DETAILED ACTION
Claims 1-20 are pending and have been examined.
--
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 06/08/2023 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Specification
The disclosure is objected to because of the following informalities: Specification objection [0069] “As a fifth step, the algorithm can identify a synthetic point on a Euclidean distance out of the one or more Euclidean distances, wherein a length of a distance vector representing the Euclidean distance is smaller that a defined threshold (e.g., smaller that the remaining Euclidean distances calculated for a fixed parameter)” where “smaller that” should be “smaller than.”
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 17-20 are rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim 17 recites “predicting ‘a value of an input parameter’ that yields ‘an output parameter value’” in the preamble, but the claim 17 further recites “a value at least one variable input parameter” and “a known output value” in the body. The terminology does not match between preamble and body, so it is unclear whether these are the same elements or not. For examination purposes examiner has interpreted these are the same elements.
Claims 18-20 are also rejected due to their dependency on a rejected claim.
Claim Rejections - 35 USC § 101
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.
-
Claims 1-20 rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more
Step 1: Claims 1-8 recite a system. Claims 9-16 recite a computer-implemented method. Claims 17-20 recite a computer program product. Therefore, claims 1-8 are directed to a machine, claims 9-16 are directed to a process, and claims 17-20 are directed to a manufacture.
With respect to claims 1, 9 and 17:
2A Prong 1: The claim recites a judicial exception.
determines a value for at least one variable input parameter in a first dataset, based on one or more fixed input parameter values in the first dataset and one or more respective fixed input parameter values in a second dataset, such that the value yields a known output value in the first dataset. (mental process – evaluation or judgement; determining a value for input parameter such that the value yields a known output value)
2A Prong 2: The judicial exception is not integrated into a practical application.
(claim 1) a memory that stores computer-executable components; and a processor that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise (claim 9) by a system operatively coupled to a processor (claim 17) a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to… by the processor (mere instructions to apply an exception, (2) Whether the claim invokes computers - MPEP 2106.05(f); generic computer components)
(claim 1) a neural network model that (claim 9) using a neural network model (claim 17) using a neural network model (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; using a neural network model)
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea.
2B: The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
(claim 1) a memory that stores computer-executable components; and a processor that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise (claim 9) by a system operatively coupled to a processor (claim 17) a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to… by the processor (mere instructions to apply an exception, (2) Whether the claim invokes computers - MPEP 2106.05(f); generic computer components)
(claim 1) a neural network model that (claim 9) using a neural network model (claim 17) using a neural network model (mere instructions to apply an exception – MPEP 2106.05(f), (3) The particularity or generality of the application of the judicial exception; using a neural network model)
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
With respect to claims 2, 10 and 18:
2A Prong 2: The judicial exception is not integrated into a practical application.
wherein the first dataset comprises information provided by a user of the neural network model, wherein the known output value belongs to a class selected by the user, and wherein the second dataset comprises training data for the neural network model. (whether additional elements meaningfully limit the judicial exception – MPEP 2106.05(e); not a meaningful limitation, no actual steps, merely additional details of the claim elements)
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea.
2B: The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
wherein the first dataset comprises information provided by a user of the neural network model, wherein the known output value belongs to a class selected by the user, and wherein the second dataset comprises training data for the neural network model. (whether additional elements meaningfully limit the judicial exception – MPEP 2106.05(e); not a meaningful limitation, no actual steps, merely additional details of the claim elements)
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
With respect to claims 3, 11 and 19:
2A Prong 1: The claim recites a judicial exception.
further comprising: a computation component that computes respective Euclidean distances between the one or more fixed input parameter values in the first dataset and the one or more respective fixed input parameter values in the second dataset to enable determination of the value. (mathematical concept - mathematical calculation, computing respective Euclidean distances)
With respect to claims 4, 12 and 20:
2A Prong 1: The claim recites a judicial exception.
