Response to Amendment
This communication is in response to the amendment filed on 10/10/2025. Claims 1-25, 27-53, and 55-57 are pending.
Specification
The objection to the Abstract is withdrawn based on the amendment filed on 10/20/2025, and receipt of the IDS listing the references that are cited in the Specification is acknowledged.
Claim Rejections - 35 USC § 112
The rejections of Claims 14-15 and 41-42 under 35 U.S.C. 112(b) are withdrawn based on the amendments filed on 10/10/2025.
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(s) 1, 2, 4-8, 12, 14, 17, 21, 23-25, 28, 29, 31-35, 39, 41, 44-45, 49, 51-53, and 56-57 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo et al (U.S. Pub. No. 2023/0197207, hereinafter “Angulo”) in view of Amit et al (U.S. Pub. No. 2024/0201159, hereinafter “Amit”) and Creelman et al (U.S. Pub. No. 2022/0072547, hereinafter “Creelman”).
Regarding Claim 1, Angulo teaches a system for generating machine learning training data sets for fluid monitoring applications (Fig. 9), the system comprising: two or more containers, each container for storing a fluid sample with a known concentration of one or more additive chemical parameters (paragraph [0094]-[0095], syringes contain solutions of selected components with known concentrations, paragraph [0103]); a fluidic controller for independently controlling the flow of the two or more fluid samples, through fluidic conduits, from their respective containers to a mixing unit, in such a way that the relative ratios of the two or more fluid samples delivered to the mixing unit is monitored (paragraph [0094]-[0095], programmable pumps; automatic pumping system, paragraph [0103]); a mixer for homogenizing the mixture of the two or more fluid samples in the mixing unit to create a homogenously mixed sample (paragraph [0023], components are mixed using T-mixers); a first sensor for performing one or more measurements on the homogenously mixed sample (Fig. 9, FTIR spectroscopy, paragraph [0023]); a database (Fig. 9, training set and test set are stored in database, paragraph [0059]); and a processor (paragraph [0059]) configured to: receive as an input, for each fluid sample, the concentration of the one or more additive chemical parameters (paragraphs [0094]-[0095], programmable pumping system is instructed to mix components with known concentrations); instruct the fluidic controller and mixer so as to generate the homogenously mixed sample of the fluid samples (paragraph [0023], T-mixer; paragraphs [0094]-[0095], programmable pumping system is instructed to mix components with known concentrations); determine a concentration of the one or more additive chemical parameters of the homogenously mixed sample from a combination of the relative ratios of the two or more fluid samples and of the known concentration of their respective additive chemical parameters (paragraph [0094], mass concentrations in wt %); obtain results of one or more measurements performed by the first sensor on the homogenously mixed sample (Fig. 9, FTIR spectra); and store in the database the result(s) of the one or more measurements performed by the first sensor, as feature(s), and the concentration of the one or more additive chemical parameter(s) of the homogenously mixed sample and/or the relative ratios of the two or more fluid samples, as label(s) (Fig. 9, training set and test set, paragraph [0094], labelled spectra).
Angulo does not specifically teach wherein the first sensor is selected from the group of sensors consisting of: an optical spectrometer for measuring an absorbance spectrum measured in the ultraviolet, visible and/or near infrared spectral range; a fluorescence spectrometer, and the measurement includes an emission spectrum, an excitation spectrum, or an excitation-emission matrix; a Raman spectrometer; a chromatography system, and the measurement includes a chromatograph recorded with a detector; and a chemical sensor array. However, Angulo does teach infrared spectroscopy in paragraph [0023]. Further, Amit teaches, in paragraphs [0058] and [0109], that spectral features of water samples may be determined by values of light absorption of the water samples in one or more light spectral regions, for example, fluorescence UV, IR, NIR, and fluorescence NIR. It would have been obvious to one skilled in the art before the effective filing date of the invention to include any of the fluorescence UV, NIR, and fluorescence NIR spectroscopy taught in Amit in the system of Angulo because such spectral test equipment is simple, low cost, and accessible, and such spectroscopic techniques are known in the art for measuring the light absorption of water samples (see Amit, paragraphs [0058] and [0109]).
