DETAILED ACTION
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. Applicant’s submission filed 19 December 2025 [hereinafter Response], where:
Claims 1-23 have been amended.
Claims 1-23 are pending.
Claims 1-23 are rejected.
Claim Rejections - 35 U.S.C. § 112
3. The rejection to claims 1-23 under 35 U.S.C. § 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention is WITHDRAWN in view of the Applicant’s amendments to the claims.
Claim Rejections - 35 U.S.C. § 101
4. 35 U.S.C. § 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
5. Claims 1-23 are rejected under 35 U.S.C. § 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 recites a computing system, which is a product, and thus one of the statutory categories of patentable subject matter. (35 U.S.C. § 101).
However, under Step 2A Prong One, the claim recites the limitations of “[(b)]1 generating fingerprints of primary class probabilities of the known samples.” The claim does not limit the plain meaning of “[(b)] generating fingerprints,” which as explained in the Specification, (Specification ¶ 0026), encompasses mathematical concepts that can be performed as a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). Also, the activity requires a specific mathematical calculation to “[(a)] generating fingerprints” that corresponds to each sample and is calculated by Equation (1), (Specification ¶ 0026), where the broadest reasonable interpretation of “[(a)] generate fingerprints” requires specific mathematical calculations and therefore encompasses a mathematical concept, (MPEP § 2106.04(a)(2) sub I), which is one of the groupings of abstract ideas. The claim also recites more details or specifics to the abstract idea of “[(b)] generating fingerprints,” “[(b.1)] wherein each fingerprint of the primary class probabilities represents a value corresponding to an attribute of a respective known sample,” and accordingly, is merely more specific to the abstract idea.
Also, the claim recites limitations of “[(c)] removing the first portion of the known samples,” “[(d)] creating a distribution of predicted subclass probabilities of the second portion of the known samples,” and “[(e)] applying the distribution of the predicted subclass probabilities to unknown samples to determine a sub-class of ones of the unknown samples.” The activities of “[(b)] removing,” “[(d)] creating” and “[(e)] applying” can practically be performed in the human mind, including, for example, observations, evaluations, judgments, and opinions, and accordingly, are a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). The claim also recites more details or specifics to the abstract idea of “[(d)] creating a distribution,” where “[(d.1)] [(d.1)] the distribution of predicted subclass probabilities based on the generated fingerprints ,” and accordingly, is merely more specific to the abstract idea. Thus, claim 1 recites an abstract idea.
Under Step 2A Prong Two, the claim as a whole is not integrated into a practical application, because the additional elements recited in the claim beyond the identified abstract idea include a “processor,” and a “non-transitory computer readable storage medium, having stored thereon program instructions that, upon execution by the processor, cause,” a “database,” and a “network,” which are described at a high-level of generality, and thus are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that do not serve to integrate the abstract idea into a practical application.
The claim also recites “[(a)] accessing, from a database via a network, known samples associated with survey data, the survey data obtained from a plurality of mobile devices,” which is the pre-processing insignificant extra-solution of data gathering, (MPEP § 2106.04(g)), that does not serve to integrate the abstract idea into a practical application. The claim also recites more details or specifics to the additional element of “[(a)] accessing known samples,” wherein “[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes different from a respective known primary class of one or more known primary classes,” and “[(a.2)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes,” and accordingly, are merely more specific to the additional element. Thus, claim 1 recites an abstract idea.
Finally, under Step 2B, the additional elements, taken alone or in combination, do not represent significantly more than the abstract idea itself. The additional elements include a “processor,” and a “non-transitory computer readable storage medium, having stored thereon program instructions that, upon execution by the processor, cause,” a “database,” and a “network,” which are described at a high-level of generality, and thus are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that do not amount to significantly more than the abstract idea.
The claim also recites “[(a)] accessing, from a database via a network, known samples associated with survey data, the survey data obtained from a plurality of mobile devices,” which is the well-understood, routine, and conventional activity of receiving data over a network, (MPEP § 2106.05(d) sub II.i), which does not amount to significantly more than the abstract idea. The claim also recites more details or specifics to the additional element of “[(a)] accessing known samples,” wherein “[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes different from a respective known primary class of one or more known primary classes,” and “[(a.2)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes,” and accordingly, are merely more specific to the additional element. Therefore, claim 1 is subject-matter ineligible.
Claim 10 recites an method, which is a process, and thus one of the statutory categories of patentable subject matter. (35 U.S.C. § 101).
However, under Step 2A Prong One, the claim recites the limitations of “[(b)] generating fingerprints of primary class probabilities of the known samples.” The claim does not limit the plain meaning of “[(b)] generating, by executing instructions with the at least one processor, fingerprints,” which as explained in the Specification, (Specification ¶ 0026), encompasses mathematical concepts that can be performed as a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). Also, the activity requires a specific mathematical calculation to “[(a)] generating fingerprints” that corresponds to each sample and is calculated by Equation (1), (Specification ¶ 0026), where the broadest reasonable interpretation of “[(a)] generate fingerprints” requires specific mathematical calculations and therefore encompasses a mathematical concept, (MPEP § 2106.04(a)(2) sub I), which is one of the groupings of abstract ideas. The claim also recites more details or specifics to the abstract idea of “[(b)] generating fingerprints,” “[(b.1)] wherein each fingerprint of the primary class probabilities represents a value corresponding to an attribute of a respective known sample,” and accordingly, is merely more specific to the abstract idea.
Also, the claim recites limitations of “[(c)] removing, by executing instructions with the at least one processor, the first portion of the known samples,” “[(d)] creating, by executing instructions with the at least one processor, a distribution of predicted subclass probabilities of the second portion of the known samples,” and “[(e)] applying, by executing instructions with the at least one processor, the distribution of the predicted subclass probabilities to unknown samples to determine a sub-class of ones of the unknown samples.” The activities of “[(b)] removing,” “[(d)] creating” and “[(e)] applying” can practically be performed in the human mind, including, for example, observations, evaluations, judgments, and opinions, and accordingly, are a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). The claim also recites more details or specifics to the abstract idea of “[(d)] creating a distribution,” where “ [(d.1)] the distribution of predicted subclass probabilities based on the generated fingerprints ,” and accordingly, is merely more specific to the abstract idea. Thus, claim 10 recites an abstract idea.
Under Step 2A Prong Two, the claim as a whole is not integrated into a practical application, because the additional elements recited in the claim beyond the identified abstract idea include “at least one processor,” and a “database,” which are recited at a high level of generality, and thus are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that do not serve to integrate the abstract idea into a practical application.
The claim also recites “[(a)] retrieving, by executing instructions at least one processor, known samples associated with survey data from a database,” which is the pre-processing insignificant extra-solution of data gathering, (MPEP § 2106.04(g)), that does not serve to integrate the abstract idea into a practical application. The claim also recites more details or specifics to the additional element of “[(a)] retrieving known samples,” wherein “[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes different from a respective known primary class of one or more known primary classes,” and “[(a.2)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes,” and accordingly, are merely more specific to the additional element. Thus, claim 10 recites an abstract idea.
