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 .
DETAILED ACTION
The following NON-FINAL Office Action is in response to application 18/027,390 filed on 03/21/2023. This communication is the first action on the merits.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/21/2023 has been considered by the examiner.
Drawings
The drawings were received on 03/21/2023. These drawings are acceptable.
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.
Claim 1-12 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 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 applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1, 10 and 11 recites “wherein the fluid network is equipped with at least one flow rate sensor at the inlet of the fluid network and with at least one other hydraulic sensor, of the flow rate or pressure sensor type, configured to provide hydraulic behavior data” however it is unclear whether the “flow rate sensor” or “hydraulic sensor” or both provide the recited “configured to provide hydraulic behavior data”. Thus, it is unclear which sensor or sensors are required to provide the hydraulic behavior data. For the purpose of compact prosecution, Examiner interprets and suggest the claims to be amended to recite “wherein the fluid network is equipped with at least one flow rate sensor at the inlet of the fluid network and with at least one other hydraulic sensor, of the flow rate or pressure sensor type, wherein the at least one flow rate sensor and at least one other hydraulic sensor are configured to provide hydraulic behavior data”.
Also, Claim 1 recites “a plurality of leak scenarios associating leak characterization data among a leak area and a leak flow rate with a set of hydraulic behavior data” however it is unclear whether the recited “hydraulic behavior data” is data provided by the previously recited sensors or data stored in the database. Thus, the source of the hydraulic behavior data is ambiguous, and the scope of the claim cannot be determined with reasonable certainty.
Also, Claim 10 and 11 recites “a statistical learning model, configured to receive as input, a set of hydraulic behavior data” however it is unclear whether the recited “hydraulic behavior data” is data provided by the previously recited sensors or data stored in the database. Thus, the source of the hydraulic behavior data is ambiguous, and the scope of the claim cannot be determined with reasonable certainty.
Dependent claims 2-9 are similarly rejected by virtue of their dependency on rejected parent claim 1.
Dependent claims 12 are similarly rejected by virtue of their dependency on rejected parent claim 11.
CLAIM INTERPRETATION
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
Claim 11-12 limitation “a module for characterizing a leak in a fluid network” invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. The claim limitation "a module for characterizing a leak in a fluid network..." recites a generic placeholder term "module" coupled with functional language and does not itself recite sufficiently define structure for performing the claimed function. Although, the specification describes a leak characteristic module that may be implemented on a computer or remote server and includes components such as a digital mapping of the fluid network, hydraulic model, a data base, and a statistical learning model (See, e.g., Spec. [0087-0088]), the claim does not recite these structures or otherwise identify what structure performs the recited function. Accordingly, the claim fails to particularly point out and distinctly claim the invention. Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
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 1-13 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. A subject matter eligibility analysis is set forth below. See MPEP 2106.
Specifically, representative Claim 1 recites:
A method for training a statistical learning model intended for the characterization of a leak in a fluid network, the fluid network including several interconnected areas, wherein the fluid network is equipped with at least one flow rate sensor at the inlet of the fluid network and with at least one other hydraulic sensor, of the flow rate or pressure sensor type, configured to provide hydraulic behavior data, wherein the fluid network is provided with a digital mapping comprising at least the geometry of the fluid network and the location of said at least one flow rate sensor and said at least one other hydraulic sensor, the method comprising constructing a database containing:
a plurality of leak scenarios associating characterization data among a leak area and a leak flow rate with a set of hydraulic behavior data, and
a plurality of leak-free scenarios associating a “no leak” label with the set of hydraulic behavior data;
wherein the method further comprises training of the statistical learning model on the constructed database,
wherein the fluid network is provided with a digital model of the hydraulic behavior of the fluid network including at least one nominal consumption scenario, and
wherein the database contains at least one leak scenario simulated using the digital mapping of the fluid network and the digital model of the hydraulic behavior of the fluid network.
The claim limitations in the abstract idea have been highlighted in bold above; the remaining limitations are “additional elements.”
Similar limitations comprise the abstract idea of Method Claim 10 and System Claim 11, which corresponds to Method Claim 1 and comprises:
Receiving, by a statistical learning model as input, a set of hydraulic behavior data; and
Providing, by the statistical learning model, as output, leak characterization data among a leak area and a leak flow rate.
