Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
The United States Patent & Trademark Office appreciates the application that is submitted by the inventor/assignee. The United States Patent & Trademark Office reviewed the following application and has made the following comments below.
Priority
This application claims benefit of foreign priority under 35 U.S.C. 119(a)-(d) of EP 22169148.8, filed in Europe on 04/21/2022, and PCT/EP/2023/058706, filed on 04/15/2023.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/03/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Preliminary Amendment
Applicant submitted a preliminary amendment on 10/03/2024. The Examiner acknowledges the amendment and has reviewed the claims accordingly.
Specification
The disclosure is objected to because of the following informalities:
On page 4, line 26 “form the one or more positions” should read “from the one or more positions.”
On page 5, lines 12-13, “as indicates by the predicted spatial distribution” should read “as indicated by the predicted spatial distribution.”
On page 7, line 13, “simultaneous build a new one” should read, “simultaneously build a new one.”
On page 10, line 5, “training data only include sets” should read, “training data only includes sets.”
On page 11, line 9, “such pretreating may comprising” should read, “such pretreating may comprise”
On page 16, line 23, “barriers 4” should read “barriers 6.”
On page 17, line 31, “cameras 4” should read “cameras 14.”
On page 22, line 13, “amount of feed ped into each area” should read “amount of feed put/dispensed into each area.”
On page 23, line 6, “this allows to determine the trajectory for that crustaceans” should read “this allows determination of the trajectory for that crustacean.”
On page 24, line 8, “Figure 4D is a histogram illustrates” should read, “Figure 4D is a histogram that illustrates.”
On page 24, line 23, “which may the future spatial” should read, “which may indicate the future spatial.”
On page 25, line 12, “preferable relate” should read “preferably related.”
On page 25, lines 12-13, “training data only describe situation that have actually occurred” should read “training data only describes situations that have actually occurred.”
On page 26, line 1, “the training data are preferably relate” should read “the training data are preferably related.”
On page 26, line 2, “only describe situation that have actually occurred” should read “only describes situations that have actually occurred.”
Appropriate correction is required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103(a) are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-2, 6-9, and 11-14 are rejected under 35 U.S.C. 103(a) as being unpatentable over Rishi et al. (U.S. Patent Pub. No. 2020/0170227, hereafter referred to as Rishi) in view of Shahrestani (U.S. Patent No. 11,493,629, hereafter referred to as Shahrestani).
Regarding Claim 1, Rishi teaches a computer-implemented method (Abstract, Paragraph [0079], Rishi teaches a computer-implemented method for feeding one or more aquatic animals such as crustaceans.) for determining a spatial feed insert distribution for feeding (Paragraphs [0035], [0079], Rishi teaches deriving an amount of feed, a rate at which feed should be provided, feed conversion rate, and instructing placement of a derived amount of feed. The Examiner interprets determining a spatial feed distribution to include determining an amount of feed to be provided to the cage in light of Applicant’s specification (Page 7, lines 7-10), which states “the spatial feed insert distribution indicates for each position out of the one or more positions, an amount of feed that is to be inserted into the volume…” In addition, the Examiner interprets “in” the cage to be one or more positions in a “volume.”) that are present in a volume at least partially enclosed by one or more barriers for keeping the (Paragraphs [0010], [0079], Rishi teaches the feeding of one or more aquatic animals takes place in a confined place containing water. One or more enclosed spaces may comprise one or more cages and/or one or more aquatic animal farms. The techniques may be applied to all water-based animals, including crustaceans.), the method comprising; determining by a processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras (Paragraphs [0011], [0134], Fig. 5, Rishi teaches capturing image data. Fig. 5 shows a view from six separate image sensors.),
PNG
media_image1.png
342
683
media_image1.png
Greyscale
an actual spatial distribution of (Paragraphs [0019], [0011], [0079], Rishi teaches determining activity features such as placement of fish within a cage or fish density. The techniques are applicable to all water-based animals, including crustaceans. Under BRI, the Examiner interprets placement of fish in a cage, fish density and/or displayed images (see above) each represent or show the actual spatial distribution of the water-based animals in the cage.) determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras, for one or more (Paragraphs [0047], [0079], Rishi teaches monitoring the activity level over a plurality of image frames. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), each activity value being indicative of how active one or more (Paragraphs [0011], [0079], Rishi teaches fish activity data which comprises fish speed, fish schooling data, reaction of fish towards feed, etc. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), and based on the determined actual spatial distribution (Paragraphs [0019], [0079], Rishi teaches the activity features may include placement of fish within a cage and/or density of fish, and/or distance of fish from surface. The activity features are input into one or more learned decision-making models. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and the determined activity values (Paragraphs [0105], [0107], [0079], Rishi teaches inputting features, including “activity features” into one or more learned decision-making models. Activity features include how close the fish are to the camera, how they are schooling, distance of fish from surface, speed of fish, density of fish, placement of fish within a cage. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), predicting by the processor (Paragraph [0040], Rishi teaches a processor.), for a future time, a future spatial distribution of (Paragraphs [0017], [0011], [0024], [0125], [0079], Rishi teaches predicting future “fish activity” and/or variables. Fish activity may include fish density and/or distance of fish from sensors, biomass data, etc. Under BRI, the Examiner interprets predicting future fish density and/or distance of fish from the sensors to be predicting a future spatial distribution because “fish density” measures the number of fish present in a specific unit of water and describes how the fish are spread out across a geographical area (spatial distribution). Further, distance of fish from sensors describes how the fish are distributed vertically in relation to the sensors. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on the future spatial distribution of (Abstract, Paragraphs [0043-44], [0093-95], Rishi teaches determining, by one or more learned decision-making models using the received pre-processed sensor data, feeding instructions for one or more aquatic animals and outputting the feeding instruction from the one or more learned decision-making models. The output may comprise an optimized level of feed to provide to one or more aquatic animals within a confined space containing water.) the spatial feed distribution indicating one or more positions at a boundary of the volume and/or within the volume from which feed is to be inserted in the volume by a feed system (Paragraphs [0037], [0123], Rishi teaches instructing placement of the derived amount of feed directly to a control feed apparatus and/or other automatic controls around the one or more cages and/or the one or more fish farms. The output of the one or more learned functions causes the feeding equipment to place feed in the respective cages. Under BRI, the Examiner interprets “in the respective cages” to be “one or more positions” within the volume. In addition, the Examiner interprets “and/or” to only one of either one or more positions at a boundary of the volume or within the volume is required to meet the claim limitation.).
Rishi does not explicitly disclose determining a spatial feed insert distribution for feeding crustaceans that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume, an actual spatial distribution of crustaceans within the volume, for one or more crustaceans in the volume, one or more activity values each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans, predicting for a future time, a future spatial distribution of crustaceans within the volume and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution.
