CA3139212A1 - Agricultural or industrial supply chain distributed network using multi-input decision algorithm - Google Patents
Agricultural or industrial supply chain distributed network using multi-input decision algorithm Download PDFInfo
- Publication number
- CA3139212A1 CA3139212A1 CA3139212A CA3139212A CA3139212A1 CA 3139212 A1 CA3139212 A1 CA 3139212A1 CA 3139212 A CA3139212 A CA 3139212A CA 3139212 A CA3139212 A CA 3139212A CA 3139212 A1 CA3139212 A1 CA 3139212A1
- Authority
- CA
- Canada
- Prior art keywords
- data
- production system
- local production
- diagnostic
- local
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 claims abstract description 166
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000010801 machine learning Methods 0.000 claims abstract description 28
- 238000004891 communication Methods 0.000 claims description 23
- 230000009471 action Effects 0.000 claims description 22
- 239000002689 soil Substances 0.000 claims description 11
- 235000015097 nutrients Nutrition 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000001228 spectrum Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000004378 air conditioning Methods 0.000 claims description 5
- 238000010438 heat treatment Methods 0.000 claims description 5
- 238000009423 ventilation Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000013068 supply chain management Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 2
- 241000196324 Embryophyta Species 0.000 description 25
- 238000012806 monitoring device Methods 0.000 description 20
- 230000008569 process Effects 0.000 description 13
- 241000220223 Fragaria Species 0.000 description 10
- 239000003570 air Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 239000000758 substrate Substances 0.000 description 7
- 235000021012 strawberries Nutrition 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000003339 best practice Methods 0.000 description 3
- 230000012010 growth Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 235000016623 Fragaria vesca Nutrition 0.000 description 2
- 235000011363 Fragaria x ananassa Nutrition 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 230000008635 plant growth Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 235000013311 vegetables Nutrition 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009418 agronomic effect Effects 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 238000013481 data capture Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 150000003112 potassium compounds Chemical class 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/50—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using hash chains, e.g. blockchains or hash trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q2220/00—Business processing using cryptography
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mining & Mineral Resources (AREA)
- Computer Security & Cryptography (AREA)
- Marine Sciences & Fisheries (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
There is described a method and distributed network for managing a supply chain. At least one local production system is fed with an algorithm for producing a good or service (such as agricultural produce) over a production duration. An edge computing device, receives and treats data originating from the at least one local production system. A server periodically receives, from remote data sources, data relative to a market for the good or service, after a time period which is less than the production duration, and receives data treated by the edge computing device to perform comparisons with the data relative to the market to make a diagnostic. The diagnostic is transmitted to a machine learning module for updating the algorithm for production after the time period which is less than the production duration and feeding the algorithm as updated to the at least one local production system.
Description
AGRICULTURAL OR INDUSTRIAL SUPPLY CHAIN DISTRIBUTED NETWORK USING MULTI-INPUT
DECISION ALGORITHM
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims benefit or priority of U.S. provisional patent application 62/859,862, filed June 11, 20191 and U.S. provisional patent application 62/859,865, filed June 11, 20191 which are hereby incorporated herein by reference in their entirety.
BACKGROUND
(a) Field
DECISION ALGORITHM
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims benefit or priority of U.S. provisional patent application 62/859,862, filed June 11, 20191 and U.S. provisional patent application 62/859,865, filed June 11, 20191 which are hereby incorporated herein by reference in their entirety.
BACKGROUND
(a) Field
[0002] The subject matter disclosed generally relates to crop or plant growth monitoring technologies. More specifically, it relates to a distributed network for supply chain management and production yield planning in a context of industrial or agricultural processes.
(b) Related Prior Art
(b) Related Prior Art
[0003] There are various ways of organizing the production of agricultural produce. There is a need to improve organization, decision making and resource allocations in a way which is consistent with the market needs.
BRIEF DESCRIPTION OF THE DRAWINGS
BRIEF DESCRIPTION OF THE DRAWINGS
[0004] Further features and advantages of the present disclosure will become apparent from the following detailed description, taken in combination with the appended drawings, in which:
[0005] Fig. 1 is a schematic diagram illustrating the distributed network, according to an embodiment of the invention;
[0006] Figs. 2A-2D are close-up views on the schematic diagram of Fig. 1, illustrating with greater detail the local production systems, the machine learning module, the edge computing device and the diagnostic module, respectively;
[0007] Fig. 3 is a flowchart illustrating a method for managing a supply chain, according to an embodiment;
[0008] Fig. 4 is a flowchart illustrating a method for acquiring and treating data from a crop facility for yield prediction, according to an embodiment;
[0009] Fig. 5 is a diagram illustrating a method for monitoring and controlling a plant substrate and its environment, according to an embodiment; and
[0010] Fig. 6 is a diagram illustrating a computing and telecommunication infrastructure suitable for implementing the network and method described herein, according to an embodiment.
[0011] It will be noted that throughout the appended drawings, like features are identified by like reference numerals.
SUMMARY
SUMMARY
[0012] According to a first aspect, there is provided a method for managing a production of agricultural produce in a controlled environment comprising at least one local production system, the method comprising the steps of: collecting data originating from the at least one local production system in which the agricultural produce is produced during a production duration; at a server, periodically receiving, from remote data sources, data relative to a market for the agricultural produce, after a time period which is less than the production duration; at the server, making a prediction of a production from the at least one local production system based on the data collected therefrom; at the server, performing comparisons of the prediction with the data relative to the market to make a diagnostic;
determining a level of action for the diagnostic; and transmitting the diagnostic to an appropriate address of a device in the at least one local production system corresponding to the level of action.
determining a level of action for the diagnostic; and transmitting the diagnostic to an appropriate address of a device in the at least one local production system corresponding to the level of action.
