DETAILED ACTION
Notice of 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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 7/2/2026 has been entered.
Response to Amendment
Applicant’s Amendment and remarks dated 7/2/2026 have been considered. Claims 1-10 are pending.
Response to Arguments
On page 6 of Applicant’s 7/2/2026 Amendment and remarks, Applicant asserts that at least paras. 0062 and 0084 of the instant specification provide written description support for the claim amendments.
The examiner agrees that the portions of the disclosure identified by Applicant provide sufficient written description support for the claim amendments.
On page 7 of Applicant’s 7/2/2026 Amendment and remarks, with respect to the rejections under 35 U.S.C. 101, Applicant argues that the present claims are analogous to Example 47 of the subject matter eligibility examples.
PNG
media_image1.png
226
668
media_image1.png
Greyscale
The examiner respectfully disagrees. Example 47 pertains to anomaly detection to detect malicious network packets. Example 47 explains that claim 3 is eligible because the claim relates to an improvement to a computer or to a technological field. In contrast, the present claims do not present any improvements to a computer or to a technological field.
The examiner further finds that limitation e1), which recites at a high-level “increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality” is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation attempts to cover a solution to an identified problem with no restriction on how the result is accomplished, or provides no description of the mechanism for accomplishing the result (any techniques for increasing fresh air supply are covered, such as opening windows, opening doors, using HVAC systems, etc.). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
On page 7 of Applicant’s 7/2/2026 Amendment and remarks, with respect to the rejections under 35 U.S.C. 103, Applicant argues that the prior art of record does not teach the “normalization and mean-imputation” limitations, and further that the prior art of record does not disclose “generating both real-time and future predictions based on measured IAQ data.”
Applicant’s argument is persuasive. The previous rejections under 35 U.S.C. 103 are withdrawn, and new grounds of rejection in view of the TANGUCHI, LIU, SAVAKKANAVAR, LI, and LU references are provided below.
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.
Claims 1-10 are rejected 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.
In claim 1, limitation e1) recites “increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality.” The recitation to “the prediction” is indefinite because in limitation e), there are 2 different predictions introduced (real-time and future predictions) and it is unclear which of these predictions (or both) are being utilized in limitation e1). MPEP 2173.02 explains: “if the language of a claim, given its broadest reasonable interpretation, is such that a person of ordinary skill in the relevant art would read it with more than one reasonable interpretation, then a rejection under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph is appropriate.” Therefore, because “the prediction” could refer to (1) the real-time prediction, (2) the future prediction, (3) at least one of the real-time and future predictions, or (4) both the real-time and future predictions, the claim is indefinite. For purposes of compact prosecution, “the prediction” will be interpreted as at least one of the real-time and future predictions.
Claims 2-8 depend from claim 1, do not remedy the deficiencies of claim 1, and are rejected for the same reasons explained above with respect to claim 1.
In claim 9, limitation vii) recites “increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality.” The recitation to “the prediction” is indefinite because in limitation vi), there are 2 different predictions introduced (real-time and future predictions) and it is unclear which of these predictions (or both) are being utilized in limitation e1). MPEP 2173.02 explains: “if the language of a claim, given its broadest reasonable interpretation, is such that a person of ordinary skill in the relevant art would read it with more than one reasonable interpretation, then a rejection under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph is appropriate.” Therefore, because “the prediction” could refer to (1) the real-time prediction, (2) the future prediction, (3) at least one of the real-time and future predictions, or (4) both the real-time and future predictions, the claim is indefinite. For purposes of compact prosecution, “the prediction” will be interpreted as at least one of the real-time and future predictions.
In claim 10, limitation e1) recites “increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality.” The recitation to “the prediction” is indefinite because in limitation e), there are 2 different predictions introduced (real-time and future predictions) and it is unclear which of these predictions (or both) are being utilized in limitation e1). MPEP 2173.02 explains: “if the language of a claim, given its broadest reasonable interpretation, is such that a person of ordinary skill in the relevant art would read it with more than one reasonable interpretation, then a rejection under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph is appropriate.” Therefore, because “the prediction” could refer to (1) the real-time prediction, (2) the future prediction, (3) at least one of the real-time and future predictions, or (4) both the real-time and future predictions, the claim is indefinite. For purposes of compact prosecution, “the prediction” will be interpreted as at least one of the real-time and future predictions.
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 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding Step 1 of the Alice/Mayo framework, Claims 1-8 are directed to a method (a process), Claim 9 is directed to an apparatus (a machine), and Claim 10 is directed to a non-transitory computer readable medium (an article of manufacture), which each fall within one of the four statutory categories of inventions.
Regarding Claim 1
Step 2A, prong 1 (Is the claim directed to a law of nature, a natural phenomenon or an abstract idea).
Claim 1 recites the following mental processes, that in each case under the broadest reasonable interpretation, covers performance of the limitation in the mind (including an observation, evaluation, judgment, opinion) or with the aid of pencil and paper but for the recitation of generic computer components (e.g., “artificial intelligence (AI) models” and “computing devices”).
A method for predicting concentration of indoor bioaerosols and maintaining indoor air quality, comprising steps of: (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally predict a concentration of indoor bioaerosols, e.g., a prediction of 0% for clean room with state-of-the-art filtering, and the human can mentally determine steps for maintaining indoor air quality of the clean room)
b) evaluating a prediction accuracy of each of the plurality of Al models for a venue; (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally evaluate the prediction accuracy of each of the AI models for a venue, such as by mentally reviewing the outputs of an analysis of the prediction accuracy for each model)
c) choosing a best model from the plurality of Al models for the venue; and (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally choose the model with the highest accuracy as the recited “best model”)
c2) conducting mean imputation on the measured data (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally view time-series data, and if the data appears to have missed a value, mean imputation can be used to impute the missing value mentally)
c3) normalizing the measured data and concentrations of a plurality of indoor bioaerosols (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally normalize measured data and concentrations so that they are within pre-specified ranges and concentration types (e.g., per mL vs. per liter)
e) generating real-time and future predictions of concentration of a plurality of indoor (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally bioaerosols ... for the venue using the measured data (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally predict real-time and future concentrations of indoor bioaerosols using measured data for a venue, e.g., a prediction of 0% for clean room with state-of-the-art filtering)
Step 2A, prong 2 (Does the claim recite additional elements that integrate the judicial exception into a practical application?).
