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
Claims 1 and 22 – 40 are pending in the application.
Claims 1, 28, and 35 are independent.
Claims 2 – 21 are cancelled.
This action is a non-final Action based on a RCE application filed on 11/03/2025.
Claim Objections
Claim 1 is objected to because of the following informalities: Claim 1 contains the element of “…and when, during the particular feeding session, the particular sensor data satisfies one or more of the threshold values that are included in the meal configuration data, adjusting, by the control unit, the execution of the meal plan based on the one or more adjustment parameters that are included in the meal configuration data.” However, if the sensor data is within a threshold value, the control unit probably should not adjust the execution of the meal plan as taught in the element above. The meaning of “satisfies” or “satisfied” as stated in the specification has a dual meaning which makes the claim ambiguous. For example, specification paragraph 0012 teaches adjustment of a meal plan based on a condition being satisfied. However, paragraph 0027 and 0044 and other paragraphs suggest that when configuration data metric/threshold is satisfied to stop feeding rather than an adjustment of an execution. Appropriate correction is possibly required.
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, 22 - 25, 27 - 32, and 34 – 39 are rejected under 35 U.S.C. 103 as being unpatentable over Rishi et al. (US PG Pub. No. 20200113158), herein “Rishi,” in view of Blyth et al. (US Patent No. 6,443,098), herein “Blyth.”
Regarding claim 1,
Rishi teaches a computer-implemented method comprising: (Par. 0039: “According to a second aspect, there is provided a computer-implemented method for feeding animals in an enclosed space containing water…” Par. 0023: “To help ensure the profitability of raising animals for a farmer, particularly in relation to farmed fish, it can be important to minimise feed wastage. Wasted feed does not contribute to the growth of the fish, which detriments one of the ultimate goals of farming fish.”)
obtaining, by a control unit, (preprocessing modules 304, figure 3) meal configuration data including multiple parameters of a meal plan for feeding farmed fish, the multiple parameters included in the meal configuration data comprising: (item 302, figure 3 shows activity, pellets, environment, sensor data, auxiliary data that inputs to the preprocessing module(s) 304. Par. 0194: “FIG. 3 shows a more detailed view of the performance of the one or more learned functions. A number of inputs 302 are provided into the pre-processing module 304 including any or all of Activity, Pellets, Environment, Sensor and Auxiliary Data. These inputs 302 are inputted to one or more pre-processing modules 304 which may include Growth models, Biological models and Time Series Analysis.” See also Blyth cited below that teaches multiple parameters.)
Rishi also teaches the element of: after obtaining the meal configuration data, executing, by the control unit and using the meal configuration data, the meal plan during a feeding session; (Par. 0107: “I) BEFORE. The "before" activity may comprise data relating to activity of fish during their anticipation of feed, before the feed has actually been provided.” See also Par. 0039 – 0042 (Before, during and after feeding the processing of input data to create a plan). Par. 0194: “FIG. 3 shows a more detailed view of the performance of the one or more learned functions. A number of inputs 302 are provided into the pre-processing module 304 including any or all of Activity, Pellets, Environment, Sensor and Auxiliary Data. These inputs 302 are inputted to one or more pre-processing modules 304 which may include Growth models, Biological models and Time Series Analysis. In the embodiment shown in FIG. 2, the preprocessing module includes the switcher 206 and the computer vision module 208 for example. The one or more learned model(s) 306 may comprise models arranged to provide an output 308 such as to: derive the amount of food required; estimate growth of the fish from temperature, dissolved oxygen, fish size, and/or fish age; calculate the time before harvest; and/or calculate required treatment levels.” Par. 0133: “According to a further aspect, there is provided an apparatus for controlling the feeding of animals in a confined space containing water, the apparatus comprising: an input for receiving a video signal from at least one video sensor, a memory, and a processor arranged to: determine, from at least the video signal, an activity level for animals prior to and/or during feeding, derive an amount of feed required in response…” Par. 0019: “The model which is assembled can then provide an efficient feeding schedule and/or quantity of feed in order to minimise waste while still maximising growth rate of the fish.” See also Par. 0064, 0078, and 0112.)