[0013] According to an aspect, the method further comprises formatting the data from the at least one local production system into a packet.
[0014] According to an aspect, the method further comprises verifying integrity of the packet originating from the at least one local production system using a private blockchain ledger in communication therewith.
[0015] According to an aspect, the method further comprises filtering the packet prior to transmission to perform immediate feedback in the at least one local production system when the packet is filtered as requiring the immediate feedback, and thereby avoid transmitting said packet.
[0016] According to an aspect, collecting data originating from the at least one local production system comprises collecting data on soil moisture using a soil moisture sensor, and transmitting the diagnostic to the at least one local production system comprises transmitting a diagnostic for controlling watering in the at least one local production system.
[0017] According to an aspect, collecting data originating from the at least one local production system comprises collecting visual data on the agricultural produce using a camera, and transmitting the diagnostic to the at least one local production system comprises transmitting a diagnostic for controlling a quantity of nutrients fed to the agricultural produce, a lighting intensity, or a lighting spectrum.
[0018] According to an aspect, collecting data originating from the at least one local production system comprises collecting data on air temperature or air humidity using a temperature sensor or a humidity sensor, respectively, and transmitting the diagnostic to the at least one local production system comprises transmitting a diagnostic for controlling heating, ventilation and air conditioning (HVAC) systems in the at least one local production system.
[0019] According to an embodiment, there is provided a method for managing a supply chain comprising the steps of: feeding at least one local production system with an algorithm for producing a good or service over a production duration; by an edge computing device, receiving and treating data originating from the at least one local production system; at a server, periodically receiving, from remote data sources, data relative to a market for the good or service, after a time period which is less than the production duration; at the server, receiving data treated by the edge computing device to perform comparisons with the data relative to the market to make a diagnostic; and transmitting the diagnostic to a machine learning module for updating the algorithm for producing the good or service after the time period which is less than the production duration and feeding the algorithm as updated to the at least one local production system.
[0020] According to an aspect, the method further comprises collecting the data in the at least one local production system.
[0021] According to an aspect, the method further comprises verifying integrity of data collected in the at least one local production system using a private blockchain ledger in communication therewith.
[0022] According to an aspect, collecting the data in the at least one local production system comprises collecting data on soil moisture using a soil moisture sensor, and transmitting the diagnostic to the machine learning module comprises transmitting a diagnostic for updating control of watering in the at least one local production system.
[0023] According to an aspect, collecting the data in the at least one local production system comprises collecting visual data on the good or service using a camera, respectively, and transmitting the diagnostic to the machine learning module comprises transmitting a diagnostic for updating control of a quantity of nutrients fed to the good or service, a lighting intensity, or a lighting spectrum.
[0024] According to an aspect, collecting the data in the at least one local production system comprises collecting data on air temperature or air humidity using a temperature sensor or a humidity sensor, respectively, and transmitting the diagnostic to the machine learning module comprises transmitting a diagnostic for updating control of heating, ventilation and air conditioning (HVAC) systems in the at least one local production system.
[0025] According to an aspect, the method further comprises formatting the data collected in the at least one local production system into a packet
[0026] According to an aspect, the method further comprises verifying integrity of the packet originating from the at least one local production system using a private blockchain ledger in communication therewith.
[0027] According to an aspect, the method further comprises filtering the packet prior to transmission to perform immediate feedback in the at least one local production system when the packet is filtered as requiring the immediate feedback, and thereby avoid transmitting said packet.
[0028] According to an embodiment, there is provided a distributed network for supply chain management comprising: at least one local production system for producing a good or service over a production duration; a machine learning module which feeds the at least one local production system with an algorithm for producing the good or service; an edge computing device receiving and treating data originating from the at least one local production system; and a diagnostic module in communication with remote data sources relative to a market for the good or service for a periodic update after a time period which is less than the production duration, and further in communication with the edge computing device to receive data therefrom, adapted to perform comparisons with the remote data sources relative to the market to make a diagnostic and to transmit the diagnostic to the machine learning module for updating the algorithm for producing the good or service.
[0029] According to an aspect, the distributed network further comprises a private blockchain ledger in communication with the at least one local production system to verify integrity of data originating therefrom.
[0030] According to an aspect, the diagnostic module is operated on a cloud computing facility.
[0031] According to an aspect, wherein the machine leaming module comprises a convolutional neural network.
DETAILED DESCRIPTION
DETAILED DESCRIPTION
[0032] Referring to Fig. 1, there is shown a schematic diagram illustrating the distributed network for managing a supply chain in an industrial or agricultural context. With respect to the agricultural context, the underlying agricultural process which takes part in the supply chain should be an agricultural process in which there is both a substantial flow of information from the status of the agricultural process and a possibility to control portions of the agricultural process, i.e., a feedback can be applied. Therefore, it applies to agricultural processes which are industrialized and information-centric in nature.
[0033] An information loop should be present to ensure that the agricultural processes taking place in the distributed network are monitored and ensure that they undergo feedback based on the monitoring according to the method shown in Fig. 4.
[0034] The distributed network and the corresponding method apply to a supply chain that involves the production of a good or service, including the production of agricultural produce, especially one for which a feedback can be applied during the production. The feedback implies that there should be controls for the production and a way to monitor to production process.
[0035] Therefore, the distributed network comprises a local production system 100, comprising monitoring devices 110 and controls 120, shown in Fig. 2k
[0036] The local production should involve a good or service, such as agricultural produce (crops), forwhich a typical duration for production is greater than a characteristic time period of the market variability for the good or product. For example, market demand and market prices for fresh produce (fruit, vegetable, etc.) typically varies on a weekly basis, while the produce takes several weeks to grow. The local production of the produce can therefore undergo feedback depending on market considerations at the other end.