Under Step 1 of the analysis, claim 1 belongs to a statutory category, namely it is a method claim. Likewise, claim 10 is a method claim, and claim 11 is a system claim.
Under Step 2A, prong 1: This part of the eligibility analysis evaluates whether the claim recites a judicial exception. As explained in MPEP 2106.04, subsection II, a claim “recites” a judicial exception when the judicial exception is “set forth” or “described” in the claim.
In the instant case, claim 1 is found to recite at least one judicial exception (i.e. abstract idea), that being a Mental Process and a Mathematical Concept. This can be seen in the claim limitations of “training a statistical learning model “, “a plurality of leak scenarios associating characterization data among a leak area and a leak flow rate with a set of hydraulic behavior data”, “a plurality of leak-free scenarios associating a “no leak” label with the set of hydraulic behavior data”, and “wherein the method further comprises training of the statistical learning model on the constructed database” which is the judicial exception of a mental process because these limitations are merely data observations, evaluations, and/or judgements in order to calculate and classify leak characterization data and train the statistical learning model using labeled hydraulic behavior data, and is capable of being performed mentally and/or with the aid of pen and paper. Additionally, the aforementioned limitations recite mathematical calculations, e.g. see Spec. [0097]-[0103], these operations involve mathematical calculations and optimization techniques applied to hydraulic models in order to generate and label simulated leak scenarios for training the statistical learning model.
Claim 10 and Claim 11 also are is found to recite at least one judicial exception (i.e. abstract idea), that being a Mental Process and a Mathematical Concept. This can be seen in the claim limitations of “receiving, by a statistical learning model as input, a set of hydraulic behavior data”, and “providing, by the statistical learning model, as output, leak characterization data among a leak area and a leak flow rate” which is the judicial exception of a mental process because these limitations are merely data observations, evaluations, and/or judgements in order to process hydraulic behavior data to generate and classify leak characterization data including a leak area and a leak flow rate, and is capable of being performed mentally and/or with the aid of pen and paper.
Step 2A, prong 2 of the eligibility analysis evaluates whether the claim as a whole integrates the recited judicial exception(s) into a practical application of the exception. This evaluation is performed by (a) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (b) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application.
In addition to the abstract ideas recited in claim 1, the claimed method recites additional elements including “a method for training a statistical learning model intended for the characterization of a leak in a fluid network, the fluid network including several interconnected areas, wherein the fluid network is equipped with at least one flow rate sensor at the inlet of the fluid network and with at least one other hydraulic sensor, of the flow rate or pressure sensor type, configured to provide hydraulic behavior data, wherein the fluid network is provided with a digital mapping comprising at least the geometry of the fluid network and the location of said at least one flow rate sensor and said at least one other hydraulic sensor”, “wherein the fluid network is provided with a digital model of the hydraulic behavior of the fluid network including at least one nominal consumption scenario”, and “wherein the database contains at least one leak scenario simulated using the digital mapping of the fluid network and the digital model of the hydraulic behavior of the fluid network” however these elements are found to be data gathering and output steps, which are recited at a high level of generality, and thus merely amount to “insignificant extra-solution” activity(ies). See MPEP 2106.05(g) “Insignificant Extra-Solution Activity,”. Furthermore, the claim recites “digital mapping”, “database”, and “sensors” however this is found to be equivalent to adding the words “apply it” and mere instructions to apply a judicial exception on a general purpose computer does not integrate the abstract idea into a practical application. See MPEP 2106.05(f).
The generic data gathering, processing, and output steps, are recited at such a high level of generality (e.g. using “database” and “statistical learning model”) that it represents no more than mere instructions to apply the judicial exceptions on a computer. It can also be viewed as nothing more than an attempt to generally link the use of the judicial exceptions to the technological environment of a computer. Noting MPEP 2106.04(d)(I): “It is notable that mere physicality or tangibility of an additional element or elements is not a relevant consideration in Step 2A Prong Two. As the Supreme Court explained in Alice Corp., mere physical or tangible implementation of an exception does not guarantee eligibility. Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 224, 110 USPQ2d 1976, 1983-84 (2014) ("The fact that a computer ‘necessarily exist[s] in the physical, rather than purely conceptual, realm,’ is beside the point")”.
