DETAILED ACTION
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 .
Amendments
This Office Action is in response to the amendment filed on February 18, 2026.
Claims 1, 8-9, and 11 have been amended.
No claims have been cancelled.
No new claims have been added.
The objections and rejections from the prior correspondence that are not restated herein are withdrawn.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on January 26, 2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
Applicant's arguments filed on February 18, 2026 have been fully considered.
Applicant’s arguments regarding the 35 U.S.C. 101 rejections of the previous office action have been fully considered but are not persuasive. Applicant argues:
Applicant submits that the amendments to claim 1 apply the alleged judicial exception in some meaningful way beyond generally linking the use of the judicial exception to a particular technological environment such that the claim as a whole is more than a drafting effort to monopolize the exception. For example, the claim recites "triggering the learned time-series model to generate a forecast of the evidentiary time series during a posterior period, wherein the posterior period begins at a point in time corresponding to an event occurring in the aquaculture environment." Applicant submits that the claims, as amended, are similar to the claims in Diamond v. Diehr 450 US. 175, 209 USPQ 1 (1981), where the claims in Diamond were found to be patent eligible because the additional elements limited the use of the judicial exception. Here, the amended limitation of "the posterior period begins at a point in time corresponding to an event occurring in the aquaculture environment," limits the use of the alleged judicial exception of mental process ( e.g., "generate the forecast of the evidentiary time series for the posterior period" as recited in claim 1) because the posterior period is specifically a period "beginning at a point in time corresponding to an event occurring in the aquaculture environment." In other words, the additional limitation "the posterior period begins at a point in time corresponding to an event occurring in the aquaculture environment" affects the process of triggering the learned time-series model to generate the forecast of the evidentiary time series, thereby applying the alleged judicial exception. Accordingly, because the claims apply the alleged judicial exception in some meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, the claims are considered to be integrated into a practical application under Step 2A Prong II.
Even if the claims are deemed to be directed towards an abstract idea, the claims are patent eligible under Step 2B of the MPEP 2106.05 because the claims amount to significantly more than the alleged judicial exception. In particular, as discussed with respect to Step 2A (prong II), the claims recite a specific method of "learning a time-series model based on a prior period of the evidentiary time series" and "triggering using the learned time-series model to generate a forecast of the evidentiary time series for a posterior period, wherein the posterior period begins at a point in time corresponding to an event occurring in the aquaculture environment," as recited in amended claim 1. Accordingly, the claims amount to significantly more than the alleged judicial exception under Step 2A Prong II.
Examiner respectfully disagrees. The amended limitation of “the posterior period begins at a point in time corresponding to an event occurring in the aquaculture environment” merely restricts when to perform a judicial exception, and does not integrate the exception into a practical application. In Diamond v. Diehr, the claimed invention used a mathematical equation to trigger the control of a physical process, specifically, opening the molding press and removing the cured product; it involved a process for molding raw, uncured synthetic rubber into cured precision products, which the courts have the determined as “Effecting a transformation or reduction of a particular article to a different state or thing (see MPEP § 2106.05(c)). In the present application, the relationship is inverted: an observable (i.e., physical) event occurring in an aquaculture environment triggers an abstract idea. Furthermore, considering the claim as a whole, the additional elements recited in the claims do not amount to significantly more than the abstract idea because the temporal restriction simply limits when to apply the judicial exception within the particular field of interest.
Applicant’s arguments regarding the 35 U.S.C. 103 rejections of the previous office action have been fully considered but are moot because the newly applied prior art reference of BRODERSEN, in combination with RISHI, SHOHAM, KONTKANEN, and BRITTEN teach the added limitations as shown in the rejections below.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Claims 1-10 are directed to a process. Claims 11-20 are directed to a machine or an article of manufacture.
With respect to claim(s) 1 and 11:
2A Prong 1: The claims recite an abstract idea. Specifically:
[…] determining a subset of the plurality of time-stamped images satisfy one or more frame characteristics comprising at least one of a brightness of a time-stamped image or a blur of the time-stamped image, […] (Mental process – A person can mentally evaluate one or more frame characteristics and make a judgement to determine a subset of images – see MPEP § 2106.04(a)(2)(III))
responsive to […] generating an evidentiary time series using the subset of the plurality of time-stamped images of the aquatic organisms in the aquaculture environment (Mental process – A person can mentally evaluate the subset of images to generate an evidentiary time series by using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
[…] to generate a forecast of the evidentiary time series for a posterior period (Mental process – A person can mentally evaluate the evidentiary time series and generate a forecast for a posterior period using the physical aid of a pen and paper – see MPEP § 2106.04(a)(2)(III))
learning a time-series model based on a prior period of the evidentiary time series; (Mental process –A person can mentally evaluate a prior period of the evidentiary time series and learn a time-series model by using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
If claim limitations, under their broadest reasonable interpretation, cover performance of the limitations as a mental process, but for the recitation of generic computer components, then the claim limitations fall within the mental process grouping of abstract ideas. Accordingly, the claim “recites” an abstract idea.
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
(Claim 11) one or more electronic devices to implement a biomass estimation system; (Mere recitation of a generic computer component – see § MPEP 2106.05(b)(I))
(Claim 11) one or more electronic devices to implement a forecasting system, […] (Mere recitation of a generic computer component – see § MPEP 2106.05(b)(I))
(Claim 11) the forecasting system comprising instructions which when execute cause the forecasting system to: (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
obtaining a plurality of time-stamped images of aquatic organisms in an aquaculture environment during a feeding event; (Adding insignificant extra-solution activity of mere data gathering to the judicial exception – see § MPEP2106.05(g).)
the evidentiary time series reflecting biomass estimates of the aquatic organisms in the aquaculture environment made by a biomass estimation system; (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
triggering the learned time-series model […] (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
wherein the posterior period begins at a point in time corresponding to an event occurring in the aquaculture environment, (Mere instructions to apply an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea – see MPEP 2106.05(f).)
wherein the forecast of the evidentiary time series comprises biomass estimates of the aquatic organisms in the aquaculture environment at points in time in the posterior period; (Generally linking the use of a judicial exception to a particular technological environment or field of use – see MPEP § 2106.05(h).)
causing a computer graphical user interface to be displayed, […] (Adding insignificant extra-solution activity to the judicial exception – see § MPEP2106.05(g).)
the graphical user interface including a graph that plots the evidentiary time series for at least a portion of the prior period with the forecast of the evidentiary time series for the posterior period, (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
wherein a first axis of the graph corresponds to biomasses of aquatic organisms in the aquaculture environment and a second axis of the graph corresponds to time spanning at least the portion of the prior period and the posterior period; and (Mere instructions to apply an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea – see MPEP 2106.05(f).)
(Claim 1) wherein the method is performed by one or more electronic devices. (Mere recitation of a generic computer component – see § MPEP 2106.05(b)(I))
Since the claim as a whole, looking at the additional elements individually and in combination, does not contain any other additional elements that are indicative of integration into a practical application, the claim is directed to an abstract idea.
