SAS Institute Inc.

Patent Trials and Appeals Board

Jan 6, 2021

2019005130 (P.T.A.B. Jan. 6, 2021)

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.
15/887,037 02/02/2018 Arin Chaudhuri 04500-0070-03 1524
114605 7590 01/06/2021
Bell & Manning, LLC
2801 West Beltline Hwy.
Ste. 210
Madison, WI 53713
EXAMINER
NILSSON, ERIC
ART UNIT PAPER NUMBER
2122
NOTIFICATION DATE DELIVERY MODE
01/06/2021 ELECTRONIC
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.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
cbell@bellmanning.com
docketing@bellmanning.com
eofficeaction@appcoll.com
PTOL-90A (Rev. 04/07)

UNITED STATES PATENT AND TRADEMARK OFFICE
________________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
________________

Ex parte ARIN CHAUDHURI, DEOVRAT VIJAY KAKDE,
CAROL WAGIH SADEK, SEUNG HYUN KONG, and
LAURA LUCIA GONZALEZ
________________

Appeal 2019-005130
Application 15/887,037
Technology Center 2100
________________

Before JASON V. MORGAN, JON M. JURGOVAN, and
JOHN E. SCHNEIDER, Administrative Patent Judges.

MORGAN, Administrative Patent Judge.

DECISION ON APPEAL
STATEMENT OF THE CASE
Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals from the
Examiner’s decision to reject claims 1–30. We have jurisdiction under
35 U.S.C. § 6(b).
We AFFIRM.

1 “Appellant” refers to “applicant” as defined in 37 C.F.R. § 1.42. Appellant
identifies the real party in interest as SAS Institute Inc. Appeal Br. 3.
Appeal 2019-005130
Application 15/887,037

2

SUMMARY OF THE DISCLOSURE
Appellant’s claimed subject matter relates to computing a mean
pairwise distance value between observation vectors. Abstract.
REPRESENTATIVE CLAIM
1. A non-transitory computer-readable medium having stored
thereon computer-readable instructions that when executed by a
computing device cause the computing device to:
compute a mean pairwise distance value between a plurality of
observation vectors, wherein each observation vector of the
plurality of observation vectors includes a variable value for
each variable of a plurality of variables, wherein the mean
pairwise distance value is computed using 𝐷𝐷�2 = 2𝑁𝑁
(𝑁𝑁−1)
∑ 𝜎𝜎𝑗𝑗2
𝑝𝑝
𝑗𝑗=1 ,
where 𝐷𝐷� is the mean pairwise distance value, N is a number of
the plurality of observation vectors, p is a number of the
plurality of variables, and 𝜎𝜎𝑗𝑗2 is a variance of each variable of
the plurality of variables;
compute a scaling factor value based on a number of the
plurality of observation vectors and a predefined tolerance
value;
compute a Gaussian bandwidth parameter value using the
computed mean pairwise distance value and the computed
scaling factor value;
compute an optimal value of an objective function that includes
a Gaussian kernel function that uses the computed Gaussian
bandwidth parameter value, wherein the objective function
defines a support vector data description (SVDD) model using
the plurality of observation vectors to define a set of support
vectors and a set of Lagrange constants, wherein a Lagrange
constant is defined for each support vector of the defined set of
support vectors;
output the computed Gaussian bandwidth parameter value, the
defined set of support vectors, and the set of Lagrange
constants;
Appeal 2019-005130
Application 15/887,037