Angulo does not specifically teach wherein at least one of the fluid conduits, mixing unit, mixer and first sensor is a microfluidic device, and wherein the system further includes a filter on the fluidic conduits and/or the inlet of the sensor. However, Creelman teaches wherein at least one of the fluid conduits, mixing unit, mixer and first sensor is a microfluidic device (Abstract, paragraph [0069], microfluidic device including optical spectroscopy), and wherein the system further includes a filter on the fluidic conduits and/or the inlet of the sensor (paragraphs [0019]-[0020] and [0026], filter membranes). It would have been obvious to one skilled in the art before the effective filing date of the invention to include a microfluidic device such as is described in Creelman in the spectroscopic system of Angulo, in order to optically collect environmental metadata efficiently (see Creelman, paragraph [0056]).
Regarding Claim 2, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo further teaches wherein the fluidic controller is configured to provide fluid sample flow from each container to the mixing unit under the action of gravity (no patentable weight due to “or”), of an external pressure or force applied to the sample (Fig. 9, pumping system), and/or of a vacuum applied to the outlet (no patentable weight due to “or”).
Regarding Claim 4, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo further teaches wherein the fluidic controller includes an individual metering pump and/or an automatic pipetting system, for controlling the individual amounts of the different fluid samples added to the mixing unit (Fig. 9, pumping system).
Regarding Claim 5, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo further teaches wherein the fluidic controller is configured to control a flow rate of each individual fluid sample flowing towards the mixing unit (Fig. 9, pumping system, paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 6, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 5. Angulo further teaches wherein the fluidic controller includes a controllable pump for controlling the flow rate of each fluid sample (Fig. 9, pumping system, paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 7, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 5. Angulo further teaches wherein the fluidic controller includes one or multiple flow meters installed on the fluid conduits for measuring the flow rate of the fluid samples as they flow towards the mixing unit (paragraph [0110], flow rates maintained at particular values).
Regarding Claim 8, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 5. Angulo further teaches wherein the fluidic controller is configured to have the ability to adjust the individual pressure or force applied to each fluid sample, so as to adjust its flow rate in the respective fluid conduit (Fig. 9, pumping system, paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 12, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 5. Angulo further teaches wherein the mixer is an in-line mixer configured to homogenize the different fluid sample streams on the fly (paragraph [0023], T-mixer; Fig. 9), wherein the first sensor is an in-line sensor configured to measure the resulting homogenously mixed sample while it flows (paragraph [0110]), and wherein the processor is configured to determine the relative ratios of the two or more fluid samples present in the homogenously mixed sample stream from their respective instantaneous flow rates (paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 14, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo further teaches wherein the processor automatically generates a selection of fluid sample combinations that are directed to a predetermined portion of a phase space of possible combinations (paragraph [0110]-[0111], set of compositions to sample determined using a Sobol sequence).
Regarding Claim 17, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo further teaches further including a machine learning system trained on the data stored in the database, for predicting at least one of the one or more chemical parameters values and the relative ratios of two or more fluid samples, from measurements performed on new fluid samples (Fig. 9; paragraph [0023], concentration prediction; paragraph [0042]).
Regarding Claim 21, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 17. Angulo further teaches wherein the machine learning system is at least partially based on an artificial neural network (paragraph [0008], ANN).
Regarding Claim 23, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 17. Angulo further teaches wherein the processor is further configured to determine an error estimate based on comparing the predicted and the determined parameter values for one or more new sample fluids with a known concentration of one or more additive chemical parameters, but that are not yet included in the database (paragraph [0007]; Fig. 9; test set, Fig. 19, blocks 115 and 118; Fig. 20, blocks 115 and 118).
Regarding Claim 24, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 23. Angulo further teaches wherein the processor is further configured to: select new fluid sample combinations to generate new features and labels to include in an enlarged training database; re-train the machine learning system on the enlarged training database; recalculate a new error estimate, and iteratively repeat the process of selecting, re-training and recalculating until the error estimate decreases below a desired precision threshold, or a maximum number of iterations is reached (paragraph [0007]; Fig. 9; test set, Fig. 19, blocks 115 and 118; Fig. 20, blocks 115 and 118; later stages in the ML training is equated to new fluid sample combinations and re-training).
Regarding Claim 25, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo further teaches wherein the two or more fluid samples are selected from one of: surface water matrices likely to be encountered at a specific location and/or pollutant streams known to contaminate the respective surface water matrices, hydrocarbon mixtures found in downhole oilfield exploration, refining operations and/or produced crude oils, an alcoholic beverage combined with a product used to adulterate alcoholic beverages, pure drinking water combined with pollutants, contaminants, chemical warfare agents, nerve agents (no patentable weight due to “one of”), toxic and/or poisonous compounds (paragraph [0037], isopropanol, butanol, acrylonitrile, adiponitrile, propionitrile), and pure air combined with pollutants, chemical warfare agents, nerve agents, toxic and/or poisonous compounds (no patentable weight due to “one of”).