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
(Claim 11) one or more electronic devices to implement a biomass estimation system; (Mere recitation of a generic computer component – see § MPEP 2106.05(b)(I))
(Claim 11) one or more electronic devices to implement a forecasting system, […] (Mere recitation of a generic computer component – see § MPEP 2106.05(b)(I))
(Claim 11) the forecasting system comprising instructions which when execute cause the forecasting system to: (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
obtaining a plurality of time-stamped images of aquatic organisms in an aquaculture environment during a feeding event; (Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception (WURC)- see MPEP § 2106.05(d)(ll)(i) - Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information).)
the evidentiary time series reflecting biomass estimates of the aquatic organisms in the aquaculture environment made by a biomass estimation system; (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
triggering the learned time-series model […] (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
wherein the posterior period begins at a point in time corresponding to an event occurring in the aquaculture environment, (Mere instructions to apply an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea – see MPEP 2106.05(f).)
wherein the forecast of the evidentiary time series comprises biomass estimates of the aquatic organisms in the aquaculture environment at points in time in the posterior period; (Generally linking the use of a judicial exception to a particular technological environment or field of use – see MPEP § 2106.05(h).)
causing a computer graphical user interface to be displayed, […] (Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception (WURC) - see § MPEP 2106.05(d)(II)) - Presenting offers and gathering statistics, OIP Techs., 788 F.3d at 1362-63, 115 USPQ2d at 1092-93)
the graphical user interface including a graph that plots the evidentiary time series for at least a portion of the prior period with the forecast of the evidentiary time series for the posterior period, (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
wherein a first axis of the graph corresponds to biomasses of aquatic organisms in the aquaculture environment and a second axis of the graph corresponds to time spanning at least the portion of the prior period and the posterior period; and (Mere instructions to apply an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea – see MPEP 2106.05(f).)
(Claim 1) wherein the method is performed by one or more electronic devices. (Mere recitation of a generic computer component – see § MPEP 2106.05(b)(I))
Considering the additional elements individually and in combination, and the claim as a whole, the additional elements do not provide significantly more than the abstract idea. Therefore, the claim is not patent eligible.
With respect to claim(s) 2 and 12:
2A Prong 1: The claims recite an abstract idea. Specifically:
generates biomass estimates of the evidentiary time series (Mental process – A person can mentally evaluate the evidentiary time series to generate biomass estimates by using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
wherein the biomass estimation system is a computer vision-based biomass estimation system that (Claim 12) is configured to […] based on applying computer vision techniques to images or video captured by a camera immersed underwater in the aquaculture environment. (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
wherein the biomass estimation system is a computer vision-based biomass estimation system that (Claim 12) is configured to […] based on applying computer vision techniques to images or video captured by a camera immersed underwater in the aquaculture environment. (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 3 and 13:
2A Prong 1: The claims recite an abstract idea. Specifically:
wherein the time-series model is a Bayesian time-series model (Mathematical concepts – learning the time-series model, wherein the time-series model is a Bayesian time-series model requires mathematical calculations for performing the learning – see MPEP § 2106.04(a)(2)(I))
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 4 and 14:
2A Prong 1: The claims recite an abstract idea. Specifically:
learning the time-series model based on the prior period of the set of one or more reference time series. (Mental process – A person can mentally evaluate a prior period of the evidentiary time series and learn a time-series model by using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
(Claim 14) the forecasting system further comprising instructions which when execute cause the forecasting system to: (Mere instructions to apply an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea – see MPEP 2106.05(f).)
receiving a set of one or more reference time series; and (Adding insignificant extra-solution activity of mere data gathering to the judicial exception – see § MPEP2106.05(g).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
(Claim 14) the forecasting system further comprising instructions which when execute cause the forecasting system to: (Mere instructions to apply an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea – see MPEP 2106.05(f).)
receiving [(Claim 14) receive] a set of one or more reference time series; and (Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception (WURC)- see MPEP § 2106.05(d)(ll)(i)- Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 5 and 15:
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
wherein a reference time series of the set of one or more reference time series is based on a biological model of fish growth. (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
wherein a reference time series of the set of one or more reference time series is based on a biological model of fish growth. (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 6 and 16:
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
wherein a reference time series of set of one or more reference time series is based on a feed growth-model. (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
wherein a reference time series of set of one or more reference time series is based on a feed growth-model. (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 7 and 17:
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
wherein a reference time series of the set of one or more reference time series reflects biomass estimates of aquatic organisms in a different aquaculture environment than the aquaculture environment. (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
wherein a reference time series of the set of one or more reference time series reflects biomass estimates of aquatic organisms in a different aquaculture environment than the aquaculture environment. (Generally linking the use of a judicial exception to a particular technological environment or field of use, as discussed in MPEP § 2106.05(h).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 8 and 18:
2A Prong 1: The claims recite an abstract idea. Specifically:
(Claim 8) comparing the evidentiary time series of the posterior period with the forecast of the evidentiary time series for the posterior period; (Mental process – A person can mentally compare two time series – see MPEP § 2106.04(a)(2)(III))
determining [(Claim 18) determine] that the evidentiary time series for the posterior period is a statistically significant deviation from the forecast of the evidentiary time series for the posterior period using the comparison; (Mental process– determining […] statistically significant deviation can be practically performed in the human mind, or by a human using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
generating [(Claim 18) generate] an alert or a notification about the statistically significant deviation. (Mental process – generating an alert is an observation/opinion that can be practically performed in the human mind, or by a human using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
(Claim 18) the forecasting system further comprising instructions which when execute cause the forecasting system to: (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
(Claim 18) the forecasting system further comprising instructions which when execute cause the forecasting system to: (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 9 and 19:
2A Prong 1: The claims recite an abstract idea. Specifically:
(Claim 9) comparing the evidentiary time series of the posterior period with the forecast of the evidentiary time series for the posterior period; (Mental process – A person can mentally compare two time series – see MPEP § 2106.04(a)(2)(III))
determining [(Claim 19) determine] that the evidentiary time series for the posterior period is a statistically significant deviation below the forecast of the evidentiary time series for the posterior period using the comparison; (Mental process– determining […] statistically significant deviation can be practically performed in the human mind, or by a human using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
correlating [(Claim 19) correlate] the statistically significant deviation with a sea lice count or a body wound count for aquatic organisms in the aquaculture environment for a period comprising a least a portion of the prior period or the posterior period; (Mental process – correlating is an evaluation that can be practically performed in the human mind, or by a human using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
generating [(Claim 19) generate] an alert or a notification about health of the aquatic organisms in the aquaculture environment. (Mental process – generating an alert is an observation/opinion that can be practically performed in the human mind, or by a human using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
(Claim 19) the forecasting system further comprising instructions which when execute cause the forecasting system to: (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
(Claim 19) the forecasting system further comprising instructions which when execute cause the forecasting system to: (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
With respect to claim(s) 10 and 20:
2A Prong 1: The claims recite an abstract idea. Specifically:
generate the forecast of the evidentiary time series for the posterior period. (Mental process – generating a forecast of the evidentiary time series can be practically performed in the human mind, or by a human using a pen and paper as a physical aid – see MPEP § 2106.04(a)(2)(III))
2A Prong 2: The additional elements recited in the claims do not integrate the abstract idea into a practical application, individually or in combination.