The judicial exception is not integrated into a practical application. In particular, the claim recites the additional elements (e.g., “artificial intelligence (AI) models” and “computing devices”) which are recited at a high-level of generality such that they amount to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
Regarding the “a) providing a plurality of artificial intelligence (AI) models on a computing device” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of AI models on generic computing devices. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (AI models, without specific details about such AI model’s architecture, training, configuration, hyperparameters, etc.). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Regarding the “c1) measuring, using a real-time air quality sensor located in the venue, physical and chemical properties of indoor air at the venue in real-time to obtain measured data; the real-time air quality sensor connected to the computing device” limitation, such additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process (see MPEP 2106.05(g)).
Regarding the “d) inputting the measured data into the best model on the computing device” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of AI models. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (AI models, without specific details about such AI model’s architecture, training, configuration, hyperparameters, etc.). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Regarding the “... by the best model” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of AI models. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (AI models, without specific details about such AI model’s architecture, training, configuration, hyperparameters, etc.). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Regarding the “e1) increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation attempts to cover a solution to an identified problem with no restriction on how the result is accomplished, or provides no description of the mechanism for accomplishing the result. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Accordingly, at Step 2A, prong two, after considering all claim elements individually and as an ordered combination, it is determined that the claims do not integrate the judicial exception into a practical application.
Step 2B (Does the claim recite additional elements that amount to significantly more than the judicial exception?)
In accordance with Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more that the judicial exception. As discussed above, the additional elements (e.g., “artificial intelligence (AI) models” and “computing devices”) are recited at a high-level of generality such that they amount to no more than mere instructions to apply the exception using a generic computer component (See MPEP 2106.05(f)).
Regarding the “a) providing a plurality of artificial intelligence (AI) models on a computing device” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding the “c1) measuring, using a real-time air quality sensor located in the venue, physical and chemical properties of indoor air at the venue in real-time to obtain measured data; the real-time air quality sensor connected to the computing device” limitation, as discussed above, the additional element of a data gathering step is recited at a high level of generality and amounts to extra-solution activity of receiving data, i.e. pre-solution activity of gathering data for use in the claimed process. The courts have found limitations directed to obtaining information electronically, recited at a high level of generality, to be well-understood, routine, and conventional (see MPEP 2106.05(d)(II), “receiving or transmitting data over a network”, "electronic record keeping," and "storing and retrieving information in memory").
Regarding the “d) inputting the measured data into the best model on the computing device” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding the “... by the best model” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding the “e1) increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation attempts to cover a solution to an identified problem with no restriction on how the result is accomplished, or provides no description of the mechanism for accomplishing the result. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Accordingly, at Step 2B, after considering all claim elements individually and as an ordered combination, it is determined that the claims do not amount to significantly more than the judicial exception.
Regarding Claim 2
Step 2A, Prong 2
Regarding the “wherein the plurality of Al models includes one or more of a linear regression model, a lasso regression model, a random forest (RF) model, an extreme gradient boosting model, a multilayer perceptron model, an LSTM model, and a recurrent neural network model” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of an AI model. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (an AI model of a particular type, which still does not claim sufficient details regarding the architecture, configuration, training, hyperparameters, etc.). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)). Moreover, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use (particular categories of machine learning models). As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not integrate a judicial exception into a practical application.
Step 2B
Regarding the “wherein the plurality of Al models includes one or more of a linear regression model, a lasso regression model, a random forest (RF) model, an extreme gradient boosting model, a multilayer perceptron model, an LSTM model, and a recurrent neural network model” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)). Moreover, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use as explained above, which does not amount to significantly more than the judicial exception. MPEP 2106.05(h).
Regarding Claim 3
Step 2A, Prong 1
h) finding, for each of the plurality of Al model, a difference data between predicted test data and measured test data; (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally subtract the measured test data from the predicted test data to determine difference data; the examiner further notes that this subtraction operation is a mathematical calculation, which is another type of abstract idea)
i) determining one of the plurality of Al models that has a best difference data as the best model. (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally determine that the AI model that has the highest accuracy, or the lowest difference data, as the best model)
Step 2A, Prong 2
Regarding the “f) inputting test data for the venue into each of the plurality of Al models” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception. In particular, the claim only recites the additional element of AI models. This additional element is recited at a high-level of generality and amounts to no more than mere instructions to apply the exception using a generic computer component (AI models, without specific details about such AI model’s architecture, training, configuration, hyperparameters, etc.). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Regarding the “g) applying more than one pair of input and output time windows” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation attempts to cover a solution to an identified problem with no restriction on how the result is accomplished, or provides no description of the mechanism for accomplishing the result (applying any pair of time windows to a generic AI model, without any particular guidance as to how to select the time windows and how to configure the AI model to utilize such time windows). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Step 2B
Regarding the “f) inputting test data for the venue into each of the plurality of Al models” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation merely provides instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding the “g) applying more than one pair of input and output time windows” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation attempts to cover a solution to an identified problem with no restriction on how the result is accomplished, or provides no description of the mechanism for accomplishing the result. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding Claim 4
Step 2A, Prong 1
wherein the difference data comprises one or more of a mean squared error (MSE), a root-mean-square error (RMSE) and a value on a revised version of the Willmott's index (WI). (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally subtract the measured test data from the predicted test data to determine difference data and then perform calculations of MSE or RMSE; the examiner further notes that this operation is a mathematical calculation, which is another type of abstract idea)
Regarding Step 2A, Prong 2, the claim does not include any additional elements that integrate the judicial exception into a practical application and regarding Step 2B, there are no additional elements recited that amount to significantly more than the judicial exception.
Regarding Claim 5
Step 2A, Prong 2
Regarding the “wherein the more than one pair of input and output time windows comprises a real-time window pair” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation attempts to cover a solution to an identified problem with no restriction on how the result is accomplished, or provides no description of the mechanism for accomplishing the result (applying any pair of time windows to a generic AI model, without any particular guidance as to how to select the time windows and how to configure the AI model to utilize such time windows). Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea (See MPEP 2106.05(f)).
Step 2B
Regarding the “wherein the more than one pair of input and output time windows comprises a real-time window pair” limitation, such limitation is recited at a high-level of generality and amounts to no more than adding the words “apply it” (or an equivalent) with the judicial exception, because the limitation attempts to cover a solution to an identified problem with no restriction on how the result is accomplished, or provides no description of the mechanism for accomplishing the result. Accordingly, this additional element does not add significantly more than the judicial exception. (See MPEP 2106.05(f)).