Finally, under Step 2B, the additional elements, taken alone or in combination, do not represent significantly more than the abstract idea itself. The additional elements include “at least one processor,” and a “database,” which are recited at a high level of generality, and thus are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that do not amount to significantly more than the abstract idea.
The claim also recites “[(a)] retrieving, by executing instructions with at least one processor, known samples associated with survey data from a database,” which is the well-understood, routine, and conventional activity of receiving data over a network, (MPEP § 2106.05(d) sub II.i), which does not amount to significantly more than the abstract idea. The claim also recites more details or specifics to the additional element of “[(a)] retrieving known samples,” wherein “[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes different from a respective known primary class of one or more known primary classes,” and “[(a.2)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes,” and accordingly, are merely more specific to the additional element. Therefore, claim 10 is subject-matter ineligible.
Claim 17 recites a non-transitory machine readable medium, which is a product, and thus one of the statutory categories of patentable subject matter. (35 U.S.C. § 101).
However, under Step 2A Prong One, the claim recites the limitations of “[(b)] generating fingerprints of primary class probabilities of the known samples.” The claim does not limit the plain meaning of “[(b)] generating fingerprints,” which as explained in the Specification, (Specification ¶ 0026), encompasses mathematical concepts that can be performed as a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). Also, the activity requires a specific mathematical calculation to “[(a)] generating fingerprints” that corresponds to each sample and is calculated by Equation (1), (Specification ¶ 0026), where the broadest reasonable interpretation of “[(a)] generate fingerprints” requires specific mathematical calculations and therefore encompasses a mathematical concept, (MPEP § 2106.04(a)(2) sub I), which is one of the groupings of abstract ideas. The claim also recites more details or specifics to the abstract idea of “[(b)] generating fingerprints,” “[(b.1)] wherein each fingerprint of the primary class probabilities represents a value corresponding to an attribute of a respective known sample,” and accordingly, is merely more specific to the abstract idea.
Also, the claim recites limitations of “[(c)] removing the first portion of the known samples,” “[(d)] creating a distribution of predicted subclass probabilities of the second portion of the known samples,” and “[(e)] applying the distribution of the predicted subclass probabilities to unknown samples to determine a sub-class of ones of the unknown samples.” The activities of “[(b)] removing,” “[(d)] creating” and “[(e)] applying” can practically be performed in the human mind, including, for example, observations, evaluations, judgments, and opinions, and accordingly, are a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). The claim also recites more details or specifics to the abstract idea of “[(d)] creating a distribution,” where “[(d.1)] the distribution of predicted subclass probabilities based on the generated fingerprints ,” and accordingly, is merely more specific to the abstract idea. Thus, claim 1 recites an abstract idea.
Under Step 2A Prong Two, the claim as a whole is not integrated into a practical application, because the additional elements recited in the claim beyond the identified abstract idea include a “non-transitory computer-readable storage medium. having stored thereon program instructions that, upon execution by a processor, cause performance of a set of operations,” a “database,” and a “network,” which are described at a high-level of generality, and thus are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that do not serve to integrate the abstract idea into a practical application.
The claim also recites “[(a)] accessing, from a database via a network, known samples associated with survey data, the survey data obtained from a plurality of mobile devices,” which is the pre-processing insignificant extra-solution of data gathering, (MPEP § 2106.04(g)), that does not serve to integrate the abstract idea into a practical application. The claim also recites more details or specifics to the additional element of “[(a)] accessing known samples,” wherein “[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes different from a respective known primary class of one or more known primary classes,” and “[(a.2)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes,” and accordingly, are merely more specific to the additional element. Thus, claim 1 recites an abstract idea.
Finally, under Step 2B, the additional elements, taken alone or in combination, do not represent significantly more than the abstract idea itself. The additional elements include a “non-transitory computer-readable storage medium. having stored thereon program instructions that, upon execution by a processor, cause performance of a set of operations,” a “database,” and a “network,” which are described at a high-level of generality, and thus are generic computer components used to implement the abstract idea, (MPEP § 2106.05(f)), that do not amount to significantly more than the abstract idea.
The claim also recites “[(a)] accessing, from a database via a network, known samples associated with survey data, the survey data obtained from a plurality of mobile devices,” which is the well-understood, routine, and conventional activity of receiving data over a network, (MPEP § 2106.05(d) sub II.i), which does not amount to significantly more than the abstract idea. The claim also recites more details or specifics to the additional element of “[(a)] accessing known samples,” wherein “[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes different from a respective known primary class of one or more known primary classes,” and “[(a.2)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes,” and accordingly, are merely more specific to the additional element. Therefore, claim 17 is subject-matter ineligible.
Claims 2, 3, 4 and 7 depend directly or indirectly from claim 1. Claims 11, 12, 13 and 15 depend directly or indirectly from claim 10. Claims 18, 19, 20 and 22 depend directly or indirectly from claim 17. The claims recite more details or specifics to the abstract idea of “[(b)] generating fingerprints,” where (claims 2, 11, and 18: “[(b.2)] based on class numbers that are ranked according to the respective primary class probabilities”; claims 3, 12, and 19: “[(b.3)] based on a configurable parameter that can reduce at least one of a statistical bias or variance of the fingerprint”; claims 4, 13, and 20: [(b.1)] wherein the attribute of the respective known sample [(b.1.1)] represents a characteristic, a category, an interest, or an affiliation of a user of a mobile device of the plurality of mobile devices”; and claims 7, 15, and 22: “generating respective ones of the fingerprints [(b.2)] by arranging the known samples in an array”), and accordingly, are merely more specific to the abstract idea. The abstract idea of these claims are not integrated into a practical application, (see MPEP § 2106.04(d)), nor do they amount to significantly more than the abstract idea, (MPEP § 2106.05 sub I; see also MPEP § 2106.05(a) – (h)), because the claims recite no more than the abstract idea. Therefore claims 2-4, 7, 11-13, 15, 18-20, and 22 are subject-matter ineligible.
Claim 5 depends directly or indirectly from claim 1. The claim recites more details or specifics to the abstract idea of “[(b)] generating fingerprints,” “wherein [(b.1)] attribute of the respective known sample comprises [(b.1.1)] an age group,” and accordingly, is merely more specific to the abstract idea. Also, the claim recites more details or specifics of the abstract idea of “[(e)] applying the distribution,” “wherein [(e))] the sub-class of ones of the unknown samples [(e.1)] is an integer associated with age,” and accordingly, is merely more specific to the abstract idea. Therefore claim 5 is subject-matter ineligible.