wherein the respective Euclidean distances are computed for an amount of the one or more respective fixed input parameter values in the second dataset that fall within a defined distance from the one or more fixed input parameter values in the first dataset. (mathematical concept - mathematical calculation and mental process – evaluation or judgement, computing respective Euclidean distances and distance comparison)
With respect to claims 5 and 13:
2A Prong 1: The claim recites a judicial exception.
further comprising: a selection component that selects a Euclidean distance from the respective Euclidean distances, such that a distance vector for the Euclidean distance is smaller than a first defined threshold, to further enable the determination of the value. (mental process – evaluation or judgement, select a Euclidean distance and distance comparison)
With respect to claims 6 and 14:
2A Prong 1: The claim recites a judicial exception.
wherein determining the value further comprises multiplying the Euclidean distance with a random number between 0 and 1. (mathematical concept - mathematical calculation, multiplying the Euclidean distance with a number)
With respect to claims 7 and 15:
2A Prong 1: The claim recites a judicial exception.
wherein determining the value further comprises identifying a point on the distance vector such that the point falls under a class in the second dataset corresponding to a known output value and projecting the point on a multi-dimensional plane. (mental process – evaluation or judgement, identifying a point and projecting the point)
With respect to claims 8 and 16:
2A Prong 1: The claim recites a judicial exception.
wherein determining the value using the respective Euclidean distances maintains a computational load on the neural network model below a second defined threshold. (mental process – evaluation or judgement, determining the value which would cause less computational load of the model as an intended result of the process of selection or feature values modification (see specification [0044] [0035]), and therefore ‘the computational load’ is not given patentable weight; see specification [0044] “Thereafter, selection component 110 can select a Euclidean distance from the respective Euclidean distances” and [0035] “Embodiments described herein can focus on feature values modification… Such an approach can involve less computation or extensive searches”)
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-2, 9-10 and 17-18 rejected under 35 U.S.C. 102 (a)(1) as being anticipated by McGrath (US 20220129794 A1)
In regard to claims 1, 9 and 17, McGrath teaches: A system, comprising: a memory that stores computer-executable components; and a processor that executes the computer-executable components stored in the memory, wherein the computer-executable components comprise: (McGrath, [0071] "As shown in FIG. 5, device 500 may include a bus 510, a processor 520, a memory 530, a storage component 540, an input component 550, an output component 560, and a communication component 570.")
a neural network model that determines a value for at least one variable input parameter in a first dataset… such that the value yields a known output value in the first dataset. (McGrath, [0044] "FIG. 2 is a diagram of an example 200 associated with generating counterfactual explanations using a machine learning model... the machine learning model may include a deep neural network, a generative adversarial network, a sequence-to-sequence learning model, or the like."; [0021] "the labeled counterfactuals may be used to train a machine learning model to determine optimal counterfactual explanations [a neural network model that determines a value for variable input parameter in a first dataset] for a prediction output [a known output value] of the qualification."; [0017]-[0018] "As shown, the reference counterfactuals may be labeled as 'good' (e.g., feasible, usable, relevant, and/or the like) or 'bad' (e.g., infeasible, unusable, irrelevant, and/or the like)... the counterfactual explanation generation model to be trained and/or updated according to feedback for sets of relevant counterfactual explanations, as described herein."; [0024]-[0025] "For example, the generator model may be configured to convert counterfactuals associated with parameters of the user information [a value for variable input parameter in a first dataset] and qualification model to text versions of the counterfactuals, referred to herein as 'counterfactual explanations.'"; see Fig. 1A, examples of counterfactual explanation such as "Increase base income by 200%" includes a value (200%) for variable input parameter (Income), hence determining counterfactual explanations includes 'determining a value for variable input parameter')
… based on one or more fixed input parameter values in the first dataset and one or more respective fixed input parameter values in a second dataset… (McGrath, [0022] "receive feedback data from the user [e.g. a first data set] that is associated with the set of counterfactual explanations, and/or train the counterfactual explanation generation model based on the set of counterfactual explanations and the feedback data, as described herein."; [0019]-[0021] "As another example, for a loan application, the user information [e.g. a first data set] may include income of the user, debt of the user, credit rating of the user, assets of the user, an amount of the loan, and/or the like... As further shown in FIG. 1B, and by reference number 115, the counterfactual explanation generation model receives, via the generator model, the user information and the prediction output."; [0048]-[0050] "As shown by reference number 305, a machine learning model may be trained using a set of observations. The set of observations may be obtained from historical data, such as training data [a second dataset] gathered during one or more processes described herein. In some implementations, the machine learning system may receive the set of observations (e.g., as input) from a user device, as described elsewhere herein... As shown by reference number 310, the set of observations includes a feature set. The feature set may include a set of variables, [fixed input parameter values] and a variable may be referred to as a feature."; in light of specification [0010]-[0011], [0042], a first dataset is the data provided by the user and a second dataset is the training data)]