Shahrestani is in the same field of art of providing information about the status and composition of aquaculture farming tanks or ponds to optimize farming practices. Further, Shanrestani teaches determining a spatial feed insert distribution for feeding crustaceans (Col. 5, lines 40-42, Shahrestani teaches using the aquaculture data to generate shrimp feed administration data.) that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume (Col. 9, lines 21-37, Fig. 7, Shahrestani teaches aquaculture farming data includes shrimp behavior data uploaded from a single pond, an entire farm or ponds, or an entire region of farms of ponds.),
PNG
media_image2.png
295
243
media_image2.png
Greyscale
an actual spatial distribution of crustaceans within the volume (Col. 14, lines 17-27, Fig. 5b, Shahrestani teaches performing “sweeps” on the entire tank (360) with a range of 5 m. Each sweep is a representation of the density and distribution of target objects (shrimp) across 600 seconds. Shrimp information observed within a 3D space (water-column) are compressed into a 2D (top-down) intensity map.),
PNG
media_image3.png
287
750
media_image3.png
Greyscale
for one or more crustaceans in the volume, one or more activity values (Col. 15, lines 28-47, Shahrestani teaches identifying locations of each individual shrimp within the designated sample space across the time-series. Using these locations, the system processes the intensity and observes how this process changes over time. Temporal behaviors associated with intensity in time can be graphed to provide behavioral data.) each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans (Col. 20, lines 48-50, Shahrestani teaches shrimp are not static objects but dynamic organisms that move in- and out- of frame.), predicting for a future time, a future spatial distribution of crustaceans within the volume (Col. 14, lines 28-47, Shahrestani teaches using mathematical models to forecast an anticipated count of the shrimp in the tank considering both the size of the tank and the spatial processes of the shrimp. The weight distribution of the shrimp may be extrapolated to produce a biomass estimate of the population.) and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution (Col. 21, lines 63-65, Shahrestani teaches the data can be used to provide production data to the farmers regarding feed administration.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi by replacing the fish (in Rishi) with crustaceans, such as shrimp that is taught by Shahrestani, to make the invention that predicts a future spatial distribution of crustaceans and therefore determines a future spatial feed distribution; thus, one of ordinary skilled in the art would be motivated to combine the references since the techniques of Rishi are applicable in other embodiments to other water-based animals, including crustaceans (Rishi, Paragraph [0079]) .
Regarding Claim 2, Rishi in view of Shahrestani teaches the method according to claim 1, wherein the spatial feed insert distribution indicates, for each position out of the one or more positions (Paragraphs [0035], [0037], Rishi teaches instructing placement of a derived amount of feed. Feeding recommendations are tailored and modified to each individual fish cage. Under Broadest Reasonable Interpretation (BRI), the Examiner interprets “one or more” to mean only one position is required to meet the claim limitation (i.e., at least one cage).), an amount of feed that is to be inserted into the volume (Paragraphs [0012], [0084], Rishi teaches providing as close to the precise amount of feed required to encourage optimal growth.).
Regarding Claim 6, Rishi in view of Shahrestani teaches the method according to claim 1, wherein the actual spatial distribution occurs at a first time before the future time (Paragraph [0019], Rishi teaches selecting collected features such as activity features which includes placement of fish within a cage and/or fish density.), the method further comprising: determining a second actual spatial distribution of crustaceans within the volume (Col. 14, lines 17-47, Col. 20, lines 1-8, Fig. 5, Shahrestani teaches collecting data for 5 minutes (i.e., 300 sweeps). Each sweep is a representation of the density and distribution of target objects (shrimp) across 600 seconds. Intensity maps or sonar images as seen in Fig. 5 are produced from the density of target objects in the sample space. Image analysis software can identify locations of each individual shrimp within the designated sample space across the time series. Under BRI, the Examiner interprets the “second actual spatial distribution” to be the second sweep.), the second actual spatial distribution occurring at a second time before the future time, the second time being after the first time (Col. 21, lines 10-18, Shahrestani teaches a time-series of shrimp counts (t1-300) may be used to describe population density as a function of both space/time and modeled.), wherein predicting the future spatial distribution of crustaceans is performed based on the determined actual spatial distribution and based on the determined second actual spatial distribution (Col. 21, lines 29-32 and lines 42-54, Shahrestani teaches with a known weight distribution, the system can estimate population biomass using the corrected Total CountRefined and achieve an improved estimate of population biomass. Calculation of shrimp population density within this region enabled simple extrapolation of total shrimp biomass.).
In regards to Claim 7, Rishi in view of Shahrestani teaches the method according to claim 1, further comprising: determining, for one or more crustaceans in the volume, one or more characteristic crustacean values (Paragraphs [0107], [0079], Rishi teaches determining activity features for the fish. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), each characteristic crustacean value indicating a property of one or more crustacean (Paragraphs [0107], [0079], Rishi teaches activity values such as how close the fish are to the camera, how they are schooling, distance of fish from the surface, speed of fish, density of fish, placement of fish within a cage, and size of fish. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), such as (Paragraphs [0107], [0079], Rishi teaches activity features such as size of fish. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]). Under BRI, the Examiner interprets the claim language of “one or more” characteristic crustacean values to mean only one of the listed types is required to meet the claim limitation (weight or size or health status or moulting status, etc.), health status (Paragraphs [0030], [0079], Rishi teaches health monitoring and detecting health problems. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), (Paragraph [0017], Rishi teaches collecting the past feed conversion ratio.), age of one or more crustaceans (Paragraphs [0019], [0079], Rishi teaches collecting features such as age of fish. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), and based on the determined one or more characteristic crustacean values, determining the spatial feed insert distribution (Paragraphs [0092-93], [0079], Fig. 3, Rishi teaches a decision-making model which provides outputs such as to: derive a feed intensity score, the amount of food required, derive the amount of food required, feed which is input into the cage, as well as from fish genetics such as fish size, biomass, and fish age. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).).
In regards to Claim 8, Rishi in view of Shahrestani teaches the method according to claim 1, wherein determining the one or more activity values may comprise recording a sequence of images (Paragraphs [0082], [0085], [0079], Fig. 2, Rishi teaches various monitoring of the fishes’ conditions is performed via video cameras. Video streams may be obtained and time-based extraction may be implemented to analyze the behavior of the aquatic animals. The techniques are applicable to all water-based animals, including crustaceans.), each image being associated with a respective time (Paragraphs [0011], [0085], Rishi teaches collecting video data. Video streams may be obtained and time-based extraction may be applied.), the sequence of image showing crustaceans moving about to a more or lesser extent (Paragraphs [0021], [0079], Rishi teaches monitoring the activity level over a plurality of individual frames. The techniques are applicable to all water-based animals, including crustaceans.).