Additional elements:
receiving [(Claim 20) receive] a set of one or more reference time series; and (Adding insignificant extra-solution activity of mere data gathering to the judicial exception – see § MPEP2106.05(g).)
using [(Claim 20) use] the learned time-series model and set of one or more reference time series for the posterior period to […] (Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
2B: The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Additional elements:
receiving [(Claim 20) receive] a set of one or more reference time series; and (Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception (WURC)- see MPEP § 2106.05(d)(ll)(i)- Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information).)
using [(Claim 20) use] the learned time-series model and set of one or more reference time series for the posterior period to […](Adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea - see MPEP 2106.05(f).)
Since the claim does not recite additional elements that either integrate the judicial exception into a practical application, nor provide significantly more than the judicial exception, the claim is not patent eligible. Therefore, the claim is not patent eligible.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over RISHI (US 20200170227 A1) in view of SHOHAM (US 20150250113 A1), KONTKANEN (US 20220374470 A1), BRITTEN ("Extended fisheries recovery timelines in a changing environment"), and BRODERSEN (“Inferring Causal Impact Using Bayesian Structural Time-Series Models”), hereafter RISHI, SHOHAM, KONTKANEN, BRITTEN, and BRODERSEN respectively.
Regarding Claim 1:
RISHI teaches:
A computer-implemented method comprising:
obtaining a plurality of time-stamped images of aquatic organisms in an aquaculture environment during a feeding event; (RISHI [0085] teaches: "Video streams 204 may be obtained, time-based extraction may be implemented and data input into a computer vision module which pre-processes and analyses the behaviour of the aquatic animals in one or more pre-processing models 206." RISHI [0008] teaches: "receiving pre-processed sensor data in relation to the one or more aquatic animals;" Additionally, RISHI [0011] teaches: "[...] further optionally wherein the one or more signals comprises pre-processed sensor data; [...] wherein the one or more signals comprises: image data; video data; acoustic data; sonar data; light data; biomass data; environmental data; stereo vision data; acoustic camera data; and/or fish activity data [...]." Additionally, RISHI [0017] discusses the depth of the camera, distance of fish from sensors, extracting pH of water, and analyzing water temperature. All of these imply that the sensor is immersed underwater (i.e., in an aquaculture environment). Furthermore, RISHI [0011] teaches: "wherein the one or more signals comprises: [...] mass of feed being consumed; [...] sound of fish eating; […]". Moreover, RISHI [0034] teaches: "Typically, the sample frames and recorded data referred to above will be uploaded to the cloud during the night when no feeding is occurring (and there is plenty of time to compensate for the poor data rate)". Therefore, the data (i.e., images, video, sounds, etc.) in RISHI is obtained while the feeding is occurring.)
[…] the evidentiary time series reflecting biomass estimates of the aquatic organisms in the aquaculture environment made by a biomass estimation system; (RISHI [0008] teaches: "According to a first aspect, there is provided a computer-implemented method for feeding one or more aquatic animals, the method comprising the steps of: receiving pre-processed sensor data in relation to the one or more aquatic animals;" Additionally, RISHI [0011] teaches: "[...] further optionally wherein the one or more signals comprises pre-processed sensor data; [...] wherein the one or more signals comprises: image data; video data; acoustic data; sonar data; light data; biomass data; environmental data; stereo vision data; acoustic camera data; and/or fish activity data [...]." RISHI [0082] teaches: "[...] a number of video monitors showing the activity in the various cages of the farm." Examiner's note: under BRI, "evidentiary time series reflecting biomass estimates" can be interpreted as pre-processed sensor data received from video stream time-based extraction of aquatic animals in fish cages/farms (i.e., aquaculture environment). Further, the pre-processed data includes "biomass data" for aquatic animals (i.e. aquatic organisms), and “biomass estimation system” can be interpreted as the sensor.)
learning a time-series model based on a prior period of the evidentiary time series; (RISHI [0025-0026] teaches: "Optionally, the one or more learned decision-making models is updated using reinforcement learning techniques and/or time series analysis: optionally wherein the time series analysis considers any one or more of feed score over time, monthly diseases and/or other combination of factors which led to previous disease outbreaks. [0026] In order to understand long term historic behaviours/other environmental factors and take this available data into account in strategic farming, time series analysis may be performed to integrate into feeding recommendation by taking past data into account." Examiner's note: under BRI, "learning a time-series model" can be interpreted as the updating of the learned decision-making models using reinforcement learning, and "based on a prior period of the evidentiary time series" can be interpreted as "time series analysis [...] by taking past data into account".)
[…] learned time-series model to generate a forecast of the evidentiary time series for a posterior period, (RISHI [0025-0026] teaches: "Optionally, the one or more learned decision-making models is updated using reinforcement learning techniques and/or time series analysis: optionally wherein the time series analysis considers any one or more of feed score over time, monthly diseases and/or other combination of factors which led to previous disease outbreaks. [0026] In order to understand long term historic behaviours/other environmental factors and take this available data into account in strategic farming, time series analysis may be performed to integrate into feeding recommendation by taking past data into account.” RISHI [0017] teaches: "Other features which may be selected in optimizing a feeding/automatic strategy include live feed data; depth of camera; acoustic data; sonar data; light data; biomass data; environmental data; [...] in order to predict future fish activity and/or variables.")
[…] the aquaculture environment, […] (RISHI [0017] teaches: "Other features which may be selected in optimizing a feeding/automatic strategy include live feed data; depth of camera; acoustic data; sonar data; light data; biomass data; environmental data; [...] in order to predict future fish activity and/or variables." Examiner’s note: The sensors are implied to be in the same environment (i.e., aquaculture environment) as the fish, as taught above by RISHI in paragraph [0017].)
wherein the forecast of the evidentiary time series comprises biomass estimates of the aquatic organisms in the aquaculture environment at points in time in the posterior period, […] (RISHI [0093] teaches: "The decision-making model 306 may comprise models arranged to provide outputs 308 such as to: derive a feed intensity score, health anomaly detection, farmer performance score, the amount of food required; derive the amount of food required; estimate growth of the fish from environmental factors such as temperature and dissolved oxygen, feed which is input into the cage/farm, as well as from fish genetics such as fish size, biomass and/or fish age; [...]" RISHI [0017] teaches: "Other features which may be selected in optimizing a feeding/automatic strategy include live feed data; depth of camera; acoustic data; sonar data; light data; biomass data; environmental data; [...] in order to predict future fish activity and/or variables." Examiner’s note: under BRI, the “learned time-series” can be interpreted as RISHI’s learned decision-making model that uses pre-processed data, as outlined above, in order to predict future fish (i.e., aquatic organisms) activity and/or variables (i.e., forecast of the evidentiary time series for a posterior period), which include biomass data (i.e., biomass estimates). The sensors are implied to be in the same environment (i.e., aquaculture environment) as the fish, as taught above by RISHI in paragraph [0017].)
