Precision agriculture system

Patent metadata

Field	Value
Publication number	US-2016202227-A1
Application number	US-201514663989-A
Country	US
Kind code	A1
Filing date	Mar 20, 2015
Priority date	Jan 14, 2015
Publication date	Jul 14, 2016
Grant date	—

Abstract

A device may receive sensor data from a sensor device located on a particular farm. The device may identify an alert, associated with the particular farm, based on the sensor data and using a model. The model may be created based on imagery data and numeric data relating to a group of farms. The device may determine, using the model, a recommended course of action to address the alert, and provide, to a user device associated with the particular farm, the recommended course of action.

First claim

What is claimed is:

1 . A method comprising:
receiving, by a processor of a device, data,
the data including first data and second data,
the first data being received from a plurality of sensor devices located on one or more farms, and
the second data being received from one or more devices located external to the one or more farms;

creating, by the processor and using the data, a model; receiving, by the processor, sensor data,
the sensor data relating to a particular farm of the one or more farms;
identifying, by the processor, an alert, associated with the particular farm, based on the sensor data and using the model; determining, by the processor and using the model, a recommended course of action to address the alert; and providing, by the processor and to a user device associated with the particular farm, the recommended course of action.

2 . The method of claim 1 , where, when determining the recommended course of action, the method includes:
determining a plurality of recommended courses of action to address the alert, determining, for each recommended course of action of the plurality of recommended courses of action, a financial impact of performing the recommended course of action or not performing the recommended course of action, ranking the plurality of recommended courses of action, based on determining the financial impact for each recommended course of action, to create a ranked list, and where, when providing the recommended course of action, the method includes:
providing the ranked list to the user device.

3 . The method of claim 1 , where, when creating the model, the method includes:
creating a plurality of models for a farm of the one or more farms,
the plurality of models including:
a first model that is associated with a first portion of the farm, and
a second model that is different than the first model and that is associated with a second portion of the farm,
the first portion and the second portion corresponding to different plots of the farm or different crops of the farm.

4 . The method of claim 1 , where the alert includes one or more of:
a farming equipment alert relating to a maintenance or malfunction of a piece of farming equipment associated with the particular farm, a financial alert relating to harvesting, storing, or selling a particular crop associated with the particular farm, a disease alert relating to detection of a disease in a plot of the particular farm, an insect alert relating to detection of an insect issue in connection with the plot, or an irrigation alert relating to an irrigation issue associated with the plot.

5 . The method of claim 1 , where the alert includes a financial alert relating to harvesting, storing, or selling a particular crop associated with the farm, and
where, when determining the alert, the method includes:
determining a peak price time period, during a calendar year, for the particular crop,
determining a growth degree days maturity time period, during the calendar year, for the particular crop,
determining a peak price harvest period, during the calendar year, based on the peak price time period and the growth degree days maturity time period,
determining a peak yield time period, during the calendar year, for the particular crop,
predicting a yield gross, for a period during the calendar year, based on the peak price harvest period and the peak yield time period, and
determining the financial alert based on the predicted yield gross.

6 . The method of claim 1 , further comprising:
detecting selection of the recommended course of action; and causing one of:
the recommended course of action to be automatically performed, or
the recommended course of action to be scheduled to be manually performed.

7 . The method of claim 1 , where the recommended course of action includes causing an unmanned aerial vehicle (UAV) to capture imagery of a plot of the particular farm, and
where the method further comprises:
detecting selection of the recommended course of action;
identifying a particular UAV based on detecting the selection; and
causing the particular UAV to capture images of the plot of the particular farm.

8 . A computer-readable medium storing instructions, the instructions comprising:
a plurality of instructions, which, when executed by a processor of a device, cause the processor to:
receive data,
the data including first data and second data,
the first data including sensor-related data received from sensor devices located on one or more farms, and
the second data including farming-related data received from devices that are located external to the one or more farms;

create a model using the data;
receive, after creating the model, sensor data,
the sensor data being received from a sensor device located on a particular farm;

identify an alert, associated with the particular farm, based on the sensor data and using the model;
determine, using the model, a recommended course of action to address the alert; and
provide, to a user device associated with the particular farm, the recommended course of action.

9 . The computer-readable medium of claim 8 , where the plurality of instructions that cause the processor to determine the recommended course of action, further cause the processor to:
determine a plurality of recommended courses of action to address the alert, determine, for each recommended course of action of the plurality of recommended courses of action, a financial impact of performing the recommended course of action or not performing the recommended course of action, order the plurality of recommended courses of action, based on determining the financial impact for each recommended course of action, to create an ordered list, and where the plurality of instructions, when executed by the processor to provide the recommended course of action, further cause the processor to:
provide the ordered list to the user device.

10 . The computer-readable medium of claim 8 , where the plurality of instructions that cause the processor to create the model, further cause the processor to:
create a plurality of models for a farm of the one or more farms,
the plurality of models including:
a first model,
the first model being associated with a first portion of the farm,

and
a second model,
the second model being different than the first model,
the second model being associated with a second portion of the farm, and
the first portion and the second portion corresponding to different crops of the farm or different plots of the farm.

11 . The computer-readable medium of claim 8 , where the sensor data relates to a particular plot of the particular farm,
where the alert relates to an insect infestation or a disease, and where the plurality of instructions further cause the processor to:
provide, to the user device, a set of images of the plot,
the set of images providing a timeline of an effect of the insect infestation or the disease on the plot over time.

12 . The computer-readable medium of claim 8 , where the alert includes one or more of:
a farming equipment alert relating to a maintenance or malfunction of a piece of farming equipment associated with the particular farm, a financial alert relating to harvesting, storing, or selling a particular crop associated with the farm, a disease alert relating to detection of a disease in a plot of the particular farm, an insect alert relating to detection of an insect issue in connection with the plot, or an irrigation alert relating to an irrigation issue of the plot.

13 . The

Assignees

• Accenture Global Services Ltd

Inventors

• Mathur Ankur
• Barsamian Paul M
• Garrison Daniel P
• Mullan Pramila
• Mendez Juan Carlos

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G01C11/025

  by scanning the object · CPC title

• G06F30/00

  Computer-aided design [CAD] · CPC title

• G06Q50/02 Primary

  Agriculture; Fishing; Forestry; Mining · CPC title

• A01C15/00

  Fertiliser distributors ({combined with seeders} A01C7/06) · CPC title