In regards to Claim 9, Rishi in view of Shahrestani discloses the method according to claim 1, further comprising performing a machine learning method for predicting (Paragraph [0115], Rishi teaches using any type of machine learning technique to build models for estimation and prediction.), for the future time, the future spatial distribution of crustaceans within the volume (Paragraphs [0017], [0011], [0079], Rishi teaches predicting future fish activity and/or variables. Fish activity may comprise fish density and or distance of fish from sensors, biomass data, etc. Although the embodiment focuses on salmon farming, the techniques are applicable to crustaceans.), the machine learning method comprising: constructing a model based on training data (Paragraph [0030], Rishi teaches constructing a model from a training data set.), the training data associating sets of one or more input parameters relating to a third time (Col. 21, lines 10-18, Col. 20, lines 1-8, Shahrestani teaches a time series of shrimp counts (t1-300) may be used to describe population density as a function of both space/time and modeled. The Examiner interprets “t1-300” implies collecting shrimp counts at t1, t2, t3, t4, and so on. Therefore, the Examiner interprets shrimp counts collected at t3, for example, to be data associated with a third time. Alternatively, the Examiner interprets t3 as the time associated with the third “sweep” out of the 300 sweeps performed.), with respective actual spatial distributions of crustaceans within the volume at a fourth time, (Col. 21, lines 10-18, Col. 20, lines 1-8, Shahrestani teaches using real-world data to adjust distribution parameters. A time series of shrimp counts (t1-300) may be used to describe population density as a function of both space/time and modeled. The Examiner interprets “t1-300” implies collecting shrimp counts at t1, t2, t3, t4, and so on. Therefore, the Examiner interprets shrimp counts collected at t4, for example, to be data associated with a fourth time. Alternatively, the Examiner interprets t4 as the time associated with the fourth “sweep” out of the 300 sweeps performed on the tank.), the fourth time being after the third time (Col. 21, lines 22-32, Col. 14, lines 28-47, Shahrestani teaches collecting a 300-sweep-time-series of shrimp counts. Image analysis software identifies the location of each individual shrimp within the sample space across the time-series. The Examiner interprets that the shrimp counts were obtained over a period of time (“time-series”). In addition, the Examiner interprets that the fourth sweep occurs after the third sweep.), and measuring one or more input parameters relating to a time before the future time (Paragraph [0097], Rishi teaches performing time-series analysis to integrate into feeding recommendation by taking past data into account. The time-series analysis may be pre-processed like any other feature and may be mapped to a probability distribution map.), and using the constructed model for predicting on the basis of the measured one or more input parameters (Paragraphs [0017], [0011], Fig. 3, Rishi teaches predicting future fish activity using a learned decision-making model. The learned decision-making model receives pre-processed sensor data/signals such as image data, video data, fish activity, fish density, etc.), the spatial distribution of crustaceans within the volume at the future time (Paragraphs [0015-17], [0079], Rishi teaches predicting future fish activity using the learned decision-making model. Fish activity may include fish density and/or distance of fish from sensors, etc. The techniques are applicable to all water-based animals, including crustaceans. The Examiner interprets “density” and/or distance from camera/sensors to be spatial distributions since they both describe the arrangements of fish (aquatic animals) in space/volume. Although the embodiment focuses on salmon farming, the techniques are applicable to crustaceans.), wherein the one or more input parameters comprise: one or more determined actual spatial distributions of crustaceans (Paragraphs [0107], [0079], Rishi teaches extracting features from data such as placement of fish within a cage. The techniques may be applicable to all water-based animals, including crustaceans.), and wherein, preferably, the one or more input parameters comprise: and/or one or more activity values (Paragraphs [0011], [0079], Rishi teaches collecting fish activity data. The techniques may be applicable to all water-based animals, including crustaceans. Under BRI, the Examiner interprets “and/or” to mean only one of the trajectories, activity values, or characteristic crustacean values are required to meet the claim limitation.), each activity value being indicative of how active one or more crustaceans are (Paragraphs [0011], [0079], Rishi teaches fish activity data comprises any or a combination of: fish schooling data, surface feeding activity, fish density, fish speed, and/or distance of fish from sensors, etc. The techniques may be applicable to all water-based animals, including crustaceans.), and/or one or more characteristic crustacean values (Paragraphs [0019], [0079], Rishi teaches activity features. The techniques may be applicable to all water-based animals, including crustaceans.), each characteristic crustacean value indicating a property of one or more crustacean, such as weight, size, health status, moulting status, color appearance, starvation level, prior feed activity, age of one or more crustaceans (Paragraphs [0104-107], [0079], Rishi teaches extracting features from data collected such as age of fish and size of fish. The techniques may be applicable to all water-based animals, including crustaceans.).
In regards to Claim 11, Rishi in view of Shahrestani discloses the method according to claim 1, wherein the determined actual spatial distribution of crustaceans and the future spatial distribution of crustaceans each distinguish between a spatial distribution of crustaceans of at least a first type and a second type of crustacean (Col. 14, lines 28-47, Col. 15, lines 20-30, Shahrestani teaches identifying the locations of each shrimp within the designated sample across the time-series. The system parameterizes the intensity and observes how this process changes over time. For example, temporal behaviors associated with intensity in time can be graphed to provide behavioral data. Mathematical models may be used to describe the temporal patterns in the dataset and forecast an anticipated count of shrimp in the tank considering the spatial processes of the shrimp. The Examiner interprets temporal behaviors to be a “type” in type in light of Applicant’s specification which states, “the first type and second type of crustacean may differ with respect to any property, such as size, weight, color, activity value, moulting status, color appearance, starvation level, prior feed activity, age, species, et cetera.”).
In regards to Claim 12, Rishi in view of Shahrestani teaches the method according to claim 1, further comprising causing insertion of feed into the volume in accordance with the spatial feed insert distribution (Paragraphs [0041], [0036], Rishi teaches instructing placement of feed by signaling to a feed distribution apparatus. Signaling directly to a feed distribution apparatus enables feed to be provided automatically where it is required.).
In regards to Claim 13, Rishi teaches a data processing system (Paragraph [0083], Fig. 1, Rishi teaches a computer (106).)
PNG
media_image4.png
548
772
media_image4.png
Greyscale
comprising: an input interface for receiving images from one or more cameras (Paragraphs [0083], [0132], Fig. 1, Fig. 4, Fig. 5, Rishi teaches four display screens (102) which are displaying the fish in each of a number of cages for the human operator to view. In addition, Fig. 4 shows a user interface which may show a view of the cage (402).);
PNG
media_image5.png
523
793
media_image5.png
Greyscale
an output interface for sending control signals to a feeding system (Paragraph [0083], Rishi teaches the computer (106) allows the operator to be able to control aspects of the fish farm such as the pellet feeding machinery, etc.); and a processor (Paragraph [0040], Rishi teaches a processor.) that is configured to perform the method according to claim 1 as follows:
Rishi teaches a computer-implemented method (Abstract, Paragraph [0079], Rishi teaches a computer-implemented method for feeding one or more aquatic animals such as crustaceans.) for determining a spatial feed insert distribution for feeding (Paragraphs [0035], [0079], Rishi teaches deriving an amount of feed, a rate at which feed should be provided, feed conversion rate, and instructing placement of a derived amount of feed. The Examiner interprets determining a spatial feed distribution to include determining an amount of feed to be provided to the cage in light of Applicant’s specification (Page 7, lines 7-10), which states “the spatial feed insert distribution indicates for each position out of the one or more positions, an amount of feed that is to be inserted into the volume…” In addition, the Examiner interprets “in” the cage to be one or more positions in a “volume.”) that are present in a volume at least partially enclosed by one or more barriers for keeping the (Paragraphs [0010], [0079], Rishi teaches the feeding of one or more aquatic animals takes place in a confined place containing water. One or more enclosed spaces may comprise one or more cages and/or one or more aquatic animal farms. The techniques may be applied to all water-based animals, including crustaceans.), the method comprising; determining by a processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras (Paragraphs [0011], [0134], Fig. 5, Rishi teaches capturing image data. Fig. 5 shows a view from six separate image sensors.), an actual spatial distribution of (Paragraphs [0019], [0011], [0079], Rishi teaches determining activity features such as placement of fish within a cage or fish density. The techniques are applicable to all water-based animals, including crustaceans. Under BRI, the Examiner interprets placement of fish in a cage, fish density and/or displayed images (see above) each represent or show the actual spatial distribution of the water-based animals in the cage.) determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras, for one or more (Paragraphs [0047], [0079], Rishi teaches monitoring the activity level over a plurality of image frames. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), each activity value being indicative of how active one or more (Paragraphs [0011], [0079], Rishi teaches fish activity data which comprises fish speed, fish schooling data, reaction of fish towards feed, etc. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), and based on the determined actual spatial distribution (Paragraphs [0019], [0079], Rishi teaches the activity features may include placement of fish within a cage and/or density of fish, and/or distance of fish from surface. The activity features are input into one or more learned decision-making models. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and the determined activity values (Paragraphs [0105], [0107], [0079], Rishi teaches inputting features, including “activity features” into one or more learned decision-making models. Activity features include how close the fish are to the camera, how they are schooling, distance of fish from surface, speed of fish, density of fish, placement of fish within a cage. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), predicting by the processor (Paragraph [0040], Rishi teaches a processor.), for a future time, a future spatial distribution of (Paragraphs [0017], [0011], [0024], [0125], [0079], Rishi teaches predicting future “fish activity” and/or variables. Fish activity may include fish density and/or distance of fish from sensors, biomass data, etc. Under BRI, the Examiner interprets predicting future fish density and/or distance of fish from the sensors to be predicting a future spatial distribution because “fish density” measures the number of fish present in a specific unit of water and describes how the fish are spread out across a geographical area (spatial distribution). Further, distance of fish from sensors describes how the fish are distributed vertically in relation to the sensors. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on the future spatial distribution of (Abstract, Paragraphs [0043-44], [0093-95], Rishi teaches determining, by one or more learned decision-making models using the received pre-processed sensor data, feeding instructions for one or more aquatic animals and outputting the feeding instruction from the one or more learned decision-making models. The output may comprise an optimized level of feed to provide to one or more aquatic animals within a confined space containing water.) the spatial feed distribution indicating one or more positions at a boundary of the volume and/or within the volume from which feed is to be inserted in the volume by a feed system (Paragraphs [0037], [0123], Rishi teaches instructing placement of the derived amount of feed directly to a control feed apparatus and/or other automatic controls around the one or more cages and/or the one or more fish farms. The output of the one or more learned functions causes the feeding equipment to place feed in the respective cages. Under BRI, the Examiner interprets “in the respective cages” to be “one or more positions” within the volume. In addition, the Examiner interprets “and/or” to only one of either one or more positions at a boundary of the volume or within the volume is required to meet the claim limitation.).
Rishi does not explicitly disclose determining a spatial feed insert distribution for feeding crustaceans that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume, an actual spatial distribution of crustaceans within the volume, for one or more crustaceans in the volume, one or more activity values each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans, predicting for a future time, a future spatial distribution of crustaceans within the volume and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution.
Shahrestani is in the same field of art of providing information about the status and composition of aquaculture farming tanks or ponds. Further, Shanrestani teaches determining a spatial feed insert distribution for feeding crustaceans (Col. 5, lines 40-42, Shahrestani teaches using the aquaculture data to generate shrimp feed administration data.) that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume (Col. 9, lines 21-37, Fig. 7, Shahrestani teaches aquaculture farming data includes shrimp behavior data uploaded from a single pond, an entire farm or ponds, or an entire region of farms of ponds.), an actual spatial distribution of crustaceans within the volume (Col. 14, lines 17-27, Fig. 5b, Shahrestani teaches performing “sweeps” on the entire tank (360) with a range of 5 m. Each sweep is a representation of the density and distribution of target objects (shrimp) across 600 seconds. Shrimp information observed within a 3D space (water-column) are compressed into a 2D (top-down) intensity map.), for one or more crustaceans in the volume, one or more activity values (Col. 15, lines 28-47, Shahrestani teaches identifying locations of each individual shrimp within the designated sample space across the time-series. Using these locations, the system processes the intensity and observes how this process changes over time. Temporal behaviors associated with intensity in time can be graphed to provide behavioral data.) each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans (Col. 20, lines 48-50, Shahrestani teaches shrimp are not static objects but dynamic organisms that move in- and out- of frame.), predicting for a future time, a future spatial distribution of crustaceans within the volume (Col. 14, lines 28-47, Shahrestani teaches using mathematical models to forecast an anticipated count of the shrimp in the tank considering both the size of the tank and the spatial processes of the shrimp. The weight distribution of the shrimp may be extrapolated to produce a biomass estimate of the population.) and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution (Col. 21, lines 63-65, Shahrestani teaches the data can be used to provide production data to the farmers regarding feed administration.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi by replacing the fish (in Rishi) with crustaceans, such as shrimp that is taught by Shahrestani, to make the invention that predicts a future spatial distribution of crustaceans and therefore determines a future spatial feed distribution; thus, one of ordinary skilled in the art would be motivated to combine the references since the techniques of Rishi are applicable in other embodiments to other water-based animals, including crustaceans (Rishi, Paragraph [0079]).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
In regards to Claim 14, Rishi teaches a system for feeding crustaceans (Paragraphs [0041], [0036], [0079], Rishi teaches a system operable to instruct placement of feed by signaling to a feed distribution apparatus. Signaling directly to a feed distribution apparatus can provide a level of automation to the farm, wherein feed can be provided automatically where it is required.) that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume (Paragraphs [0010], [0079], Rishi teaches the feeding of one or more aquatic animals takes place in a confined place containing water. One or more enclosed spaces may comprise one or more cages and/or one or more aquatic animal farms. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), the system comprising: a feed system for inserting feed into said volume from one or more positions at a boundary of the volume and/or within the volume (Paragraphs [0036], [0093], Rishi teaches a feed distribution apparatus, wherein feed can be provided automatically where it is required. The feed is inserted into the cage. Under BRI, the Examiner interprets “and/or” to mean only one of either one or more positions “at a boundary” or “within” the volume is required to meet the claim limitation.), and the data processing system according to claim 13 as follows:
Rishi teaches a data processing system (Paragraph [0083], Fig. 1, Rishi teaches a computer (106).) comprising: an input interface for receiving images from one or more cameras (Paragraphs [0083], [0132], Fig. 1, Fig. 4, Fig. 5, Rishi teaches four display screens (102) which are displaying the fish in each of a number of cages for the human operator to view. In addition, Fig. 4 shows a user interface which may show a view of the cage (402).); an output interface for sending control signals to a feeding system (Paragraph [0083], Rishi teaches the computer (106) allows the operator to be able to control aspects of the fish farm such as the pellet feeding machinery, etc.); and a processor (Paragraph [0040], Rishi teaches a processor.) that is configured to perform the method according to claim 1 as follows: Rishi teaches a computer-implemented method (Abstract, Paragraph [0079], Rishi teaches a computer-implemented method for feeding one or more aquatic animals such as crustaceans.) for determining a spatial feed insert distribution for feeding (Paragraphs [0035], [0079], Rishi teaches deriving an amount of feed, a rate at which feed should be provided, feed conversion rate, and instructing placement of a derived amount of feed. The Examiner interprets determining a spatial feed distribution to include determining an amount of feed to be provided to the cage in light of Applicant’s specification (Page 7, lines 7-10), which states “the spatial feed insert distribution indicates for each position out of the one or more positions, an amount of feed that is to be inserted into the volume…” In addition, the Examiner interprets “in” the cage to be one or more positions in a “volume.”) that are present in a volume at least partially enclosed by one or more barriers for keeping the (Paragraphs [0010], [0079], Rishi teaches the feeding of one or more aquatic animals takes place in a confined place containing water. One or more enclosed spaces may comprise one or more cages and/or one or more aquatic animal farms. The techniques may be applied to all water-based animals, including crustaceans.), the method comprising; determining by a processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras (Paragraphs [0011], [0134], Fig. 5, Rishi teaches capturing image data. Fig. 5 shows a view from six separate image sensors.), an actual spatial distribution of (Paragraphs [0019], [0011], [0079], Rishi teaches determining activity features such as placement of fish within a cage or fish density. The techniques are applicable to all water-based animals, including crustaceans. Under BRI, the Examiner interprets placement of fish in a cage, fish density and/or displayed images (see above) each represent or show the actual spatial distribution of the water-based animals in the cage.) determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras, for one or more (Paragraphs [0047], [0079], Rishi teaches monitoring the activity level over a plurality of image frames. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), each activity value being indicative of how active one or more (Paragraphs [0011], [0079], Rishi teaches fish activity data which comprises fish speed, fish schooling data, reaction of fish towards feed, etc. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), and based on the determined actual spatial distribution (Paragraphs [0019], [0079], Rishi teaches the activity features may include placement of fish within a cage and/or density of fish, and/or distance of fish from surface. The activity features are input into one or more learned decision-making models. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and the determined activity values (Paragraphs [0105], [0107], [0079], Rishi teaches inputting features, including “activity features” into one or more learned decision-making models. Activity features include how close the fish are to the camera, how they are schooling, distance of fish from surface, speed of fish, density of fish, placement of fish within a cage. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), predicting by the processor (Paragraph [0040], Rishi teaches a processor.), for a future time, a future spatial distribution of (Paragraphs [0017], [0011], [0024], [0125], [0079], Rishi teaches predicting future “fish activity” and/or variables. Fish activity may include fish density and/or distance of fish from sensors, biomass data, etc. Under BRI, the Examiner interprets predicting future fish density and/or distance of fish from the sensors to be predicting a future spatial distribution because “fish density” measures the number of fish present in a specific unit of water and describes how the fish are spread out across a geographical area (spatial distribution). Further, distance of fish from sensors describes how the fish are distributed vertically in relation to the sensors. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on the future spatial distribution of (Abstract, Paragraphs [0043-44], [0093-95], Rishi teaches determining, by one or more learned decision-making models using the received pre-processed sensor data, feeding instructions for one or more aquatic animals and outputting the feeding instruction from the one or more learned decision-making models. The output may comprise an optimized level of feed to provide to one or more aquatic animals within a confined space containing water.) the spatial feed distribution indicating one or more positions at a boundary of the volume and/or within the volume from which feed is to be inserted in the volume by a feed system (Paragraphs [0037], [0123], Rishi teaches instructing placement of the derived amount of feed directly to a control feed apparatus and/or other automatic controls around the one or more cages and/or the one or more fish farms. The output of the one or more learned functions causes the feeding equipment to place feed in the respective cages. Under BRI, the Examiner interprets “in the respective cages” to be “one or more positions” within the volume. In addition, the Examiner interprets “and/or” to only one of either one or more positions at a boundary of the volume or within the volume is required to meet the claim limitation.).
Rishi does not explicitly disclose determining a spatial feed insert distribution for feeding crustaceans that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume, an actual spatial distribution of crustaceans within the volume, for one or more crustaceans in the volume, one or more activity values each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans, predicting for a future time, a future spatial distribution of crustaceans within the volume and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution.
Shahrestani is in the same field of art of providing information about the status and composition of aquaculture farming tanks or ponds. Further, Shanrestani teaches determining a spatial feed insert distribution for feeding crustaceans (Col. 5, lines 40-42, Shahrestani teaches using the aquaculture data to generate shrimp feed administration data.) that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume (Col. 9, lines 21-37, Fig. 7, Shahrestani teaches aquaculture farming data includes shrimp behavior data uploaded from a single pond, an entire farm or ponds, or an entire region of farms of ponds.), an actual spatial distribution of crustaceans within the volume (Col. 14, lines 17-27, Fig. 5b, Shahrestani teaches performing “sweeps” on the entire tank (360) with a range of 5 m. Each sweep is a representation of the density and distribution of target objects (shrimp) across 600 seconds. Shrimp information observed within a 3D space (water-column) are compressed into a 2D (top-down) intensity map.), for one or more crustaceans in the volume, one or more activity values (Col. 15, lines 28-47, Shahrestani teaches identifying locations of each individual shrimp within the designated sample space across the time-series. Using these locations, the system processes the intensity and observes how this process changes over time. Temporal behaviors associated with intensity in time can be graphed to provide behavioral data.) each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans (Col. 20, lines 48-50, Shahrestani teaches shrimp are not static objects but dynamic organisms that move in- and out- of frame.), predicting for a future time, a future spatial distribution of crustaceans within the volume (Col. 14, lines 28-47, Shahrestani teaches using mathematical models to forecast an anticipated count of the shrimp in the tank considering both the size of the tank and the spatial processes of the shrimp. The weight distribution of the shrimp may be extrapolated to produce a biomass estimate of the population.) and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution (Col. 21, lines 63-65, Shahrestani teaches the data can be used to provide production data to the farmers regarding feed administration.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi by replacing the fish (in Rishi) with crustaceans, such as shrimp that is taught by Shahrestani, to make the invention that predicts a future spatial distribution of crustaceans and therefore determines a future spatial feed distribution; thus, one of ordinary skilled in the art would be motivated to combine the references since the techniques of Rishi are applicable in other embodiments to other water-based animals, including crustaceans (Rishi, Paragraph [0079]).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claims 3 and 4 are rejected under 35 U.S.C. 103(a) as being unpatentable over Rishi et al. (U.S. Patent Pub. No. 2020/0170227, hereafter referred to as Rishi) in view of Shahrestani (U.S. Patent No. 11,493,629, hereafter referred to as Shahrestani) in further view of Minami (U.S. Patent Pub No. 2019/0216059, hereafter referred to as Minami).
Regarding Claim 3, Rishi in view of Shahrestani teaches the method according to claim 1, wherein the spatial feed insert distribution indicates, for each position out of the one or more positions, (Paragraph [0035], Rishi teaches deriving an amount of feed, a rate at which feed should be provided, feed conversion rate, instructing placement of a derived amount of feed. The Examiner interprets determining a spatial feed distribution to include determining an amount of feed to be provided to the cage in light of Applicant’s specification (Page 7, lines 7-10), which states “the spatial feed insert distribution indicates for each position out of the one or more positions, an amount of feed that is to be inserted into the volume…” In addition, the Examiner interprets in a cage to be one or more positions in a “volume.”), one or more properties of the feed that is to be inserted into the volume (Paragraphs [0035], [0037], Rishi teaches instructing placement of a derived amount of feed, a rate at which feed should be provided, feed conversion rate. The Examiner interprets feed conversion rate to be “one or more” properties of the feed.).
Rishi in view of Shahrestani does not explicitly disclose a size of the feed pellets and/or such as a disintegration rate of the feed pellets and/or such as a disintegration time of the feed pellet.