Regarding Claim 28, Angulo teaches a method of generating machine learning training data sets for fluid monitoring applications (Fig. 9), the method comprising: mixing two or more fluid samples to generate a homogenously mixed sample such that the relative ratios of the two or more fluid samples that are mixed is known, each sample having a known concentration of one or more additive chemical parameters (paragraphs [0094]-[0095], programmable pumping system is instructed to mix components with known concentrations; paragraph [0023], T-mixer); determining a concentration of the one or more additive chemical parameters of the homogenously mixed sample from a combination of the relative ratios of the two or more fluid samples and of the known concentration of their respective additive chemical parameters (paragraph [0094], mass concentrations in wt %); obtaining results of one or more sensor measurements on the homogenously mixed sample (Fig. 9, FTIR spectra); and storing in a database the result(s) of the one or more measurements, as feature(s), and the concentration of the one or more additive chemical parameter(s) of the homogenously mixed sample and/or the relative ratios of the two or more fluid samples, as label(s) (Fig. 9, training set and test set, paragraph [0094], labelled spectra).
Angulo does not specifically teach wherein the obtaining includes using one of: an optical spectrometer for measuring an absorbance spectrum measured in the ultraviolet, visible and/or near infrared spectral range; a fluorescence spectrometer, and the measurement includes an emission spectrum, an excitation spectrum, or an excitation-emission matrix; a Raman spectrometer; a chromatography system, and the measurement includes a chromatograph recorded with a detector; and a chemical sensor array. However, Angulo does teach infrared spectroscopy in paragraph [0023]. Further, Amit teaches, in paragraphs [0058] and [0109], that spectral features of water samples may be determined by values of light absorption of the water samples in one or more light spectral regions, for example, fluorescence UV, IR, NIR, and fluorescence NIR. It would have been obvious to one skilled in the art before the effective filing date of the invention to include any of the fluorescence UV, NIR, and fluorescence NIR spectroscopy taught in Amit in the system of Angulo because such spectral test equipment is simple, low cost, and accessible, and such spectroscopic techniques are known in the art for measuring the light absorption of water samples (see Amit, paragraphs [0058] and [0109]).
Angulo does not specifically teach using a microfluidic device, and wherein using the microfluidic device includes using a filter to eliminate suspended matter that may interfere with the measurement. However, Creelman teaches using a microfluidic device (Abstract, paragraph [0069], microfluidic device including optical spectroscopy), and wherein using the microfluidic device includes using a filter to eliminate suspended matter that may interfere with the measurement (paragraphs [0019]-[0020] and [0026], filter membranes). It would have been obvious to one skilled in the art before the effective filing date of the invention to include a microfluidic device such as is described in Creelman in the spectroscopic system of Angulo, in order to optically collect environmental metadata efficiently (see Creelman, paragraph [0056]).
Regarding Claim 29, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo further teaches wherein each fluid sample is stored in a separate container (paragraphs [0095] and [0103], syringes], and wherein mixing two or more fluid samples includes providing flow of fluid sample from each container to a mixing unit under the action of gravity (no patentable weight due to “or”), of an external pressure or force applied to the sample (Fig. 9, pumping system), and/or of a vacuum or suction pump applied to the outlet (no patentable weight due to “or”).
Regarding Claim 31, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 29. Angulo further teaches wherein providing fluid sample flow from each container to the mixing unit includes using an individual metering pump and/or an automatic pipetting system, for controlling the individual amounts of the different fluid samples added to the mixing unit (Fig. 9, pumping system).
Regarding Claim 32, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 29. Angulo further teaches wherein providing fluid sample flow from each container to the mixing unit includes controlling a flow rate of each individual fluid sample flowing towards the mixing unit (Fig. 9, pumping system, paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 33, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 32. Angulo further teaches wherein controlling the flow rate of each individual fluid sample flowing towards the mixing unit includes using a controllable pump for controlling the flow rate of each fluid sample (Fig. 9, pumping system, paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 34, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 32. Angulo further teaches wherein controlling the flow rate of each individual fluid sample flowing towards the mixing unit includes measuring the flow rate of the fluid samples as they flow towards the mixing unit (paragraph [0110], flow rates maintained at particular values).