Other industrial products involving production cycles which are long in comparison to a characteristic time period of the market situation can take advantage of the distributed network too.
Other industrial products involving production cycles which are long in comparison to a characteristic time period of the market situation can take advantage of the distributed network too.
[0037] Examples of monitoring devices 110 in the local production system 100 include, without limitation, cameras, thermometers, hygrometers, presence sensors, light sensors, speed sensors, spectrometers, etc. A plurality and a variety of such devices are normally provided in the local production system 100, in accordance with the actual good or service being produced therein.
[0038] Examples of controls 120 in the local production system 100 include, without limitation, actuators, dispensers, valves, pumps, lamps, electric switches, electric devices, machines, tools, robotic devices, etc. Again, a plurality and a variety of such devices are normally provided in the local production system 100, in accordance with the actual good or service being produced therein. Parameters of the controls 120 can be modified or modulated as part of the control being exerted. For example, the lighting applied by the lamps may be modulated in spectrum and intensity over time.
[0039] Both the monitoring devices 110 and the controls 120 are expected to have their power source and also have connections to a network (such as the intemet) or to a communication channels to a computing device of some sort (local computer, edge computing device, remote server, etc.) in order to feed the data to the computing device and receive instructions therefrom, the connection being provided by an appropriate connector (Ethernet connector, VViFi connector, Bluetooth connector, etc.).
[0040] According to an embodiment, there is provided a local decision node 200 at the level of the local production system 100, shown in Fig. 2A. The local decision node 200 can be embodied as a packet filter, for example. The computing device being used as a local decision node 200 serves the purpose of acting locally for simple decision tasks, thereby saving bandwidth and data storage capacity that would otherwise be required to transmit the raw data to a remote location (i.e., a server) to arrive at the same result. Making decisions on a local computing device is more efficient both in terms of required infrastructure and also in terms of time needed to perform the controls on the local production. Therefore, the local decision node 200 ads in unison with the local production system 100, comprising monitoring devices 110 to receive raw data and controls 120 to apply the immediate control feedback. The local decision node 200 is therefore very useful to perform routine operations in the local production workflow, such as acting on the controls 120 based on the monitoring devices 110 in cases when the action to perform is obvious, such as when some value exceeds some threshold. An action is then identified without requiring particular intelligence and the local decision node 200 can then take care of the action.
[0041] According to an embodiment, there is provided a machine learning module 300, shown in Fig. 2B, which feeds the local production system 100 with appropriate rules for production to be implemented by the local production controls 120. According to an embodiment, the machine learning module 300 comprises a neural network, which is trained using a suitable database and with operational rules such as best practices which pertain to the type of local production being managed.
[0042] For example, if the local production involves growing produce, the suitable database would comprise images of the variety of stages in plant growth and fruit/vegetable color, and the operational rules which are fed as an input of the machine learning algorithm would be best practices in growing this type of produce. In this case, growing produce involves analyzing actual images, and the machine learning algorithm can advantageously be implemented in the form of a convolutional neural network into which the actual images are fed in the appropriate format.
[0043] According to an embodiment, the data originating from the local process is transmitted via a network or via any other type of communication channel to an edge computing device 400, shown in Fig. 2G.
[0044] The edge computing device 400 may be adapted to perform low-level routine tasks as is the local decision node 200. More advantageously, the edge-computing device 400 is adapted to perform mid- to high-level tasks to manage the local production system 100. For example, for any data collected by the local production monitoring devices 110 that extends beyond the scope of the local decision node 200, the data should be sent using an appropriate communication channel to the edge computing device to be analyzed, such that appropriate feedback instructions are prepared by the edge computing device 400 and sent back to the controls 120 of the local production system 100 to put the feedback instructions into effect.
[0045] The edge computing device 400 is typically located on the site of the local production system 100, to avoid having to transit very large quantities of data. Indeed, the use of cameras or similar devices acting as monitoring devices 110 involves a significant quantity of data, and transmitting and/or storing such data may not be required or advantageous. Using an edge computing device 400 addresses this issue.
[0046] Now referring to Fig. 4, the flowchart illustrates a method for acquiring data from the local production system and treat the data to perform a yield prediction 3020 and take action on the controls 120 in a local production system at the appropriate level of action 3030.
[0047] The yield prediction 3020 is performed using machine learning which ingests a great quantity and variety of data collected from the local production measuring devices 110 (each one having its data tagged with their origin address in the metadata). The images, temperature, hygrometry and other data are compared to references to assess the level of maturity or health status of the plants. This comparison can be made using a knowledge base or can be made in an opaque manner, i.e., using neural networks to make prediction in conformity with the output taught by training with large datasets.
[0048] The local production monitoring devices 110 should comprise devices to capture images of the plants at the local level, i.e., cameras. The image of a plant at a given instant can be used to assess the level of maturity and general health condition of the plant and of its fruits.
[0049] The local production monitoring devices 110 should further comprise devices to capture physical data about the plants at the local level, i.e., devices to measure temperature, air humidity, soil humidity. These devices can include additional devices such as devices to measure electrical conductivity of the plants, spectrometers, and other more specialized tools. The variety of collected data and the fact that the data are collected across a large number of plants spanning over different levels of action 3030 makes the yield prediction a multi-input prediction. The fact that the data collected from remote sources relative to the market are taken into account to make a decision (decision to perform feedback using the controls 120 on a given level of action) makes the decision a multi-input decision.
[0050] All these devices which form the local production monitoring devices 110 should be connected to a network or to a computing device for analyzing the data collected by the local production monitoring devices 110.
[0051] Typically, as shown in Fig. 4, the data undergoes a step of packet formatting. Data is arranged in a specific format by the local production monitoring devices 110.