causing a computer graphical user interface to be displayed, […] (RISHI [0093] teaches: "[…] These outputs may be viewed by the operator via a user interface.”)
wherein the method is performed by one or more electronic devices. (RISHI [0008] teaches: "According to a first aspect, there is provided a computer-implemented method for feeding one or more aquatic animals, the method comprising the steps of: receiving pre-processed sensor data in relation to the one or more aquatic animals;" Additionally, RISHI [0040] teaches: "[0040] According to a second aspect, there is provided an apparatus operable to perform the method of any preceding claim; optionally wherein the one or more learned decision-making models are substantially implemented on a graphical processing unit; and/or optionally wherein the method is performed substantially locally to where the aquatic animals are located; and/or optionally wherein the apparatus comprises any or any combination of: an input; a memory; a processor; and an output.")
RISHI is not relied upon for teaching:
responsive to determining a subset of the plurality of time-stamped images satisfy one or more frame characteristics, comprising at least one of a brightness of a time-stamped image or a blur of the time-stamped image, generating an evidentiary time series using the subset of the plurality of time-stamped images of the aquatic organisms in the aquaculture environment, […]
triggering the learned time-series model […], wherein the posterior period begins at a point in time corresponding to an event occurring in the […] environment,
[…] the graphical user interface including a graph that plots the evidentiary time series for at least a portion of the prior period with the forecast of the evidentiary time series for the posterior period, wherein a first axis of the graph corresponds to biomasses of aquatic organisms in the aquaculture environment and a second axis of the graph corresponds to time spanning at least the portion of the prior period and the posterior period;
However, SHOHAM teaches: responsive to determining a subset of the plurality of time-stamped images satisfy one or more frame characteristics, […] generating an evidentiary time series using the subset of the plurality of time-stamped images of the aquatic organisms in the aquaculture environment; (SHOHAM [0193] teaches: "In 710, the method starts when server 384 receives a request to determine at least one characteristic related the aquatic plant culture. In 715, server 384 may adjust the imaging equipment, for example, image sensors 374, and prepare for acquiring an image. In 720, server 384 may receive at least one image of the culture, for example, from at least one image sensor 374. In 725, server 384 may identify at least one parameter of a plurality of parameters related to the aquatic plants by employing at least one image processing technique on the at least one image. In 730, server 384 may store the identified parameter(s) along with the results of the image processing technique within database 382 together with a time stamp." SHOHAM [0194] teaches: “In 735, server 384 may analyze the results related to the identified parameters to determine at least one characteristic related to the aquatic plant culture. […] If there are no additional images to be processed, server 384 may proceed to 755.” SHOHAM [0195] teaches: “The integrated data analysis may be, but is not limited to, an image processing technique that compares a received image with reference data related to parameters and characteristics from stored images, […]”. Furthermore, SHOHAM [0247] teaches: “FIGS. 23A and 23B illustrate how control unit 370 is capable of altering the growing conditions within bioreactor 310 after preforming an image processing technique on a culture of aquatic plants within bioreactor 310. The y-axis in both figures represents the relative healthiness of an aquatic plant culture and the x-axis represents time (in days).” Examiner's note: SHOHAM teaches a process for analyzing and determining at least one characteristic or parameter of collected images of aquatic organisms. If the server identifies a characteristic or parameter, the server stores the characteristics in a database. Additionally, SHOHAM [0195] teaches: “in an image processing technique that compares a received image with reference data related to parameters and characteristics from stored images,” and therefore the images with identified characteristics are also stored. Under BRI, "determining a subset of the plurality of time-stamped images satisfy one or more frame characteristics" SHOHAM’s process as described above. Furthermore, SHOHAM [FIG. 23B] teaches a graph with the x-axis representing time, and thus a time-series relating to images of a culture of aquatic plants.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teachings of RISHI and SHOHAM before them, to include SHOHAM’s process of identifying at least one characteristic or parameter of collected images of aquatic organisms into RISHI’s decision-making system. One would have been motivated to make such a combination "for monitoring the culture for early detection of stressful conditions and invaders that will allow for continuous adjustment and optimization of conditions related to the growth of the culture, thus increasing the safety, quality, and yield volume of the harvest." (SHOHAM [0141]).
RISHI in view of SHOHAM is not relied upon for teaching:
[...] determining a subset of the plurality of […] images satisfy one or more frame characteristics, comprising at least one of a brightness of a time-stamped image or a blur of the time-stamped image, […]
triggering the learned time-series model […], wherein the posterior period begins at a point in time corresponding to an event occurring in the […] environment,
[…] the graphical user interface including a graph that plots the evidentiary time series for at least a portion of the prior period with the forecast of the evidentiary time series for the posterior period, wherein a first axis of the graph corresponds to biomasses of aquatic organisms in the aquaculture environment and a second axis of the graph corresponds to time spanning at least the portion of the prior period and the posterior period;
However, KONTKANEN teaches: [...] determining a subset of the plurality of […] images satisfy one or more frame characteristics, comprising at least one of a brightness of a time-stamped image or a blur of the time-stamped image, […] (KONTKANEN [0022] teaches: "In some embodiments, the media application 103 selects a particular pair of images [...] where the images depict certain types of subjects (e.g., faces, pets, humans, etc.) […] where images meet a quality threshold (e.g., are not blurry, are well-lit, etc.), […]." KONTKANEN [0079] teaches: "[0079] In some embodiments, each intermediate image is associated with a respective timestamp that has a value between the timestamp of the first static image and the timestamp of the second static image.")
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teachings of RISHI, SHOHAM, and KONTKANEN before them, to include KONTKANEN’s filtering module that selects images that meet a quality threshold in RISHI and SHOHAM’s decision-making system. One would have been motivated to make such a combination in order to implement a filtering module that excludes the images with a quality less than a quality threshold to improve the responsiveness of the media application (KONTKANEN [0045] and [0069]).