Claim 6 depends directly or indirectly from claim 1. Claim 14 depends directly or indirectly from claim 10. Claim 21 depends directly or indirectly from claim 17. The claims provide more details or specifics to the abstract idea of “[(d)] creating a distribution,” (claims 6, 14, and 21: “[(d)] creating the distribution [(d.1)] by pivoting a table based on at least one value of the values of fingerprints”), and accordingly, are merely more specific to the abstract idea. The abstract idea of these claims are not integrated into a practical application, (see MPEP § 2106.04(d)), nor do they amount to significantly more than the abstract idea, (MPEP § 2106.05 sub I; see also MPEP § 2106.05(a) – (h)), because the claims recite no more than the abstract idea. Therefore claims 6, 14, and 21 are subject-matter ineligible.
Claim 8 depends directly or indirectly from claim 1. The claim recites “wherein the set of operations further comprise [(f)] pivoting the array based on the attributes of the known samples.” The limitation encompasses mathematical concepts that can be performed as a mental process, (MPEP § 2106.04(a)(2) sub III), which is one of the groupings of abstract ideas. (MPEP § 2106.04(a)(2)). The abstract idea of these claims are not integrated into a practical application, (see MPEP § 2106.04(d)), nor do they amount to significantly more than the abstract idea, (MPEP § 2106.05 sub I; see also MPEP § 2106.05(a) – (h)), because the claims recite no more than the abstract idea. Therefore, claim 8 is subject-matter ineligible.
Claims 9 depends directly or indirectly from claim 1. Claim 16 depends directly or indirectly from claim 10. Claim 23 depends directly or indirectly from claim 17. The claims recite more details or specifics to the additional elements of “[(a)] accessing known samples,” and “[(a)] retrieving known samples,” “wherein the [(a)] survey data [(a.3)] includes demographic information of respective users of the plurality of mobile devices,” “wherein [(a.4)] the known samples are indicative of the respective users,” and wherein [(a.5)] the attribute of the respective known sample is a demographic attribute,” and accordingly, are merely more specific to the additional element. Therefore, claims 9, 16, and 23 are subject-matter ineligible.
Claim Rejections – 35 U.S.C. § 103
6. The following is a quotation of 35 U.S.C. § 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
7. The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. § 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
8. This application currently names joint inventors. In considering patentability of the claims the Examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the Examiner to consider the applicability of 35 U.S.C. § 102(b)(2)(C) for any potential 35 U.S.C. § 102(a)(2) prior art against the later invention.
9. Claims 1, 4, 5, 9, 10, 13, 17, 19, 20 and 23 are rejected under 35 U.S.C. § 103 as being unpatentable over US Published Application 20080086493 to Zhu [hereinafter Zhu] in view of US Published Application 20150332156 to Pliner [hereinafter Pliner].
Regarding claims 1, 10, and 17, Zhu teaches [a] computing system (Zhu ¶ 0011 teaches a “system for modeling and discriminating complex data sets of large information systems”) of claim 1, [a] method (Zhu, Abstract, teaches a "method is disclosed for modeling and discriminating complex data sets of large information systems") of claim 10, and [a] non-transitory computer-readable storage medium (Zhu ¶ 0006 teaches "For example, a critical issue is how to guarantee the collected and stored data are consistent and valid in terms of the essential characteristics (e.g., categories, meanings) of the data sets [(that is, "stored" is a non-transitory machine readable medium)]") of claim 17, comprising:
a processor; and
a non-transitory computer readable storage medium, having stored thereon program instructions that, upon execution by the processor, cause performance of a set of operations comprising:
[(a)] accessing, from a database via a network (Zhu, claim 1, teaches “providing a database having a number of data records”), known samples associated with survey data (Zhu, Fig. 2, teaches accessing known samples [Examiner annotations in dashed-line text boxes]:
PNG
media_image1.png
627
1121
media_image1.png
Greyscale
Zhu ¶ 0035 teaches ” FIG. 2 shows an example in which the data points of class 1 have a concave distribution and that of class 2 have a discontinuous distribution. These kinds of distributions are not unusual in many real world applications [(that is, accessing, from a database via a network, known samples associated with survey data)]”; Zhu ¶ 0037 teaches “system of the present invention is based on the nonlinear modeling of the statistical distributions of the data collections [(that is, a “data collection” being survey data)], which likewise reduces the complexity of the distribution”);
[Examiner notes that the plain meaning of “survey data” is a systematic collection of information, where the broadest reasonable interpretation of the term “survey data” covers the teachings of Zhu pertaining to a collection of data, which is not inconsistent with Applicant’s disclosure. (MPEP § 2111; Specification ¶ 0025 (“For example, the fingerprint generator 106 receives the samples as tables representing survey data and/or known data from a third-party source (e.g., purchased demographic data)”)]) . . . , wherein the known samples comprise:
[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes (Zhu ¶ 0011 teaches “the expressional essentials of the information characteristics and accounts for uncertainties of the information piece with explicit quantification useful to infer [(that is, predicted)] the discriminative nature of the data sets”) different from a respective known primary class of one or more known primary classes (Zhu ¶ 0030 teaches “process is applicable to small sized, moderate sized and very large sized data sets, and applicable to moderately mixed data sets and to heavily mixed data sets of different categories [(that is, “different categories” is different from a respective known primary class of one or more known primary classes)]”), and
[(a.2)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes (Zhu ¶ 0034 teaches “[m]any known data analyzing systems deal with the relations between a set of known classes (categories), denoted as Ω={ω1, ω2, . . . , ωc}, and a set of known data points (vectors), denoted as x=[x1, x2, . . . , xn]. The total possible occurrences of the data points xs form an n-dimensional space R(x). Collections of the [data points] xs partition the [n-dimensional space] R(x) into regions R(ωi), i=1, 2, . . . , c, where
PNG
media_image2.png
57
512
media_image2.png
Greyscale
The R(ꞷ;)s represent clusters of xs based on the characteristics of the ꞷis. The surfaces, called decision boundaries, that separate these R(w;) regions are described by discriminate functions”; Zhu ¶ 0043 teaches that “[u]nder the condition that the a priori probabilities [(that is, predicted primary class)] are all equal (i.e., ∀(ωi, ωjεΩ)P(ωi)=P(ωj)) [(that is, “equal” is identical, in which a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes)], the decision rule for the classifier built on the subclass model can be expressed as
PNG
media_image3.png
62
520
media_image3.png
Greyscale
;