PNG
media_image1.png
566
670
media_image1.png
Greyscale
PNG
media_image2.png
178
744
media_image2.png
Greyscale
Claims 9 and 17 recite substantially the same limitation as claim 1, therefore the rejection applied to claim 1 also applies to claims 9 and 17. In addition, McGrath teaches: (claim 9) by a system operatively coupled to a processor (claim 17) a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to… by the processor (McGrath, [0071] "As shown in FIG. 5, device 500 may include a bus 510, a processor 520, a memory 530, a storage component 540, an input component 550, an output component 560, and a communication component 570.")
In regard to claims 2, 10 and 18, McGrath teaches: wherein the first dataset comprises information provided by a user of the neural network model, (McGrath, [0022] "receive feedback data from the user [e.g. a first data set] that is associated with the set of counterfactual explanations, and/or train the counterfactual explanation generation model based on the set of counterfactual explanations and the feedback data, as described herein."; [0019]-[0021] "As another example, for a loan application, the user information [e.g. a first data set] may include income of the user, debt of the user, credit rating of the user, assets of the user, an amount of the loan, and/or the like... As further shown in FIG. 1B, and by reference number 115, the counterfactual explanation generation model receives, via the generator model, the user information and the prediction output.")
wherein the known output value belongs to a class selected by the user, and (McGrath, [0017] "As shown, the reference counterfactuals may be labeled as 'good' (e.g., feasible, usable, relevant, and/or the like) [e.g. a class] or 'bad' (e.g., infeasible, unusable, irrelevant, and/or the like)"; [0069] "The user device may be associated with a user (e.g., an individual that provides user information to a qualification model to attempt to qualify for a service or product) [e.g. a class: qualification for a service]"; [0022] "receive feedback data from the user that is associated with the set of counterfactual explanations")
wherein the second dataset comprises training data for the neural network model. (McGrath, [0048]-[0050] "As shown by reference number 305, a machine learning model may be trained using a set of observations. The set of observations may be obtained from historical data, such as training data [a second dataset] gathered during one or more processes described herein.")
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
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.
Claims 3-5, 8, 11-13, 16 and 19-20 rejected under 35 U.S.C. 103 as being unpatentable over McGrath as applied to claims 1, 9 and 17 in view of Cirrincione ("The on-line curvilinear component analysis (onCCA) for real-time data reduction" 20150712)
In regard to claims 3, 11 and 19, McGrath teaches: … the one or more fixed input parameter values in the first dataset and the one or more respective fixed input parameter values in the second dataset to enable determination of the value. (McGrath, [0022] "receive feedback data from the user [e.g. a first data set] that is associated with the set of counterfactual explanations, and/or train the counterfactual explanation generation model based on the set of counterfactual explanations and the feedback data, as described herein."; [0019]-[0021] "As another example, for a loan application, the user information [e.g. a first data set] may include income of the user, debt of the user, credit rating of the user, assets of the user, an amount of the loan, and/or the like... As further shown in FIG. 1B, and by reference number 115, the counterfactual explanation generation model receives, via the generator model, the user information and the prediction output."; [0048]-[0050] "As shown by reference number 305, a machine learning model may be trained using a set of observations. The set of observations may be obtained from historical data, such as training data [a second dataset] gathered during one or more processes described herein. In some implementations, the machine learning system may receive the set of observations (e.g., as input) from a user device, as described elsewhere herein... As shown by reference number 310, the set of observations includes a feature set. The feature set may include a set of variables, [fixed input parameter values] and a variable may be referred to as a feature."; in light of specification [0010]-[0011], [0042], a first dataset is the data provided by the user and a second dataset is the training data)
McGrath does not teach, but Cirrincione teaches: further comprising: a computation component that computes respective Euclidean distances between the... parameter values… and the… parameter values (Cirrincione, p. 4, A. The Algorithm "Compute the Euclidean distances between x and the X-weights which belong to the cluster of the closest BnB centroid")
It would have been obvious to one of ordinary skills in the art, before the effective filing date of the claimed invention, to have modified McGrath to incorporate the teachings of Cirrincione by including Euclidean distance with thresholds. Doing so would emphasize local distances, giving high priority to small distances (local neighborhoods) while de-emphasizing or ignoring larger distances in the output or input space. (Cirrincione, p. 3, The Curvilinear Component Analysis "CCA defines a distance function threshold, say λ (topological constraint), in order to determine short and long between-point distances Dij. In this way, the CCA favors short distances, which implies local distance preservation.")