RISHI in view of SHOHAM and KONTKANEN is not relied upon for teaching:
triggering the learned time-series model […], wherein the posterior period begins at a point in time corresponding to an event occurring in the […] environment,
[…] the graphical user interface including a graph that plots the evidentiary time series for at least a portion of the prior period with the forecast of the evidentiary time series for the posterior period, wherein a first axis of the graph corresponds to biomasses of aquatic organisms in the aquaculture environment and a second axis of the graph corresponds to time spanning at least the portion of the prior period and the posterior period;
However, BRITTEN teaches: […] the graphical user interface including a graph that plots the evidentiary time series for at least a portion of the prior period with the forecast of the evidentiary time series for the posterior period, wherein a first axis of the graph corresponds to biomasses of aquatic organisms in the aquaculture environment and a second axis of the graph corresponds to time spanning at least the portion of the prior period and the posterior period; (BRITTEN [pg. 5, Figure 3] teaches figures (a,b), which is a plot of fish biomass (in tonnes) in the vertical axis (i.e., first axis of the graph) against time in the horizontal axis (i.e., second axis of the graph). BRITTEN [pg. 5, Figure 3] teaches: "Vertical black lines differentiate the observed period and 10 years after. The mean biomass trajectories beyond the observed period are given as solid black lines" (i.e., spanning at least the portion of the prior period and the posterior period). Examiner's note: RISHI [0093] teaches the graphical user interface as outlined above. Additionally, RISHI teaches the evidentiary time series pre-processed data over time from video streams using time-based extraction.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teachings of RISHI, SHOHAM, KONTKANEN and BRITTEN before them, to include BRITTEN’s graph in RISHI, SHOHAM, KONTKANEN’s decision-making system. One would have been motivated to make such a combination in order to track productivity variation and provide a framework for adaptive fishery management to aid in sustainably harvesting fish populations, rebuilding depleted stocks, and meeting international biodiversity targets. (BRITTEN [pg. 6, Discussion]).
RISHI in view of SHOHAM, KONTKANEN, and BRITTEN is not relied upon for teaching, but BRODERSEN teaches: “triggering the learned time-series model […], wherein the posterior period begins at a point in time corresponding to an event occurring in the […] environment, […] (BRODERSEN [page 248, section 1. Introduction] teaches: “Here, we focus on measuring the impact of a discrete marketing event, such as the release of a new product, the introduction of a new feature, or the beginning or end of an advertising campaign, […].” BRODERSEN [page 259, Posterior predictive simulation] teaches: “As shown by its indices, the density in equation (2.14) is defined precisely for that portion of the time series which is unobserved: the counterfactual market response
y
~
n
+
1
,
…
,
y
~
m
that would have been observed in the treated market, after the intervention, in the absence of treatment.” BRODERSEN [page 271, section 5. Discussion] teaches: “At the same time, our approach could be used for many other applications involving causal inference. Examples include problems found in economics, epidemiology, biology or the political and social sciences.” Examiner’s note: BRODERSEN [page 266, Fig. 5 (a)] teaches fitting a model in during the pre-intervention. The fitted model (i.e., learned time-series model) begins the counterfactual forecasting at the vertical dashed line denoting the start of the intervention, which triggers the model to begin generating the counterfactual-forecast. Additionally, BRODERSEN [page 256, Fig. 2.] teaches the pre-intervention activity observed values as
y
1
:
n
, teaches
y
n
+
1
:
m
as the actual post-intervention observed values, and teaches
y
~
n
+
1
as the counterfactual forecasted post-intervention values. Therefore, under BRI, the posterior period begins at a point in time corresponding to an event occurring in the […] environment can be interpreted as the forecast
y
~
n
+
1
,
…
,
y
~
m
beginning at a time
t
=
n
+
1
, which is the first point in time after the intervention (i.e., event occurring). Furthermore, BRODERSEN [page 266, Fig. 5.] teaches causal effects of online advertising on clicks in treated regions, and thus the environment in which the event occurs is the environment in which the causal effect experiments are taking place. Moreover, BRODERSEN [page 271, section 5. Discussion] teaches that the approach can be extended to other applications involving causal inference, such as economics or biology.)
Accordingly, it would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention, having the teachings of RISHI, SHOHAM, KONTKANEN, BRITTEN, and BRODERSEN before them, to include BRODERSEN’s causal inference approach in of RISHI, SHOHAM, KONTKANEN, and BRITTEN’s decision-making system. One would have been motivated to make such a combination in order to predict what would have occurred had no intervention taken place (BRODERSEN [page 247, Abstract]).
Regarding Claim 2:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 1 as outlined above. Further, RISHI teaches:
The method of claim 1, wherein the biomass estimation system is a computer vision-based biomass estimation system that generates biomass estimates of the evidentiary time series based on applying computer vision techniques to images or video captured by a camera immersed underwater in the aquaculture environment. (RISHI [0085] teaches: "Video streams 204 may be obtained, time-based extraction may be implemented and data input into a computer vision module which pre-processes and analyses the behaviour of the aquatic animals in one or more pre-processing models 206" Additionally, RISHI [0017] teaches: "Other features which may be selected in optimizing a feeding/automatic strategy include live feed data; depth of camera; acoustic data; sonar data; light data; biomass data; environmental data; stereo vision data; acoustic camera data; and/or fish activity data; fish type; feed type; past and present feed conversion ratio; biological feed conversion ratio; economical feed conversion ratio; past and present standard growth rate; past and present specific growth rate; mortality data; feed input data comprising amount and/or rate and/or intensity; reaction of fish towards feed; fish schooling data; surface feeding activity; fish density; fish speed; and/or distance of fish from sensors; dissolved oxygen level; state of the tide; pH of the water; visibility through the water; intensity of light incident on the water; biomass data; mass of feed being consumed; air and/or water temperature; sunlight; cleanliness of water; salinity; saturation; rainfall; tide level; state of nets; treatments; sea lice count; oxygen input data; current or wind data; fish genetic data; and/or fish vaccination etc. in order to predict future fish activity and/or variables." Examiner's note: under BRI, the "depth of camera", and other extracted features such as fish speed, distance of fish from sensors, pH of the water, dissolved oxygen levels, and water temperature imply that the camera is immersed underwater.)
Regarding Claim 3:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 1 as outlined above. Further, BRITTEN teaches:
The method of claim 1, wherein the time-series model is a Bayesian time-series model. (BRITTEN [pg. 1] teaches: "We use models of dynamic stock productivity fitted via Bayesian inference to forecast rebuilding timelines for depleted stocks." Additionally, BRITTEN incorporates the reference West et al, "Bayesian Forecasting and Dynamic Models", which teaches: "Thus Bayesian forecasting involves the provision of forecast information (i.e., future information or predictions) in terms of probability distributions that represent and summarise current uncertain knowledge and beliefs. (i.e., historical data)" (West [pg. 32, section 1.3 Bayesian Modelling and Forecasting]).