Zhu ¶ 0045 teaches “hyper-ellipsoidal clustering is established as follows. Let S be a set of labeled data points (records) [(that is, known samples)], xks, i.e., S = {xk; k = 1, 2, . . . , N}, in which each data point xk is associated with a specific class Si, i.e.,
PNG
media_image4.png
68
208
media_image4.png
Greyscale
where Si is a set of data points that are labeled by ωi, ωi ϵ S, there exists an i, (i = 1, 2, . . . . , c), such that [(xk ϵ Si) ⇢ (xk ϵ ωi )]”; further, Zhu ¶ 0075 teaches “If data points in the data collection are not labeled, label the data according to a pre-determined set of discriminate functions {Pi(x ) | i = 1, 2, . . . , c}, where x stands for a data point (c = 2 if the data points are in two types [(that is, being in two types is one being different from a respective known primary class and the other being identical from a respective known primary class)”);
[(b)] generating fingerprints of primary class probabilities of the known samples (Zhu, Fig. 2, teaches data points of the same category [Examiner annotations in dashed-line text boxes]:
PNG
media_image5.png
463
693
media_image5.png
Greyscale
Zhu ¶ 0012 teaches in reference to Fig. 2, that the “method is directed at detecting and configuring data sets of different categories in numerical expressions into multiple hyper-ellipsoidal clusters with a minimum number of the hyper-ellipsoids covering the maximum amount of data points of the same category [(that is, known samples)]”; Zhu ¶ 0039 teaches “[l]et
P
^
(x | ωi) = P(x | Si) be the class-conditional distribution of x defined on the given data set Si of class ωi. [(that is, generate fingerprints of primary class probabilities of known samples)]. The P(x | ωi) under the subclass modeling can be expressed as a combination of the sub-distribution P(x l ϵik)s such that:
PNG
media_image6.png
146
522
media_image6.png
Greyscale
[(that is, generating fingerprints of primary class probabilities of known samples)]”; Zhu ¶ 0045 teaches “hyper-ellipsoidal clustering is established as follows. Let S be a set of labeled data points (records) [(that is, known samples)], xks, i.e., S = {xk; k= 1, 2, . . . , N}, in which each data point xk is associated with a specific class Si, i.e.,
PNG
media_image4.png
68
208
media_image4.png
Greyscale
where Si is a set of data points that are labeled by [class] ωi, ωi ϵ S, there exists an i, (i = 1, 2, . . . . , c), such that [(xk ϵ Si) ⇢ (xk ϵ ωi )]”),
[(b.1)] wherein each fingerprint of the primary class probabilities represents a value corresponding to an attribute of a respective known sample(Zhu ¶ 0040 teaches [f]rom the fact that
PNG
media_image7.png
41
333
media_image7.png
Greyscale
The
P
^
(
x
|
ω
i
)
can be computed by:
PNG
media_image8.png
52
422
media_image8.png
Greyscale
[(that is, each fingerprint . . . represents a value corresponding to an attribute of a respective known sample )]”; further, Zhu ¶ 0042 teaches “[i]t is know that a Bayes classifier classifies a feature vector x ϵ R(x) [(that is, a “feature” is an attribute of a respective known sample)] to class ꞷi based on an evaluation
∀
j
≠
i
P
X
|
ω
i
≥
P
X
ω
j
. . . . Therefore a classifier built on the subclasses is a Bayes classifier with respect to the distribution functions P(x l ϵik)s.”);
[(c)] removing the first portion of the known samples (Zhu, Fig. 6, teaches removing known samples from intertwined data [Examiner annotations in dashed-line text boxes]:
PNG
media_image9.png
633
892
media_image9.png
Greyscale
Zhu ¶¶ 0077-81 teaches, in relation to Moment-Driven Clustering Algorithm, that “2) While not all data blocks are pure (purity-degree > ε): 2.1) for each impure block k,
2.1.1) remove (μk, ∑k) from the μk - ∑k list.
2.1.2) compute the (μi, ∑i) i = l, 2, . . . , c for each type's data points in the block k.
2.1.3) insert the (μi, ∑i) i = l, 2, . . . , c into the μ - ∑ list.
Zhu ¶ 0037 teaches “[d]ata collections in these subspaces have high intra-subclass and low inter-subclass similarities [(that is, “low inter-class similarities” is to removing the first portion of the known samples)]);
[(d)] creating a distribution of predicted subclass probabilities of the second portion of the known samples (Zhu ¶ 0045 teaches “hyper-ellipsoidal clustering is established as follows. Let S be a set of labeled data points (records) [(that is, known samples)], xks, i.e., S = {xk; k = 1, 2, . . . , N}, in which each data point xk is associated with a specific class Si, i.e.,
PNG
media_image4.png
68
208
media_image4.png
Greyscale
where Si is a set of data points that are labeled by ωi, ωi ϵ S, there exists an i, (i = 1, 2, . . . . , c), such that [(xk ϵ Si) ⇢ (xk ϵ ωi )]”; further, Zhu ¶ 0075 teaches “If data points in the data collection are not labeled [(that is, “not labeled data points” are unknown samples)], label the data according to a pre-determined set of discriminate functions {Pi(x ) | i = 1, 2, . . . , c}, where x stands for a data point (c = 2 if the data points are in two types)”;Zhu ¶¶ 0076-80 teaches “1) [l]et the whole data collection be a single data block, mark it unpurified, calculate its mean vector μ0 and co-variance matrix ∑0, place (μ0, ∑0) into the μ-∑ list, 2) While not all data blocks are pure (purity-degree > ϵ), 2.1) for each impure block k, 2.1.1) remove (μk, ∑k) from the μ - ∑ list, 2.1.2) compute the (μi, ∑i) i = 1, 2, . . . , c for each type's data points in the block k.), 2.1.3) insert the (μi, ∑i) i = 1, 2, . . . , c into the μ-∑ list, [and] 2.3) for each data block Bk, calculate the purity degree according to the purity measurement function Purity-degree (Bk) [(that is, the “μ-∑ list” is creating a distribution of predicted subclass probabilities of the second portion of the known samples)]”),
[(d.1)] the distribution of predicted subclass probabilities based on the generated fingerprints (Zhu ¶ 0082 teaches “2.2) for each data point xj in the whole data set [(that is, in relation to “the generated fingerprints” is based on the generated fingerprints)] place xj into corresponding data block according to the shortest Mahalanobis distance measurement with respect to the (μi, ∑i) in the μ-∑ list [(that is, the “Mahalanobis distance” is the distribution of predicted subclass probabilities based on the generated fingerprints)]”); and
[(e)] apply the distribution of the predicted subclass probabilities to unknown samples to determine a sub-class of ones of the unknown samples (Zhu ¶ 0037 teaches the “overall distribution of a data class is a combining set of the distributions of the subclasses (not necessary to be additive). In this sense, subclasses of one data class are the component clusters of the data sets, as the example shows in FIG. 3”; Zhu ¶ 0038 teaches “[f]or a given observation vector x of unknown class membership, if class distributions p(x | ωi) and prior probabilities P(ωi) for the class ωi, (i = 1, 2, . . . , w) are provided, then a posterior probability p(ωi | x) can be computed by Bayes rule and an optimal classifier can be formed. It is known that the class distributions {p(x | ωi); i = 1, 2, . . . , w} dominate the computation of the classifier”; Zhu ¶ 0136 teaches the “usage of the data system and method of the present invention provides for the cleansing or purifying of data collections to find irregularity (singularity) points in the data sets, and then rid the data collections of these irregularity points [(that is, “data set purification” is to apply the distribution of the predicted subclass probabilities to unknown samples to determine a sub-class of ones of the unknown samples)]”).