3

receive a new observation vector;
compute a distance value using the defined set of support
vectors, the defined set of Lagrange constants, and the received
new observation vector; and
when the computed distance value is greater than a computed
threshold, identify the received new observation vector as an
outlier.
REJECTION
The Examiner rejects claims 1–30 under 35 U.S.C. § 101 as being
directed to patent-ineligible subject matter. Final Act. 2–4.
PRINCIPLES OF LAW
To constitute patent-eligible subject matter, an invention must be a
“new and useful process, machine, manufacture, or composition of matter,
or [a] new and useful improvement thereof.” 35 U.S.C. § 101. There are
implicit exceptions to the categories of patentable subject matter identified
in 35 U.S.C. § 101, including: (1) laws of nature; (2) natural phenomena;
and (3) abstract ideas. Alice Corp. v. CLS Bank Int’l, 573 U.S. 208, 216
(2014). The U.S. Supreme Court has set forth a framework for
distinguishing patents with claims directed to these implicit exceptions
“from those that claim patent-eligible applications of those concepts.” Id. at
217 (citing Mayo Collaborative Servs. v. Prometheus Labs., Inc., 566 U.S.
66 (2012)). The evaluation follows a two-part framework: (1) determine
whether the claim is directed to a patent-ineligible concept, e.g., an abstract
idea; and (2) if so, then determine whether any element, or combination of
elements, in the claim is sufficient to ensure that the claim amounts to
significantly more than the patent-ineligible concept itself. See id. at 217–18.
Appeal 2019-005130
Application 15/887,037

4

Under U.S. Patent and Trademark Office USPTO guidance, we first
look to whether the claim recites:
(1) any judicial exceptions, including certain groupings
of abstract ideas (i.e., mathematical concepts, certain methods
of organizing human activity such as a fundamental economic
practice, or mental processes) (MPEP § 2106.04(a)(2); USPTO,
2019 Revised Patent Subject Matter Eligibility Guidance, 84
Fed. Reg. 50, 52 (Jan. 7, 2019) (“2019 Revised Guidance”)
(step 2A, prong one); USPTO, October 2019 Update: Subject
Matter Eligibility, 3–9, available at https://www.uspto.gov/
sites/default/files/documents/peg_oct_2019_update.pdf (Oct.
17, 2019) (“Oct. 2019 Update”)); and
(2) additional elements that integrate the judicial
exception into a practical application (MPEP §§ 2106.04(d),
2106.05(a)–(c), (e)–(h); 2019 Revised Guidance, 84 Fed. Reg.
at 54–55; Oct. 2019 Update at 10–14).
Only if a claim (1) recites a judicial exception and (2) does not
integrate that exception into a practical application, do we then look to
whether the claim:
(3) adds a specific limitation beyond the judicial
exception that is not “well-understood, routine, conventional”
in the field; or
(4) simply appends well-understood, routine,
conventional activities previously known to the industry,
specified at a high level of generality, to the judicial exception.
Appeal 2019-005130
Application 15/887,037

5

MPEP § 2106.05(d); 2019 Revised Guidance, 84 Fed. Reg. at 56; Oct. 2019
Update at 16.
ADOPTION OF EXAMINER’S FINDINGS AND CONCLUSIONS
We agree with and adopt as our own the Examiner’s findings as set
forth in the Answer and in the Final Action from which this appeal was
taken, and we concur with the Examiner’s conclusions. We have considered
Appellant’s arguments, but we do not find them persuasive of error. We
provide the following explanation for emphasis.
ANALYSIS
Step 2A, Prong One
In rejecting claim as being directed to patent-ineligible subject matter,
the Examiner determines that claim 1 recites “a process that, under its
broadest reasonable interpretation, covers mathematical formulas and
calculations but for the recitation of generic computer components.” Ans. 3–
4; Final Act. 2–3. That is, the Examiner determines that claim 1 recites
“[m]athematical concepts—mathematical relationships, mathematical
formulas or equations, mathematical calculations.” 2019 Revised Guidance,
84 Fed. Reg. at 52.
Appellant contends the Examiner erred because “[n]either
computation of a support vector data description (SVDD) model nor
identification of an outlier can be equated to merely analyzing data and
displaying results.” Appeal Br. 16. Thus, Appellant contends claim 1 is “not
directed to mathematical relationships, mathematical formulas or equations,
[or] mathematical calculations on their own per se.” Id.
Appeal 2019-005130
Application 15/887,037