Regarding Claim 6
Step 2A, Prong 1
the method further comprising a step of determining which one of the plurality of input features is more important than another one by conducting a permutation importance analysis (under the broadest reasonable interpretation, a human can mentally perform this limitation, for example, a human can mentally perform a permutation importance analysis to determine the input feature that is most important to the accuracy of the AI models, e.g., trying different permutations of input features and mentally determining which permutation has the highest accuracy)
Step 2A, Prong 2
Regarding the “wherein the measured data comprises a plurality of input features” limitation, this limitation merely describes the types of input data being processed, and therefore such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not integrate a judicial exception into a practical application.
Step 2B
Regarding the “wherein the measured data comprises a plurality of input features” limitation, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use as explained above, which does not amount to significantly more than the judicial exception. MPEP 2106.05(h).
Regarding Claim 7
Step 2A, Prong 2
Regarding the “wherein the plurality of input features comprises one or more of temperature, relative humidity (RH), concentrations of CO2, total volatile organic compounds (TVOCs), PM2.5 and PM10” limitation, this limitation merely describes the types of input data being processed, and therefore such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not integrate a judicial exception into a practical application.
Step 2B
Regarding the “wherein the plurality of input features comprises one or more of temperature, relative humidity (RH), concentrations of CO2, total volatile organic compounds (TVOCs), PM2.5 and PM10” limitation, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use as explained above, which does not amount to significantly more than the judicial exception. MPEP 2106.05(h).
Regarding Claim 8
Step 2A, Prong 2
Regarding the “wherein the plurality of input features comprises concentrations of more than one biological matters” limitation, this limitation merely describes the types of input data being processed, and therefore such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use. As explained by the Supreme Court, a claim directed to a judicial exception cannot be made eligible "simply by having the applicant acquiesce to limiting the reach of the patent for the formula to a particular technological use." Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981). Thus, limitations that amount to merely indicating a field of use or technological environment in which to apply a judicial exception do not integrate a judicial exception into a practical application.
Step 2B
Regarding the “wherein the plurality of input features comprises concentrations of more than one biological matters” limitation, such limitation amounts to no more than generally linking the use of a judicial exception to a particular technological environment or field of use as explained above, which does not amount to significantly more than the judicial exception. MPEP 2106.05(h).
Regarding Claim 9
Step 2A, Prong 1
Claim 9 recites an apparatus that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 1 with respect to claim 1 also applies to this claim 9. While claim 9 recites additional generic computing components (“one or more processors”, “memory storing computer-executable instructions”, “artificial intelligence (AI) models”), such additional generic computing components do not change the analysis under Step 2A, Prong 1.
Step 2A, Prong 2
Claim 9 recites an apparatus that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 2 with respect to claim 1 also applies to this claim 9. While claim 9 recites additional generic computing components (“one or more processors”, “memory storing computer-executable instructions”, “artificial intelligence (AI) models”), such additional generic computing components do not change the analysis under Step 2A, Prong 2.
Step 2B
Claim 9 recites an apparatus that corresponds to the method of claim 1, and therefore the analysis under Step 2B with respect to claim 1 also applies to this claim 9. While claim 9 recites additional generic computing components (“one or more processors”, “memory storing computer-executable instructions”, “artificial intelligence (AI) models”), such additional generic computing components do not change the analysis under Step 2B.
Regarding Claim 10
Step 2A, Prong 1
Claim 10 recites a non-transitory computer readable medium that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 1 with respect to claim 1 also applies to this claim 10. While claim 10 recites additional generic computing components (processor”, “non-transitory computer readable medium”, “computing device” and “artificial intelligence (AI) models”), such additional generic computing components do not change the analysis under Step 2A, Prong 1.
Step 2A, Prong 2
Claim 10 recites a non-transitory computer readable medium that corresponds to the method of claim 1, and therefore the analysis under Step 2A, Prong 2 with respect to claim 1 also applies to this claim 10. While claim 10 recites additional generic computing components (processor”, “non-transitory computer readable medium”, “computing device” and “artificial intelligence (AI) models”), such additional generic computing components do not change the analysis under Step 2A, Prong 2.
Step 2B
Claim 10 recites a non-transitory computer readable medium that corresponds to the method of claim 1, and therefore the analysis under Step 2B with respect to claim 1 also applies to this claim 10. While claim 10 recites additional generic computing components (processor”, “non-transitory computer readable medium”, “computing device” and “artificial intelligence (AI) models”), such additional generic computing components do not change the analysis under Step 2B.
Claim Rejections - 35 USC § 103
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 1-2 and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over US 20210012244 A1, hereinafter referenced as TANIGUCHI, in view of Liu, Zhijian, et al. "Quick estimation model for the concentration of indoor airborne culturable bacteria: an application of machine learning." International journal of environmental research and public health 14.8 (2017): 857, hereinafter referenced as LIU, and further in view of US 20210364184 A1, hereinafter referenced as SAVAKKANAVAR, and further in view of Li, Xiaonan, et al. "Forecasting of bioaerosol concentration by a Back Propagation neural network model." Science of the Total Environment 698 (2020), hereinafter referenced as LI, and further in view of US 20220076836 A1, hereinafter referenced as LU.
Regarding Claim 1
TANIGUCHI discloses:
a) providing a plurality of artificial intelligence (AI) models on a computing device; (TANIGUCHI, para. 0021: A model generation program according to the present invention causes a computer to execute the processes of: ... determining a prediction model used for the progress prediction from among the plurality of the learned prediction models based on an evaluation result regarding the prediction accuracy and an evaluation result regarding the graph shape or the number of defective samples.”;
TANIGUCHI, para. 0080: “The model selection unit 13 selects a prediction model that has a high prediction accuracy and has a small number of samples (hereinafter referred to as the number of defective samples) that cannot be interpreted from among a plurality of prediction models (learned models having mutually different values of the regularization parameters that affect the term of the strong regularization variable) learned by the model learning unit 12.”;
TANIGUCHI, para. 0246: “FIG. 19 is a schematic block diagram showing a configuration example of a computer according to each exemplary embodiment of the present invention. A computer 1000 includes a CPU 1001, a main storage device 1002, an auxiliary storage device 1003, an interface 1004, a display device 1005, and an input device 1006.”)
b) evaluating a prediction accuracy of each of the plurality of Al models ...; (TANIGUCHI, para. 0257: “The accuracy evaluation means 63 (for example, a part of the model selection unit 13, a part of the model selection unit 223, the model evaluation unit 131), evaluates the prediction accuracy of each of the plurality of learned prediction models using the predetermined verification data.”)
c) choosing a best model from the plurality of Al models ...; (TANIGUCHI, para. 0089: “Next, the model selection unit 13 selects a prediction model having a high prediction accuracy and a small number of defective samples from among the plurality of learned prediction models, and stores it in the model storage unit 14 (step S104).”;
TANIGUCHI, para. 0259: “The model determination means 65 (for example, a part of the model selection unit 13, a part of the model selection unit 223, the model determination unit 132) determines, based on the evaluation result regarding the prediction accuracy and the evaluation result regarding the graph shape or the number of defective samples, a single prediction model to be used for the progress prediction from among the plurality of learned prediction models.”)
