Patent · US Active

Pest detector to identify a type of pest using machine learning

US11234429B2 · kind B2 · utility

6Cited by
8References
20Claims
0Family size

Inventors

Key dates

Filing dateJun 10, 2020
Grant dateFeb 1, 2022
Priority date
Expiry dateJul 8, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/20
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In some implementations, a pest detector may receive sensor data from a sensor. The pest detector may determine, using a machine learning algorithm, that the sensor data indicates a presence of a first type of pest. The pest detector may send a notification message, including at least a portion of the sensor data, to a computing device and visually indicate that the first type of pest was detected using an indicator. The pest detector may receive an update to the machine learning algorithm from a server and install the update to create an updated machine learning algorithm. The pest detector may receive second sensor data and determine, using the updated machine learning algorithm, that the second sensor data indicates the presence of a second type of pest that is not recognized by the machine learning algorithm.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.