6

Appellant’s arguments are not persuasive because, as the Examiner
correctly determines, the claimed “SVDD model is a group of calculations
and an objective function that results in a Gaussian bandwidth parameter to
determine if a new vector is an outlier or not.” Ans. 4. The Examiner’s
characterization of the claimed SVDD model accords with the
Specification’s disclosure that SVDD “is a machine-learning technique used
for single class classification and outlier or anomaly detection” by
partitioning a “whole space into an inlier region[,] which consists of the
region near the training data, and an outlier region[,] which consists of
points away from the training data.” Spec. ¶ 2. Specifically, the
Specification discloses that “SVDD 126 may be used to classify data stored
in dataset 1824 and to identify outliers in dataset 1824.” Id. ¶ 71.
The disclosed and claimed classification of data (i.e., determining
whether points belong or do not belong in a region based on training data) is
comparable to the patent-ineligible mathematical concept of interpolation.
See In re Gitlin, 775 F. App’x 689 (Fed. Cir. 2019). That is, determining
whether a new vector is an outlier or not interpolates the points within the
range of training data that should be classified as inliers and extrapolates any
points outside the range of training data that should also be classified as
inliers. Therefore, we agree with the Examiner that claim 1 at least recites an
abstract idea in the form of a mathematical concept (mathematical
relationships, mathematical formulas or equations, mathematical
calculations). Ans. 4.
Step 2A, Prong Two
The Examiner determines that claim 1 does not integrate the
underlying judicial exception, the mathematical concept, “into a practical
Appeal 2019-005130
Application 15/887,037

7

application because the claim only recites generic computer components as
additional recitations.” Ans. 4. Appellant contends the Examiner erred
because the “claimed subject matter is directed to solving the problem of
how to automatically compute a Gaussian bandwidth parameter value to
achieve accurate outlier identification results for new observations much
faster than previous computerized methods.” Appeal Br. 17–18. Appellant
argues “[t]he claimed process not only includes the new method for
computing the Gaussian bandwidth parameter value, but also applies the
Gaussian bandwidth parameter value to define an SVDD model and applies
the SVDD model to determine that a new observation vector is an outlier
based on a distance computed using the SVDD model.” Id. at 18; Reply Br.
2–4.
Appellant’s arguments are not persuasive because, as discussed above,
“SVDD 126 may be used to classify data stored in dataset 1824 and to
identify outliers in dataset 1824” (Spec. ¶ 71), but neither the claim nor the
Specification defines data stored in dataset 1824 in a manner that
distinguishes the data from abstract numerical data. Instead, the
Specification broadly discloses that data “stored in dataset 1824 may be a
sensor measurement or a data communication value, may be generated or
capture in response to occurrence of an event or a transaction, generated by a
device such as in response to an interaction . . .” Id. ¶ 75. Moreover,
examples disclosed in the Specification, and reproduced in the Appeal Brief,
demonstrate that the SVDD training data can be mere arbitrary points in an
abstract space, resulting in a delineation between inliner and outlier regions
that is similarly arbitrary and abstract.
Appeal 2019-005130
Application 15/887,037

8

An example of SVDD training data consisting of arbitrary points in an
abstract space is given in the Specification’s Figure 7, which is reproduced
below.

The Specification’s Figure 7 depicts a dataset having a star shape in
an x-y plane. Spec. ¶¶ 14, 95.
Applying the claimed algorithm results in the delineation of the x-y
plane into inlier and outlier regions, as depicted in the Specification’s Figure
8A, which is reproduced below.
Appeal 2019-005130
Application 15/887,037

9

The Specification’s Figure 8A depicts a dark region 800a that “shows
observation vectors not identified as outliers [(in other words, inliers)] with
[a] Guassian bandwidth parameter s = 0.614647 computed using the mean
criterion technique” of claim 1. Spec. ¶ 96. The Specification’s Figures 8B–
D depicts unclaimed variants of the claimed algorithm that use the median
criterion, peak criterion, and median2 criterion techniques respectively (with
differing Guassian bandwidth parameters). Id.
Although Appellant cites to the Figure 8A example and other
disclosed examples to argue claim 1 is “directed to solving the problem of
automatically computing a Gaussian bandwidth parameter value without
Appeal 2019-005130
Application 15/887,037