[0052] As shown in Fig. 4, there can be a step of packet filtering which follows packet formatting.
Between these two steps, security checks on the data are performed, possibly using the blockchain ledger 700.
Between these two steps, security checks on the data are performed, possibly using the blockchain ledger 700.
[0053] Metadata related to the local production monitoring devices 110 (e.g., device identifier, facility identifier, location, timestamp, conditions in which data is collected, etc.) is added to the other data (collected by the devices 110) being transmitted.
[0054] The step of packet filtering would be performed by the local decision node 200. This step allows making security checks easily, to have the packets transmitted over the network or not.
[0055] From the packets filtered as "good", statistics can be computed. These statistics are sent to the diagnostic module 500, or prepared by the diagnostic module 500, for yield predictions based on the statistics.
[0056] Fig. 2D illustrates a diagnostic module 500 which is used to receive relevant data from the edge computing device and eventually provide feedback instructions. The diagnostic module 500 is normally run on a server (dedicated, cloud, etc.) which is located at a remote location with respect to the local production system 100 and therefore comprises a communication channel (such as the intemet network) for communication with the edge computing device 400 or with a plurality of edge computing devices 400.
[0057] More precisely, the diagnostic module 500 is used to receive, as an input, the output from the edge computing device 400 and market data, and provides as an output instructions or data for eventual application in the local process controlling devices. The market data can include, for example, market prices for the goods produced by the local processes, or indicators of customer demand.
[0058] The diagnostic module 500 can collect the market data by querying a database on a server or any other equivalent (dedicated server, cloud storage, etc.), either as a private server or a server from another party granting access to the diagnostic module 500. Other techniques may be applicable, such as a subscription to an RSS feed, web scraping, or reception of post queries from a third party to feed new market data to the diagnostic module 500. The same applies for customer demand information, which can be derived from real-time or up-to-date sales data from partnering supermarkets, for example, and accessed using similar means.
[0059] According to an embodiment, the data originating from the local monitoring devices 110 can be verified for integrity. For example, a blockchain ledger 700, which is preferably a private blockchain ledger, can be implemented to verify the integrity and origin of the data originating from the local monitoring devices. This implementation implies that a direct communication channel between the local monitoring devices 110 and the blockchain ledger 700 should be provided. As shown in Fig.
2C, the data can be collected prior to being treated by the local decision node 200, and be transmitted to the blockchain ledger 700 at this level for verification, after which it is effectively transmitted to the local decision node 200 for treatment. Otherwise, this can be assessed using other methods such as crypted communications.
Ensuring the integrity and origin of data is useful to prevent industrial hacking or sabotage, or to prevent adverse effects that could result from other technical problems that can occur in the communication channels between the local monitoring devices and the other systems.
2C, the data can be collected prior to being treated by the local decision node 200, and be transmitted to the blockchain ledger 700 at this level for verification, after which it is effectively transmitted to the local decision node 200 for treatment. Otherwise, this can be assessed using other methods such as crypted communications.
Ensuring the integrity and origin of data is useful to prevent industrial hacking or sabotage, or to prevent adverse effects that could result from other technical problems that can occur in the communication channels between the local monitoring devices and the other systems.
[0060] The diagnostic module 500 is adapted to determine if there are actions that need to be performed at the level of any one of the local production system(s) 100. More specifically, the diagnostic module 500 is trained to compare the activity monitored by the local production monitoring devices 110, or other information outputted by the edge computing device 400, and compare the monitored activity with the raw market data or other market indicators to determine if actions need to be applied by the local production controls 120.
[0061] More specifically, it can use a knowledge base and/or a machine learning algorithm to determine if the local production system 100 is well positioned to meet market demand. More advantageously, it can predict the production volume of the local production and compare with a market prediction at a particular date in the future, and produce instructions for the controls 120 accordingly to either meet specific criteria or to optimize sales.
[0062] Advantageously, the diagnostic module 500 can receive data from a plurality of local production systems 100, each being distinct from the others and presumably remote from each other. The diagnostic module 500 can therefore make global or total predictions taking into account all of the local production systems 100. If actions need to be performed, the instructions are given to the controls 120 of the local production system 100 for which the feedback is the most likely to be effective, or the one for which the expected monetary benefit is the highest. This is useful in cases where the cost of transportation of the produced good is high or if there is a significant disparity in the production cost between different local production systems 100.
[0063] According to an embodiment, the instructions sent by the diagnostic module 500 are not practical, low-level instructions to the controls 120, and rather comprise a prediction or representation of the plurality of local productions systems 100 and a prediction or representation of the market data. The diagnostic module 500 then proceeds to feeding these pieces of information into the machine learning module 300, where the newly fed pieces of information are used by the machine learning module 300 as new data which modify the machine learning algorithm. Once the machine learning module 300 has integrated the new data and the new machine learning algorithm is ready, it is fed to the local production systems 100 for application by the local production systems 100 under the new version of the machine learning algorithm.
[0064] This feedback loop is how the controls 120 at the local level are adapted to fit the constraints from the market data that are being collected and compared at the level of the diagnostic module 500, as discussed in relation with Figs. 3-4.
[0065] The method for operating the distributed network for supply chain management is shown in Fig. 3, and comprising the following steps:
[0066] step 310 - feeding at least one local production system with an algorithm for producing a good or service over a production duration;
[0067] step 320 - verifying integrity of data originating from the at least one local production system using a private blockchain ledger in communication therewith
[0068] step 330 - by an edge computing device, receiving and treating data originating from the at least one local production system;
[0069] step 340 - at a server, periodically receiving, from remote data sources, data relative to a market for the good or service, after a time period which is less than the production duration;
[0070] step 350 - at the server, receiving data treated by the edge computing device to perform comparisons with the data relative to the market to make a diagnostic;
[0071] step 360 - transmitting the diagnostic to a machine learning module for updating the algorithm for producing the good or service after the time period which is less than the production duration and feeding the algorithm as updated to the at least one local production system (and then, go back to step 310, as the whole process is iterative for continuous improvement).