Though Zhu teaches a classifier to minimize the probability of overall decision error on samples in the data vector space, Zhu, however, does not explicitly teach –
* * *
[(a) accessing . . . known samples] . . . , the survey data obtained from a plurality of mobile devices, . . . :
* * *
But Pliner teaches -
* * *
[(a) accessing . . . known samples] . . . , the survey data obtained from a plurality of mobile devices (Pliner ¶¶ 0030-31 teaches” In a particular example, a mobile communication service provider desires to know an age range and/or other demographics information for all lines of service, particularly additional lines of service associated with an account of a primary user. . . . In this example, survey data is collected by a third party unaffiliated with the service provider [(that is, the survey data obtained from a plurality of mobile devices)]”), . . . :
* * *
Zhu and Pliner are from the same or similar field of endeavor. Zhu teaches detecting and configuring data sets of different categories in nature into a set of structures that distinguish the categorical features of the data sets. Pliner teaches forming a prior probability that a user within the summary data belongs to a respective class, a first conditional probability of a first predictor within the summary data and a second conditional probability of a second predictor within the summary data are calculated.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify Zhu pertaining to a classifier detecting and configuring data sets of different categories in nature with the survey sample data of Pliner.
The motivation to do so is because “a need exists for predicting class membership (e.g., age range), and thus demographic information, for each line associated with an account for mobile communication services.” (Pliner ¶ 0003).
Examiner notes that the terms “processor,” “at least one processor,” "at least one memory,” “database,” and/or “network,” and/or recited in Applicant's claims are interpreted to be a well-known hardware structures.
Regarding claims 4, 13, and 20, the combination of Zhu and Pliner teaches all of the limitations of claims 1, 10, and 17, respectively, as described above in detail.
Pliner teaches -
[(a.1)] wherein the attribute of the respective known sample represents a characteristic, a category, an interest, or an affiliation of a user of a mobile device of the plurality of mobile devices (Pliner ¶ 0014 teaches that “[t]o identify the most promising customers/users, for example, predictive models help estimate the probability to make a purchase or sign up for a service. In this example, P(Y=1|X=x) represents the probability to make the purchase or sign up for the service for the whole customer base. [Vector] X, in this example, is a vector of customer characteristics/attributes [(that is, the attribute of the respective known sample)].” For example, [vector] X might represent gender while x is either male or female. Then, P(Y=1|X=x) represents the probabilities that purchasers are either male or female [(that is, the attribute . . . represents a characteristic, a category, . . . or an affiliation)]”).
Regarding claim 5, the combination of Zhu and Pliner teaches all of the limitations of claim 1, as described above in detail.
Pliner teaches -
wherein the attribute of the respective known sample comprises an age group (Pliner ¶ 0014 teaches “[vector] X might represent age while x is a range of ages such as 13-17, 18-24, 25-34, 35-54 and 55+. Then, P(Y=1|X=x) represents the probabilities that purchasers are within a particular age range [(that is, the attribute of the respective known sample comprises an age group)]”), and
wherein the sub-class of ones of the unknown samples is an integer associated with age (Pliner ¶ 0016 teaches “[e]ven if the survey is conducted among customers of a single company, for example, a match between survey responses and individual customers is not available [(that is, unknown samples)]. In addition to the primary preference question (e.g., “Would you purchase this product/service?”), questions, for example, about each respondent (e.g., demographics) are also asked. Results are known, for example, for the whole survey sample (e.g., P(Y=1) or the overall proportion of respondents who would be interested in making a purchase) as well as by sub-groups (e.g., (P(Y=1|gender=‘F’) for women and P(Y=1|gender=‘M’) for men), if questions regarding a sub-group are asked [(that is, “sub-group” is the sub-class of ones of the unknown samples)]. The additional sub-group questions are denoted, for example, X=(X1, . . . , Xk). For example, X1 is gender, X2 is age, X3 is ethnicity, etc. and, for X1, x1 is male and x2 is female while xi is each age range for X2; Pliner ¶ 0014 teaches “X might represent age while x is a range of ages such as 13-17, 18-24, 25-34, 35-54 and 55+ [(that is, these “range of ages” are an integer associated with age)]”).
Regarding claim 19, the combination of Zhu and Pliner teaches all of the limitations of claim 18, as described above in detail.
Zhu teaches -
wherein [(a.1.1)] generating the fingerprints is based on a configurable parameter that can reduce at least one of a statistical bias or variance of the fingerprint (Zhu ¶ 0037 teaches “nonlinear modeling of the statistical distributions of the data collections, which likewise reduces the complexity of the distribution”; Zhu ¶¶ 0060-61 teaches the “covariance parameters ∑ik of the clusters [(that is, generating the fingerprints based on a configurable parameter)] can be estimated by extending the results of the moving centroid . . . . The parameters are to be continuously updated upon the examination of additional data points xs [(that is, “continuously updated” that “reduces the distribution complexity” is a configurable parameter that can reduce at least one of a statistical bias or variance of the fingerprint)] additional data points xs” and the addition of them into the selected subclass clusters [(that is, “continuously updated” that “reduces the distribution complexity” is a configurable parameter that can reduce at least one of a statistical bias or variance of the fingerprint)]”).
Regarding claims 9 and 23, the combination of Zhu and Pliner teaches all of the limitations of claims 1 and 17, respectively, as described above in detail.
Pliner teaches -
wherein the survey data includes demographic information of respective users of the plurality of mobile devices (Pliner ¶ 0031 teaches “survey data is collected by a third-party unaffiliated with the service provider. Alternatively, or in addition, survey data may be collected directly by the service provider and/or based on actual usage of some subset of customers of the service provider. The survey data includes, for example, age range and/or other demographics information corresponding to some users of the service provider's communication services as well as some users of communication services of other service providers [(that is, the survey data includes demographic information of respective users of the plurality of mobile devices)]”);
wherein the known samples are indicative of the respective users (Pliner ¶ 0016 teaches “[s]urveys are, for example, anonymous. Even if the survey is conducted among customers of a single company, for example, a match between survey responses and individual customers is not available. In addition to the primary preference question (e.g., “Would you purchase this product/service?”), questions, for example, about each respondent (e.g., demographics) are also asked. Results are known, for example, for the whole survey sample (e.g., P(Y=1) or the overall proportion of respondents who would be interested in making a purchase) as well as by sub-groups (e.g., (P(Y=1|gender=‘F’) for women and P(Y=1|gender=‘M’) for men), if questions regarding a sub-group are asked [(that is, “conducted among customers” is the known samples are indicative of the respective users)]”); and
wherein the attribute of the respective known sample is a demographic attribute (Pliner ¶ 0033 teaches “third-party survey data and the mobile communication service usage data collected by the service provider are utilized, for example, to generate distributions of potential predictors (e.g., distributions of potential predictors based on third-party survey data and distributions of potential predictors based on collected usage data) for identifying an age range and/or other demographics information of a user of a line of service of the service provider [(that is, the attribute of the respective known sample is a demographic attribute)]”).