d) inputting the measured data into the best model on the computing device; and (TANIGUCHI, para. 0080: “When the prediction target data is input, the model application unit 15 uses the prediction model stored in the model storage unit 14 to perform progress prediction.”;
TANIGUCHI, para. 0082: “When the prediction target data is input, the model application unit 15 uses the prediction model stored in the model storage unit 14 to perform progress prediction.”;
TANIGUCHI, para. 0092: “When the prediction target data is input, the model application unit 15 reads the prediction model stored in the model storage unit 14 (step S202), applies the prediction target data to the read prediction model, and obtains a predicted value at each prediction time point included in the evaluation target period (step S203).”;
TANIGUCHI, para. 0263: “The prediction means 67 (for example, the model application unit 15, the model application unit 25), when the prediction target data is given, uses the prediction model stored in the model storage means 66 to perform progress prediction.”);
TANIGUCHI, para. 0246: “FIG. 19 is a schematic block diagram showing a configuration example of a computer according to each exemplary embodiment of the present invention. A computer 1000 includes a CPU 1001, a main storage device 1002, an auxiliary storage device 1003, an interface 1004, a display device 1005, and an input device 1006.”)
However, TANIGUCHI fails to explicitly teach:
A method for predicting concentration of indoor bioaerosols and maintaining indoor air quality, comprising steps of:
... for a venue
... for the venue
c1) measuring, using a real-time air quality sensor located in the venue, physical and chemical properties of indoor air at the venue in real-time to obtain measured data; the real-time air quality sensor connected to the computing device
c2) conducting mean imputation on the measured data;
c3) normalizing the measured data and concentrations of a plurality of indoor bioaerosols;
e) generating real-time and future predictions of concentrations of a plurality of indoor bioaerosols by the best model for the venue using the measured data
e1) increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality
However, in a related field of endeavor (neural networks to estimate the indoor concentration of airborne culturable bacteria, see p. 2, section 1), LIU teaches:
A method for predicting concentration of indoor bioaerosols ..., comprising steps of: (LIU, p. 2, section 1: “In this communication, we aim to propose a quick estimation method of the concentration of indoor airborne culturable bacteria using ANN models. Our results show that with the simple inputs of indoor PM2.5 and PM10, temperature, relative humidity, and CO2 concentration, the model trained from our experimental database with 249 data groups can effectively predict the concentration of indoor airborne culturable bacteria with relatively low root mean square errors (RMS errors).”; Examiner’s Note: The TANIGUCHI-LIU combination now utilizes the techniques of TANIGUCHI with respect to selecting a particular, high accuracy machine learning model, in order to estimate concentrations of indoor airborne culturable bacteria (corresponding to recited “indoor bioaerosols”) of LIU)
b) evaluating a prediction accuracy of each of the plurality of Al models for a venue; (LIU, p. 2, section 2: “To develop a model for estimating the concentration of indoor airborne culturable bacteria, we chose a series of independent variables that can be easily measured inside a building, .... All the data were measured in various buildings in Baoding”; Examiner’s Note: LIU teaches estimating the concentration of indoor airborne culturable bacteria in a building (corresponding to recited “venue”); TANIGUCHI-LIU combination now utilizes the techniques of TANIGUCHI with respect to evaluating accuracy of a plurality of models to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU)
c) choosing a best model from the plurality of Al models for the venue; (LIU, p. 2, section 2: “To develop a model for estimating the concentration of indoor airborne culturable bacteria, we chose a series of independent variables that can be easily measured inside a building, .... All the data were measured in various buildings in Baoding”; Examiner’s Note: LIU teaches estimating the concentration of indoor airborne culturable bacteria in a building (corresponding to recited “venue”); TANIGUCHI-LIU combination now utilizes the techniques of TANIGUCHI with respect to choosing a high accuracy model (corresponding to recited “best model”) from a plurality of models to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU)
e) generating ... predictions of concentrations of a plurality of indoor bioaerosols by the best model for the venue ... (LIU, p. 2, section 2: “To develop a model for estimating the concentration of indoor airborne culturable bacteria, we chose a series of independent variables that can be easily measured inside a building, .... All the data were measured in various buildings in Baoding”; Examiner’s Note: LIU teaches estimating the concentration of indoor airborne culturable bacteria in a building (corresponding to recited “venue”), where more than one types of bacteria corresponds to the recited “plurality of indoor bioaerosols”; the TANIGUCHI-LIU combination now utilizes the techniques of TANIGUCHI with respect to using a selected model (based on high accuracy) to estimate the concentrations of indoor airborne culturable bacteria in a building as in LIU)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI the teachings of LIU as explained above. As disclosed by LIU, one of ordinary skill would have been motivated to do so because “many indoor microorganisms are potential threats to human health” and determining the concentration of such indoor microorganisms will help to “reduce the potential threats of indoor inhalable microorganisms.” (LIU, p. 1, section 1). One of ordinary skill in the art would further understand the benefit of using the teachings of LIU, which teach an estimation technique that “can dramatically reduce the measurement time from days to seconds, saving much time, economic cost, and manpower.” (LIU, p. 7, section 4).
However, TANIGUICHI and LIU fail to explicitly teach:
... maintaining indoor air quality
c1) measuring, using a real-time air quality sensor located in the venue, physical and chemical properties of indoor air at the venue in real-time to obtain measured data; the real-time air quality sensor connected to the computing device
... using the measured data.
c2) conducting mean imputation on the measured data;
c3) normalizing the measured data and concentrations of a plurality of indoor bioaerosols;
e) real-time and future predictions of concentrations ... using the measured data
e1) increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality
However, in a related field of endeavor (“accurately measuring and controlling air quality of indoor environment using IoT technology and Artificial Intelligence”, para. 0001), SAVAKKANAVAR teaches and makes obvious:
A method for predicting concentration of indoor bioaerosols and maintaining indoor air quality, comprising steps of: (SAVAKKANAVAR, para. 0070: “The system helps to achieve desired effect in the indoor environment and can be used for providing clean/fresh air in the indoor environment. Further, the system helps to measures taken in emergency situations such as during earthquake, fire, electrocution and accordingly control the indoor environment to supply clean air and to reduce indoor pollution.”;
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR combination now maintains indoor air quality (for indoor venues of LIU and SAVAKKANAR) by using the teachings of SAVAKKANAR to supply clean air and to reduce indoor pollution)
c1) measuring, using a real-time air quality sensor located in the venue, physical and chemical properties of indoor air at the venue in real-time to obtain measured data; the real-time air quality sensor connected to the computing device (SAVAKKANAVAR, para. 0025: “The system 110 might include a server or a computer or a laptop, a smart phone or any electronic device comprising an application to execute functions for measuring air quality of indoor environment and controlling the air quality.”
