in
the art that it would be obvious for the method to build the dictionary to an
inputted maximum dictionary size.
The Examiner next points to Kostoff, column 4 lines 39 to 49, in
which a memory limitation is expressed. (Ans., p. 15, bottom). A closer
reading of this memory limitation indicates that the teaching is indeed
inapposite: “[i]n the preferred embodiment the number of trivial phrases that
can be selected is unlimited except for the limitations imposed by computer
Appeal 2007-3786
Application 09/629,831
8
memory size.” The context is the listing of the “trivial phrases” mentioned
above (FF #2). The patent is indicating that there is no limit to the number
of these phrases that are allowed, except the computer’s memory
complement. We do not find this to suggest “inputting a maximum
dictionary size” as claimed.
This teaching in Kostoff is relied upon in the rejection of each of the
independent and dependent claims.
CONCLUSION OF LAW
Based on the findings of facts and analysis above, we conclude that
the Examiner erred in rejecting claims 1 to 17.
DECISION
The Examiner's rejections of claims 1 to 17 are reversed.

REVERSED

pgc

FREDERICK W. GIBB, III
Gibb & Rahman, LLC
2568-A RIVA ROAD
SUITE 304
ANNAPOLIS MD 21401