Minami is in the same field of art of aquaculture of shrimps (crustaceans) in an aquaculture system. Further, Minami teaches a size of the feed pellets and/or such as a disintegration rate of the feed pellets and/or such as a disintegration time of the feed pellet (Paragraph [0049], Minami teaches the feed pellet size is 2.4 mm. Under BRI, the Examiner interprets “and/or” to mean only one of the size, disintegration rate, or disintegration time are required to meet the limitation.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi in view of Shahrestani by specifying the size of the feed pellet to be provided in the cages that is taught by Minami, to make the invention that provides an exact estimate of the quantity of food to be provided into the enclosure to feed the crustaceans; thus, one of ordinary skilled in the art would be motivated to combine the references since providing as close to the optimal amounts of food each time over the duration of each feed is ideal and helps minimize food waste and encourage optimal growth (Rishi, Paragraphs [0003], [0012]).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
In regards to Claim 4, Rishi in view of Shahrestani discloses the method according to claim 1.
Rishi in view of Shahrestani does not explicitly disclose wherein the crustaceans belong to the superfamily Penaeoidea, preferably from the families Aristeidae or Penaeidae, such as such as gamba shrimps and/or tiger prawns and/or whiteleg shrimps and/or Atlantic white shrimps and/or Indian prawns.
Minami is in the same field of art of aquaculture of shrimps in an aquaculture system. Further, Minami discloses wherein the crustaceans belong to the superfamily Penaeoidea, preferably from the families Aristeidae or Penaeidae, such as such as gamba shrimps and/or tiger prawns and/or whiteleg shrimps and/or Atlantic white shrimps and/or Indian prawns (Paragraph [0023], Minami teaches the whiteleg shrimp that belongs to the genus Litopenaeus in the family Penaeidae is one of the subjects.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi in view of Shahrestani by replacing the aquatic animals (crustaceans) with whiteleg shrimp that is taught by Minami, to make the invention that aquacultures whiteleg shrimp; thus, one of ordinary skilled in the art would be motivated to combine the references since nektonic species, such as whiteleg shrimp are suitable for production in an overcrowded state, and the culturing of shrimps is generally carried out in an overcrowded state (Minami, Paragraphs [0024], [0063]). Therefore, the growing and harvesting of this group of crustaceans (shrimp) allows them to be provided for use, processing, and/or sale (Minami, Paragraph [0025]).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claim 5 is rejected under 35 U.S.C. 103(a) as being unpatentable over Rishi et al. (U.S. Patent Pub. No. 2020/0170227, hereafter referred to as Rishi) in view of Shahrestani (U.S. Patent No. 11,493,629, hereafter referred to as Shahrestani) in further view of Kozachenok et al. (U.S. Patent Pub No. US 2021/0329892 A1, hereafter referred to as Kozachenok (892)).
In regards to Claim 5, Rishi in view of Shahrestani teaches the method according to claim 1, further comprising: obtaining a sequence of images of the volume (Paragraph [0085], Rishi teaches obtaining video streams for analyzing the behavior of the aquatic animals.), wherein each image out of the sequence of images is associated with a different time (Paragraph [0085], Rishi teaches performing time-based extraction from the video streams.).
Rishi in view of Shahrestani does not explicitly disclose determining, based on the sequence of images, a plurality of trajectories through the volume of a plurality of respective crustaceans, this step comprising, for each of the plurality of crustaceans, detecting an image object in an image out of the sequence of images, the object representing the crustacean in question, and tracking the object across several images out of the sequence of images in order to determine a trajectory of the crustacean in question through the volume, wherein the method further comprises based on the determined plurality of trajectories, determining the actual spatial distribution of crustaceans and/or predicting the future spatial distribution of crustaceans.
Kozachenok (892) is in the same field of art of collecting data indicative of underwater object parameters corresponding to underwater objects, such as crustaceans within a marine enclosure. Further Kozachenok (892) teaches determining, based on the sequence of images, a plurality of trajectories through the volume of a plurality of respective crustaceans (Paragraphs [0057-59], [0047], [0096], Kozachenok (892) teaches determining class labels for underwater objects in image data, such as the location. Underwater objects may be identified in various images over time. Image data may include a plurality of image frames. An object may include one or more crustaceans (see Paragraph [0096]).), this step comprising, for each of the plurality of crustaceans (Paragraphs [0057], [0096], Kozachenok (892) teaches determining a location of each fish. Instead, the object may include one or more crustaceans (see Paragraph [0096]).), detecting an image object in an image out of the sequence of images (Paragraphs [0058], [0096], Kozachenok (892) teaches a R-CNN to generate a class label and output bounding box coordinates for each underwater object in an image. An object may include one or more crustaceans (see Paragraph [0096]).), the object representing the crustacean in question (Paragraphs [0058-59], [0184], Kozachenok (892) teaches generating bounding box coordinates for each detected underwater object. Additionally, identification of individual fish may be used to identify the fish in various images overtime. Although primarily discussed in the context of fish, the techniques may be applied to any aquatic, aquaculture species such as crustaceans (see Paragraph [0184]).), and tracking the object across several images out of the sequence of images in order to determine a trajectory of the crustacean in question through the volume (Paragraphs [0085], [0059], [0184], [0096], Kozachenok (892) teaches receiving image data for identification and tracking of individual fish. Image analysis may be performed on captured image data to identify unique freckle ID of a fish. This freckle ID may correspond to a unique signature of the fish and may be used to identify the fish in various images over time. Although primarily discussed in the context of fish, the techniques may be applied to any aquatic, aquaculture species such as crustaceans (see Paragraphs [0096] and [0184]).), wherein the method further comprises based on the determined plurality of trajectories, determining the actual spatial distribution of crustaceans and/or predicting the future spatial distribution of crustaceans (Paragraphs [0038], [0018], Kozachenok (892) teaches monitoring multiple fish or an entire population of fish within the marine enclosure. Image data measurements may be used to identify fish positions in the water and determine the distribution of underwater objects. Underwater objects may include one or more crustaceans. Under BRI, the Examiner interprets “and/or” to mean only one of either the actual spatial distribution or the future spatial distribution is required to meet the claim limitation.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi in view of Shahrestani by tracking various underwater objects such as crustaceans across multiple image frames that is taught by Kozachenok (892), to make the invention that improves both productivity and efficiency of farming operations by enabling farmers to better respond to spatial and temporal variabilities in farming (aquaculture) conditions; thus, one of ordinary skilled in the art would be motivated to combine the references since monitoring the trajectories of the crustaceans provides an efficient manner for automated and dynamic monitoring of fish (crustaceans) to improve the results of aquaculture operations, including feeding observations and health monitoring (Kozachenok (892), Paragraph [0034]) .
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Claims 10 and 15 are rejected under 35 U.S.C. 103(a) as being unpatentable over Rishi et al. (U.S. Patent Pub. No. 2020/0170227, hereafter referred to as Rishi) in view of Shahrestani (U.S. Patent No. 11,493,629, hereafter referred to as Shahrestani) in further view of Kozachenok et al. (U.S. Patent Pub No. US 2021/0212284 A1, hereafter referred to as Kozachenok (284)).
Regarding Claim 10, Rishi in view of Shahrestani teaches the method according to claim 1, further comprising performing a machine learning method for determining the spatial feed insert distribution (Abstract, Rishi teaches one or more learned decision-making models trained to substantially optimize the rate and amount of food provided to the aquatic animals.).