Regarding Claim 35, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 32. Angulo further teaches wherein controlling the flow rate of each individual fluid sample flowing towards the mixing unit includes adjusting the individual pressure or force applied to each fluid sample (Fig. 9, pumping system, paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 39, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo further teaches wherein mixing two or more fluid samples to generate a homogenously mixed sample includes homogenizing different fluid sample streams on the fly (paragraph [0023], T-mixer; Fig. 9), wherein obtaining results of one or more sensor measurements on the homogenously mixed sample includes measuring the resulting homogenously mixed sample while it flows (paragraph [0110]), and wherein the relative ratios of the two or more fluid samples present in the homogenously mixed sample stream is determined from their respective instantaneous flow rates (paragraph [0094], programmed flow rates, paragraph [0110]).
Regarding Claim 41, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo further teaches generating a selection of fluid sample combinations for mixing that are directed to a predetermined portion of a phase space of possible combinations (paragraph [0110]-[0111], set of compositions to sample determined using a Sobol sequence).
Regarding Claim 44, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo further teaches further comprising training a machine learning system on the data stored in the database (Fig. 9, training set, ML training algorithm; paragraph [0059]).
Regarding Claim 45, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo further teaches predicting, by the machine learning system, the one or more chemical parameters values and/or the relative ratios of two or more fluid samples, from measurements performed on new fluid samples not included in the training (Fig. 9; paragraph [0023], concentration prediction; paragraph [0042]).
Regarding Claim 49, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 44. Angulo further teaches wherein the machine learning system is at least partially based on an artificial neural network (paragraph [0008], ANN).
Regarding Claim 51, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 44. Angulo further teaches determining an error estimate based on comparing the predicted and the determined parameter values for new fluid sample combinations that are not yet included in the database, which have a known concentration of one or more additive chemical parameters (paragraph [0007]; Fig. 9; test set, Fig. 19, blocks 115 and 118; Fig. 20, blocks 115 and 118).
Regarding Claim 52, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 51. Angulo further teaches selecting new fluid sample combinations to generate new features and labels to include in an enlarged training database; re-training the machine learning system on the enlarged training database; recalculating a new error estimate, and iteratively repeating the process of selecting, re-training and recalculating until the error estimate decreases below a desired precision threshold, or a maximum number of iterations is reached (paragraph [0007]; Fig. 9; test set, Fig. 19, blocks 115 and 118; Fig. 20, blocks 115 and 118; later stages in the ML training is equated to new fluid sample combinations and re-training).
Regarding Claim 53, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo further teaches wherein the two or more fluid samples are selected from one of: surface water matrices likely to be encountered at a specific location and/or pollutant streams known to contaminate the respective surface water matrices, hydrocarbon mixtures found in downhole oilfield exploration, refining operations and/or produced crude oils, an alcoholic beverage combined with a product used to adulterate alcoholic beverages, pure drinking water combined with pollutants, contaminants, chemical warfare agents, nerve agents (no patentable weight due to “one of”), toxic and/or poisonous compounds (paragraph [0037], isopropanol, butanol, acrylonitrile, adiponitrile, propionitrile), and pure air combined with pollutants, chemical warfare agents, nerve agents, toxic and/or poisonous compounds (no patentable weight due to “one of”).
Regarding Claim 56, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo further teaches performing the method using the system of claim 1 (see the rejection of Claim 1, above; method is performed by processor).
Regarding Claim 57, Angulo in view of Amit and Creelman teaches a method of generating machine learning training data sets for fluid monitoring applications, performed using the system of claim 1 (see the rejection of Claim 1, above; method is performed by processor).
Claim(s) 3 and 30 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Verhaverbeke (U.S. Pub. No. 2004/0002430).
Regarding Claim 3, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 2. Angulo does not teach wherein the fluidic controller includes individual on-off valves for successively controlling the flow of each fluid sample from the containers to the mixing unit, and further includes one of a scale and a calibrated level meter for measuring the amount of each sample fluid that is being dispensed while the respective valve is in the on position. However, Verhaverbeke teaches in Fig. 3 and paragraph [0042] valves 317, 309, and 314 that are controlled (i.e., turned on and off) by a liquid level sensor 320 to dispense specific amounts of fluid into a mixing vessel 314. It would have been obvious to one skilled in the art before the effective filing date of the invention to use the valves and liquid level sensor described in Verhaverbeke to dispense the component solutions of Angulo, in order to deliver known volumes of fluids into a mixing vessel (see Verhaverbeke, paragraph [0042]).