receiving, by the control unit, (pre-processing modules 304) particular sensor data from the one or more sensors when the meal plan is executed during the particular feeding session; (Par. 0064: “In this embodiment, a task to be performed may be defining images obtained through real time image data as either “feed” or “not feed”, thereby detecting when feed is not being consumed by the fish. The model which is assembled can then provide an efficient feeding schedule and/or quantity of feed in order to minimise waste while still maximising growth rate of the fish.” Par. 0134: “Such an apparatus can provide the advantages described herein in relation to the computer-implemented method of feeding animals in a confined space containing water. [0135] Optionally, an input is provided for a signal from at least a further video sensor and arranged to process video data from at least two distinct confined spaces in parallel. Optionally, an input is provided for receiving a further video signal corresponding to at least one further confined space.” See also Par. 0112 and 0133. See figure 3 that shows the pre-processing device and sensor data (part of item 302). Note – Rishi teaches 102 instances of sensor(s). Examiner’s Note – Rishi teaches the meal plan by a model which provides an efficient feed schedule. See paragraph 0019: “The model which is assembled can then provide an efficient feeding schedule and/or quantity of feed in order to minimise waste while still maximising growth rate of the fish.”)
and when, during the particular feeding session, the particular sensor data satisfies one or more of the threshold values that are included in the meal configuration data, adjusting, by the control unit, (processing unit (CPU), Par. 0031; or pre-processing modules (item 304, Par. 0194); that feed into a model and then output the schedule.). the execution of the meal plan based on the one or more adjustment parameters that are included in the meal configuration data. (Par. 0040: “The three time periods may be defined as follows: [0041] 1) BEFORE. The “before” activity may comprise data relating to activity of fish during their anticipation of feed, before the feed has actually been provided. [0042] 2) DURING. During feeding the activity may be heavily weighted when a Learned model (also referred to as just a “model”) is being developed. The presence of feed pellets can be detected and measured during this time, to provide a recommendation for reducing, maintaining, or increasing the volume of feed. The behaviours of the fish may also be more accurately understood, particularly with regard to their activity during the feeding process. [0043] 3) AFTER. The detection of pellets (or lack thereof) and the activity of the fish as a reaction may cause the recommendation of feed for the following feeding session to be adjusted.” See also Par. 0041, 0071 0073, 0098, 0107, 0194, 0211. Examiner’s Note – Several paragraphs teach that the system is automated such as Par. 0013, 0049, 0064, 0112, 0133, 0166, 0167, 0192, and others. Rishi also teaches the element of threshold(s) in paragraphs 0036, 0068, 0183, and 0189.)
Rishi may implicitly teach multiple parameters and more than one threshold values such as pellet counts and oxygen levels (Par. 0188). However, Blyth explicitly teaches the multiple parameters included in the meal configuration data comprising: (Col. 4, lines 21 – 22: “The system may incorporate multiple sensors through a single controller and a single sensor or variations thereof.” Col. 4, lines 34 – 36: “System parameters (sensor calibration and program settings) are initially set by the user or from pre-defined internal tables of settings.”)