Thus, under Step 2A, prong 2 of the analysis, even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application and the claim is directed to the judicial exception. No specific practical application is associated with the claimed system. For instance, nothing is done with the generated leak characterization data (i.e., the leak area and leak flow rate), and the claims merely recite providing the calculated results without any additional control, modification, or technological improvement to the fluid network itself.
Under Step 2B, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements, as described above with respect to Step 2A Prong 2, merely amount to a general purpose computer system that attempts to apply the abstract idea in a technological environment, limiting the abstract idea to a particular field of use, and/or merely performs insignificant extra-solution activit(ies) (claims 1, 10 and 11). Such insignificant extra-solution activity, e.g. data gathering and output, when re-evaluated under Step 2B is further found to be well-understood, routine, and conventional as evidenced by MPEP 2106.05(d)(II) (describing conventional activities that include transmitting and receiving data over a network, electronic recordkeeping, storing and retrieving information from memory, and electronically scanning or extracting data from a physical document).
Therefore, similarly the combination and arrangement of the above identified additional elements when analyzed under Step 2B also fails to necessitate a conclusion that claim 1, as well as claim 10 and 11, amount to significantly more than the abstract idea.
With regards to the dependent claims, claims 2-9 and 12, merely further expand upon the algorithm/abstract idea and do not set forth further additional elements that integrate the recited abstract idea into a practical application or amount to significantly more. Therefore, these claims are found ineligible for the reasons described for claims 1, 10 and 11. Specifically:
With respect to dependent claims 2-6 specifically, the claims further recite additional elements regarding the generation and organization of leak scenarios, including variations by time, time series duration, and multi-leak scenarios, sensors, and stochastic variability. These limitations merely expand upon how the data is generated and analyzed within the abstract data modeling framework described above. Such features amount to additional data manipulation of the underlying abstract idea. They do not improve the functioning of a computer or any other technology, and therefore fail to integrate the abstract idea into a practical application. See MPEP 2106.05(g).
With respect to dependent claims 7-9 specifically, the claims further recite determining an optimized sensor location, and calibrating the digital model using simulated and real scenarios, and using a neural networks within the statistical learning model. These limitations recite mathematical optimization, calibration, and use of a particular modeling technique within the abstract framework. The use of optimization techniques or a neural network constitutes abstract mathematical concepts applied to data and does not reflect an improvement to computer functionality or another technological field. Accordingly, these claims merely further refine the abstract idea and fail to integrate it into a practical application or amount to significantly more. See MPEP 2106.05(g)(h).
With respect to dependent claims 12 specifically, the claim further recite that the module comprises a plurality of hydraulic sensors configured to provide hydraulic behavior data. This limitation merely specifies additional data gathering components used to supply input to the abstract data processing steps described above. The collection and use of additional sensor data constitutes insignificant extra solution activity and does not integrate the abstract idea into a practical application. See MPEP 2106.05(g).
Accordingly, for the reasons above and those discussed in relation to independent claim 1, 10, and 11, the dependent claims are insufficient to integrate the claimed abstract ideas into a practical application or significant more.
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4 and 6-12 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by EP 3112960 A1, Guillaume et al (hereinafter Guillaume).