In regard to claims 4, 12 and 20, McGrath teaches: the one or more respective fixed input parameter values in the second dataset… the one or more fixed input parameter values in the first dataset. (McGrath, [0022] "receive feedback data from the user [e.g. a first data set] that is associated with the set of counterfactual explanations, and/or train the counterfactual explanation generation model based on the set of counterfactual explanations and the feedback data, as described herein."; [0019]-[0021] "As another example, for a loan application, the user information [e.g. a first data set] may include income of the user, debt of the user, credit rating of the user, assets of the user, an amount of the loan, and/or the like... As further shown in FIG. 1B, and by reference number 115, the counterfactual explanation generation model receives, via the generator model, the user information and the prediction output."; [0048]-[0050] "As shown by reference number 305, a machine learning model may be trained using a set of observations. The set of observations may be obtained from historical data, such as training data [a second dataset] gathered during one or more processes described herein. In some implementations, the machine learning system may receive the set of observations (e.g., as input) from a user device, as described elsewhere herein... As shown by reference number 310, the set of observations includes a feature set. The feature set may include a set of variables, [fixed input parameter values] and a variable may be referred to as a feature."; in light of specification [0010]-[0011], [0042], a first dataset is the data provided by the user and a second dataset is the training data)
McGrath does not teach, but Cirrincione teaches: wherein the respective Euclidean distances are computed for an amount of the… parameter values… that fall within a defined distance from the… parameter values... (Cirrincione, p. 4, A. The Algorithm "Compute the Euclidean distances [the Euclidean distance] between x and the X-weights which belong to the cluster of the closest BnB centroid; if there exists a neuron whose X-distance is higher than the scalar threshold ρ [a defined distance] (novelty test), go to step 3 (see Fig. 3), else go to step 14 (see Fig. 4) [a subset of points in the X space, an amount of the values]")
The rationale for combining the teachings of McGrath and Cirrincione is the same as set forth in the rejection of claim 3.
In regard to claims 5 and 13, McGrath does not teach, but Cirrincione teaches: further comprising: a selection component that selects a Euclidean distance from the respective Euclidean distances, such that a distance vector for the Euclidean distance is smaller than a first defined threshold, to further enable the determination of the value. (Cirrincione, p. 4, A. The Algorithm "Compute the Euclidean distances between x and the X-weights which belong to the cluster of the closest BnB centroid; if there exists a neuron whose X-distance [selects a Euclidean distance (x-1, x-2) from the respective Euclidean distances (in X space)] is higher than the scalar threshold ρ (novelty test), go to step 3 (see Fig. 3), else [a distance length for the Euclidean distance (x-1, x-2 in X space) is smaller than a first defined threshold ρ] go to step 14 (see Fig. 4)... 14. Find the nearest X-weight, say x-1(first winner) and the second-nearest X-weight, say x-2 (second winner)... 21. Determine the neurons whose Y-weights are within the sphere of radius λ centered in the first winner, say λ-neurons (topological constraint). 22. Fix a λ-neuron and adjust the Y-weights of the other λ-neurons according to (2) for several projection steps. [enable the determination of the value]")
PNG
media_image3.png
688
702
media_image3.png
Greyscale
The rationale for combining the teachings of McGrath and Cirrincione is the same as set forth in the rejection of claim 3.