one or more threshold values that are specified for sensor data that is to be received from one or more sensors when the meal plan is executed, (Col. 6, line 63 - Col. 7, line 14: “The system of the invention may include the following process steps: (A) determine historical system settings; (B) modify current system parameters if necessary; (C) set the feed distributor output to a minimum feed value; (D) Record "background" events, that is uncalibrated objects outside of the sensing window and define the number of model groupings using statistical techniques; (E) dispense the selected amount of feed; (F) commence sensing just prior to the sensing window. Compare uncalibrated objects in the presensing window to calibrated objects; (G) compare pre-window uncalibrated objects to window sensed objects and compensate if necessary; (H) adjust if necessary; (I) measure any feed pellets which pass through the sensor; (J) wait for a short period, for example, 1-60 seconds; (K) if less than a predetermined threshold number of pellets were counted and the feeder output is less than a predetermined maximum value, increase output of feeder by one increment, if greater than the threshold number of pellets are counted, reduce output of feeder by an increment of its previous value, if the number of pellets counted equals threshold or is within a band, maintain feeder output; (L) if the feeder output determined is less than a predetermined minimum then wait for a predetermined sleep time, for example 30 minutes to 1 hour, and compare feed rate per time of day to historical information to optimize sleep value. If pattern recognition response criteria has been met, then sleep for a predetermined period, then return to step (A).” See also Rishi paragraphs 0042, 0072, and 0108 starting with “DURING.”)
and one or more adjustment parameters that indicate how execution of the meal plan is to be adjusted when the sensor data that is received during the execution of the meal plan satisfies the one or more threshold values; (See Col. 6, line 63 - Col. 7, line 14; especially Col. 7, lines 6 – 7: “…if the number of pellets counted equals threshold or is within a band, maintain feeder output..”)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined using a computing device to control and execute a fish feeding system that uses multiple inputs such as pellet count and image data (sensor data) before the feeding of the fish, process the data and create a model that is used in a feeding schedule (Par. 0019, 0032, 0064, 0078, and 0112) as in Rishi with using a computing system with having a fish feeding system that has a plurality of sensors that monitors various parameters including the amount of pellets giving in a certain amount of time and adjust the number of pellets based on a threshold amount whether the amount is above or below certain threshold as in Blyth in order to “…adjust and match the preferred feed values meted to the cultured species at any given time.” (Col. 1, lines 54- 56)
Regarding claim 22,
Rishi and Blyth teach the limitations of claim 1 which claim 22 depends. Blyth also teaches that executing the meal plan comprises: selecting one or more of the multiple parameters included in the meal configuration data; and sending a signal to a feeding mechanism indicating the selected one or more of the parameters. (Col. 4, line 52 – Col. 7, line 14, cited in part: “ The system accomplishes this by comparing historical averages relevant to the species, average for size, stock density, culture unit type, seasonal variations such as water temperature and latitude. Various parameters may then be varied automatically, for example such parameters include…” See also figure 1 that depicts a sensor (5) and control unit (8) attached by signal wire (cable item 7). Col. 3, lines 6 – 9: “The general design allows different sensors with a range of apertures to be manufactured utilizing common operating principles and manufacturing techniques.”)
Regarding claim 23,
Rishi and Blyth teach the limitations of claim 1 which claim 22 depends. Blyth also teaches that the signal is configured to instruct the feeding mechanism to stop feeding the farmed fish. (Col. 1, lines 24 – 28: “Such systems may include detection devices which are able to shut off the supply of feed if an amount of feed is detected above a minimum value. Such systems generally are merely a "on/off" system…” Col. 6, lines 11 – 15: “ The meal maximum sets the upper limit to the amount of food delivered in a meal, that is without a sleep period intervening before the system will warn the user or turn off automatically. This is a safeguard against over feeding due to malfunction of hardware.” Col. 8, lines 32 – 34: “The sensor should be positioned in such a way to establish the end of the feeding period without wasting food.”)
Regarding claim 25,
Rishi and Blyth teach the limitations of claim 1 which claim 25 depends. Blyth also teaches that the meal configuration data includes a policy that prevents adjustments to the execution of the meal plan that are indicated by the one or more adjustment parameters from over-feeding or under-feeding the farmed fish. (Col. 6, lines 11 – 15: “The meal maximum sets the upper limit to the amount of food delivered in a meal, that is without a sleep period intervening before the system will warn the user or turn off automatically. This is a safeguard against over feeding due to malfunction of hardware.”)