[0072] Now referring back to Fig. 4, there is shown that when the packet is filtered as containing data which is indicative that something is not good for the plant, a treatment prescription (Rx) can be applied to the plant directly, without having to send to data through a network, as the data collected is sufficient to immediately dictate a treatment.
[0073] The treatment prescription (Rx) can otherwise be instructed by the diagnostic module after having compared the yield prediction 3020 with the market demand.
[0074] As shown in Fig. 4, the feedback is applied at the appropriate level of granularity on the facilities, i.e., level of action 3030. For example, actions can be taken for a whole farm, for a single growth chamber, for a single machine, or for a single plant. The local production controls 120 can therefore be addressed (i.e., each instance of the controls 120 has its own address such as an IP address) at the level which is right to act on a level comprises the desired group of plants in order to be more effective. For example, nutrients can be given to a given farm for which the yield prediction concludes that the yield is likely to be insufficient for the market demand, such that the productivity of that farm increases to meet the demand. If it is detected that a plant has a disease, or the plants in a single growth chamber have a disease, then a treatment can be applied to the plant or growth chamber, accordingly.
Resources are therefore allocated in an optimal fashion and in accordance with a planning of the yield of a facility. The yield of a facility is also tailored, using the feedback applied through the controls, to meet the market demand, especially in a regional area of the facility (i.e., the market that the facility caters).
Resources are therefore allocated in an optimal fashion and in accordance with a planning of the yield of a facility. The yield of a facility is also tailored, using the feedback applied through the controls, to meet the market demand, especially in a regional area of the facility (i.e., the market that the facility caters).
[0075] As mentioned above, the feedback can advantageously be provided by updating the machine teaming algorithms which are applied at a given level of action in the facility. Otherwise, the instructions can also be applied more directly by instructing the controls 120 with a well-defined action instead of updating the algorithm that runs them.
[0076] Example
[0077] A practical example of a production which would benefit from the method would include strawberry production. The at least one local production systems would include a plurality of dispersed and independent facilities in which strawberries are produced, each being monitored and controlled using the distributed network.
[0078] The machine learning module 300 would first integrate images of strawberries at various stages thereof, and agronomical knowledge would be integrated into a knowledge base to know how to properly act upon the strawberry plants depending on their state. For example, the strawberries may need different substances or type of lighting depending on their stage, and some visual features of the strawberries may indicate diseases which may require action.
[0079] By feeding the algorithm from the machine learning module 300 to the local facilities, strawberry plants can be properly monitored and controlled by implementing the machine learning algorithm into the local instruments (water dispenser, nutrient dispensers, lamps, etc.). Relevant information can be sent to the edge computing device for treatment.
[0080] Reports from the edge computing device 400 are sent at a sufficient frequency to the diagnostic module, typically on the cloud or dedicated server. The diagnostic module 500 would be integrated with other partners, such as supermarket chains, to query or receive market data, such as prices for the strawberry, demands from various supermarkets, etc. A comparison would then be made to see if there is enough production available from the various facilities.
[0081] For example, the edge computing device 400 may have sent to the diagnostic module a report indicating that a disease has spread in a particular facility. The diagnostic module 500 may then compare with predictions for market data and determine that replacing or treating the plants would result in a deficit because the strawberries would be ready at a time where prices are low and the market is saturated. The diagnostic module could also determine that the market will be underserved in a particular area, with expected high prices and unmet demand, and recommend treating the plants at a particular facility which is located in that area.
[0082] To do so, the diagnostic module will integrate such a determination or diagnostic into instructions which are fed to the machine learning module 300, which will take them into account and update the algorithm. After the update, the updated algorithm is transmitted to the at least one facility for application therein.
[0083] Market data are normally collected periodically at a high frequency, after a time period (i.e., inverse of frequency) which is smaller than a production time for the strawberries, to ensure that the updates of the algorithm are applied and have an effect in a given production batch.
[0084] In the end, instructions are transmitted to the IP address of the device which belongs to the appropriate level of action for the feedback, ranging from the plant level to the farm-wide level.
[0085] Fig. 5 illustrates the example in greater detail. Each box in the diagram represents a parameterwhich can beaded upon, i.e., represents a control 120, or a parameter which can be measured, i.e., represents a monitoring device 110. Arrows represent relationships between these parameters.
[0086] For example, measurements are taken and actions are taken with respect to the crops, centered on the plant substrate which receives water and nutrient and is being monitored. As an example of control 120, a mixer in a facility is controlled to feed each specific plant substrate in the facility. The mixer receives water, which can be a mixture between city water and wastewater from the facility itself. After being conditioned properly based on its contents, the water is mixed with nutrients according to an appropriate recipe (quantities) of nitrogen, phosphorus and potassium compounds. A distribution system comprising piping is controlled using pumps to feed the plant substrate with water (watering) and with nutrients in appropriate quantities. The other main parameter to control is lighting, which is controlled both in intensity and in spectrum to give appropriate lighting for the plants to grow and to yield produce (such as fruit).
[0087] Still referring to Fig. 5, the plant substrate is monitored using monitoring devices 110. A
temperature sensor, a pH sensor, a humidity sensor and a CO2 sensor are used and provide measurements which can be analyzed using the network and method described above to ensure a proper flow of information through the network, i.e., actions are taken at the local level without having to transmit unnecessary data, while other data is transmitted remotely to monitor the facility as a whole and to update the instructions based on a high-level diagnostic of the situation (adequation between expected production and market) and also based on agronomic best practices.
temperature sensor, a pH sensor, a humidity sensor and a CO2 sensor are used and provide measurements which can be analyzed using the network and method described above to ensure a proper flow of information through the network, i.e., actions are taken at the local level without having to transmit unnecessary data, while other data is transmitted remotely to monitor the facility as a whole and to update the instructions based on a high-level diagnostic of the situation (adequation between expected production and market) and also based on agronomic best practices.