SAVAKKANAVAR, para. 0031: “Referring to FIG. 1, the system 110 might be communicatively coupled to the indoor sensors 150, 152, 154, and 156. In one example, the indoor sensor 150 may indicate a sensor configured for measuring the amount of at least one or more volatile organic compounds (□VOCs□), carbon dioxide, carbon monoxide, methane gas, or a combination thereof in the air, and wherein the solid particles and/or liquid droplets are mold spores, bacteria, dust mites, dust, PM2.5, insect faeces, pollen, smoke, dander, saliva, mucus, other airborne allergens, or a combination thereof.”;
SAVAKKANAVAR, para. 0032: “In one example, the indoor sensor 152 may indicate a sensor configured for sensing parameter that can affect IAQ parameters. For example, the indoor sensor 154 may include occupancy sensors, activity sensors, sunlight sensors, ground-moisture sensors, and so on.”
SAVAKKANAVAR, para. 0061: “Specifically, the system 110 might learn the pattern of the IAQ parameters measured and set desired IAQ parameters automatically monitor air quality, air pollutant signatures, and thermal comfort levels in real-time. In addition, based on a mathematical classifier (i.e., algorithm) trained on a supervised machine-learning method (such as SVM), the system 110 might automatically turn on/off, power up/down and/or open/close the healthy gas storage container 175, the air conditioned unit 180 and operate the plurality of indoor filters 160, 162, according to different air-related data measured in real-time using the plurality of indoor sensors 150, 152, 154, 156, the indoor air sample analyser 170, the healthy gas storage container 175, the air conditioned unit 180, the external sensors 200, the outdoor air sample analyser 205, the environment server 210, the outdoor temperature sensor 215, and the outdoor healthy air sensor 220 to control the air quality of the indoor environment 107.”;
Examiner’s Note: SAVAKKANAVAR discloses monitoring, using indoor real-time sensors, properties such as the amount of “carbon dioxide, carbon monoxide, methane gas” in the air (corresponding to recited “chemical properties”) and sensors including “occupancy sensors, activity sensors, sunlight sensors, ground-moisture sensors” (corresponding to recited sensors for “physical properties”), where such sensors are connected to a computing device; the TANIGUCHI-LIU-SAVAKKANAVAR combination now utilizes the techniques of TANIGUCHI with respect to using a selected model (based on high accuracy) to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU, where real-time sensor data is collected for the building or room as in SAVAKKANAVAR)
e) generating real-time ... predictions of concentrations of indoor bioaerosols of a plurality of indoor bioaerosols by the best model for the venue using the measured data. (SAVAKKANAVAR, para. 0031: “Referring to FIG. 1, the system 110 might be communicatively coupled to the indoor sensors 150, 152, 154, and 156. In one example, the indoor sensor 150 may indicate a sensor configured for measuring the amount of at least one or more volatile organic compounds (□VOCs□), carbon dioxide, carbon monoxide, methane gas, or a combination thereof in the air, and wherein the solid particles and/or liquid droplets are mold spores, bacteria, dust mites, dust, PM2.5, insect faeces, pollen, smoke, dander, saliva, mucus, other airborne allergens, or a combination thereof.”;
SAVAKKANAVAR, para. 0032: “In one example, the indoor sensor 152 may indicate a sensor configured for sensing parameter that can affect IAQ parameters. For example, the indoor sensor 154 may include occupancy sensors, activity sensors, sunlight sensors, ground-moisture sensors, and so on.”
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR combination now utilizes the techniques of TANIGUCHI with respect to using a selected model (based on high accuracy) to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU, where real-time sensor data is measured for the building or room as in SAVAKKANAVAR such that the model of LIU is used to generate a real-time prediction based on the real-time measured data of SAVAKKANAVAR)
e1) increasing fresh air supply based on the prediction to maintain the indoor air quality, if the prediction indicates a worsening of the indoor air quality (SAVAKKANAVAR, para. 0070: “The system helps to achieve desired effect in the indoor environment and can be used for providing clean/fresh air in the indoor environment. Further, the system helps to measures taken in emergency situations such as during earthquake, fire, electrocution and accordingly control the indoor environment to supply clean air and to reduce indoor pollution.”;
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR combination now maintains indoor air quality (for indoor venues of LIU and SAVAKKANAR) by using the teachings of SAVAKKANAR to supply clean air and to reduce indoor pollution)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI the teachings of LIU and SAVAKKANAVAR as explained above. As disclosed by SAVAKKANAVAR, one of ordinary skill would have been motivated to do so “to accurately measure air quality of indoor environment and control the air quality so as to improve indoor air quality and livability of subjects (human beings or animals).” (para. 0003).
However, TANIGUCHI, LIU, and SAVAKKANAVAR fail to explicitly teach:
c2) conducting mean imputation on the measured data;
c3) normalizing the measured data and concentrations of a plurality of indoor bioaerosols;
... future predictions ...
However, in a related field of endeavor (forecasting bioaerosol concentrations using a neural network), LI teaches and makes obvious:
e) generating real-time and future predictions of concentrations of a plurality of indoor bioaerosols by the best model for the venue using the measured data (LI, p. 2, section 1: “To our best knowledge, this study is the first time to use BP neural network to forecast bioaerosol concentration.”;
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR-LI combination now forecasts bioaerosol concentrations for future concentrations of bioaerosols as in LI)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI the teachings of LIU, SAVAKKANAVAR, and LI as explained above. As disclosed by LI, one of ordinary skill would have been motivated to do so in order to “used as a guide to environment and public health researchers.” (p. 9, section 4).