Regarding claim 27,
Rishi and Blyth teach the limitations of claim 1 which claim 27 depends. Blyth also teaches that the one or more thresholds comprise a fall through depth. (Col. 3, lines 20 – 25: “The underwater sensor may be submerged to a depth which is dependent on the type of cage structure, average water conditions, the species feeding behaviour, the number of species in the cage, the age of the species and the type of feed used. For example, fish feeding depth will also alter under certain environmental and temporal conditions.” See also Col. 5, lines 23 – 30.)
Regarding claims 28, 29, 30, 32, and 34,
they are directed to a non-transitory readable medium to implement the methods set forth in claims 1, 22, 23, 25, and 27, respectively. Rishi and Blyth teach the method in claims 1, 22, 23, 25, and 27. Rishi also teaches a non-transitory readable medium in paragraph 0133: “a memory, and a processor arranged to:…”…” Therefore, Rishi and Blyth teach the non-transitory readable medium, to implement the method of steps, in claims 28, 29, 30, 32, and 34.
Regarding claims 35 - 37, and 39, they are directed to computer-implemented system to implement the methods set forth in claims 1, 22, 23, and 25 respectively. Rishi and Blyth teach the method in claims 1, 22, 23, and 25. Rishi also teaches a computer-implemented system and method in paragraph 0133. Therefore, Rishi and Blyth teach the computer-implemented system, to implement the method of steps, in claims 35 – 37 and 39.
Regarding claim 24,
Rishi and Blyth teach the limitations of claim 1 which claim 24 depends. Rishi also teaches that the particular sensor data is data that has been processed using a trained neural network model. (Par. 0019: “Neural networks are computing systems which can be arranged to progressively improve their performance in relation to specific tasks through the use of training. Such training may be provided through labelled examples, or manual correction of the neural network when necessary. Neural networks are conventionally arranged from one or more layers of nodes, wherein each layer is set up to perform a specific role in the overall task to be performed. In this embodiment, a task to be performed may be defining images obtained through real time image data as either “feed” or “not feed”, thereby detecting when feed is not being consumed by the fish. The model which is assembled can then provide an efficient feeding schedule and/or quantity of feed in order to minimise waste while still maximising growth rate of the fish.”) Also Par. 0098 teaches: “…combination of machine learning and stereo vision cameras to perform biomass estimation…”) Par. 0178: “The neural network may be divided into 3 distinct processes, which are trained simultaneously via the fully convolutional model: (1) a complete frame of video is analysed to perform pellet detection and localisation; then (2) information from earlier frames of video are analysed to identify movement and/or warping factor of pellets relative to the current frame; and then (3) the outputs of both analysis are utilised in a feedback loop to enhance the distinction of feed from waste for future frames.” Paragraph 0204 teaches: “feed history, past feed conversion rates, biomass of fish and other data may be taken into consideration in training neural networks.” See also Par. 0179.)
Regarding claim 31, it is dependent on claim 28 and is directed to a non-transitory readable medium to implement the methods set forth in claim 24. Rishi and Blyth teach the method in claim 28. Rishi also teaches a non-transitory readable medium in paragraph 0133: “a memory, and a processor arranged to:…” Rishi and Blyth teach the elements of claim 24. Therefore, Rishi and Blyth teach the non-transitory readable medium, to implement the method of steps, in claim 31.
Regarding claim 38, it is dependent on claim 35 and is directed to computer-implemented system to implement the methods set forth in claim 24. Rishi and Blyth teach the method in claim 35. Rishi also teaches a computer-implemented system in many paragraphs such as Par. 0032, 0064, etc. Rishi and Blyth teach the elements of claim 24. Therefore, Rishi and Blyth teach the computer-implemented system, to implement the method of steps, in claim 38.
Claims 26, 33, and 40 are rejected under 35 U.S.C. 103 as being unpatentable over Rishi in view of Blyth in further view of Chinese patent document Rao et al. (CN 112956440 A).