10

supervised data that does not over or underestimate a number of anomalies
or outliers” (Appeal Br. 19), the arbitrary, abstract nature of the depicted
datasets accentuates that Appellant disclosed and claims a mathematical
technique in the abstract, not in its application to a particular problem.
Table II of the Specification, which discloses computation times in
seconds to calculate Guassian parameters for widely varying datasets (e.g.,
data from an air compressor, chemical manufacturing process, network
traffic monitor, email classifier) further demonstrates that the disclosed and
claimed invention recites a mathematical algorithm itself, thus raising issues
of preemption that might not otherwise be of concern were a specific
application of the mathematical algorithm disclosed and claimed. Spec.
¶ 110; see also Appeal Br. 24–26 (reproducing Table II of the Specification,
which also compares accuracy and performance of the claimed algorithm,
which uses the mean criterion, with a variation that uses the peak criterion);
Gottschalk v. Benson, 409 U.S. 63, 72 (1972) (a claim to an invention that
“would wholly pre-empt [a] mathematical formula and in practical effect
would be a patent on the algorithm itself” is patent ineligible). “The
preemption concern arises when the claims are not directed to a specific
invention and instead improperly monopolize ‘the basic tools of scientific
and technological work.’” McRO, Inc. v. Bandai Namco Games Am. Inc.,
837 F.3d 1299, 1314 (Fed. Cir. 2016) (quoting Alice, 573 at 216).
Appellant emphasizes that the claimed method operates “much faster
than previous computerized methods,” yet achieves comparable results.
Appeal Br. 17–18; Reply Br. 2–3; see also, e.g., Appeal Br. 26 (claim 1
“provides accurate results 4 to 6 orders of magnitude faster (i.e., ~40,000 to
~2.65 million times faster) and with fewer input requirements relative to
Appeal 2019-005130
Application 15/887,037

11

existing methodologies”). “But merely calling for a mathematical concept to
be performed more efficiently or with a particular input does not amount to
an application of the mathematical concept that is patent-eligible.” Gitlin,
775 F. App’x at 691 (Fed. Cir. 2019) (citing Diamond v. Diehr, 450 U.S.
175, 182 n.7 (1981)) (emphasis added). An advance in a mathematical
concept remains in the realm of abstract ideas so long as the advance
continues to be a mathematical concept that is not integrated into a practical
application and that fails to include additional recitations that transform the
abstract idea into a patent-eligible invention. Cf. SAP Am., Inc. v. InvestPic,
LLC, 898 F.3d 1161, 1163 (Fed. Cir. 2018) (an advance in the finance field
remained patent-ineligible).
Appellant argues that “[d]irectly analogous to McRO, [claim 1 is]
directed to an automatic process that is new and non-obvious to compute the
value of the Gaussian bandwidth parameters that provides accurate outlier
identification and, as a result, is an improvement in the operation of a
computer.” Appeal Br. 34. But the patent-eligible claim in McRO was
“focused on a specific asserted improvement in computer animation, i.e., the
automatic use of rules of a particular type.” McRO, 837 F.3d at 1314. It did
not “simply use a computer as a tool to automate conventional activity.” Id.
That is, the claim in McRO was “directed to a patentable, technological
improvement over the existing, manual 3-D animation techniques.” Id. at
1316. Here, no such practical application has been claimed. The computer is
merely used as a tool to execute a mathematical algorithm. This does not
improve the computer itself. Therefore, McRO does not show that claim 1 is
patent-eligible.
Appeal 2019-005130
Application 15/887,037

12

Appellant argues that analogous to Finjan, Inc. v. Blue Coat Sys., Inc.,
879 F.3d 1299 (Fed. Cir. 2018), claim 1 recites “specific steps that
accomplish the result of a good SVDD model and accurate outlier
identification and do not merely recite the improvement.” Id. at 37. But the
specific steps in the patent-eligible invention of Finjan included “generating
a security profile that identifies suspicious code and linking it to a
downloadable.” Finjan, 879 F.3d at 1305. That is, rather than encompassing
abstract subject matter such as identification of data as inliers or outliers, the
patent-eligible claim of Finjan enabled “a computer security system to do
things it could not do before.” Id. Specifically, the security profile’s
identification of suspicious code allowed “the system to accumulate and
utilize newly available, behavior-based information about potential threats”;
thus, the patent-eligible claim was “directed to a non-abstract improvement
in computer functionality.” Id.
For these reasons, we agree with the Examiner that claim 1 does not
include additional recitations that integrate the underlying abstract idea (i.e.,
a mathematical concept) into a patent-eligible practical application. Ans. 4
Step 2B
The Examiner, having determined that claim 1 is directed to an
abstract idea, further determines claim 1 does “not include additional
elements . . . sufficient to amount to significantly more than the judicial
exception because the additional computer elements, which are recited at a
high level of generality, provide conventional computer functions that do not
add meaningful limits to practicing the abstract idea.” Final Act. 2; Ans. 4.
Appellant contends the Examiner erred because claim 1 is “directed to
a new and non-obvious process that cannot be directed to well-understood,
Appeal 2019-005130
Application 15/887,037