10. Claims 2, 3, 11, 12, and 18 are rejected under 35 U.S.C. § 103 as being unpatentable over US Published Application 20080086493 to Zhu [hereinafter Zhu] in view of US Published Application 20150332156 to Pliner [hereinafter Pliner] and Kawase et al., “Exploiting the wisdom of the crowds for characterizing and connecting heterogeneous resources,” ACM (2014) [hereinafter Kawase].
Regarding claims 2, 11, and 18, the combination of Zhu and Pliner teaches all of the limitations of claims 1, 10, and 17, respectively, as described above in detail.
Though Zhu and Pliner teach a classifier to minimize the probability of overall decision error on samples in the data vector space, the combination of Zhu and Pliner, however, does not explicitly teach –
wherein [(a.1)] generating the fingerprints is based on class numbers that are ranked according to the respective primary class probabilities.
But Kawase teaches -
wherein [(a.1)] generating the fingerprints based on class numbers that are ranked according to the respective primary class probabilities (Kawase, Abstract, teaches that “[w]e use entity extraction and categorization to create ‘fingerprints' that allow for meaningful comparison. As a basis taxonomy, we use the 23 main categories [(that is, “23 main categories” are class numbers)] of Wikipedia Category Graph, which has been assembled over the years by the wisdom of the crowds”; Kawase, right column of p. 9, “7.2 Approach and Baseline,” first paragraph, teaches that “to generate recommendations, we used cosine similarity between the fingerprints. Thus, given a learning object and its fingerprint, we rank the movies [(that is, “rank the movies” is based on class numbers that are ranked)] according to their ‘fingerprint' cosine similarity. As a result, for each resource, a ranked list of `contextualized' movies is produced. With the purpose of comparison, we also generated rankings based solely on textual similarities [(that is, the “fingerprint similarity” is generate the fingerprints based on class numbers that are ranked according to the respective primary class probabilities)]”).
Zhu, Pliner, and Kawase are from the same or similar field of endeavor. Zhu teaches detecting and configuring data sets of different categories in nature into a set of structures that distinguish the categorical features of the data sets. Pliner teaches forming a prior probability that a user within the summary data belongs to a respective class, a first conditional probability of a first predictor within the summary data and a second conditional probability of a second predictor within the summary data are calculated. Kawase teaches differences in topic coverage and the impact of topics in different kinds of Web services.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify the combination of Zhu and Pliner pertaining to a classifier detecting and configuring survey sample data sets of different categories with the fingerprint ranking of web service content topics of Kawase.
The motivation to do so is because “Fingerprints also provide users insight in differences in focus for different systems. For systems such as IMDb, knowledge on significant differences in user ratings per topic can be used for compensating for these differences, in order to better cater queries for specific (niche) topics or for users with a high interest in these specific topics.” (Kawase, right column of p. § 10, “8. Conclusion,” third paragraph).
Regarding claims 3 and 12, the combination of Zhu, Pliner, and Kawase teaches all of the limitations of claims 2 and 11, respectively, as described above in detail.
Zhu teaches -
wherein [(a.1.1)] generating the fingerprints is based on a configurable parameter that can reduce at least one of a statistical bias or variance of the fingerprint (Zhu ¶ 0037 teaches “nonlinear modeling of the statistical distributions of the data collections, which likewise reduces the complexity of the distribution”; Zhu ¶¶ 0060-61 teaches the “covariance parameters ∑ik of the clusters [(that is, generating the fingerprints is based on a configurable parameter)] can be estimated by extending the results of the moving centroid . . . . The parameters are to be continuously updated upon the examination of additional data points xs [(that is, “continuously updated” that “reduces the distribution complexity” is a configurable parameter that can reduce at least one of a statistical bias or variance of the fingerprint)] additional data points xs” and the addition of them into the selected subclass clusters [(that is, “continuously updated” that “reduces the distribution complexity” is a configurable parameter that can reduce at least one of a statistical bias or variance of the fingerprint)]”).
11. Claims 6-8, 14-16, 21 and 22 are rejected under 35 U.S.C. § 103 as being unpatentable over US Published Application 20080086493 to Zhu [hereinafter Zhu] in view of US Published Application 20150332156 to Pliner [hereinafter Pliner] and US Published Application 20060167655 to Barrow et al. [hereinafter Barrow].
Regarding claims 6, 14, and 21, the combination of Zhu and Pliner teaches all of the limitations of claims 1, 10, and 17, respectively, as described above in detail.
Though Zhu and Pliner teach a table of a collection of records, the combination of Zhu and Pliner does not explicitly teach -
wherein [(c.1)] creating the distribution by pivoting a table based on at least one value of the values of fingerprints.
But Barrow teaches -
the processor circuitry is execute the instructions to
wherein [(c.1)] creating the distribution by pivoting a table based on at least one value of the values of fingerprints (Barrow ¶ 0115 teaches “the table of training data is re-indexed using the determined probability estimates [(that is, based on at least one value of the values of fingerprints instead of the attribute values. . . . [T]he instances are binned into the generated probability ranges according to the indexed probability"; Barrow ¶ 0061 & Figs. 5a-c teach
PNG
media_image10.png
530
758
media_image10.png
Greyscale
Barrow ¶ 0083 teaches “for all observed combinations of probability range bin membership, p(repay | probability range bin values), the joint posterior probability of class membership given the combinations of probability range bin membership is calculated [(that is, these “tables” is creating the distribution by pivoting a table)]”;
[Examiner notes the plain meaning of the term “pivot table” is a data analysis tool that summarizes large datasets, allowing users to dynamically reorganize and analyze information by dragging fields into different areas like rows, columns, and values to calculate sums, averages, counts, or percentages, and accordingly, the broadest reasonable interpretation of the term covers the teachings of Barrow, which is not inconsistent with the Applicant’s Specification (MPEP § 2111)).
Zhu, Pliner, and Barrow are from the same or similar field of endeavor. Zhu teaches detecting and configuring data sets of different categories in nature into a set of structures that distinguish the categorical features of the data sets. Pliner teaches forming a prior probability that a user within the summary data belongs to a respective class, a first conditional probability of a first predictor within the summary data and a second conditional probability of a second predictor within the summary data are calculated. Barrow teaches calculating first and second estimates of a posterior probability of class membership and binning the first and second estimates into a respective plurality of first and second probability range bins.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify the combination of Zhu and Pliner pertaining to a classifier detecting and configuring survey sample data sets of different categories with pivot tables incorporating the posterior probability of class membership of Barrow.
The motivation to do so is to generate “a model for use in classifying new instance data on the basis of a training set of instance data, which is efficient in terms of processing and memory requirements.” (Barrow ¶ 0030).
Regarding claims 7, 15, and 22, the combination of Zhu and Pliner teaches all of the limitations of claims 1, 10, and 17, respectively, as described above in detail.
Though Zhu and Pliner teach a table of a collection of records, the combination of Zhu and Pliner does not explicitly teach –
wherein [(a.1)] generating the fingerprints comprises arranging the known samples in an array.