Regarding Claim 4:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 1 as outlined above. Further, RISHI teaches:
-The method of claim 1, further comprising:
receiving a set of one or more reference time series; and (RISHI [0092] teaches: "FIG. 3 shows a more detailed view of the performance of the one or more learned functions 310. A number of inputs 302 are provided into the pre-processing module 304 including data inputs relating to any or any combination of: (fish) activity, pellets, environment, sensor(s) and auxiliary data." Additionally, RISHI [0019] teaches: "4) Auxiliary sensor data—current, tide, wind, pH, sunlight, oxygen, temperature, salinity, turbidity, rain, biomass data, fish mortalities, algae sensor data etc." Examiner's note: under BRI, "a set of one or more reference time series" can be interpreted as the auxiliary sensor data.)
learning the time-series model based on the prior period of the set of one or more reference time series. (RISHI [0092] teaches: "[…] These inputs 302 are inputted into one or more pre-processing modules 304 which may include any or any combination of: growth models, biological models and time series analysis." Additionally, RISHI[0024] teaches: "[...] Training of machine learning models is done over a ‘sliding window’ of the data from input to output, where the size of the sliding window is a hyperparameter of the system." Furthermore, RISHI [0025] teaches: "[...] the one or more learned decision-making models is updated using reinforcement learning techniques and/or time series analysis". Moreover, RISHI [0026] teaches: "In order to understand long term historic behaviours/other environmental factors and take this available data into account in strategic farming, time series analysis may be performed to integrate into feeding recommendation by taking past data into account." Examiner's note: under BRI, "learning the time-series model" can be interpreted as updating the learned decision-making model using reinforcement learning techniques or time series analysis, and "based on the prior period of the set of one or more reference time series" can be interpreted as inputting the auxiliary data to the learning models over a sliding window.)
Regarding Claim 5:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 4 as outlined above. Further, RISHI teaches:
The method of claim 4, wherein a reference time series of the set of one or more reference time series is based on a biological model of fish growth. (RISHI [0086] teaches: "[…] For example, higher water temperatures lead to increased growth from food and hence desirable to feed more while lower dissolved oxygen content leads to farmers decreasing amounts of feed. Therefore, there is a need for systems to take environmental factors into account as part of auxiliary data when determining and substantially optimising for factors such as fish growth." Additionally, RISHI [0089-0093] teaches: "[0089] In the described embodiments, a learned function broadly comprises two parts: [0090] 1) one or more pre-processing mathematical and/or neural network models; and [0091] 2) one or more decision making models which further responds to the vision/sensor based auxiliary data. [0092] FIG. 3 shows a more detailed view of the performance of the one or more learned functions 310. A number of inputs 302 are provided into the pre-processing module 304 including data inputs relating to any or any combination of: (fish) activity, pellets, environment, sensor(s) and auxiliary data. These inputs 302 are inputted into one or more pre-processing modules 304 which may include any or any combination of: growth models, biological models and time series analysis. [0093] The one or more pre-processing models 304 may comprise models arranged to perform any of, or any combination of, the following tasks: derive the amount of food required; estimate growth of the fish from environmental factors such as temperature and dissolved oxygen, feed which is input into the cage/farm, as well as from fish genetics such as fish size, biomass and/or fish age; calculate the time before harvest; calculate forecasts for growth of sea lice/algae blooms; and/or calculate required treatment levels".)
Regarding Claim 6:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 4 as outlined above. Further, RISHI teaches:
The method of claim 4, wherein a reference time series of set of one or more reference time series is based on a feed growth-model. (RISHI [0092] teaches: "[…] These inputs 302 are inputted into one or more pre-processing modules 304 which may include any or any combination of: growth models, biological models and time series analysis." Additionally, RISHI [0090-0091] teaches: "1) one or more pre-processing mathematical and/or neural network models; and 2) one or more decision making models which further responds to the vision/sensor based auxiliary data.")
Regarding Claim 7:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 4 as outlined above. Further, RISHI teaches:
The method of claim 4, wherein a reference time series of the set of one or more reference time series […] (RISHI [0092] teaches: "FIG. 3 shows a more detailed view of the performance of the one or more learned functions 310. A number of inputs 302 are provided into the pre-processing module 304 including data inputs relating to any or any combination of: (fish) activity, pellets, environment, sensor(s) and auxiliary data." Additionally, RISHI [0019] teaches: "4) Auxiliary sensor data—current, tide, wind, pH, sunlight, oxygen, temperature, salinity, turbidity, rain, biomass data, fish mortalities, algae sensor data etc." Examiner's note: under BRI, "a set of one or more reference time series" can be interpreted as the auxiliary sensor data.)
Further, SHOHAM teaches: […] reflects biomass estimates of aquatic organisms in a different aquaculture environment than the aquaculture environment. (SHOHAM [0156] teaches: "The computer algorithm may also include an algorithm for comparing a received image with reference data related to parameters and/or characteristics from stored images, including but not limited to, baseline images, reference images previously collected from the same culture, and/or reference images previously collected from a different culture stored in a database to determine a growth phase and/or current state of the aquatic plants." Additionally, SHOHAM [0157] teaches: "The state of the aquatic culture may be, but is not limited to a biomass density, a growth acceleration rate, a growth slowdown rate, a healthy culture, a contaminated culture, a stressed culture, a dead culture, a dying culture, selective macronutrients or micronutrients concentration/profile, a growth phase of the culture, a morality rate, etc." Moreover, SHOHAM [0140] teaches: "As used herein the term "aquatic organism" includes all biological organisms living or growing in, on, or near the water such as, but not limited to, fish, molluscs, crustaceans, echinoderms, other invertebrates and their lifestages, as well as aquatic (e.g., marine and fresh water) plants. Types of aquatic plants include, but are not limited to, algae, Spirodela, Landoltia, Lemna, Wolffiella, Wolffia, and the like. While embodiments described herein may refer to "aquatic plants," "an aquatic plant culture," or "culture of aquatic plants" any of the embodiments descried herein may be used to grow, culture, harvest, etc. any type of "aquatic organism." Examiner’s note: under BRI, the “aquaculture environment” can be interpreted as the “same culture” and the “different aquaculture environment” can be interpreted as the “different culture”.)
Regarding Claim 8:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 1 as outlined above. BRODERSEN further teaches:
comparing the evidentiary time series of the posterior period with the forecast of the evidentiary time series for the posterior period; (BRODERSEN [page 248, section 1. Introduction] teaches: “In the present setting the response variable is a time series, so the causal effect of interest is the difference between (i.e., comparing) the observed series (i.e., the evidentiary time series of the posterior period) and the series that would have been observed had the intervention not taken place (i.e., with the forecast of the evidentiary time series for the posterior period).” BRODERSEN [page 260, section 2.4. Evaluating impact] teaches: “Samples from the posterior predictive distribution over counterfactual activity can be readily used to obtain samples from the posterior causal effect, that is, the quantity we are typically interested in. For each draw τ and for each time point t = n+1, . . . , m, we set
2.15
ϕ
t
(
τ
)
≔
y
t
-
y
~
t
τ
,
yielding samples from the approximate posterior predictive density of the effect attributed to the intervention.”)
determining that the evidentiary time series for the posterior period is a statistically significant deviation from the forecast of the evidentiary time series for the posterior period using the comparison; (BRODERSEN [page 262, Sensitivity and specificity] teaches: “For each of the effect sizes 0%, 0.1%, 1%, 10% and 100%, a total of
2
8
=
256
simulations were run. This number was chosen simply on the grounds that it provided reasonably tight intervals around the reported summary statistics without requiring excessive amounts of computation. In each simulation, we concluded that a causal effect was present if and only if the central 95% posterior probability interval of the cumulative effect excluded zero.” Examiner’s note: Under BRI, is a statistically significant deviation can be interpreted as a determining that a causal effect is present such as when the central 95% posterior probability interval of the cumulative effect excludes zero. Additionally, BRODERSEN [page 261, Fig. 3] teaches that the blue shaded area illustrated in the various figures correspond to the central 95% credible intervals. BRODERSEN [page 266, Fig. 5(c)] teaches that the central 95% interval after during intervention excluded the zero line, and thus there is a causal effect present (i.e., is a statistically significant deviation).)