[0088] Finally, each environment (not only the plant substrate but also the ambient air) can be monitored in temperature and humidity to ensure proper control of the HVAC
systems (heating, ventilation and air conditioning) to maintain the environment within suitable air parameters, consistently with the operation of the illumination system.
systems (heating, ventilation and air conditioning) to maintain the environment within suitable air parameters, consistently with the operation of the illumination system.
[0089] Although not shown in Fig. 5, images acquired from cameras can be used as part of the monitoring, as already mentioned above.
[0090] Fig. 6 is a diagram illustrating a computing and telecommunication infrastructure suitable for implementing the network and method described herein. Most aspects have already been mentioned above but are shown in a more formal way in Fig. 6. It should be understood that the network and method described herein seek to allow a distributed production (i.e., geographically distributed), which can allow a better matching between the local production and the local consumption, and therefore considerably reduce the transportation requirements of the produce. However, doing this creates new considerations, such as the amount of disseminated data to be acquired and analyzed. In a single traditional outdoor field, or greenhouse, the cultivator can see the production very easily. In a distributed production setting, all production units are remote from each other and a visual inspection may not suffice. Moreover, getting more quantitative measurements is useful from an agronomical perspective because production can be analyzed. Therefore, there is a challenge of transmitting and analyzing information because data is produced at various locations and can be collected at very high rates (especially images from cameras, which have a heavy file size that is hard to treat efficiently) which are difficult to transmit and to analyze properly when considering a network of several production units to be monitored and controlled from a centralized location.
[0091] The structure of computing and data processing devices and the way data is transmitted according to certain criteria reduce the load of required data transmission and makes this challenge more bearable. In other words, thanks to an iterative update of the instructions based on machine learning, instructions are implemented at a local level and reviewed repeatedly. Data-intensive acquisitions, such as images, can be treated locally based on these instructions, avoiding transmission of such data and centralized analysis. Mid-level information is transmitted to middleware, such as edge computing, which have higher processing power and is able to treat a filtered quantity of data.
High-level analysis of overall production and market considerations are treated centrally and only relevant information is sent to the remote, central processing unit. The same applies to the diagnostic, which is not based on a large quantity of data, but rather on high-level data which is easier to treat.
High-level analysis of overall production and market considerations are treated centrally and only relevant information is sent to the remote, central processing unit. The same applies to the diagnostic, which is not based on a large quantity of data, but rather on high-level data which is easier to treat.
[0092] Still referring to Fig. 6, it is shown that data capture takes place using sensors (temperature of the plant/substrate and of the air/enclosure; air humidity, soil moisture, soil pH, infrared sensors);
cameras (infrared or optical spectrum), and any other type of data which can be entered by an operator via a user interface. All the data is sent to a layer of data communication which, in practice, is implemented by appropriate hardware for data communication such as the implementation of a local area network (LAN), comprising WSN, VVi-Fi, Bluetooth, Zigbee, LORA or RFID devices and implementing the appropriate protocols. IP protocols are also used (including UD, TCP, HTTPS, QUIC loT, MOTT) to switch to a wide-area network (WAN) implementing a cellular network, or using fiber, hybrid fiber-coaxial, or xDSL
technologies along with the VVi-Fi connection.
cameras (infrared or optical spectrum), and any other type of data which can be entered by an operator via a user interface. All the data is sent to a layer of data communication which, in practice, is implemented by appropriate hardware for data communication such as the implementation of a local area network (LAN), comprising WSN, VVi-Fi, Bluetooth, Zigbee, LORA or RFID devices and implementing the appropriate protocols. IP protocols are also used (including UD, TCP, HTTPS, QUIC loT, MOTT) to switch to a wide-area network (WAN) implementing a cellular network, or using fiber, hybrid fiber-coaxial, or xDSL
technologies along with the VVi-Fi connection.
[0093] This data can be sent through the WAN to a data interpretation layer embodied by a computer, in particular a client computer of any type (tabletop, laptop, tablet, phone, wearable computer, etc.), for display to the on-site operator.
[0094] Instead of having the data transmitted immediately from its site of capture to the WAN for display to the user, the data can be sent to a middleware for analysis and eventual transmission to the WAN for display to the user, as shown in Fig. 6.
[0095] The middleware comprises edge computing for receiving the data and performing, at the middleware level, the monitoring of environmental data, climate data, irrigation and nutrient data; process local images, merge or apply operations on the sensor data, and act as a local decision node, a local database and an loT data broker with the outside. Operations such as formatting, matching, querying and getting responses, storing and processing data can be done at this level.
[0096] When necessary, the information from the edge computing can be transmitted to a remote cloud computing installation which is useful for high-level management (such as a dashboard), API
management, event database, any necessary cloud-based image processing or training and the application of remote decisions.
management, event database, any necessary cloud-based image processing or training and the application of remote decisions.
[0097] Both the edge computing and cloud computing systems can communicate together and their output can be used to trigger a diagnostic which interacts with the automated processes that take place, and can be sed to send alerts, diagnostic or status information to the operator through the WAN
described above.
described above.
[0098] A layer of security is added on top of the infrastructure, implementing, for example, the blockchain ledger described above, especially at the level of data transmission.
[0099] While preferred embodiments have been described above and illustrated in the accompanying drawings, it will be evident to those skilled in the art that modifications may be made without departing from this disclosure. Such modifications are considered as possible variants comprised in the scope of the disclosure.
