Messaging based on agricultural knowledge graph
Implementations are described herein for leveraging an agricultural knowledge graph to generate messages automatically. In various implementations, an agricultural event may trigger proactive performance of one or more of the following operations. Nodes of the agricultural knowledge graph may be identified as related to the agricultural event, including field node(s) representing subject agricultural field(s) to which the agricultural event is relevant and other node(s) connected to one or more of the field nodes by edge(s). Machine learning model(s) may be accessed based on the identified nodes and/or the edges that connect the identified nodes. Data relevant to the subject agricultural field(s) may be retrieved from data source(s) controlled by an agricultural entity and processed based on the machine learning model(s) to generate inference(s) about the subject agricultural field(s). Agricultural message(s) based on the inference(s) may be pushed to client computing device(s) controlled by the agricultural entity.
1 . A method implemented using one or more processors and comprising:
detecting that an agricultural event has occurred, wherein the agricultural event is detected when new data is included in an agricultural knowledge graph in relation to an event that occurs in a nearby agricultural field that is adjacent to, or within a predetermined distance of, one or more subject agricultural fields; and
in response to detecting that the agricultural event has occurred, proactively performing the following operations:
identifying a plurality of nodes of the agricultural knowledge graph as related to the agricultural event, wherein the agricultural knowledge graph includes nodes connected by edges that represent semantic relationships between the nodes, and wherein the plurality of identified nodes includes one or more field nodes representing the one or more subject agricultural fields, one or more field nodes representing the nearby agricultural field to which the agricultural event is relevant, and one or more other nodes connected to the one or more field nodes by one or more edges, wherein the one or more other nodes correspond to past practices implemented in the nearby agricultural field;
accessing one or more machine learning models based on one or more of the plurality of identified nodes or the one or more edges that connect two or more of the plurality of identified nodes, wherein at least one of the one or more machine learning models generates inferences related to a past practice of the past practices;
retrieving data from one or more data sources controlled by an agricultural entity, wherein the one or more data sources contain data that is relevant to the one or more subject agricultural fields;
processing the retrieved data based on the one or more machine learning models to generate one or more inferences about the one or more subject agricultural fields, the one or more inferences related to implementation of the past practice in the one or more subject agricultural fields;
generating one or more agricultural messages based on the one or more inferences, wherein the one or more agricultural messages includes a recommendation for an agricultural operation to be performed with respect to the one or more subject agricultural fields in response to the detected agricultural event; and
pushing the one or more agricultural messages to one or more client computing devices.
2 . The method of claim 1 , wherein the one or more proactively performed operations include proactively causing at least one of the one or more client computing devices to solicit identification of and/or access to the one or more of the data sources controlled by the agricultural entity.
3 . The method of claim 1 , wherein detecting that the agricultural event has occurred includes detecting one or more changes to the agricultural knowledge graph, wherein the one or more changes corresponds to the agricultural event being included as data in a location corresponding to the nearby agricultural field.
4 . The method of claim 3 , wherein the agricultural event includes a weather event, and the one or more changes to the agricultural knowledge graph include onboarding of new weather data describing the weather event.
5 . The method of claim 3 , wherein the agricultural event includes a valuation of a type of crop grown in the nearby agricultural field, and the one or more changes to the agricultural knowledge graph include onboarding of new data describing the valuation.
6 . The method of claim 1 , wherein the agricultural event includes a presence of a computing device carried by an agricultural worker being detected in the nearby agricultural field.
7 . The method of claim 1 , wherein identifying the plurality of nodes includes traversing the agricultural knowledge graph from the one or more field nodes representing the subject agricultural fields to another field node representing the nearby agricultural field.
8 . The method of claim 1 , wherein the agricultural event includes one or more of an application of an herbicide or an application of a pesticide.
9 . The method of claim 1 , wherein the agricultural event includes one or more of an incidence of a plant disease or a pest infestation.
10 . The method of claim 1 , wherein the detected agricultural event is crop yield that is predicted to fall below a threshold, the recommendation includes to perform the agricultural operation to increase the crop yield, the agricultural operation to correspond to a remedial action for the one or more subject agricultural fields.
11 . The method of claim 1 , wherein to detect that the agricultural event has occurred the one or more processors are to detect one or more changes to the agricultural knowledge graph, wherein the one or more changes corresponds to the agricultural event being included as data in a location corresponding to the nearby agricultural field.