However, TANIGUCHI, LIU, SAVAKKANAVAR, and LI fail to explicitly teach:
c2) conducting mean imputation on the measured data;
c3) normalizing the measured data and concentrations of a plurality of indoor bioaerosols;
However, in a related field of endeavor (machine learning models, see para. 0002), LU teaches and makes obvious:
c2) conducting mean imputation on the measured data; (LU, para. 0091: For non-XGBoost models, mean imputation was used for missing data.”;
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU combination now performs mean imputation on the measured data of SAVAKKANAVAR to impute missing data that can be used by the prediction models of LIU and LI)
c3) normalizing the measured data and concentrations of a plurality of indoor bioaerosols; (LU, para. 0075: “In various embodiments, step 404 may include selectively excluding one or more baseline parameters, normalizing values for one or more of the tumor kinetic parameters and/or baseline parameters, processing the training data in some other manner, or a combination thereof.”;
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU combination now normalizes the measured data of SAVAKKANAVAR so that normalized data is input into the prediction models of LIU and LI)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI the teachings of LIU, SAVAKKANAVAR, LI, and LU as explained above. As disclosed by LU, one of ordinary skill would have been motivated to do so in order to use mean imputation to impute potentially missing data so that a complete dataset can be provided to the predictive models. (para. 0091). One of ordinary skill would further understand the benefit of normalizing measured data so that the machine learning models receive pre-processed data in ranges that are expected, in order to improve the accuracy of such models.
Regarding Claim 2
TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU teach the method of claim 1 as explained above. TANIGUCHI further teaches:
wherein the plurality of Al models includes one or more of a linear regression model, a lasso regression model, a random forest (RF) model, an extreme gradient boosting model, a multilayer perceptron model, an LSTM model, and a recurrent neural network model. (TANIGUCHI, para. 0051: “ the prediction model is not particularly limited to a linear model, and for example, a piecewise linear model used for heterogeneous mixture learning, a neural network model, or the like may be used.”
TANIGUCHI, para. 0095: “Here, the regularization parameter corresponds to parameters λ and λ.sub.j (where j=1 to M) used in the penalty term of the error function. Note that “∥.sup.q” in the formula represents a norm, and for example, q=1 (L1 norm) is used in the Lasso method and q=2 (L2 norm) is used in the Ridge regression method. The above description is an example of the regularization parameter used for the linear model, but the regularization parameter is not limited to this.”)
Regarding Claim 9
TANIGUCHI teaches:
a) one or more processors; and (TANIGUCHI, para. 0252: “Also, some or all of the components in each of the above-described exemplary embodiments are implemented by a general-purpose or dedicated circuit (circuitry), a processor or the like, or a combination thereof.”)
b) a memory storing computer-executable instructions that, when executed, cause the one or more processors to (TANIGUCHI, para. 0247: “In that case, the operation of each device may be stored in the auxiliary storage device 1003 in the form of a program. The CPU 1001 reads the program from the auxiliary storage device 1003, expands it in the main storage device 1002, and executes the predetermined processing in each exemplary embodiment according to the program.”;
TANIGUCHI, para. 0248: “The auxiliary storage device 1003 is an example of a non-transitory tangible medium. Other examples of non-transitory tangible medium include a magnetic disk, a magneto-optical disk, CD-ROM, DVD-ROM, a semiconductor memory, or the like that is connected via the interface 1004.”)
The remaining limitations in claim 9 correspond to the method of claim 1, and therefore this claim 9 is rejected for substantially the same reasons explained above with respect to claim 1 under 35 U.S.C. 103 in view of the TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU references.
Regarding Claim 10
TANIGUCHI teaches:
A non-transitory computer readable medium, comprising executable instructions that, when executed by at least one processor of a computing device, direct the at least one processor to perform a method, the method comprising: (TANIGUCHI, para. 0246: “FIG. 19 is a schematic block diagram showing a configuration example of a computer according to each exemplary embodiment of the present invention. A computer 1000 includes a CPU 1001, a main storage device 1002, an auxiliary storage device 1003, an interface 1004, a display device 1005, and an input device 1006.”)
TANIGUCHI, para. 0247: “In that case, the operation of each device may be stored in the auxiliary storage device 1003 in the form of a program. The CPU 1001 reads the program from the auxiliary storage device 1003, expands it in the main storage device 1002, and executes the predetermined processing in each exemplary embodiment according to the program.”;
TANIGUCHI, para. 0248: “The auxiliary storage device 1003 is an example of a non-transitory tangible medium. Other examples of non-transitory tangible medium include a magnetic disk, a magneto-optical disk, CD-ROM, DVD-ROM, a semiconductor memory, or the like that is connected via the interface 1004.”)
The remaining limitations in claim 10 correspond to the method of claim 1, and therefore this claim 10 is rejected for substantially the same reasons explained above with respect to claim 1 under 35 U.S.C. 103 in view of the TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU references.
Claims 3-5 are rejected under 35 U.S.C. 103 as being unpatentable over TANIGUCHI in view of LIU, SAVAKKANAVAR, LI, and LU and further in view of US 20240362472 A1, hereinafter referenced as FU.
Regarding Claim 3
TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU teach the method of claim 1 as explained above. TANIGUCHI further teaches:
wherein Step b) further comprises steps of: f) inputting test data ... into each of the plurality of Al models; (TANIGUCHI, para. 0080: “When the prediction target data is input, the model application unit 15 uses the prediction model stored in the model storage unit 14 to perform progress prediction.”;
TANIGUCHI, para. 0082: “When the prediction target data is input, the model application unit 15 uses the prediction model stored in the model storage unit 14 to perform progress prediction.”;
TANIGUCHI, para. 0092: “When the prediction target data is input, the model application unit 15 reads the prediction model stored in the model storage unit 14 (step S202), applies the prediction target data to the read prediction model, and obtains a predicted value at each prediction time point included in the evaluation target period (step S203).”;
TANIGUCHI, para. 0263: “The prediction means 67 (for example, the model application unit 15, the model application unit 25), when the prediction target data is given, uses the prediction model stored in the model storage means 66 to perform progress prediction.”;
Examiner’s Note: Pursuant to MPEP 2144.04 VI.B, the examiner notes that the mere duplication of parts or steps (e.g., inputting test data into more than 1 AI model) “has no patentable significance unless a new and unexpected result is produced”)
However, TANIGUCHI fails to explicitly teach:
f) inputting test data for the venue into each of the plurality of Al models g) applying more than one pair of input and output time windows;
g) applying more than one pair of input and output time windows;
h) finding, for each of the plurality of Al model, a difference data between predicted test data and measured test data; and
i) determining one of the plurality of Al models that has a best difference data as the best model.