Regarding claim 26,
Rishi and Blyth teach the limitations of claim 1 which claim 26 depends. They do not teach determining an open mouth of a fish. However, Rao does teach that the one or more thresholds comprise specify a number of the farmed fish that have open mouths during the particular feeding session. (Page 6, Par. 3: “based on fish pond precise feeding control system, comprising: an image acquisition module: for collecting fish pond feeding characterization data…” Page 8, Par. 2: “…the fish pond feeding token data comprises fish motion data; when the fish motion data reaches the pre-set time, then pausing feeding; the fish is basically not floating on the water surface, fish eating generally is floating open mouth feeding and then sinking, if not eating, it will repeat the action, when the fish sinking or walking does not repeat the feeding process, feeding pause, waiting for 10 minutes, if there is no change, the feeding stop, and recording the data; floating the floating feed number on the water surface, namely in the camera identification range, covering the water surface 0.04-0.5 square meters, the area is determined according to the size of the pond, temporarily stopping feeding; if the fish group meets the feeding condition after ten minutes, then continuously feeding according to the existing feeding parameter, until the feeding condition does not meet.” Page 3, Par. 2: “The mode, the reasonable analysis and video correction technology big data the feeding amount is just the needed number of fish, greatly reduces the pollution of the feed to the breeding water environment…”)
It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have combined using a computing device to control and execute a fish feeding system that uses multiple inputs such as pellet count and image data (sensor data) before the feeding of the fish, process the data and create a model that is used in a feeding schedule as in Rishi with using a computing system with having a fish feeding system that has a plurality of sensors that monitors various parameters including the amount of pellets giving in a certain amount of time and adjust the number of pellets based on a threshold amount whether the amount is above or below certain threshold as in Blyth with taking images of feeding fish wherein the images represent feeding characterization data, where imaging data will be used to determine whether a fish has an open mouth while feeding as in Rao in order to ensure biological health, fast growth, and reduce waste of feed to the maximum extent. (Page 2, last paragraph).
Regarding claim 33, it is dependent on claim 28 and is directed to a non-transitory readable medium to implement the methods set forth in claim 26. Rishi and Blyth teach the method in claim 28. Rishi also teaches a non-transitory readable medium in paragraph 0133: “a memory, and a processor arranged to:…” Rishi and Blyth teach the elements of claim 26. Therefore, Rishi, Blyth, and Rao teach the non-transitory readable medium, to implement the method of steps, in claim 33.
Regarding claim 40, it is dependent on claim 35 and is directed to computer-implemented system to implement the methods set forth in claim 26. Rishi and Blyth teach the method in claim 35. Rishi also teaches a computer-implemented system and method in paragraph 0133. Rishi, Blyth, and Rao teach the elements of claim 26. Therefore, Rishi, Blyth, and Rao teach the computer-implemented system, to implement the method of steps, in claim 40.
Response to Arguments
Applicant has amended the application with specific elements that after obtaining data related to meal configuration the control unit (pre-processing modules in Rishi) executing the configuration data during a feeding session. Rishi teaches this element, wherein inputs (item 302) are input to the pre-processing modules (item 304) that creates a model and outputs a schedule that is executed by the system to feed fish automatically (Par. 0085). Thus the arguments with respect to all claims have been considered but are moot because the arguments do not apply in light of the new reference being used in the current rejection. Rishi was cited in the previous final rejection for claims 24, 31, and 38, but was not cited for claim 1; therefore, this action is a non-final rejection.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Midel et al. (US PG 20210153479) teaches a modern farm feeding equipment that uses a feeding system that uses images and neural network to detect the animal’s weight and change the food mixture or quantity. (Par. 0086, 0089, 0113)
Chen et al. (US PG Pub. No. 20220000079) teaches estimating a biomass center of fish using a neural network that is trained by images and provides feeding instructions to a feed controller system based on the images. (Par. 0009, Par. 0033, and Claim 1 and claim 15).