Claims (20)
1. A method for managing a production of agricultural produce in a controlled environment comprising at least one local production system, the method comprising the steps of:
- collecting data originating from the at least one local production system in which the agricultural produce is produced during a production duration;
- at a server, periodically receiving, from remote data sources, data relative to a market for the agricultural produce, after a time period which is less than the production duration;
- at the server, making a prediction of a production from the at least one local production system based on the data collected therefrom;
- at the server, performing comparisons of the prediction with the data relative to the market to make a diagnostic;
- determining a level of action for the diagnostic; and - transmitting the diagnostic to an appropriate address of a device in the at least one local production system corresponding to the level of action.
- collecting data originating from the at least one local production system in which the agricultural produce is produced during a production duration;
- at a server, periodically receiving, from remote data sources, data relative to a market for the agricultural produce, after a time period which is less than the production duration;
- at the server, making a prediction of a production from the at least one local production system based on the data collected therefrom;
- at the server, performing comparisons of the prediction with the data relative to the market to make a diagnostic;
- determining a level of action for the diagnostic; and - transmitting the diagnostic to an appropriate address of a device in the at least one local production system corresponding to the level of action.
2. The method of claim 1, further comprising formatting the data from the at least one local production system into a packet.
3. The method of claim 2, further comprising verifying integrity of the packet originating from the at least one local production system using a private blockchain ledger in communication therewith.
4. The method of claim 2 or 3, further comprising filtering the packet prior to transmission to perform immediate feedback in the at least one local production system when the packet is filtered as requidng the immediate feedback, and thereby avoid transmitting said packet.
5. The method of any one of claims 1 to 4, wherein collecting data originating from the at least one local production system comprises collecting data on soil moisture using a soil moisture sensor, and transmitting the diagnostic to the at least one local production system comprises transmitting a diagnostic for controlling watering in the at least one local production system.
6. The method of any one of claims 1 to 5, wherein collecting data originating from the at least one local production system comprises collecting visual data on the agricultural produce using a camera, and transmitting the diagnostic to the at least one local production system comprises transmitting a diagnostic for controlling a quantity of nutrients fed to the agricultural produce, a lighting intensity, or a lighting spectrum.
7. The method of any one of claims 1 to 6, wherein collecting data originating from the at least one local production system comprises collecting data on air temperature or air humidity using a temperature sensor or a humidity sensor, respectively, and transmitting the diagnostic to the at least one local production system comprises transmitting a diagnostic for controlling heating, ventilation and air conditioning (HVAC) systems in the at least one local production system.
S. A method for managing a supply chain comprising the steps of:
- feeding at least one local production system with an algorithm for producing a good or service over a production duration;
- by an edge computing device, receiving and treating data originating from the at least one local production system;
- at a server, periodically receiving, from remote data sources, data relative to a market for the good or service, after a time period which is less than the production duration;
- at the server, receiving data treated by the edge computing device to perfomi comparisons with the data relative to the market to make a diagnostic; and - transmitting the diagnostic to a mathine leaming module for updating the algorithm for producing the good or service after the time period which is less than the production duration and feeding the algorithm as updated to the at least one local production system.
- feeding at least one local production system with an algorithm for producing a good or service over a production duration;
- by an edge computing device, receiving and treating data originating from the at least one local production system;
- at a server, periodically receiving, from remote data sources, data relative to a market for the good or service, after a time period which is less than the production duration;
- at the server, receiving data treated by the edge computing device to perfomi comparisons with the data relative to the market to make a diagnostic; and - transmitting the diagnostic to a mathine leaming module for updating the algorithm for producing the good or service after the time period which is less than the production duration and feeding the algorithm as updated to the at least one local production system.
9. The method of claim 8, further comprising collecting the data in the at least one local production system.
10. The method of claim 9, further comprising verifying integrity of data collected in the at least one local production system using a private blockchain ledger in communication therewith.
11. The method of claim 9 or 10, wherein collecting the data in the at least one local production system comprises collecting data on soil moisture using a soil moisture sensor, and transmitting the diagnostic to the machine leaming module comprises transmitting a diagnostic for updating control of watering in the at least one local production system.
12. The method of any one of claims 9 to 11, wherein collecting the data in the at least one local production system comprises collecting visual data on the good or service using a camera, respectively, and transmitting the diagnostic to the machine leaming module comprises transmitting a diagnostic for updating control of a quantity of nutrients fed to the good or service, a lighting intensity, or a lighting spectrum.
13. The method of any one of claims 9 to 12, wherein collecting the data in the at least one local production system comprises collecting data on air temperature or air humidity using a temperature sensor or a humidity sensor, respectively, and transmitting the diagnostic to the machine learning module comprises transmitting a diagnostic for updating control of heating, ventilation and air conditioning (HVAC) systems in the at least one local production system.
14. The method of any one of claims 9 to 13, further comprising formatting the data collected in the at least one local production system into a packet.
15. The method of claim 14, further comprising verifying integrity of the packet originating from the at least one local production system using a private blockchain ledger in communication therewith.
16. The method of claim 14 or 15, further comprising filtering the packet prior to transmission to perform immediate feedback in the at least one local production system when the packet is filtered as requiring the immediate feedback, and thereby avoid transmitting said packet.
17. A distributed network for supply chain management comprising:
- at least one local production system for producing a good or service over a production duration;
- a machine leaming module which feeds the at least one local production system with an algorithm for produdng the good or service;
- an edge computing device receiving and treating data originating from the at least one local production system; and - a diagnostic module in communication with remote data sources relative to a market for the good or service for a periodic update after a time period which is less than the production duration, and further in communication with the edge computing device to receive data therefrom, adapted to perform comparisons with the remote data sources relative to the market to make a diagnostic and to transmit the diagnostic to the machine leaming module for updating the algorithm for producing the good or service.