[…] the statistically significant deviation […] (BRODERSEN [page 262, Sensitivity and specificity] teaches: “we concluded that a causal effect was present if and only if the central 95% posterior probability interval of the cumulative effect excluded zero.” Examiner’s note: Under BRI, the statistically significant deviation occurs when the central 95% posterior probability interval of the cumulative effect excludes zero and falls completely below the zero line.)
RISHI further teaches: generating an alert or a notification about the […] deviation. (RISHI [0129] teaches: "[…] an alert may be triggered to the farmer or user of the system, letting them know that the cage is not behaving normally or effectively in terms of farming.")
Regarding Claim 9:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 1 as outlined above. BRODERSEN further teaches:
comparing the evidentiary time series of the posterior period with the forecast of the evidentiary time series for the posterior period; (BRODERSEN [page 248, section 1. Introduction] teaches: “In the present setting the response variable is a time series, so the causal effect of interest is the difference between (i.e., comparing) the observed series (i.e., the evidentiary time series of the posterior period) and the series that would have been observed had the intervention not taken place (i.e., with the forecast of the evidentiary time series for the posterior period).” BRODERSEN [page 260, section 2.4. Evaluating impact] teaches: “Samples from the posterior predictive distribution over counterfactual activity can be readily used to obtain samples from the posterior causal effect, that is, the quantity we are typically interested in. For each draw
τ
and for each time point
t
=
n
+
1
,
…
,
m
, we set
2.15
ϕ
t
(
τ
)
≔
y
t
-
y
~
t
τ
,
yielding samples from the approximate posterior predictive density of the effect attributed to the intervention.”)
determining that the evidentiary time series for the posterior period is a statistically significant deviation below the forecast of the evidentiary time series for the posterior period using the comparison; (BRODERSEN [page 262, Sensitivity and specificity] teaches: “For each of the effect sizes 0%, 0.1%, 1%, 10% and 100%, a total of
2
8
=
256
simulations were run. This number was chosen simply on the grounds that it provided reasonably tight intervals around the reported summary statistics without requiring excessive amounts of computation. In each simulation, we concluded that a causal effect was present if and only if the central 95% posterior probability interval of the cumulative effect excluded zero.” BRODERSEN [page 271, section 5. Discussion] teaches: “At the same time, our approach could be used for many other applications involving causal inference. Examples include problems found in economics, epidemiology, biology or the political and social sciences.” Examiner’s note: Under BRI, is a statistically significant deviation below the forecast is present when the central 95% posterior probability interval of the cumulative effect excludes zero and falls completely below the zero line. BRODERSEN’s equation (2.15)
ϕ
t
(
τ
)
≔
y
t
-
y
~
t
τ
yields negative values when
y
~
t
τ
>
y
t
, as shown by the pointwise difference in some instances in BRODERSEN [page 269, Fig. 7(a)]. A statistically significant deviation below the forecast occurs when the central 95% posterior probability interval excludes zero and lies on the negative side (i.e., below the zero line).)
[…] the statistically significant deviation […] (BRODERSEN [page 262, Sensitivity and specificity] teaches: “we concluded that a causal effect was present if and only if the central 95% posterior probability interval of the cumulative effect excluded zero.” Examiner’s note: Under BRI, the statistically significant deviation occurs when the central 95% posterior probability interval of the cumulative effect excludes zero and falls completely below the zero line.)
RISHI further teaches: correlating the […] deviation with a sea lice count or a body wound count for aquatic organisms in the aquaculture environment for a period comprising a least a portion of the prior period or the posterior period; and (RISHI [0128] teaches: "On top of pellet data, fish activity data and environmental data, health monitoring and detecting health anomalies at early stages can play a vital role in fish farming in general and can also impact how to determine fish feeding strategies. In order to ascertain anomalies within fish cages/farms, features similar to that used in an optimisation algorithm may be implemented in an anomaly detection model/algorithm. Anomalies, for example, may include factors relating to oncoming diseases and/or high sea lice count over time." Additionally, RISHI [0018] teaches: "Optionally, the feeding instructions are generated through correlation analysis of the pre-processed sensor data [...]". Furthermore, RISHI [0029] teaches: "Optionally, the one or more learned decision-making models further comprises an anomaly detection algorithm: optionally wherein the anomaly detection algorithm takes into account factors relating to oncoming diseases, historic health data and/or high sea lice count over time." Examiner's note: under BRI, "correlating the […] deviation", can be interpreted as the correlation analysis of the pre-processed sensor data, which includes sea lice count.)
generating an alert or a notification about health of the aquatic organisms in the aquaculture environment. (RISHI [0062] teaches: “Health monitoring and detecting health problems at early stages can play a vital role in fish farming in general and also in determining fish feeding arrangements. In order to ascertain anomalies within fish farms, features similar to the RL algorithm may be implemented in an anomaly detection algorithm. Anomalies include factors relating to oncoming diseases and/or high sea lice count over time. Using AI, anomaly detection algorithms may be in the form of unsupervised learning tasks executed from the structuring of various data. By looking at trends in data and analysing past historic data, factors relating to health hazards can be determined and mitigated. Therefore, it can be advantageous for a farmer to be informed of such events as soon as possible, for example through the use of an alarm system, in order to mitigate the negative effects.” Additionally, RISHI [0129] teaches: "[…] an alert may be triggered to the farmer or user of the system, letting them know that the cage is not behaving normally or effectively in terms of farming." Furthermore, RISHI [0093] teaches: “[…] In some embodiments, reinforcement learning on the learned function feedback loop (or through the use of iterative learning to optimise a control loop) may be used to identify individual cage behaviour. Each cage may behave slightly differently, and so it can be advantageous for a model to learn based on the individual inputs provided. This may be implemented in a number of different ways. The decision-making model 306 may comprise models arranged to provide outputs 308 such as to: derive a feed intensity score, health anomaly detection, farmer performance score, the amount of food required; derive the amount of food required; estimate growth of the fish from environmental factors such as temperature and dissolved oxygen, feed which is input into the cage/farm, as well as from fish genetics such as fish size, biomass and/or fish age; calculate the time before harvest; calculate forecasts for growth of sea lice/algae blooms; and/or calculate required treatment levels. These outputs may be viewed by the operator via a user interface.”)