Regarding Claim 1, Guillaume discloses a method for training a statistical learning model intended for the characterization of a leak in a fluid network (Guillaume, [Page 3], Figure 7 displays an example of method for detecting anomalies in a water distribution system in a number of embodiments of the invention, using statistical learning for pre-detecting and pre-characterizing an anomaly), the fluid network including several interconnected areas (Guillaume, [Page 10] a map 800 of the network of a water distribution system is displayed to an operator through a display device. The map contains lines that represent pipes of the system, the width of the lines being representative of the diameter of the pipes. The system contains large pipes, such as pipes 810 and 811, and smaller pipes, such as pipes 820 and 821. Three leaks 830, 831, 832 have been localized in the network and are represented using large circles. Information about the relative importance of the leaks can be inserted), wherein the fluid network is equipped with at least one flow rate sensor at the inlet of the fluid network (Guillaume, [Page 4] they typically represent the individual consumptions of the users of the water distribution system, and the injection of water from water inlet into the system) and with at least one other hydraulic sensor, of the flow rate or pressure sensor type, configured to provide hydraulic behavior data (Guillaume, [Page 4] physical parameters related to water notably comprise by way of example velocity, pressure, flow rate, level in storage (reservoir and tank), temperature, etc... Further parameters can be added according to detection needs and/or the evolution of sensors. The evolution of these parameters over time depends on the characteristics of the water distribution system, the inputs and outputs at the nodes, and the state of the any equipment in the system), wherein the fluid network is provided with a digital mapping comprising at least the geometry of the fluid network (Guillaume, [Page 10] figure 8 displays an example of a presentation of the localization of anomalies to an operator) and the location (Guillaume, [Page 9] Step 250 is therefore launched with a reduced number of pre-detected anomalies, corresponding to the expected anomalies, on specific subsets of nodes and arcs. This better tuned and geographically focused iterative process results in a quicker and more accurate characterization of anomaly (location, intensity)) of said at least one flow rate sensor and said at least one other hydraulic sensor (Guillaume, [Page 3] a system for detecting anomalies in a water distribution system composed of a network of nodes, said system comprising: sensors of at least water velocity and pressure at a subset of nodes of the network; a computing device comprising a processor; communication links between sensors and the computing device), the method comprising constructing a database containing (Guillaume, [Page 5] the operators can then input in the method, for each entity, if they confirm the event and its class. The vectors can then be labeled according to the class they belong (leak, pressure anomaly, water quality anomaly ...). The historical database of vectors of features is enriched with the new classified vector of features whatever the state is "abnormal" or "normal". These vectors of features are used as inputs in the learning process of algorithms):
a plurality of leak scenarios associating characterization data among a leak area (Guillaume, [Page 8] a scenario of detection of an abnormal increase of water demand is now described below. This example demonstrates the ability of a method 600 according to the invention to detect an abnormal increase of water demand, possibly linked to a leak, with a pre-detection based on a combination of rules) and a leak flow rate with a set of hydraulic behavior data (Guillaume, [Page 5] the information contains indications about quantification of the level of abnormality (for instance the value of flow of a leak, the value of head loss), time and duration of the abnormality, known location and spread of the abnormality etc. Taking into account the context settings, this information is used to prioritize the abnormal states and provide a degree of abnormality to the user), and
a plurality of leak-free scenarios associating a “no leak” label with the set of hydraulic behavior data (Guillaume, [Page 3] detecting (530) an anomaly based on the output of identifying at least one target entity where to change the values of control variables based on at least said observations; - if no anomaly is detected, enriching a database of normal states of the entities (540); - if an anomaly is detected: o Changing (250) the set of values of control variables using a stepwise adjustment of the control variables, [Page 5] the method comprises a step 280 to determine whether the class computed for an entity corresponds to an abnormal state ("event") according to the output of machine learning algorithms or if one of the states is detected as outlier. If an event is detected, the method goes to step 290. If the states are qualified as normal, the method goes to step 291).;
wherein the method further comprises training of the statistical learning model on the constructed database (Guillaume, [Page 9] the observations of state variables are tested to determine if there are anomalies and where, before parametrizing the iterative process. The method simulates the expected values of observations, based on their past values and additional drivers. In a number of embodiments of the invention, several models are trained on past data, and the model that yields the best prediction of past data is selected, [Page 9] the distribution of residue values is tested with a statistical method, to be compared to past distribution of residues),
wherein the fluid network is provided with a digital model of the hydraulic behavior of the fluid network including at least one nominal consumption scenario (Guillaume, [Page 4] the hydraulic model can notably be configured with control variables characterizing the structure of the network and control variables characterizing a prediction of the inputs and outputs of the network at nodes over a set of time references, notably a prediction of water consumption in the network), and
wherein the database contains at least one leak scenario simulated using the digital mapping of the fluid network and the digital model of the hydraulic behavior of the fluid network (Guillaume, [Page 9] a scenario of detection of an abnormal increase of water demand is described below, [Page 9] similarly to the previous example, this example demonstrates the ability of a method according to the invention to detect an abnormal increase of water demand, possibly linked to a leak. However, this example, based on the method 700, uses a direct comparison of observations with thresholds rather than a combination of rules, [Page 9] this example describes the detection of an abnormal increase of water demand, which can be linked to a leak. The observed flow rates are combined to form water demands for given areas. These water demand are simulated with the use of past water demands and time series analysis. The simulated variables are used to compute residue values with observations. The cumulated sums of residue values are computed).