In regard to claims 8 and 16, McGrath does not teach, but Cirrincione teaches: wherein determining the value using the respective Euclidean distances maintains a computational load on the neural network model below a second defined threshold. (Cirrincione, p. 4, A. The Algorithm "The problem of the global projection: for reasons of computational cost and time, it is impossible to project all data at each iteration. Two resolution parameters, δ in the X space and λ in the Y space [a second threshold] are therefore introduced for reducing the number of projections. [maintains a computational load on the model]")
The rationale for combining the teachings of McGrath and Cirrincione is the same as set forth in the rejection of claim 3.
Claims 6-7 and 14-15 rejected under 35 U.S.C. 103 as being unpatentable over McGrath and Cirrincione as applied to claims 5 and 13, and in further view of Zhang ("Classification and prediction of spinal disease based on the SMOTE-RFE XGBoost model" 20230310)
In regard to claims 6 and 14, McGrath and Cirrincione do not teach, but Zhang teaches: wherein determining the value further comprises multiplying the Euclidean distance with a random number between 0 and 1. (Zhang, p. 12, Class imbalance processing based on SMOTE "According to the principle of the SMOTE algorithm, the process of synthesizing a new sample will randomly select one of the five nearest neighbor samples, multiply the Euclidean distance of the two samples by a random number between (0, 1), and determine the exact location of the synthesized sample based on the new distance.")
It would have been obvious to one of ordinary skills in the art, before the effective filing date of the claimed invention, to have modified McGrath and Cirrincione to incorporate the teachings of Zhang by including an over-sampling approach with synthetic examples between features. Doing so would have higher accuracy than the traditional sampling method. (Zhang, p. 6, Principle of the SMOTE algorithm "The SMOTE algorithm is essentially an oversampling; it does not sample on the data space but in the feature space, so its accuracy will be higher than the traditional sampling method.")
In regard to claims 7 and 15, McGrath and Cirrincione do not teach, but Zhang teaches: wherein determining the value further comprises identifying a point on the distance vector such that the point falls under a class in the second dataset corresponding to a known output value and projecting the point on a multi-dimensional plane. (Zhang, p. 6, Principle of the SMOTE algorithm "In the SMOTE algorithm, the neighborhood space is determined by the K-nearest neighbor method... The synthesis of the new sample x_new is calculated as shown in Eq. (1) is shown. where x is the selected master sample, x′ is the randomly selected nearest neighbor sample of x, x_new is the synthesized new sample, and rand(0, 1) denotes the random number on the generated (0, 1). x_new = x + rand(0, 1) x (x'-x) (1)"; see Fig. 2, synthetic sample is 'a point' under the class 'minority' which is a known value, and Fig. 2 is a two-
PNG
media_image4.png
314
526
media_image4.png
Greyscale
dimensional plane)
The rationale for combining the teachings of McGrath, Cirrincione and Zhang is the same as set forth in the rejection of claim 6.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Chawla ("SMOTE: Synthetic Minority Over-sampling Technique" 2002) teaches (Chawla, p. 328, 4.2 SMOTE "Synthetic samples are generated in the following way: Take the difference between the feature vector (sample) under consideration and its nearest neighbor. Multiply this difference by a random number between 0 and 1, and add it to the feature vector under consideration.")
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SU-TING CHUANG whose telephone number is (408)918-7519. The examiner can normally be reached Monday - Thursday 8-5 PT.
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, Usmaan Saeed can be reached at (571) 272-4046. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/S.C./Examiner, Art Unit 2146
/USMAAN SAEED/Supervisory Patent Examiner, Art Unit 2146
Prosecution Insights