Regarding Claim 30, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 29. Angulo does not teach wherein providing flow of fluid sample from each container to the mixing unit includes controlling the flow of fluid sample with individual on-off valves, and further includes measuring the amount of each sample fluid that is being dispensed while the respective valve is in the on position. However, Verhaverbeke teaches in Fig. 3 and paragraph [0042] valves 317, 309, and 314 that are controlled (i.e., turned on and off) by a liquid level sensor 320 to dispense specific amounts of fluid into a mixing vessel 314. It would have been obvious to one skilled in the art before the effective filing date of the invention to use the valves described in Verhaverbeke to dispense the component solutions of Angulo, in order to deliver known volumes of fluids into a mixing vessel (see Verhaverbeke, paragraph [0042]).
Claim(s) 9 and 36 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Saidman et al (U.S. Pub. No. 2003/0080153, hereinafter “Saidman”).
Regarding Claim 9, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 8. Angulo does not teach wherein the fluidic controller is configured to apply individual pressures to each fluid sample through a pressurizing fluid in gas or liquid phase, said pressurizing fluid being separated from each fluid sample by one of a compliant partition, a piston, and a threaded bag or combinations thereof. However, Saidman teaches that liquid dispensing modules are often actuated with pressurized fluid using a piston (paragraph [0004]). It would have been obvious to one skilled in the art before the effective filing date of the invention to include the liquid dispensing modules described in Saidman in the system of Angulo, because such liquid dispensing modules are often used (see Saidman, paragraph [0004]).
Regarding Claim 36, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 35. Angulo does not teach wherein adjusting the individual pressure or force applied to each fluid sample includes applying individual pressures to each fluid sample through a pressurizing fluid in gas or liquid phase, said pressurizing fluid being separated from each fluid sample by one of a compliant partition, a piston, and a threaded bag or combinations thereof. However, Saidman teaches that liquid dispensing modules are often actuated with pressurized fluid using a piston (paragraph [0004]). It would have been obvious to one skilled in the art before the effective filing date of the invention to include the liquid dispensing modules described in Saidman in the system of Angulo, because such liquid dispensing modules are often used (see Saidman, paragraph [0004]).
Claim(s) 10 and 37 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Ambrosina et al (U.S. Pub. No. 2014/0216560, hereinafter “Ambrosina”).
Regarding Claim 10, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 8. Angulo does not teach wherein each fluidic conduit further includes a hydraulic resistor that is selected, based on the respective fluid sample viscosity and the maximum pressure and/or force that the controller can apply to the fluid sample, so as to limit the flow rate of the respective fluid sample to a desired maximum value. However, Ambrosina teaches, in paragraph [0096], a variable hydraulic resistor that is used to control a flow rate in a fluid flow measurement and control system. It would have been obvious to one skilled in the art before the effective filing date of the invention to use a hydraulic resistor such as is taught in Ambrosina to dispense the component solutions of Angulo, in order to control the flow of liquid in the system (see Ambrosina, paragraph [0096]).
Regarding Claim 37, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 32. Angulo does not teach wherein controlling the flow rate of each individual fluid sample flowing towards the mixing unit includes using a hydraulic resistor. However, Ambrosina teaches, in paragraph [0096], a variable hydraulic resistor that is used to control a flow rate in a fluid flow measurement and control system. It would have been obvious to one skilled in the art before the effective filing date of the invention to use a hydraulic resistor such as is taught in Ambrosina to dispense the component solutions of Angulo, in order to control the flow of liquid in the system (see Ambrosina, paragraph [0096]).
Claim(s) 11 and 38 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Kozyuk (U.S. Pub. No. 2008/0281131).
Regarding Claim 11, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 5. Angulo does not teach wherein the fluidic controller is configured to control the effective hydraulic resistance of each fluidic conduit, by the means of operating one of a regulating valve, modulating valve, variable constriction, pinch valve, ball valve, globe valve, and needle valve or combinations thereof. However, Kozyuk teaches, in paragraph [0026], an outlet from a chamber containing a fluid comprising a localized hydraulic resistance, such as a ball valve or needle valve. It would have been obvious to one skilled in the art before the effective filing date of the invention to use a ball or needle valve such as is taught in Kozyuk to dispense the component solutions of Angulo because such valves are known in the art (see Kozyuk, paragraph [0026]).
