Manage and control pests infestation using machine learning in conjunction with automated devices

Patent metadata

Field	Value
Publication number	US-11564384-B2
Application number	US-201816010878-A
Country	US
Kind code	B2
Filing date	Jun 18, 2018
Priority date	Jun 18, 2018
Publication date	Jan 31, 2023
Grant date	Jan 31, 2023

Abstract

Embodiments of the present invention provides a systems and methods for pest control. The system detects one or more pests based on receiving sensor data from one or more sensors associated with a predefined location. The system analyzes the sensor data with cognitive machine learning based on the detected pests. The system generates a treatment recommendation report based on the analysis and outputs the treatment recommendation report.

First claim

What is claimed is:

1. A method for pest control, the method comprising:
detecting one or more pests based on receiving sensor data from one or more sensors associated with a predefined location, wherein detecting the one or more pests comprising:
receiving an auditory pattern based on the one or more pests by the one or more sensors wherein the auditory pattern comprises sounds made by the one or more pests;
determining a pest type based on the received auditory pattern;
responsive to determining the pest type, identifying the one or more pests; and
responsive to not able to determine the pest type, verifying the one or more pests based on visual identification from the one or more sensors;

analyzing the sensor data with cognitive machine learning based on the detected pests;
generating a treatment recommendation report based on the analysis; and
outputting the treatment recommendation report.

2. The method of claim 1 , wherein the sounds made by the one or more pests consisting of wingbeat pattern of certain insects, chewing woods and sound of larvae merging from their cocoon stage.

3. The method of claim 1 , wherein analyzing the sensor data with cognitive machine learning based on the detected pests further comprises:
aggregating the one or more sensor data, a reference data, a first database, and climate data, wherein the first database comprises historical data;
selecting a pest control method based on the identified one or more pests, wherein the pest control method comprises at least one of pesticides, traps, and biological predators; and
calculating action plan to apply the pest control method.

4. The method of claim 3 , further comprises:
retrieving data from the first database, wherein the data comprises one or more previous treatment plans.

5. The method of claim 1 , wherein outputting the treatment recommendation report further comprises:
sending the treatment recommendation report to one or more users and awaiting user response;
responsive to user deciding to ignore the treatment recommendation report, saving the report to a first database; and
responsive to user deciding perform a pest control method manually based on the treatment recommendation report, saving the report to a first database.

6. The method of claim 5 , further comprises:
responsive to user deciding to allow automatic treatment, sending an autonomous device to perform a pest control method based on the treatment recommendation report.

7. The method of claim 1 , wherein the one or more sensors comprise at least one of a camera, a microphone, or a drone.

8. A computer program product for pest control, the computer program product comprising:
one or more computer readable storage devices and program instructions stored on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to detect one or more pests based on receiving sensor data from one or more sensors associated with a predefined location, wherein program instructions to detect the one or more pests comprising:
program instructions to receive an auditory pattern based on the one or more pests by the one or more sensors wherein the auditory pattern comprises sounds made by the one or more pests;
program instructions to determine a pest type based on the received auditory pattern;
responsive to determining the pest type, program instructions to identify the one or more pests; and
responsive to not able to determine the pest type, program instructions to verify the one or more pests based on visual identification from the one or more sensors:

program instructions to analyze the sensor data with cognitive machine learning based on the detected pests;
program instructions to generate a treatment recommendation report based on the analysis; and
program instructions to output the treatment recommendation report.

9. The computer program product of claim 8 , wherein the sounds made by the one or more pests consisting of wingbeat pattern of certain insects, chewing woods and sound of larvae merging from their cocoon stage.

10. The computer program product of claim 8 , wherein program instructions to analyze the sensor data with cognitive machine learning based on the detected pests further comprises:
program instructions to aggregate the one or more sensor data, a reference data, a first database, and climate data, wherein the first database comprises historical data;
program instructions to select a pest control method based on the identified one or more pests, wherein the pest control method comprises at least one of pesticides, traps, and biological predators; and
program instructions to calculate action plan to apply the pest control method.

11. The computer program product of claim 10 , the stored program instructions further comprises:
program instructions to retrieve data from the first database, wherein the data comprises one or more previous treatment plans.

12. The computer program product of claim 8 , wherein program instructions to output the treatment recommendation report further comprises:
program instructions to send the treatment recommendation report to one or more users and awaiting user response;
responsive to user deciding to ignore the treatment recommendation report, program instructions to save the report to a first database; and
responsive to user deciding perform a pest control method manually based on the treatment recommendation report, program instructions to save the report to a first database.

13. The computer program product of claim 12 , the stored program instructions further comprises:
responsive to user deciding to allow automatic treatment, program instructions to send an autonomous device to perform a pest control method based on the treatment recommendation report.

14. The computer program product of claim 8 , wherein the one or more sensors comprise at least one of a camera, a microphone, or a drone.

15. A computer system for pest control, the computer system comprising:
one or more computer processors;
one or more computer readable storage devices;
program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the stored program instructions comprising:
program instructions to detect one or more pests based on receiving sensor data from one or more sensors associated with a predefined location, wherein program instructions to detect the one or more pests comprising:
program instructions to receive an auditory pattern based on the one or more pests by the one or more sensors wherein the auditory pattern comprises sounds made by the one or more pests;
program instructions to determine a pest type based on the received auditory pattern;
responsive to determining the pest type, program instructions to identify the one or more pests; and
responsive to not able to determine the pest type, program instructions to verify the one or more pests based on visual identification from the one or more sensors:

program instructions to analyze the sensor data with cognitive machine learning based on the detected pests;
program instructions to generate a treatment recommendation report based on the analysis; and
program instructions to output the treatment recommendation report.

16. The computer system of claim 15 , wherein the sounds made by the one or more pests consisting of wingbeat pattern of certain insects, chewing woods and sound of larvae merging from their cocoon stage.

17. The computer system of claim 1

Assignees

• IBM

Inventors

• Bender Michael
• Childress Rhonda L
• Daley Stan K

Classifications

• G06N20/00

  Machine learning · CPC title

• A01M99/00

  Subject matter not provided for in other groups of this subclass · CPC title

• A01M1/20

  Poisoning, narcotising, or burning insects {(fumigation apparatus A01M13/00)} · CPC title

• G06Q50/10

  Services · CPC title

• G06N5/04

  Inference or reasoning models · CPC title