Regarding Claim 2, Guillaume discloses the training method according to claim 1, wherein the database contains at least several leak scenarios relating to different times of the day, days of the week and/or seasons (Guillaume, [Page 4-5] the first time references are associated to each sensor, which is able to produce measurements at different times / rates, [Page 7] a step 510 of performing a plurality of statistical analyses of residue values for at least an entity for a selection of time references. This step consists in analyzing the distribution of residue values for an entity at each time reference in a time window. According to various embodiments of the invention, the time window may cover the totality or a subset of time references [Page 9] several models are trained on past data, and the model that yields the best prediction of past data is selected. In one embodiment, the method contains models based on time-series analysis such as autoregressive moving average (ARMA) technique, or seasonal auto-regressive integrated moving average technique (SARIMA)).
Regarding Claim 3, Guillaume discloses the training method according to claim 1, wherein each scenario of the at least several leak scenarios includes at least one time series of sets of hydraulic behavior data (Guillaume, [Page 8] The stepwise iterative adjustment of properties and control variables of a hydraulic model is then launched with the specific subset of the network and settings corresponding to water demand increase, [Page 9] this example describes the detection of an abnormal increase of water demand, which can be linked to a leak. The observed flow rates are combined to form water demands for given areas. These water demand are simulated with the use of past water demands and time series analysis) wherein the at least one time series extends over at least 4 hours (Guillaume, [Page 9] the anomalies are flagged if too many time steps of residue values are exceeding a given threshold, for a given time window. This time window depends on the nature of variables and anomalies to be detected. In one embodiment, the length of time window can be 6 hours).
Regarding Claim 4, Guillaume discloses the training method according to any one of claims 3, wherein at least one leak scenario includes several leaks characterization data (Guillaume, [Page 10] map 800 of the network of a water distribution system is displayed to an operator through a display device. Three leaks 830, 831, 832 have been localized in the network and are represented using large circles. Information about the relative importance of the leaks can be inserted. For example, the diameter of the circles may increase with the importance of the leak. It may also be possible to represent only the leak that is considered as the most severe, or display additional information about the leak, for example a list of past leaks that had the closest characteristics).
Regarding Claim 6, Guillaume discloses the training method according to claim 1, further comprising introducing a stochastic variability into the hydraulic behavior data recorded in the database for each leak scenario (Guillaume, [Page 9] this example describes the detection of an abnormal increase of water demand, which can be linked to a leak. The observed flow rates are combined to form water demands for given areas. These water demand are simulated with the use of past water demands and time series analysis. The simulated variables are used to compute residue values with observations. The cumulated sums of residue values are computed. They are compared to thresholds. These thresholds are based on observed variabilities of the cumulated sums of residue values in the past. It means that they use measurement of the variabilities, here based on computed means and standard deviations. In this example, for 2 areas over the whole network, the cumulated sum of residue values exceeds the given thresholds).
Regarding Claim 7, Guillaume discloses the training method according to claims 1, further comprising determining at least one optimized location for at least one new hydraulic sensor (Guillaume, [Page 2] method 400 further comprises a step 410 of identifying at least one target entity where to change the values of control variables based on at least said observations, [Page 6] aim of step 410 is to reduce the number of entities wherein the values of control variables are changed at step 250, while ensuring that, if an anomaly occurs in the water distribution system, it is found at the entities selected at step 410. Indeed, the computational load and complexity of step 250 may dramatically increase in large networks with a high number of entities, [Page 6] by reducing the number of entities for which the control variables are modified, the method of the invention reduces the computational load of the detection of anomalies and produces its results faster and at least as reliably as prior art methods), the determining comprising the following:
Simulating several potential hydraulic sensors at different locations in the fluid network; Simulating several leak scenarios (Guillaume, [Page 10] three leaks 830, 831, 832 have been localized in the network and are represented using large circles. Information about the relative importance of the leaks can be inserted. For example, the diameter of the circles may increase with the importance of the leak. It may also be possible to represent only the leak that is considered as the most severe, or display additional information about the leak, for example a list of past leaks that had the closest characteristics); and
Identifying potential sensors that maximize the probability of detection of the leaks and/or that maximize the discernibility of the detected leaks (Guillaume, [Page 7] performing statistical analysis for an entity comprises detecting if a residue value exceeds a predefined threshold for a predefined number of successive times steps. The threshold and number of successive time steps can be predefined based on previous detections, in order to maximize the ratio of detection of anomalies when an anomaly is present (true positives), and minimize the ratio of detection of an anomaly when it does not exist (false alarms). The analysis can use statistical tests on properties of residue values, and the computation of resulting Pvalues to qualify the result of the tests).