But Barrow teaches -
wherein [(a.1)] generating the fingerprints comprises arranging the known samples in an array (Barrow ¶¶ 0134-37 teaches “[g]iven a task in binary classification with n cases and m predictors, define the input matrix v
PNG
media_image11.png
98
439
media_image11.png
Greyscale
as an array of indices [(that is, arranging the known samples in an array)], such that
PNG
media_image12.png
58
700
media_image12.png
Greyscale
where k is the number of categories present in the j-th attribute. The matrix v thus consists of indices to attribute values. The rows consist of the cases, the columns are the values for the predictors. Also given are target values t that denotes the class membership of an input case:
PNG
media_image13.png
62
335
media_image13.png
Greyscale
Our interest is in estimating the probability of class membership from the data for arbitrary input sectors x. The prior probability of class membership is then:
PNG
media_image14.png
162
577
media_image14.png
Greyscale
[(that is, generating the fingerprints comprises arranging the known samples in an array)]”).
Zhu, Pliner, and Barrow are from the same or similar field of endeavor. Zhu teaches detecting and configuring data sets of different categories in nature into a set of structures that distinguish the categorical features of the data sets. Pliner teaches forming a prior probability that a user within the summary data belongs to a respective class, a first conditional probability of a first predictor within the summary data and a second conditional probability of a second predictor within the summary data are calculated. Barrow teaches calculating first and second estimates of a posterior probability of class membership and binning the first and second estimates into a respective plurality of first and second probability range bins.
Thus, it would have been obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant’s invention to modify the combination of Zhu and Pliner pertaining to a classifier detecting and configuring survey sample data sets of different categories with pivot tables incorporating the posterior probability of class membership of Barrow.
The motivation to do so is to generate “a model for use in classifying new instance data on the basis of a training set of instance data, which is efficient in terms of processing and memory requirements.” (Barrow ¶ 0030).
Regarding claim 8, the combination of Zhu, Pliner, and Barrow teaches all of the limitations of claim 7, as described above in detail.
Barrow teaches -
wherein [(a.1.1)] set of operations further comprise pivoting the array based on the attributes of the known samples (Barrow ¶ 0097 & Fig. 7 teaches to “re-index the training dataset table back to the attribute values—‘≦30’ and ‘>30’, and ‘own’, ‘not own’. This is shown in FIG. 7. This joint probability estimates can be summarised in the table of FIG. 8.
PNG
media_image15.png
478
728
media_image15.png
Greyscale
[(that is, the transition from the array of FIG. 7 to the pivot table of FIG. 8 is pivoting the array based on the attributes of the known samples)]”).
Regarding claim16, the combination of Zhu, Pliner, and Barrow teaches all of the limitations of claim 15, as described above in detail.
Pliner teaches -
wherein the survey data includes demographic information of respective users of the plurality of mobile devices (Pliner ¶ 0031 teaches “survey data is collected by a third-party unaffiliated with the service provider. Alternatively, or in addition, survey data may be collected directly by the service provider and/or based on actual usage of some subset of customers of the service provider. The survey data includes, for example, age range and/or other demographics information corresponding to some users of the service provider's communication services as well as some users of communication services of other service providers [(that is, the survey data includes demographic information of respective users of the plurality of mobile devices)]”);
wherein the known samples are indicative of the respective users (Pliner ¶ 0016 teaches “[s]urveys are, for example, anonymous. Even if the survey is conducted among customers of a single company, for example, a match between survey responses and individual customers is not available. In addition to the primary preference question (e.g., “Would you purchase this product/service?”), questions, for example, about each respondent (e.g., demographics) are also asked. Results are known, for example, for the whole survey sample (e.g., P(Y=1) or the overall proportion of respondents who would be interested in making a purchase) as well as by sub-groups (e.g., (P(Y=1|gender=‘F’) for women and P(Y=1|gender=‘M’) for men), if questions regarding a sub-group are asked [(that is, “conducted among customers” is the known samples are indicative of the respective users)]”); and
wherein the attribute of the respective known sample is a demographic attribute (Pliner ¶ 0033 teaches “third-party survey data and the mobile communication service usage data collected by the service provider are utilized, for example, to generate distributions of potential predictors (e.g., distributions of potential predictors based on third-party survey data and distributions of potential predictors based on collected usage data) for identifying an age range and/or other demographics information of a user of a line of service of the service provider [(that is, the attribute of the respective known sample is a demographic attribute)]”).
Response to Arguments
12. Examiner has fully considered Applicant’s arguments, and responds below accordingly.
Non-Statutory Double Patenting
13. Applicant submits that “Claims 1-23 stand rejected on the ground of nonstatutory double patenting as allegedly being unpatentable over claims 1-26 of U.S. Patent No. 11,250,339 in view of U.S. Publication No. 2008/0086493 to Zhu et al. ("Zhu") and U.S. Publication No. 2016/0078359 to Csurka et al. ("Csurka"). Without acquiescing in the Examiner's reasoning behind the double patenting rejections, Applicant submitwted a terminal disclaimer to obviate the double patenting rejections. Thus, Applicant respectfully requests that the rejections be withdrawn.” (Response at p. 10).
Examiner’s Response:
Examiner acknowledges the filing of the terminal disclaimer on 17 December 2025 accompanied by the appropriate fee, and accordingly, WITHDRAWS the nonstatutory double patenting rejection.
Section 101
14. “Applicant submits that the amended recitations cannot fall into the ‘mental process” grouping of abstracts ideas, . . . . [A] claim does not recite a mental process when it contains limitation(s) that cannot practically be performed in the human mind, for instance when the human mind is not equipped to perform the claim limitation(s)." Id.
As such, Applicant's claims-which involve, among other amended recitations, ‘[(a)] accessing, from a database via a network, known samples associated with survey data, the survey data obtained from a plurality of mobile devices;’ ‘[(d)] creating a distribution of predicted subclass probabilities of the second portion of the known samples, the distribution of predicted subclass probabilities based on the generated fingerprints;’ and ‘[(e)] applying the distribution of the predicted subclass probabilities to unknown samples to determine a sub-class of ones of the unknown samples’ cannot practically be performed in the human mind.” (Response at p. 11).
Examiner’s Response:
Examiner respectfully submits that the activities of “[(d)] creating a distribution” and “[(e.)] applying the distribution . . . to unknown samples” can practically be performed in the human mind, including, for example, observations, evaluations, judgments, and opinions, and accordingly, is a mental process. (MPEP § 2106.04(a)(2) sub III).
As shown above in detail, for Step 2A Prong One, the rejection identifies the judicial exception (that is, abstract idea) by referring to what is recited in the claim and explain why it is considered an exception. For example, the rejection identifies the abstract idea as it is recited in the claim and explains why it is an abstract idea.
With regarding to “[(d)] creating a distribution,” the plain meaning of a distribution is that of a statistical distribution pertaining to samples associated with survey data. Such a distribution can be practically be performed in the human mind including observations, evaluations, judgment, and opinions. Similarly, the activity of “‘[(e)] applying the distribution” is based on a statistical analysis, and as a result, can be performed in the human mind for similar reasons.