Regarding Claim 38, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 32. Angulo does not teach wherein controlling the flow rate of each individual fluid sample flowing towards the mixing unit includes controlling the effective hydraulic resistance using one of a regulating valve, a modulating valve, a variable constriction, a pinch valve, a ball valve, a globe valve, and a needle valve or combinations thereof. However, Kozyuk teaches, in paragraph [0026], an outlet from a chamber containing a fluid comprising a localized hydraulic resistance, such as a ball valve or needle valve. It would have been obvious to one skilled in the art before the effective filing date of the invention to use a ball or needle valve such as is taught in Kozyuk to dispense the component solutions of Angulo because such valves are known in the art (see Kozyuk, paragraph [0026]).
Claim(s) 13 and 40 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman and Spaid et al (U.S. Pub. No. 2004/0053315, hereinafter “Spaid”).
Regarding Claim 13, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo does not teach wherein the microfluidic device includes channels having lateral dimension between 1µm and 1000µm. However, Creelman teaches use of microfluidic devices for optical spectroscopy (see Abstract). Further, Spaid teaches in paragraph [0070] that microfluidic devices can include microscale channels, i.e. channels having a dimensions that are typically between about .1 micrometers and about 500 micrometers. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the claimed channel dimensions, as taught in Spaid, in the system of Angulo and Creelman, because microfluidics may be used to generate highly reproducible and rapidly changeable microenvironments for control of chemical and biological reaction conditions (see Spaid, paragraph [0004]), and because the claimed dimensions are typical for microfluidic devices (see Spaid, paragraph [0070]).
Regarding Claim 40, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo does not teach wherein the microfluidic device includes channels having lateral dimension between 1µm and 1000µm. However, Creelman teaches use of microfluidic devices for optical spectroscopy (see Abstract). Further, Spaid teaches in paragraph [0070] that microfluidic devices can include microscale channels, i.e. channels having a dimensions that are typically between about .1 micrometers and about 500 micrometers. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the claimed channel dimensions, as taught in Spaid, in the system of Angulo and Creelman, because microfluidics may be used to generate highly reproducible and rapidly changeable microenvironments for control of chemical and biological reaction conditions (see Spaid, paragraph [0004]), and because the claimed dimensions are typical for microfluidic devices (see Spaid, paragraph [0070]).
Claim(s) 15 and 42 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Hwang et al (U.S. Pub. No. 2023/0087837, hereinafter “Hwang”).
Regarding Claim 15, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 14. Angulo does not specifically teach wherein the predetermined portion of the phase space targets ranges of samples combinations based on their likelihood of being encountered in real-life situations. However, Hwang teaches in paragraph [0025], generation of training data for machine learning models such that the training data represents realistic scenarios, i.e., such that artefacts that have little to no likelihood of being to be encountered in a real-world environment are not included. It would have been obvious to one skilled in the art to include generation of training data based on likelihood of being encountered in a real-world environment, as taught in Hwang, in the machine learning model training system of Angulo, in order to avoid training the machine learning model with unnecessary and/or irrelevant data (see Hwang, paragraph [0025]).
Regarding Claim 42, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 41. Angulo does not specifically teach wherein the predetermined portion of the phase space targets ranges of samples combinations based on their likelihood of being encountered in real-life situations. However, Hwang teaches in paragraph [0025], generation of training data for machine learning models such that the training data represents realistic scenarios, i.e., such that artefacts that have little to no likelihood of being to be encountered in a real-world environment are not included. It would have been obvious to one skilled in the art to include generation of training data based on likelihood of being encountered in a real-world environment, as taught in Hwang, in the machine learning model training system of Angulo, in order to avoid training the machine learning model with unnecessary and/or irrelevant data (see Hwang, paragraph [0025]).
Claim(s) 16, 18, 20, 43, 46, and 48 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Feinberg et al (U.S. Pub. No. 2021/0358564).
Regarding Claim 16, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 1. Angulo does not specifically teach wherein the database is located on a remote computer server which communicates with the processor via a wireless or wired communication link. However, Feinberg teaches in paragraph [0082] that a system that trains machine learning models can be based on a cloud architecture including a group of servers communicating over a network to provide data and/or executable applications. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the servers and network communications of Feinberg in the system of Angulo, because cloud server configurations maybe be used for deep learning networks that train models (see Feinberg, paragraph [0082]).