Regarding Claim 8, Guillaume discloses the training method according to claims 1, comprising a step of calibrating the digital model of the hydraulic behavior of the fluid network, during which at least one parameter of the digital model of the hydraulic behavior of the fluid network is adjusted by comparing a simulated scenario with the corresponding real scenario (Guillaume, [Page 4] theoretical values defined during the modeling of the network do not always match real values. In order to obtain more accurate values of control variables related to the structure of the network, a calibration step may consist in adjusting the values of these control variables in order to provide the best prediction of the behavior of the network. this adjustment may consist in: performing observations of the inputs, outputs and a subset of the state variables of the network for a certain duration; configuring the hydraulic model of the network with values of the control variables related to the inputs, outputs and structure of the network; calculating predicted values of the state variables of the network according to the hydraulic model; calculating a difference between observed and predicted values of the state variables of the network, and modifying the values of the control variables of the network using an optimization algorithm in order to minimize the distance between observed and predicted values of the state variables of the network).
Regarding Claim 9, Guillaume discloses the training method according to claims 1, wherein the statistical learning model comprises at least one neural network (Guillaume, [Page 7] the method contains models based on machine learning algorithm such as random forest or artificial neural networks).
Regarding Claim 10 and 11, Guillaume discloses a method for characterizing a leak in the fluid network (Guillaume, [Page 3], Figure 7 displays an example of method for detecting anomalies in a water distribution system in a number of embodiments of the invention, using statistical learning for pre-detecting and pre-characterizing an anomaly), the fluid network including several interconnected areas (Guillaume, [Page 10] a map 800 of the network of a water distribution system is displayed to an operator through a display device. The map contains lines that represent pipes of the system, the width of the lines being representative of the diameter of the pipes. The system contains large pipes, such as pipes 810 and 811, and smaller pipes, such as pipes 820 and 821. Three leaks 830, 831, 832 have been localized in the network and are represented using large circles. Information about the relative importance of the leaks can be inserted), wherein the fluid network is equipped with at least one flow rate sensor at the inlet of the fluid network (Guillaume, [Page 4] they typically represent the individual consumptions of the users of the water distribution system, and the injection of water from water inlet into the system) and with at least one other hydraulic sensor, of the flow rate or pressure sensor type, configured to provide hydraulic behavior data (Guillaume, [Page 4] physical parameters related to water notably comprise by way of example velocity, pressure, flow rate, level in storage (reservoir and tank), temperature, etc... Further parameters can be added according to detection needs and/or the evolution of sensors. The evolution of these parameters over time depends on the characteristics of the water distribution system, the inputs and outputs at the nodes, and the state of the any equipment in the system), wherein the fluid network is provided with a digital mapping comprising at least the geometry of the fluid network (Guillaume, [Page 10] figure 8 displays an example of a presentation of the localization of anomalies to an operator) and the location (Guillaume, [Page 9] Step 250 is therefore launched with a reduced number of pre-detected anomalies, corresponding to the expected anomalies, on specific subsets of nodes and arcs. This better tuned and geographically focused iterative process results in a quicker and more accurate characterization of anomaly (location, intensity)) of said at least one flow rate sensor and said at least one other hydraulic sensor (Guillaume, [Page 3] a system for detecting anomalies in a water distribution system composed of a network of nodes, said system comprising: sensors of at least water velocity and pressure at a subset of nodes of the network; a computing device comprising a processor; communication links between sensors and the computing device), the method comprising:
receiving, by a statistical learning model as input, a set of hydraulic behavior data (Guillaume, [Page 3] in which the execution of stepwise iterative adjustment of properties and control variables of a hydraulic model combined to a machine learning for identifying the anomaly is dependent on the output of a classification of anomalies using a combination of rules applied to state variables; Figure 7 displays an example of method for detecting anomalies in a water distribution system in a number of embodiments of the invention, using statistical learning for pre-detecting and pre-characterizing an anomaly, [Page 9] using statistical learning for pre-detecting and pre-characterizing an anomaly and the use of a stepwise iterative adjustment of properties and control variables of a hydraulic model, added to machine learning for identifying the anomaly);
providing, by the statistical learning model, as output, leak characterization data among a leak area and a leak flow rate (Guillaume, [Page 7] the statistical analysis is typically performed on residue values of pressure or velocity. For example an analysis of flow rate for detecting a leak may be performed on windows of a few hours, [Page 9] If residue values exceed the thresholds, corresponding anomalies are selected in an area which is defined based on the locations of the different sensors [Page 9] the distribution of residue values is tested with a statistical method, to be compared to past distribution of residues).