13

routine or conventional activities.” Appeal Br. 37. Appellant argues that “[i]t
is not the act of computing by a computer, but the specific computations that
are claimed in detail that are not well-understood, routine, conventional
activity in the field.” Id. at 38; Reply Br. 4–5.
Appellant’s arguments are not persuasive because they are directed to
the underlying abstract idea (i.e., to the claimed mathematical concept), not
to additional recitations that might transform the abstract idea to a patent-
eligible invention. Moreover, it is not enough for eligibility that “the
techniques claimed are ‘[g]roundbreaking, innovative, or even brilliant,”’ or
are “novel and nonobvious”— “a claim for a new abstract idea is still an
abstract idea.” SAP Am., 898 F.3d at 1163 (citations omitted).
We also note that recitation of a “non-transitory computer-readable
medium” (found in the preamble of claim 1 and in the body of independent
claim 21), “a processor” (found in independent claim 21), and a “computing
device” (found in the preamble of claim 1 and in the body of independent
claims 21 and 22) does not transform the underlying abstract mathematical
concept to a patent-eligible invention. The Specification’s broad supporting
disclosures for these limitations show that these technologies were well-
understood, routine, and conventional. See, e.g., Spec. ¶¶ 32–34.
Appellant argues that as with Amdocs (Israel) Ltd. v. Openet Telecom,
Inc., 841 F.3d 1288 (Fed. Cir. 2016), claim 1 is
directed to a particular way for computing a Gaussian
bandwidth parameter value that is used to define an SVDD
model and to identify a new observation as an outlier to solve
the problem of how to automatically determine a good Gaussian
Appeal 2019-005130
Application 15/887,037

14

bandwidth parameter value much, much faster and with fewer
inputs while achieving accurate outlier identification.
Appeal Br. 39. That is, Appellant argues that claim 1 is like the patent-
eligible claim in Amdocs, which required “computer code for using the
accounting information with which the first network accounting record is
correlated to enhance the first network accounting record.” Amdocs, 841
F.3d at 1300 (cited in Appeal Br. 39) (emphasis added). But in Amdocs the
Court of Appeals for the Federal Circuit “construed ‘enhance’ as being
dependent upon the invention’s distributed architecture.” Id. (citations
omitted). Specifically, “enhance” was construed to require “‘in a distributed
fashion’ and . . . ‘close to the source’ of network information.” Id. (citation
omitted). “[T]his distributed enhancement was a critical advancement over
the prior art.” Id. Thus, the distributed architecture required by the
“enhance” recitation—given the particular, fact-driven construction in
Amdocs—is what provided the requisite inventive concept that met the
requirements of Step 2B.
Appellant has not shown that claim 1 includes any comparable
additional recitations. Rather, Appellant merely points to features of the
abstract mathematical concept itself. Appeal Br. 39.
For these reasons, we agree with the Examiner that claim 1 does not
include additional recitations that transform the abstract mathematical
concept into a patent-eligible invention. Final Act. 2. Accordingly, we
sustain the Examiner’s patent-eligibility rejection under 35 U.S.C. § 101 of
claim 1, and claims 2–30, which Appellant argues are patentable for similar
reasons. Appeal Br. 42–43.
Appeal 2019-005130
Application 15/887,037

15

CONCLUSION
Claims
Rejected 35 U.S.C. § Basis Affirmed Reversed
1–30 101 Eligibility 1–30
TIME PERIOD FOR RESPONSE
No time period for taking subsequent action in connection with this
appeal may be extended under 37 C.F.R. § 1.136(a). See 37 C.F.R.
§ 1.136(a)(1)(iv).
AFFIRMED