Regarding Claim 18, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 17. Angulo does not specifically teach further including a copy of the machine learning system trained on the data, for remote use with a second sensor similar to the first sensor. However, Angulo does teach a machine learning system and sensor. It would have been obvious to one skilled in the art before the effective filing date of the invention to include a second machine learning system and second sensor in the system of Angulo, since it has been held that mere duplication of the essential working parts of a device involves only routine skill in the art. St. Regis Paper Co. v. Bemis Co., 193 USPQ 8. Further, Feinberg teaches in paragraph [0082] that a system that trains machine learning models can be based on a cloud architecture including a group of servers communicating over a network to provide data and/or executable applications. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the remote provision of data and/or executable applications that is taught in Feinberg in the system of Angulo, because cloud server configurations maybe be used for deep learning networks that train models (see Feinberg, paragraph [0082]).
Regarding Claim 20, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 17. Angulo does not specifically teach wherein the machine learning system is located on a remote computer server, the first sensor transmits the measurements to the server via a wireless or wired communication link, and the server transmits back the one or more chemical parameters values predicted by the machine learning system. However, Angulo teaches measurements and chemical parameters (see, e.g., paragraph [0011]). Further, Feinberg teaches in paragraph [0082] that a system that trains machine learning models can be based on a cloud architecture including a group of servers communicating over a network to provide data (i.e., the claimed measurements and chemical parameters) and/or executable applications. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the servers and network communications of Feinberg in the system of Angulo, because cloud server configurations maybe be used for deep learning networks that train models (see Feinberg, paragraph [0082]).
Regarding Claim 43, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo does not specifically teach wherein a processor controls and/or performs the mixing, determining, obtaining and storing, and the database is located on a remote computer server which communicates with the processor via a wireless or wired communication link. However, Feinberg teaches in paragraph [0082] that a system that trains machine learning models can be based on a cloud architecture including a group of servers communicating over a network to provide data and/or executable applications. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the servers and network communications of Feinberg in the system of Angulo, because cloud server configurations maybe be used for deep learning networks that train models (see Feinberg, paragraph [0082]).
Regarding Claim 46, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 45. Angulo does not specifically teach further including a copy of the machine learning system trained on the data, for remote use. However, Angulo does teach a machine learning system trained on the date. It would have been obvious to one skilled in the art before the effective filing date of the invention to include a copy of the machine learning system in the system of Angulo, since it has been held that mere duplication of the essential working parts of a device involves only routine skill in the art. St. Regis Paper Co. v. Bemis Co., 193 USPQ 8. Further, Feinberg teaches in paragraph [0082] that a system that trains machine learning models can be based on a cloud architecture including a group of servers communicating over a network to provide data and/or executable applications. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the remote provision of data and/or executable applications that is taught in Feinberg in the system of Angulo, because cloud server configurations maybe be used for deep learning networks that train models (see Feinberg, paragraph [0082]).
Regarding Claim 48, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 44. Angulo does not specifically teach wherein the machine learning system is located on a remote computer server, the method further comprising sending the results of the one or more sensor measurements to the server via a wireless or wired communication link, and transmitting back, by the server, the one or more chemical parameters values predicted by the machine learning system. However, Angulo teaches measurements and chemical parameters (see, e.g., paragraph [0011]). Further, Feinberg teaches in paragraph [0082] that a system that trains machine learning models can be based on a cloud architecture including a group of servers communicating over a network to provide data (i.e., the claimed measurements and chemical parameters) and/or executable applications. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the servers and network communications of Feinberg in the system of Angulo, because cloud server configurations maybe be used for deep learning networks that train models (see Feinberg, paragraph [0082]).
Claim(s) 19 and 47 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Applicant Admitted Prior Art (AAPA).
Regarding Claim 19, Angulo teaches everything that is claimed above with respect to Claim 17. Angulo does not specifically teach wherein the fluid samples are acquired in an operational environment and do not have a known concentration of one or more additive chemical parameters. However, AAPA teaches, in paragraphs [0002]-[0003] in the Background section of the Specification as filed, identification of the composition of fluid samples acquired in an operational environment (e.g., collected water samples). It would have been obvious to one skilled in the art before the effective filing date of the invention to include the collected water samples of AAPA in the machine learning system for determining the composition of mixtures that is taught in Angulo, because it is important to be able to identify such mixtures, and measure their actual composition (see Applicant’s Specification as filed, paragraph [0003]).