Regarding Claim 12, Guillaume discloses the module of claim 11, wherein the at least one other sensor is configured to provide hydraulic behavior data (Guillaume, [Page 7] a water distribution system is equipped with sensors that measure parameter representative of the quality of water, in addition to hydraulic sensors).
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.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over EP 3112960 A1, Guillaume et al (hereinafter Guillaume), and in further view of US 20090066524 A1, Yukawa et al (hereinafter Yukawa).
Regarding Claim 5, Guillaume disclose the training method according to claim 1, wherein the at least one other hydraulic sensor comprises at least one flow rate sensor and at least one pressure sensor (Guillaume, [Page 5] a water distribution system is typically equipped with sensors. These sensors measure physical parameters such as velocity, flow rate, pressure, etc. at the nodes or the arcs of the network, said physical parameters at a node or an arc being state variables of the network)
Guillaume does not disclose wherein pressure sensors represent at least 50% of all sensors of the fluid network.
However, Yukawa teaches wherein pressure sensors represent at least 50% of all sensors of the fluid network (Yukawa, [0043] The water distribution block 3a is provided with a flow meter 5 and one or more pressure gauges 6a, 6b, . . . . The flow meter 5 is located on an inlet pipeline of the distribution block 3a, and measures an inflow rate flowing from the main trunk line 2 into the distribution block 3a. One or more pressure gauges 6a and 6b measures an internal pressure of the distribution block 3a. Likewise, water distribution blocks 3b, . . . are each provided with a flow meter 5 and one or more pressure gauges 6a, 6b).
Before the effective filing date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine Guillaume and Yukawa’s teaching because both references relate to monitoring distribution systems using pressure and flow sensors to obtain operational data. Yukawa teaches that each fluid monitoring unit includes a pressure sensor and a flow meter. Therefore, for each monitoring unit, pressure sensors constitute at least one of the sensors present within that unit. So, when multiple monitoring units are deployed throughout fluid network as taught by Yukawa, each unit includes a pressure sensor as part of the sensors included. Therefore, integrating Yukawa monitoring configuration into Guillaume’s water distribution system would result in pressure sensors representing at least 50% of the sensors within the network. A person of ordinary skill in the art would be motivated to combine Yukawa and Guillaume’s system in order to improve monitoring reliability and detection accuracy. The combination only merely applies a known sensor configuration to a known distribution modeling and training framework to achieve predictable results.
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant’s disclose:
-US 20180196399 A1, describing a system for managing a water distribution network including a hydraulic model of the network and subnetwork models, wherein flow and pressure values are determined using consumption data from automated metering infrastructure and used to manage the distribution network.
-WO 2020033316 A1, describing computer implemented methods and systems for detecting leaks in pipelines using artificial intelligence, including acquiring operational data during normal and simulated leak conditions and training a machine learning model to detect leaks based on the data.
-WO 2012036633 A1, describing a method for modeling a water distribution system, including simulating hydraulic characteristics of the network, estimating water consumption in demand zones, receiving pressure and flow data from sensors, and calibrating the model based on the sensor output.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IBRAHIM NAGI SHOHATEE whose telephone number is (571)272-6612. The examiner can normally be reached 8am-5pm.
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, Shelby Turner can be reached at (571) 272-6334. 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.
/IBRAHIM NAGI SHOHATEE/Examiner, Art Unit 2857
/SHELBY A TURNER/Supervisory Patent Examiner, Art Unit 2857