However, in a related field of endeavor (neural networks to estimate the indoor concentration of airborne culturable bacteria, see p. 2, section 1), LIU teaches:
f) inputting test data for the venue into each of the plurality of Al models g) applying more than one pair of input and output time windows; (LIU, p. 2, section 2: “To develop a model for estimating the concentration of indoor airborne culturable bacteria, we chose a series of independent variables that can be easily measured inside a building, .... All the data were measured in various buildings in Baoding”; Examiner’s Note: LIU teaches estimating the concentration of indoor airborne culturable bacteria in a building (corresponding to recited “venue”); the TANIGUCHI-LIU-SAV combination now utilizes the techniques of TANIGUCHI with respect implementing an accurate model to estimate the concentration of indoor airborne culturable bacteria in a particular building as in LIU)
h) finding, for each of the plurality of Al model, a difference data between predicted test data and measured test data; and (LIU, p. 3, section 2: “The training and testing of each percentage were repeated 200 times. RMS errors were calculated from the testing results for comparison.”; (EN): LIU teaches that during testing, root mean square errors were calculated (corresponding to recited “difference data between predicted test data and measured test data”); the TANIGUCHI-LIU-SAVAKKANAVAR combination now utilizes the techniques of TANIGUCHI with respect implementing an accurate model to estimate the concentration of indoor airborne culturable bacteria in a particular building as in LIU)
i) determining one of the plurality of Al models that has a best difference data as the best model. (LIU, p. 3, section 2: “The training and testing of each percentage were repeated 200 times. RMS errors were calculated from the testing results for comparison.”; (EN): LIU teaches that during testing, root mean square errors were calculated (corresponding to recited “difference data”); the TANIGUCHI-LIU-SAVAKKANAVAR combination now utilizes the techniques of TANIGUCHI with respect to choosing a high accuracy model (corresponding to the model having the “best difference data”) from a plurality of models to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI with the teachings of LIU, SAVAKKANAVAR, LI, and LU as explained above. As disclosed by LIU, one of ordinary skill would have been motivated to do so because “many indoor microorganisms are potential threats to human health” and determining the concentration of such indoor microorganisms will help to “reduce the potential threats of indoor inhalable microorganisms.” (LIU, p. 1, section 1). One of ordinary skill in the art would further understand the benefit of using the teachings of LIU, which teach an estimation technique that “can dramatically reduce the measurement time from days to seconds, saving much time, economic cost, and manpower.” (LIU, p. 7, section 4).
However, TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU fail to explicitly teach:
g) applying more than one pair of input and output time windows;
However, in a related field of endeavor (handling data drift in machine learning models, see para. 0007), FU teaches:
g) applying more than one pair of input and output time windows; (FU, para. 0163: “The input window is set to 12 samples, and the output window (prediction duration) is 6 samples. This means that 12 previous samples were evaluated to forecast 6 samples ahead which is equivalent to predicting one minute ahead in the case that the data collection rate is 10 s.”;
Examiner’s Note: FU teaches a specific example of an input window of 12 samples and an output window of 6 samples; the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU-FU combination now utilizes the techniques of TANIGUCHI with respect to inputting data into a high accuracy model from a plurality of models to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU, and now modifies the models of LIU to use input time windows of FU to predict output concentrations over an output time window as in FU; pursuant to MPEP 2144.04 VI.B, the examiner notes that the mere duplication of parts or steps (e.g., “more than one” input-output time window pair) “has no patentable significance unless a new and unexpected result is produced”)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI with the teachings of LIU, SAVAKKANAVAR, LI, LU, and FU, as explained above. As disclosed by FU, one of ordinary skill would have been motivated to do so to account for distribution changes in data. (see para. 0061). One of ordinary skill would further understand the benefit of using input and output time windows to account for changes in concentration due to environmental changes, such as accounting for the opening of a door or window that disturbs the air in the indoor environment.
Regarding Claim 4
TANIGUCHI, LIU, SAVAKKANAVAR, LI, LU, and FU teach the method of claim 3 as explained above. TANIGUCHI further teaches:
wherein the difference data comprises one or more of a mean squared error (MSE), a root-mean-square error (RMSE) and a value on a revised version of the Willmott's index (WI). (TANIGUCHI, para. 0114: “select a model having the smallest number of defective samples from among the models with the prediction accuracy (e.g., Root Mean Squared Error (RMSE) or correlation coefficient) equal to or more than a predetermined threshold.”; (EN): the examiner further notes that LIU also uses RMS error for comparing results as disclosed at p. 3, section 2).
Regarding Claim 5
TANIGUCHI, LIU, SAVAKKANAVAR, LI, LU, and FU teach the method of claim 3 as explained above. However, TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU do not explicitly teach:
wherein the more than one pair of input and output time windows comprises a real-time window pair.
However, in a related field of endeavor (handling data drift in machine learning models, see para. 0007), FU teaches:
wherein the more than one pair of input and output time windows comprises a real-time window pair. (FU, para. 0047: “Online data may contain one or multiple data samples at a time and is usually used by a trained machine learning model for inferring a real-time system status.”
FU, para. 0163: “The input window is set to 12 samples, and the output window (prediction duration) is 6 samples. This means that 12 previous samples were evaluated to forecast 6 samples ahead which is equivalent to predicting one minute ahead in the case that the data collection rate is 10 s.”;
Examiner’s Note: FU teaches a specific example of an input window of 12 samples and an output window of 6 samples; the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU-FU combination now utilizes the techniques of TANIGUCHI with respect to inputting data into a high accuracy model from a plurality of models to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU, where LIU also teaches “real-time measurement of the concentration of indoor airborne culturable bacteria, see p. 7, section 3) and now modifies the models of LIU to use input time windows of FU to predict output concentrations over an output time window as in FU; pursuant to MPEP 2144.04 VI.B, the examiner notes that the mere duplication of parts or steps (e.g., “more than one” input-output time window pair) “has no patentable significance unless a new and unexpected result is produced”)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI with the teachings of LIU, SAVAKKANAVAR, LI, LU, and FU, as explained above. As disclosed by FU, one of ordinary skill would have been motivated to do so to account for distribution changes in data. (see para. 0061). One of ordinary skill would further understand the benefit of using input and output time windows to account for changes in concentration due to environmental changes, such as accounting for the opening of a door or window that disturbs the air in the indoor environment.
Claims 6-8 are rejected under 35 U.S.C. 103 as being unpatentable over TANIGUCHI in view of LIU, SAVAKKANAVAR, LI, and LU and further in view of US 20210406707 A1, hereinafter referenced as RESNICK.
Regarding Claim 6
TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU teach the method of claim 1 as explained above. However, TANIGUCHI fails to explicitly teach:
wherein the measured data comprises a plurality of input features;
the method further comprising a step of determining which one of the plurality of input features is more important than another one by conducting a permutation importance analysis.