Regarding Claim 47, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 45. Angulo does not specifically teach wherein the new fluid samples are acquired in an operational environment. However, AAPA teaches, in paragraphs [0002]-[0003] in the Background section of the Specification as filed, identification of the composition of fluid samples acquired in an operational environment (e.g., collected water samples). It would have been obvious to one skilled in the art before the effective filing date of the invention to include the collected water samples of AAPA in the machine learning system for determining the composition of mixtures that is taught in Angulo, because it is important to be able to identify such mixtures, and measure their actual composition (see Applicant’s Specification as filed, paragraph [0003]).
Claim(s) 22 and 50 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman, and Jones (U.S. Pub. No. 2021/0313016).
Regarding Claim 22, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 17. Angulo does not specifically teach where the machine learning system implements partial least squares regression. However, Angulo does teach regression machine learning (paragraphs [0037], [0040]). Further, Jones teaches PLS regression in paragraphs [0018] and [0019]. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the partial PLS regression taught in Jones in the regression machine learning system of Angulo, because PLS regression has been used to capture chemical gradients that predict other datasets (see Jones, paragraph [0019]).
Regarding Claim 50, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 44. Angulo does not specifically teach where the machine learning system implements partial least squares regression. However, Angulo does teach regression machine learning (paragraphs [0037], [0040]). Further, Jones teaches PLS regression in paragraphs [0018] and [0019]. It would have been obvious to one skilled in the art before the effective filing date of the invention to include the partial PLS regression taught in Jones in the regression machine learning system of Angulo, because PLS regression has been used to capture chemical gradients that predict other datasets (see Jones, paragraph [0019]).
Claim(s) 27 and 55 is/are rejected under 35 U.S.C. 103 as being unpatentable over Angulo in view of Amit, Creelman and Bromley (U.S. Pub. No. 2014/0271593).
Regarding Claim 27, Angulo teaches everything that is claimed above with respect to Claim 1. Angulo in view of Amit and Creelman does not specifically teach a cleaning mechanism for cleaning and/or decontaminating the mixing unit, mixer and/or first sensor between successive measurements. However, Bromley teaches in paragraph [0580] cleaning mixing vessels between uses in a system that includes making FTIR measurements (paragraph [0253]). It would have been obvious to one skilled in the art before the effective filing date of the invention to include the cleaning such as is taught in Bromley in the FTIR system of Angulo (see Angulo, Abstract), because such cleaning between uses is typical (see Bromley, paragraph [0580]).
Regarding Claim 55, Angulo in view of Amit and Creelman teaches everything that is claimed above with respect to Claim 28. Angulo does not specifically teach wherein the method is performed by a system, the method further including cleaning and/or decontaminating the system between successive measurements. However, Bromley teaches in paragraph [0580] cleaning mixing vessels between uses in a system that includes making FTIR measurements (paragraph [0253]). It would have been obvious to one skilled in the art before the effective filing date of the invention to include the cleaning such as is taught in Bromley in the FTIR system of Angulo (see Angulo, Abstract), because such cleaning between uses is typical (see Bromley, paragraph [0580]).
Prior Art of Record
The prior art made of record and not relied upon is considered pertinent to Applicant’s disclosure.
O’Connor et al (U.S. Pub. No. 2002/0187074) teaches a microfluidic device for spectrometry (paragraph [0033]) that includes filters (paragraphs [0085] and [0096]).
Handique et al (U.S. Pub. No. 2007/0292941) teaches a microfluidic cartridge for use with an optical spectrometer (paragraph [0027]) that includes a filter (paragraphs [0031] and [0055]).
Response to Arguments
Applicant's arguments filed 10/10/2025 have been fully considered but they are not persuasive. Regarding the newly added features of Claim 1, the Amit and Creelman references teach the newly added features (see the updated rejections, above); it is noted that the references in the Prior Art of Record section above also teach the newly added features regarding the microfluidic device. Applicant argues on page 18 that combining Spaid with Angulo would render Angulo unsatisfactory for its intended purpose. However, Applicant defines the intended purpose of Angulo in an extremely narrow, self-serving manner. The Examiner considers it to be obvious to implement an ML model such as is taught in Angulo using other known types of spectrometry. Also, in the updated rejections of Claims 13 and 40, Spaid is merely cited as teaching typical dimensions for microfluidic devices.
Applicant's amendment necessitated the new ground(s) of rejection presented in this