Chen Ma (US PG Pub. No. 20210321593) is pertinent to the instant application and was cited in the previous filed rejections and teaches many elements of claim 1. Ma teaches a computer-implemented method comprising: obtaining meal configuration data including one or more parameters indicating a meal plan for feeding farmed fish; (Par. 0016: “Aquaculture techniques such as fish farming are becoming more prevalent as a way to cultivate fish for consumption. One relatively new form of aquaculture uses a fish pen deployed in open water. While such systems provide a beneficial environment for cultivating fish, the underwater deployment of the fish pen makes it difficult to monitor conditions and fish health within the pen. In order to efficiently manage operation of the fish pen, it is desired to have accurate and timely monitoring of the fish within the fish pen. Weight and health are two conditions for which accurate monitoring is desired: monitoring changes in biomass within the fish pen can inform decisions regarding whether to increase or reduce supporting feeding systems, and monitoring health of fish within the fish pen can inform decisions regarding whether to provide treatments for any conditions afflicting the fish.” Par. 0019.)
executing the meal plan based on the meal configuration data; (Par. 0046: “In some embodiments, the aquaculture management computing device 102 may measure the rate of change of the fish biomass over time, and the rate of change may be used to control the fish feeding device. In some embodiments, the biomass estimation and the trend on growth rates may be used to select a feed pellet size and/or a type of feed for the population within the fish pen 104. The biomass estimation and the trend on growth rates may also be used to set a total feed amount, feed delivery style, feed rate, and/or feed time. In some embodiments, the biomass estimate and/or the rate of change of the total fish biomass over time may be an input to a feedback loop mechanism for controlling automated feeding devices. Other input to the feedback loop mechanism may include one or more of a set of environmental data such as water temperature and water pressure (distance beneath the surface). The output of the feedback loop mechanism may indicate a go/no go for feed delivery on a given day.”)
receiving sensor data (camera) from one or more sensors during execution of the meal plan; (Abstract: “…underwater camera system may use the fish dimensions to estimate biomass of fish within the fish pen. The biomass value and rates of change of the biomass value may be used to adjust feeding of the fish in the fish pen. In some embodiments, images captured by the stereoscopic camera may be used to focus a variable focal lens camera on a fish to obtain high-resolution images that can be used for diagnosing fish conditions.” Par. 0019: “In some embodiments, the underwater camera system 106 transmits the at least one of the health information and the biomass estimates to the aquaculture management computing device 102. In some embodiments, the aquaculture management computing device 102 may present the received information to a user so that the user can take actions to manage the fish pen 104, including but not limiting to changing a rate of feeding and providing treatment for adverse health conditions. In some embodiments, the aquaculture management computing device 102 may receive the information and autonomously take management actions with or without presenting the information to a user, including but not limited to automatically changing a rate of feeding by an automated feed pellet dispenser, automatically changing a depth of the fish pen 104, and automatically dispensing a medication.” Aljapur also teaches executing a meal plan, by determining desired or optimal feed amounts and/or feed frequencies using a video or imaging system and machine learning models. See paragraphs 0012 and 0030.)
Aljapur et al. (PG Pub. No. 20230301280) teaches obtaining by a control unit parameters during a feeding session; (Par. 0026: “…edge computers 105 ( e.g., on the supply vessel 101), which may communicate with feeding equipment 106 to control feed delivery into the cage 104 (e.g., from a feed supply on the supply vessel 101).” Par. 0030.)
executing, by the control unit, the meal plan during the particular feeding session based on the meal configuration data; (optimal feed amounts and/or feed frequencies. See Par. 0012 and 0030.)
receiving, by the control unit, sensor data from one or more sensors during execution of the meal plan, wherein the sensor data is obtained during the particular feeding session; and adjusting, by the control unit and during the particular feeding session (Par. 0030).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAD G ERDMAN whose telephone number is (571)270-0177. The examiner can normally be reached Mon - Fri 7am - 5pm EST; Off every other Friday.
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, Kamini S. Shah can be reached on (571) 272-2279. 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.
/CHAD G ERDMAN/Primary Examiner, Art Unit 2116