However, in a related field of endeavor (neural networks to estimate the indoor concentration of airborne culturable bacteria, see p. 2, section 1), LIU teaches:
wherein the measured data comprises a plurality of input features; (LIU, p. 2, section 2: “To develop a model for estimating the concentration of indoor airborne culturable bacteria, we chose a series of independent variables that can be easily measured inside a building, including: (i) indoor PM2.5, (ii) indoor PM10, (iii) temperature, (iv) relative humidity, and (v) CO2 concentration. All the data were measured in various buildings in Baoding”; (EN): the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU combination now utilizes the techniques of TANIGUCHI with respect to using a selected model (based on high accuracy) to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI with the teachings of LIU, SAVAKKANAVAR, LI, and LU as explained above. As disclosed by LIU, one of ordinary skill would have been motivated to do so because “many indoor microorganisms are potential threats to human health” and determining the concentration of such indoor microorganisms will help to “reduce the potential threats of indoor inhalable microorganisms.” (LIU, p. 1, section 1). One of ordinary skill in the art would further understand the benefit of using the teachings of LIU, which teach an estimation technique that “can dramatically reduce the measurement time from days to seconds, saving much time, economic cost, and manpower.” (LIU, p. 7, section 4).
However, TANIGUCHI, LIU, SAVAKKANAVAR, LI, and LU do not explicitly teach:
the method further comprising a step of determining which one of the plurality of input features is more important than another one by conducting a permutation importance analysis.
However, in a related field of endeavor, “imputing data in computer-based reasoning systems”, see para. 0002), RESNICK teaches:
the method further comprising a step of determining which one of the plurality of input features is more important than another one by conducting a permutation importance analysis. (RESNICK, para. 0023: “For example, feature importance may be determined 120 using confidence intervals, frequency of appearance in sets of decision trees, purity of subsections of the model, permutation feature importance, entropy measures (such as cross entropy and KL divergence), variance, accuracy when dropping out data, Bayesian posterior probabilities, or Pearson correlation.”;
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU-RESNICK combination now utilizes the techniques of TANIGUCHI with respect to using a selected model (based on high accuracy) to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU, where the features of LIU (e.g., PM2.5, PM10, CO2) are analyzed using the permutation feature importance techniques of RESNICK).
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI with the teachings of LIU, SAVAKKANAVAR, LI, LU, and RESNICK as explained above. As disclosed by RESNICK, one of ordinary skill would have been motivated to do so in order to determine the most important data for a model in the event that the model needs to impute values. (para. 0016). One of ordinary skill would further understand the benefit of using the permutation feature importance techniques of RESNICK to select the best input variables for the models of LIU, e.g., to reduce the amount of data that needs to be collected and input into the models of LIU)
Regarding Claim 7
TANIGUCHI, LIU, SAVAKKANAVAR, LI, LU, and RESNICK teach the method of claim 6 as explained above. However, TANIGUCHI fails to explicitly teach:
wherein the plurality of input features comprises one or more of temperature, relative humidity (RH), concentrations of CO2, total volatile organic compounds (TVOCs), PM2.5 and PM10.
However, in a related field of endeavor (neural networks to estimate the indoor concentration of airborne culturable bacteria, see p. 2, section 1), LIU teaches:
wherein the plurality of input features comprises one or more of temperature, relative humidity (RH), concentrations of CO2, total volatile organic compounds (TVOCs), PM2.5 and PM10. (LIU, p. 2, section 2: “To develop a model for estimating the concentration of indoor airborne culturable bacteria, we chose a series of independent variables that can be easily measured inside a building, including: (i) indoor PM2.5, (ii) indoor PM10, (iii) temperature, (iv) relative humidity, and (v) CO2 concentration. All the data were measured in various buildings in Baoding”; (EN): the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU-RESNICK combination now utilizes the techniques of TANIGUCHI with respect to using a selected model (based on high accuracy) to estimate the concentration of indoor airborne culturable bacteria in a building as in LIU using the specific input features of LIU)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI with the teachings of LIU, SAVAKKANAVAR, LI, LU, and RESNICK as explained above. As disclosed by LIU, one of ordinary skill would have been motivated to do so because “many indoor microorganisms are potential threats to human health” and determining the concentration of such indoor microorganisms will help to “reduce the potential threats of indoor inhalable microorganisms.” (LIU, p. 1, section 1). One of ordinary skill in the art would further understand the benefit of using the teachings of LIU, which teach an estimation technique that “can dramatically reduce the measurement time from days to seconds, saving much time, economic cost, and manpower.” (LIU, p. 7, section 4).
Regarding Claim 8
TANIGUCHI, LIU, SAVAKKANAVAR, LI, LU, and RESNICK teach the method of claim 6 as explained above. However, TANIGUCHI and LIU fail to explicitly teach:
wherein the plurality of input features comprises concentrations of more than one biological matters.
However, in a related field of endeavor (“accurately measuring and controlling air quality of indoor environment using IoT technology and Artificial Intelligence”, para. 0001), SAVAKKANAVAR teaches and makes obvious:
wherein the plurality of input features comprises concentrations of more than one biological matters. (SAVAKKANAVAR, para. 0031: “Referring to FIG. 1, the system 110 might be communicatively coupled to the indoor sensors 150, 152, 154, and 156. In one example, the indoor sensor 150 may indicate a sensor configured for measuring the amount of at least one or more volatile organic compounds (□VOCs□), carbon dioxide, carbon monoxide, methane gas, or a combination thereof in the air, and wherein the solid particles and/or liquid droplets are mold spores, bacteria, dust mites, dust, PM2.5, insect faeces, pollen, smoke, dander, saliva, mucus, other airborne allergens, or a combination thereof.”;
Examiner’s Note: the TANIGUCHI-LIU-SAVAKKANAVAR-LI-LU combination now utilizes the sensor data from SAVAKKANAVAR as additional inputs into the predictive models of LIU and LI for predicting bioaerosol concentrations)
Before the effective filing date of the present application, it would have been obvious to one of ordinary skill in the art to combine the teachings of TANIGUCHI the teachings of LIU, SAVAKKANAVAR, LI, LU, and RESNICK as explained above. As disclosed by SAVAKKANAVAR, one of ordinary skill would have been motivated to do so “to accurately measure air quality of indoor environment and control the air quality so as to improve indoor air quality and livability of subjects (human beings or animals).” (para. 0003).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20150170055 A1 (Beymer). “Aspects of the present disclosure can be particularly useful for diagnosing medical diseases from a variety of input data. As non-limiting examples, experimental tests were conducted using different data completion solutions--zero imputation, mean-imputation and Matrix Completion with SVM classifier.” (para. 0064).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL C LEE whose telephone number is (571)272-4933. The examiner can normally be reached M-F 12:00 pm - 8:00 pm ET.
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, Omar Fernandez Rivas can be reached at 571-272-2589. 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.
/MICHAEL C. LEE/Examiner, Art Unit 2128
Prosecution Insights