Regarding Claim 10:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 1 as outlined above. Further, RISHI teaches:
The method of claim 1, further comprising:
receiving a set of one or more reference time series; and (RISHI [0092] teaches: "FIG. 3 shows a more detailed view of the performance of the one or more learned functions 310. A number of inputs 302 are provided into the pre-processing module 304 including data inputs relating to any or any combination of: (fish) activity, pellets, environment, sensor(s) and auxiliary data." Additionally, RISHI [0019] teaches: "4) Auxiliary sensor data—current, tide, wind, pH, sunlight, oxygen, temperature, salinity, turbidity, rain, biomass data, fish mortalities, algae sensor data etc." Examiner's note: under BRI, "a set of one or more reference time series" can be interpreted as the auxiliary sensor data.)
using the learned time-series model and set of one or more reference time series for the posterior period to generate the forecast of the evidentiary time series for the posterior period. (RISHI [0092] teaches: "[...] These inputs 302 are inputted into one or more pre-processing modules 304 which may include any or any combination of: growth models, biological models and time series analysis. Additionally, RISHI [0093] teaches: "The decision-making model 306 may comprise models arranged to provide outputs 308 such as to: derive a feed intensity score, health anomaly detection, farmer performance score, the amount of food required; derive the amount of food required; estimate growth of the fish from environmental factors such as temperature and dissolved oxygen, feed which is input into the cage/farm, as well as from fish genetics such as fish size, biomass and/or fish age; calculate the time before harvest; calculate forecasts for growth of sea lice/algae blooms; and/or calculate required treatment levels." Furthermore, RISHI [0099] teaches: "FIG. 6 shows an overview of one or more decision-making models in an example of a combined system working with one or more pre-processing models. The feature generator 602 analyses and pre-processes various data obtained from a fish farm. In this example system, the process of time-series forecasting on a cage-by-cage basis which is carried out by the decision-making model occurs in the cloud." Examiner's note: under BRI, the forecast can be interpreted as the outputs of the decision-making model.)
Regarding Claim 11:
The claim recites similar limitations as corresponding claim 1 and is rejected for similar reasons as claim 1 using similar teachings and rationale. RISHI also teaches:
A system comprising:
one or more electronic devices to implement a biomass estimation system; (RISHI [0008] teaches: “According to a first aspect, there is provided a computer-implemented method for feeding one or more aquatic animals, the method comprising the steps of: receiving pre-processed sensor data in relation to the one or more aquatic animals; […]” Additionally, RISHI [0085] teaches: "Video streams 204 may be obtained, time-based extraction may be implemented and data input into a computer vision module which pre-processes and analyses the behaviour of the aquatic animals in one or more pre-processing models 206".)
one or more electronic devices to implement a forecasting system, the forecasting system comprising instructions which when execute cause the forecasting system to: (RISHI [0008] teaches: “According to a first aspect, there is provided a computer-implemented method for feeding one or more aquatic animals, the method comprising the steps of: receiving pre-processed sensor data in relation to the one or more aquatic animals; inputting the pre-processed sensor data into one or more learned decision-making models, wherein the one or more learned decision-making models has been trained to substantially optimise the rate and amount of food provided to the aquatic animals; determining, by the one or more learned decision-making models using the received pre-processed sensor data, feeding instructions for the one or more aquatic animals; and outputting the feeding instructions from the one or more learned decision-making models.” Additionally, RISHI [0040] teaches: "According to a second aspect, there is provided an apparatus operable to perform the method of any preceding claim; optionally wherein the one or more learned decision-making models are substantially implemented on a graphical processing unit; and/or optionally wherein the method is performed substantially locally to where the aquatic animals are located; and/or optionally wherein the apparatus comprises any or any combination of: an input; a memory; a processor; and an output.")
Regarding Claim 12:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 11 as outlined above. Additionally, the claim recites similar limitations as corresponding claim 2 and is rejected for similar reasons as claim 2 using similar teachings and rationale.
Regarding Claim 13:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 11 as outlined above. Additionally, the claim recites similar limitations as corresponding claim 3 and is rejected for similar reasons as claim 3 using similar teachings and rationale.
Regarding Claim 14:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 11 as outlined above. Additionally, the claim recites similar limitations as corresponding claim 4 and is rejected for similar reasons as claim 4 using similar teachings and rationale. Further, RISHI teaches:
The system of claim 11, the forecasting system further comprising instructions which when execute cause the forecasting system to: (RISHI [0040-0041] teaches: “According to a second aspect, there is provided an apparatus operable to perform the method of any preceding claim; optionally wherein the one or more learned decision-making models are substantially implemented on a graphical processing unit; and/or optionally wherein the method is performed substantially locally to where the aquatic animals are located; and/or optionally wherein the apparatus comprises any or any combination of: an input; a memory; a processor; and an output. According to a third aspect, there is provided a system operable to perform the method of any preceding claim; optionally wherein the system is operable to instruct placement of feed by signalling to feed distribution apparatus.”)
Regarding Claim 15:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 14 as outlined above. Additionally, the claim recites similar limitations as corresponding claim 5 and is rejected for similar reasons as claim 5 using similar teachings and rationale.
Regarding Claim 16:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 14 as outlined above. Additionally, the claim recites similar limitations as corresponding claim 6 and is rejected for similar reasons as claim 6 using similar teachings and rationale.
Regarding Claim 17:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 14 as outlined above. Additionally, the claim recites similar limitations as corresponding claim 7 and is rejected for similar reasons as claim 7 using similar teachings and rationale.
Regarding Claim 18:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 11 as outlined above. Additionally, the claim recites similar limitations as corresponding claims 8 and 11 and is rejected for similar reasons as claims 8 and 11 using similar teachings and rationale.
Regarding Claim 19:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 11 as outlined above. Additionally, the claim recites similar limitations as corresponding claims 9 and 11 and is rejected for similar reasons as claims 9 and 11 using similar teachings and rationale.
Regarding Claim 20:
RISHI in view of SHOHAM, KONTKANEN, BRITTEN and BRODERSEN teaches the elements of claim 11 as outlined above. Additionally, the claim recites similar limitations as corresponding claims 10 and 11 and is rejected for similar reasons as claims 10 and 11 using similar teachings and rationale.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Alvaro S Laham Bauzo whose telephone number is (571)272-5650. The examiner can normally be reached Mon-Fri 7:30 AM - 11:00 AM | 1:00 PM - 5:30 PM ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Usmaan Saeed can be reached on (571) 272-4046. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/A.S.L./Examiner, Art Unit 2146
/USMAAN SAEED/Supervisory Patent Examiner, Art Unit 2146
Prosecution Insights