12 . A system comprising one or more processors and memory storing instructions that, in response to execution by the one or more processors, cause the one or more processors to:
detect that an agricultural event has occurred, wherein the agricultural event is detected when new data is included in an agricultural knowledge graph in relation to an event that occurs in a nearby agricultural field that is adjacent to, or within a predetermined distance of, one or more subject agricultural fields;
in response to detection of the agricultural event, proactively perform the following operations:
identify a plurality of nodes of the agricultural knowledge graph as related to the agricultural event, wherein the agricultural knowledge graph includes nodes connected by edges that represent semantic relationships between the nodes, and wherein the plurality of identified nodes includes one or more field nodes representing the one or more subject agricultural fields, one or more field nodes representing the nearby agricultural field to which the agricultural event is relevant, and one or more other nodes connected to the one or more field nodes by one or more edges, wherein the one or more other nodes correspond to past practices implemented in the nearby agricultural field;
access one or more machine learning models based on one or more of the plurality of identified nodes or the one or more edges that connect two or more of the plurality of identified nodes, wherein at least one of the one or more machine learning models generates inferences related to a past practice of the past practices;
retrieve data from one or more data sources controlled by an agricultural entity, wherein the one or more data sources contain data that is relevant to the one or more subject agricultural fields;
process the retrieved data based on the one or more machine learning models to generate one or more inferences about the one or more subject agricultural fields, the one or more inferences related to implementation of the past practice in the one or more subject agricultural fields;
generate one or more agricultural messages based on the one or more inferences, wherein the one or more agricultural messages includes a recommendation for an agricultural operation to be performed with respect to the one or more subject agricultural fields in response to the detected agricultural event; and
push the one or more agricultural messages to one or more client computing devices.
13 . The system of claim 12 , wherein the one or more proactively performed operations include to proactively cause at least one of the one or more client computing devices to solicit identification of and/or access to the one or more data sources controlled by the agricultural entity.
14 . The system of claim 12 , wherein the agricultural event is detected based on one or more changes to the agricultural knowledge graph, wherein the one or more changes corresponds to the agricultural event being included as data in a location corresponding to the nearby agricultural field.
15 . The system of claim 14 , wherein the agricultural event includes a weather event, and the one or more changes to the agricultural knowledge graph include onboarding of new weather data describing the weather event.
16 . The system of claim 14 , wherein the agricultural event includes a valuation of a type of crop grown in the nearby agricultural field, and the one or more changes to the agricultural knowledge graph include onboarding of new data describing the valuation.
17 . The system of claim 12 , wherein the agricultural event includes a presence of a computing device carried by an agricultural worker being detected in the nearby agricultural field.
18 . The system of claim 12 , wherein the plurality of nodes are identified by traversing the agricultural knowledge graph from the one or more field nodes representing the subject agricultural fields to another field node representing the nearby agricultural field.
19 . At least one non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to:
detect that an agricultural event has occurred, wherein the agricultural event is detected when new data is included in an agricultural knowledge graph in relation to an event that occurs in a nearby agricultural field that is adjacent to, or within a predetermined distance of, one or more subject agricultural fields; and
in response to detection that the agricultural event has occurred, proactively perform the following operations:
identify a plurality of nodes of the agricultural knowledge graph as related to the agricultural event, wherein the agricultural knowledge graph includes nodes connected by edges that represent semantic relationships between the nodes, and wherein the plurality of identified nodes includes one or more field nodes representing the one or more subject agricultural fields, one or more field nodes representing the nearby agricultural field to which the agricultural event is relevant, and one or more other nodes connected to the one or more field nodes by one or more edges, wherein the one or more other nodes correspond to past practices implemented in the nearby agricultural field;
access one or more machine learning models based on one or more of the plurality of identified nodes or the one or more edges that connect two or more of the plurality of identified nodes, wherein at least one of the one or more machine learning models generates inferences related to a past practice of the past practices;
retrieve data from one or more data sources controlled by an agricultural entity, wherein the one or more data sources contain data that is relevant to the one or more subject agricultural fields;
process the retrieved data based on the one or more machine learning models to generate one or more inferences about the one or more subject agricultural fields, the one or more inferences related to implementation of the past practice in the one or more subject agricultural fields;
generate one or more agricultural messages based on the one or more inferences, wherein the one or more agricultural messages includes a recommendation for an agricultural operation to be performed with respect to the one or more subject agricultural fields in response to the detected agricultural event; and
push the one or more agricultural messages to one or more client computing devices.
20 . The non-transitory computer-readable medium of claim 19 , wherein the one or more proactively performed operations include to proactively cause at least one of the one or more client computing devices to solicit identification of and/or access to the one or more of the data sources controlled by the agricultural entity.