Rishi in view of Shahrestani does not explicitly disclose the machine learning method comprising: constructing a second model based on second training data, the second training data associating sets of one or more second input parameters with respective spatial feed insert distributions and preferably also with a feed assessment value indicating how well and/or how efficient crustaceans were fed using the spatial feed insert distribution in question, and measuring one or more second input parameters, and using the constructed second model for predicting, based on the measured one or more second input parameters, the spatial feed insert distribution, wherein the one or more second input parameters comprise: one or more actual spatial distributions of crustaceans and/or the predicted spatial distribution of crustaceans, wherein preferably, the one or more second input parameters comprise a plurality of trajectories of respective crustaceans through the volume and/or one or more properties of the feed pellets and/or one or more activity values, each activity value being indicative of how active one or more crustaceans are, and/or one or more characteristic crustacean values, each characteristic crustacean value indicating a property of one or more crustacean, such as weight, size, health status, moulting status, color appearance, starvation level, prior feed activity, age of one or more crustaceans.
Kozachenok (284) is in the same field of art of increasing feeding management efficiency. Further, Kozachenok (284) teaches the machine learning method comprising: constructing a second model based on second training data (Abstract, Paragraphs [0086-87], Fig. 5, Kozachenok (284) teaches a second feeding appetite forecast model (522b). The learned model is trained based on input or experience during the training process.),
PNG
media_image6.png
736
539
media_image6.png
Greyscale
the second training data associating sets of one or more second input parameters with respective spatial feed insert distributions (Paragraph [0087], Kozachenok (284) teaches the learned model may be initialized through a supervised learning process to obtain a baseline set of knowledge regarding the operational environment and the performance of certain feeding appetite forecasts. The learned model may be populated as additional sensor systems and/or parameter data sets are integrated.) and preferably also with a feed assessment value indicating how well and/or how efficient crustaceans were fed using the spatial feed insert distribution in question (Paragraph [0139], Kozachenok (284) teaches additional inputs such as the results of feeding according to the forecasted appetite may be incorporated into the learned model so that the learned model evolves to facilitate the subsequent performance of similar feeding appetite forecasting. Under BRI, the Examiner interprets the word “preferably” to mean the feed assessment value is not required to meet the claim limitation, however it is included for completeness. In addition, the Examiner interprets “and/or” to mean either “how well” or “how efficient” meet the claim limitation.), and measuring one or more second input parameters (Paragraph [0042], Fig. 5, Kozachenok (284) teaches a second sensor system which generates a second feeding parameter data set (508b).), and using the constructed second model for predicting, based on the measured one or more second input parameters, the spatial feed insert distribution (Paragraphs [0050], [0064], Fig. 5, Kozachenok (284) teaches a second feeding appetite forecast model (522b) which receives the image data of the second feeding parameter set (508b) as input and generates a second feeding appetite forecast (524b). For example, the second feeding appetite forecast model (522b) uses image data related to fish position within the water below the water surface as an appetite proxy for generating the second appetite forecast (524b). The second feeding appetite forecast (524b) is a description of possible hunger level to be exhibited by the population of fish within the water for a future time period. The models may generate a feeding instruction signal based at least in part on the aggregated appetite score that instructs an automated feeding system regarding actions to be taken such as indicating a total feed volume.), wherein the one or more second input parameters comprise (Paragraph [0109], Kozachenok (284) teaches a second parameter data set (508b).): one or more actual spatial distributions of crustaceans and/or the predicted spatial distribution of crustaceans (Paragraphs [0070], [0029], Kozachenok (284) teaches the second parameter data set includes data corresponding to measurements for at least a second feeding parameter related to feeding appetite forecasting. For example, the second feeding parameter includes image data corresponding to the presence or absence, abundance, distribution, of underwater objects. An underwater object may include one or more crustaceans. The Examiner interprets “and/or” to mean only one of either the actual spatial distribution or the predicted spatial distribution is required to meet the claim limitation.), wherein preferably, and/or one or more properties of the feed pellets (Paragraphs [0070-71], Kozachenok (284) teaches the second parameter data set may monitor the falling paths of feed pellets. Under BRI, the Examiner interprets “and/or” to mean only one is required to meet the claim limitation.) and/or one or more activity values (Paragraphs [0070-71], Kozachenok (284) teaches the second parameter data set may identify swimming behavior.), each activity value being indicative of how active one or more crustaceans are (Paragraph [0071], Kozachenok (284) teaches identifying swimming behavior.), and/or one or more characteristic crustacean values, each characteristic crustacean value indicating a property of one or more crustacean, such as weight, size, health status, moulting status, color appearance, starvation level, prior feed activity, age of one or more crustaceans (Paragraphs [0028-29], [0015], Kozacheok (284) teaches capturing data corresponding to the size of underwater objects. An object may include one or more crustaceans. In addition, sensor systems may be used to identify hunger levels. Under BRI, the Examiner interprets “one or more” characteristic crustacean values to mean only one of the properties are required (i.e., one of: weight, size, health status, etc.).).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi in view of Shahrestani by predicting the spatial feed distribution to be inserted into the volume using a second learning model that is taught by Kozachenok (284), to make the invention that generates a feeding appetite forecast by the model; thus, one of ordinary skilled in the art would be motivated to combine the references to improve the precision and accuracy of feeding appetite forecasting and decreasing the uncertainties associated with conventional appetite prediction systems (Kozachenok (284), Paragraph [0017]).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
In regards to Claim 15, Rishi teaches
Rishi teaches a computer-implemented method (Abstract, Paragraph [0079], Rishi teaches a computer-implemented method for feeding one or more aquatic animals such as crustaceans.) for determining a spatial feed insert distribution for feeding (Paragraphs [0035], [0079], Rishi teaches deriving an amount of feed, a rate at which feed should be provided, feed conversion rate, and instructing placement of a derived amount of feed. The Examiner interprets determining a spatial feed distribution to include determining an amount of feed to be provided to the cage in light of Applicant’s specification (Page 7, lines 7-10), which states “the spatial feed insert distribution indicates for each position out of the one or more positions, an amount of feed that is to be inserted into the volume…” In addition, the Examiner interprets “in” the cage to be one or more positions in a “volume.”) that are present in a volume at least partially enclosed by one or more barriers for keeping the (Paragraphs [0010], [0079], Rishi teaches the feeding of one or more aquatic animals takes place in a confined place containing water. One or more enclosed spaces may comprise one or more cages and/or one or more aquatic animal farms. The techniques may be applied to all water-based animals, including crustaceans.), the method comprising; determining by a processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras (Paragraphs [0011], [0134], Fig. 5, Rishi teaches capturing image data. Fig. 5 shows a view from six separate image sensors.), an actual spatial distribution of (Paragraphs [0019], [0011], [0079], Rishi teaches determining activity features such as placement of fish within a cage or fish density. The techniques are applicable to all water-based animals, including crustaceans. Under BRI, the Examiner interprets placement of fish in a cage, fish density and/or displayed images (see above) each represent or show the actual spatial distribution of the water-based animals in the cage.) determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on images from one or more cameras, for one or more (Paragraphs [0047], [0079], Rishi teaches monitoring the activity level over a plurality of image frames. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), each activity value being indicative of how active one or more (Paragraphs [0011], [0079], Rishi teaches fish activity data which comprises fish speed, fish schooling data, reaction of fish towards feed, etc. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), and based on the determined actual spatial distribution (Paragraphs [0019], [0079], Rishi teaches the activity features may include placement of fish within a cage and/or density of fish, and/or distance of fish from surface. The activity features are input into one or more learned decision-making models. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and the determined activity values (Paragraphs [0105], [0107], [0079], Rishi teaches inputting features, including “activity features” into one or more learned decision-making models. Activity features include how close the fish are to the camera, how they are schooling, distance of fish from surface, speed of fish, density of fish, placement of fish within a cage. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).), predicting by the processor (Paragraph [0040], Rishi teaches a processor.), for a future time, a future spatial distribution of (Paragraphs [0017], [0011], [0024], [0125], [0079], Rishi teaches predicting future “fish activity” and/or variables. Fish activity may include fish density and/or distance of fish from sensors, biomass data, etc. Under BRI, the Examiner interprets predicting future fish density and/or distance of fish from the sensors to be predicting a future spatial distribution because “fish density” measures the number of fish present in a specific unit of water and describes how the fish are spread out across a geographical area (spatial distribution). Further, distance of fish from sensors describes how the fish are distributed vertically in relation to the sensors. The techniques are applicable to all water-based animals, including crustaceans (see Paragraph [0079]).) and determining by the processor (Paragraph [0040], Rishi teaches a processor.), based on the future spatial distribution of (Abstract, Paragraphs [0043-44], [0093-95], Rishi teaches determining, by one or more learned decision-making models using the received pre-processed sensor data, feeding instructions for one or more aquatic animals and outputting the feeding instruction from the one or more learned decision-making models. The output may comprise an optimized level of feed to provide to one or more aquatic animals within a confined space containing water.) the spatial feed distribution indicating one or more positions at a boundary of the volume and/or within the volume from which feed is to be inserted in the volume by a feed system (Paragraphs [0037], [0123], Rishi teaches instructing placement of the derived amount of feed directly to a control feed apparatus and/or other automatic controls around the one or more cages and/or the one or more fish farms. The output of the one or more learned functions causes the feeding equipment to place feed in the respective cages. Under BRI, the Examiner interprets “in the respective cages” to be “one or more positions” within the volume. In addition, the Examiner interprets “and/or” to only one of either one or more positions at a boundary of the volume or within the volume is required to meet the claim limitation.).
Rishi does not explicitly disclose a non-transitory computer readable medium comprising instructions which, when the instructions are executed by a processor of the data processing system, cause the data processing system to perform the method of claim 1 as follows: determining a spatial feed insert distribution for feeding crustaceans that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume, an actual spatial distribution of crustaceans within the volume, for one or more crustaceans in the volume, one or more activity values each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans, predicting for a future time, a future spatial distribution of crustaceans within the volume and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution.
Shahrestani is in the same field of art of providing information about the status and composition of aquaculture farming tanks or ponds. Further, Shanrestani teaches determining a spatial feed insert distribution for feeding crustaceans (Col. 5, lines 40-42, Shahrestani teaches using the aquaculture data to generate shrimp feed administration data.) that are present in a volume at least partially enclosed by one or more barriers for keeping the crustaceans in the volume (Col. 9, lines 21-37, Fig. 7, Shahrestani teaches aquaculture farming data includes shrimp behavior data uploaded from a single pond, an entire farm or ponds, or an entire region of farms of ponds.), an actual spatial distribution of crustaceans within the volume (Col. 14, lines 17-27, Fig. 5b, Shahrestani teaches performing “sweeps” on the entire tank (360) with a range of 5 m. Each sweep is a representation of the density and distribution of target objects (shrimp) across 600 seconds. Shrimp information observed within a 3D space (water-column) are compressed into a 2D (top-down) intensity map.), for one or more crustaceans in the volume, one or more activity values (Col. 15, lines 28-47, Shahrestani teaches identifying locations of each individual shrimp within the designated sample space across the time-series. Using these locations, the system processes the intensity and observes how this process changes over time. Temporal behaviors associated with intensity in time can be graphed to provide behavioral data.) each activity value being indicative of how active one or more crustaceans are in terms of movement of the one or more crustaceans (Col. 20, lines 48-50, Shahrestani teaches shrimp are not static objects but dynamic organisms that move in- and out- of frame.), predicting for a future time, a future spatial distribution of crustaceans within the volume (Col. 14, lines 28-47, Shahrestani teaches using mathematical models to forecast an anticipated count of the shrimp in the tank considering both the size of the tank and the spatial processes of the shrimp. The weight distribution of the shrimp may be extrapolated to produce a biomass estimate of the population.) and determining based on the future spatial distribution of crustaceans, a spatial feed insert distribution (Col. 21, lines 63-65, Shahrestani teaches the data can be used to provide production data to the farmers regarding feed administration.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi by replacing the fish (in Rishi) with crustaceans, such as shrimp that is taught by Shahrestani, to make the invention that predicts a future spatial distribution of crustaceans and therefore determines a future spatial feed distribution; thus, one of ordinary skilled in the art would be motivated to combine the references since the techniques of Rishi are applicable in other embodiments to other water-based animals, including crustaceans (Rishi, Paragraph [0079]).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Rishi in view of Shahrestani does not explicitly disclose a non-transitory computer readable medium comprising instructions which, when the instructions are executed by a processor of the data processing system, cause the data processing system to
Kozachenok (284) is in the same field of art of increasing feeding management efficiency. Further, Kozachenok (284) teaches a non-transitory computer readable medium comprising instructions (Paragraph [0161], Kozachenok (284) teaches software which includes one or more sets of executable instructions stored on or otherwise tangibly embodied on a non-transitory computer readable storage medium.) which, when the instructions are executed by a processor of the data processing system cause the data processing system to perform the method (of claim 1) (Paragraph [0162], Kozachenok (284) teaches the software can include the instructions that, when executed by the one or more processors, manipulate the one or more processors to perform one or more aspects of the techniques.).
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Rishi in view of Shahrestani by storing the method on a non-transitory computer-readable medium that is taught by Kozachenok (284), to make the invention that automates the feed distribution systems using stored instructions on a computer system to control and monitor feed for individuals or groups of animals; thus, one of ordinary skilled in the art would be motivated to combine the references since automating the feeding process reduces or eliminates the need for extra labor and feeding costs traditionally associated with human performance of feeding tasks (Kozachenok (284), Paragraph [0015]).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Pertinent Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Chen et al. (U.S. Patent Pub. No. 2022/0000079 A1) teaches a method of monocular depth estimation corresponding to images of fish within a marine enclosure and receiving acoustic data. The images and acoustic data are provided to a CNN for training a monocular depth model. The monocular depth model generates a distance from feeder estimate of a vertical biomass center of fish within the marine enclosure. Alternatively, the object may include one or more crustaceans.
Brenner (U.S. Patent Pub. No. 2022/0335721 A1) teaches methods and systems for improvements in aquaculture that allow for increasing the number and harvesting efficiency of crustaceans in an aquaculture setting by identifying and predicting internal conditions and/or physiological conditions of crustaceans based on external characteristics.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SYDNEY L BLACKSTEN whose telephone number is (571)272-7120. The examiner can normally be reached 8:30am-4:30pm.
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, Oneal Mistry can be reached at 313-446-4912. 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.
/SYDNEY L BLACKSTEN/Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674
Prosecution Insights