- at least one local production system for producing a good or service over a production duration;
- a machine leaming module which feeds the at least one local production system with an algorithm for produdng the good or service;
- an edge computing device receiving and treating data originating from the at least one local production system; and - a diagnostic module in communication with remote data sources relative to a market for the good or service for a periodic update after a time period which is less than the production duration, and further in communication with the edge computing device to receive data therefrom, adapted to perform comparisons with the remote data sources relative to the market to make a diagnostic and to transmit the diagnostic to the machine leaming module for updating the algorithm for producing the good or service.
18. The distributed network of claim 17, further comprising a private blockchain ledger in communication with the at least one local production system to verify integrity of data originating therefrom.
19. The distributed network of claim 17 or 18 wherein the diagnostic module is operated on a cloud computing facility.
20. The distributed network any one of claims 17 to 19, wherein the machine learning module comprises a convolutional neural network.
Applications Claiming Priority (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201962859865P | 2019-06-11 | 2019-06-11 | |
US201962859862P | 2019-06-11 | 2019-06-11 | |
US62/859,865 | 2019-06-11 | ||
US62/859,862 | 2019-06-11 | ||
PCT/CA2020/050796 WO2020248053A1 (en) | 2019-06-11 | 2020-06-10 | Agricultural or industrial supply chain distributed network using multi-input decision algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CA3139212A1 true CA3139212A1 (en) | 2020-12-17 |
Family
ID=73781128
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CA3139212A Pending CA3139212A1 (en) | 2019-06-11 | 2020-06-10 | Agricultural or industrial supply chain distributed network using multi-input decision algorithm |
Country Status (2)
Country | Link |
---|---|
CA (1) | CA3139212A1 (en) |
WO (1) | WO2020248053A1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112880741A (en) * | 2021-01-22 | 2021-06-01 | 谢雨函 | Urban public safety intelligent monitoring management system based on big data and video image collaborative analysis |
CN113507491B (en) * | 2021-04-30 | 2022-11-11 | 华中农业大学 | Method and system for uploading full-chain information of clean egg production in real time |
DE102021117221A1 (en) | 2021-07-05 | 2023-01-05 | Harting Systems Gmbh | Process and device for the distribution of plants |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017176733A1 (en) * | 2016-04-04 | 2017-10-12 | Freight Farms, Inc. | Modular farm control and monitoring system |
WO2019094729A1 (en) * | 2017-11-09 | 2019-05-16 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for the industrial internet of things |
-
2020
- 2020-06-10 WO PCT/CA2020/050796 patent/WO2020248053A1/en active Application Filing
- 2020-06-10 CA CA3139212A patent/CA3139212A1/en active Pending
Also Published As
Publication number | Publication date |
---|---|
WO2020248053A1 (en) | 2020-12-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Georgakopoulos et al. | Internet of things: from internet scale sensing to smart services | |
CN106657401B (en) | Crop growth monitoring platform based on Internet of things and monitoring method thereof | |
CN203433329U (en) | Intelligent greenhouse Internet-of-Things remote monitoring device | |
CA3139212A1 (en) | Agricultural or industrial supply chain distributed network using multi-input decision algorithm | |
Rodríguez et al. | A system for the monitoring and predicting of data in precision agriculture in a rose greenhouse based on wireless sensor networks | |
CN106212243B (en) | Intelligent organic agricultural product production system based on micro-culture box and cloud platform | |
US20160148104A1 (en) | System and method for plant monitoring | |
WO2019222860A1 (en) | System, method and/or computer readable medium for growing plants in an autonomous green house | |
Murugamani et al. | Machine Learning Technique for Precision Agriculture Applications in 5G‐Based Internet of Things | |
KR101132151B1 (en) | Method for managing a greenhouse in ubiquitous | |
CN103294033A (en) | Agricultural product production process control system and method based on Internet of Things | |
US20230215511A1 (en) | Real-time projections and estimated distributions of agricultural pests, diseases, and biocontrol agents | |
CN112465109A (en) | Green house controlling means based on cloud limit is in coordination | |
CN103093389A (en) | Agricultural product production management system based on network | |
CN108776874A (en) | A kind of modern agriculture regulatory analysis system | |
CN117893346A (en) | AI intelligent agriculture harvesting management system based on Internet of things and application thereof | |
Nayagam et al. | Control of pests and diseases in plants using iot technology | |
CN108234674A (en) | Intelligent vegetables household electrical appliances Internet of things system | |
Kwon et al. | Design and implementation of an integrated management system in a plant factory to save energy | |
KR20140132873A (en) | Apparatus, System and Method based on Ontology for providing growth environments to crops | |
US20220253756A1 (en) | Agricultural or industrial supply chain distributed network using multi-input decision algorithm | |
CN117933913A (en) | Intelligent agricultural data monitoring management and control system based on multidimensional data and intelligent terminal | |
CN114543869A (en) | Agricultural braced system based on internet of things | |
Khan et al. | Harnessing 5G Networks for Enhanced Precision Agriculture: Challenges and potential Solutions | |
Ramdoo et al. | A flexible and reliable wireless sensor network architecture for precision agriculture in a tomato greenhouse |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
EEER | Examination request |
Effective date: 20211123 |
|
EEER | Examination request |
Effective date: 20211123 |
|
EEER | Examination request |
Effective date: 20211123 |
|
EEER | Examination request |
Effective date: 20211123 |
|
EEER | Examination request |
Effective date: 20211123 |
|
EEER | Examination request |
Effective date: 20211123 |
|
EEER | Examination request |
Effective date: 20211123 |
|
EEER | Examination request |
Effective date: 20211123 |