In contrast to an abstract idea, the activity of “[(a)] accessing . . . known samples,” pertains to the pre-processing insignificant extra-solution activity of data gathering under Step 2A Prong Two, (MPEP § 2106.05(g)), that does not serve to integrate the abstract idea into a practical application, and under Step 2B, is the well-understood, routine, and conventional activity of receiving data over a network, (MPEP § 2106.05(d) sub. II.i), that does not amount to significantly more than the abstract idea.
Examiner submits that the rejections set out above in detail explains which limitations are considered judicial exceptions and explains the basis thereto.
15. Also, under Step 2A Prong Two, “aspects of Applicant's invention relate to, and provide improvements to, ensemble classification technology. The pending claims reduce the overall time, cost, and computational requirements for performing sub-class determinations (e.g., integer age, interests, affiliations, etc.) of a group of unknown people. In particular, the pending claims reduce and/or eliminate the use of binary trees, which require numerous levels of division before a terminal node is reached and thus, can significantly reduce computational needs. (Response at p. 11 (referring to Specification ¶¶ 0054, 0003, 0012-13); see also Ex parte Desjardins, Appeal 2024-000567 (PTAB 26 Sep 2025 (citing Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1336-1339 (Fed. Cir. 2016)).
Thus, Applicant submits that claim 1 and its dependent claims are directed to eligible subject matter, including at least the reasons articulated by Director Squires in his Ex parte Desjardins decision and reaffirmed in his December 5, 2025 Memorandum to the "Patent Examining Corps" saying that § 101 " . . . must be applied properly, as set forth in Desjardins." And for similar reasons, the remaining independent claims and their respective dependent claims are directed to eligible subject matter.” (Response at p. 12).
Examiner’s Response:
Examiner respectfully disagrees because the rejections hereinabove, under Step 2A Prong Two, identifies any additional elements recited in the claim beyond the identified judicial exception (processor, non-transitory computer readable storage medium, database, network); and evaluate the integration of the judicial exception into a practical application by explaining that the claim as a whole, looking at the additional elements individually and in combination, does not integrate the judicial exception into a practical application using the considerations set forth in MPEP §§ 2106.04(d), 2106.05(a)- (c) and (e)- (h).
As explained above, these additional elements are recited at a high-level of generality, and accordingly, are generic compute components used to implement the abstract idea, (MPEP §2106.05(f)), that do not serve to integrate the abstract idea into a practical application, nor do they amount to significantly more than the abstract idea.
Also, under Step 2A Prong Two, “integration” may be based on the improvements in the functioning of a computer or an improvement to any other technology or technical field. (MPEP § 2106.04(d)(1)). The evaluation requires, [i]n sum, that (1) the specification should be evaluated to determine if the disclosure provides sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement. Next, (2) if the specification sets forth such an improvement, the claim must be evaluated to ensure that the claim itself reflects the disclosed improvement.
By way of example to Desjardins, the MPEP provides under Step 2A Prong Two that “the [Desjardins] specification identified improvements as to how the machine learning model itself operates, including training a machine learning model to learn new tasks while protecting knowledge about previous tasks to overcome the problem of ‘catastrophic forgetting’ encountered in continual learning systems. Importantly, the [appeals review panel (ARP)] evaluated the claims as a whole in discerning at least the limitation ‘adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task’ reflected the improvement disclosed in the specification. Accordingly, the claims as a whole integrated what would otherwise be a judicial exception instead into a practical application at Step 2A Prong Two, and therefore the claims were deemed to be outside any specific, enumerated judicial exception (Step 2A: NO).” (MPEP § 2106.04(d) sub III; see “Advance Notice of Change to the MPEP in light of Ex Parte Desjardins” (05 December 2025) at p. 2) (emphasis added by Examiner)).
Applicant submits, as an improvement, that the Specification supports an improvement of “In particular, the pending claims reduce and/or eliminate the use of binary trees, which require numerous levels of division before a terminal node is reached and thus, can significantly reduce computational needs.” (Response at p. 11 (referring to Specification ¶¶ 0054, 0003, 0012-13). However, Applicant’s arguments are not tethered to the asserted claims, which do not require the limitations argued by the Applicant pertaining to an avoidance of “binary trees.” Moreover, Examiner notes that binary trees may have a distribution characteristic. In this respect, the broadest reasonable interpretation of the claim term “distribution” covers a distribution of a binary tree, which is not inconsistent with the Applicant’s disclosure. (MPEP § 2111).
Accordingly, the pending claims are subject-matter ineligible as set out above in detail.
Section 103
16. Applicant submits, “[w]ith respect to amended independent claim 1, Zhu and Csurka, alone or in any combination, do not disclose or suggest at least:
[(a) accessing . . . known samples], wherein the known samples comprise:
[(a.1)] a first portion of the known samples in which each known sample of the first portion includes a predicted primary class of one or more predicted primary classes different from a respective known primary class of one or more known primary classes, and
[(a.1)] a second portion of the known samples in which each known sample of the second portion includes a predicted primary class of the one or more predicted primary classes identical to a respective known primary class of the one or more known primary classes.
(Emphasis added). The cited references, alone or in any combination, do not teach or suggest the above-emphasized feature.” (Response at p. 14).
Examiner’s Response:
Examiner respectfully submits that the broadest reasonable interpretation of the instant claims covers the teachings of Zhu, which is not inconsistent with the Applicant’s disclosure. (MPEP § 2111). For example, the claims do not specify or limit characteristics of “samples” other than they are associated with “survey data” obtained from a “plurality of mobile devices.” In this regard, the Examiner relies upon the teachings of Pliner for these features, as set out above in detail.
Examiner respectfully submits that the rejections hereinabove clearly sets forth which claim limitations are taught by each of the prior art references, and the reason why it would be obvious to a person having ordinary skill in the art as of the effective filing date of the Applicant's invention to combine their teachings, and Applicant has not explained why the cited prior art references cannot be combined in the manner set forth in the rejection.
Conclusion
17. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
18. The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure:
(Sarasamma et al., “Min–Max Hyperellipsoidal Clustering for Anomaly Detection in Network Security,” arXiv (2006)) teaches Hyperellipsoidal clusters toward maximum intracluster similarity and minimum intercluster similarity are generated from training data sets. The novelty of the technique lies in the fact that the parameters needed to construct higher order data models in general multivariate Gaussian functions are incrementally derived from the data sets using accretive processes.
19. Any inquiry concerning this communication or earlier communications from the Examiner should be directed to KEVIN L. SMITH whose telephone number is (571) 272-5964. Normally, the Examiner is available on Monday-Thursday 0730-1730.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, Applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the Examiner by telephone are unsuccessful, the Examiner’s supervisor, KAKALI CHAKI can be reached on 571-272-3719. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/K.L.S./
Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
1 The use of references with the claim limitations is for the limited purpose of aiding in the subject-matter eligibility evaluation, and the evaluation under Sections 102 and/or 103.
Prosecution Insights