US-12626805-B2 - System, method, and apparatus for pet condition detection

Abstract

In one embodiment, a method includes accessing sensor data captured by sensors, wherein the sensor data is associated with a first pet, detecting activities of the first pet within a specified time period based on the sensor data, determining health indicators of the first pet based on one or more of the activities, wherein the health indicators are based on metrics associated with the one or more activities, generating a wellness assessment of the first pet based on the health indicators, wherein the wellness assessment comprises one or more of a wellness score or an alert of a possible medical condition, and sending instructions to a user device for presenting the wellness assessment of the first pet to a user.

Inventors

• Aletha CARSON
• Robert Donald Chambers
• Nathanael Christian Yoder

Assignees

• Tractive Inc.

Dates

Publication Date

20260512

Application Date

20220419

Claims (20)

1. 1 . A method for generating a wellness assessment of a pet based on sensor data comprising, by one or more computing systems: receiving, by one or more processors, sensor data associated with a pet from one or more sensors, wherein the one or more sensors are associated with a wearable device worn by or attached to the pet, the sensor data including: a time value corresponding to when the pet performed an activity, and an intensity point corresponding to when the pet performed the activity; detecting, by the one or more processors, an orientation of the wearable device, wherein the orientation is calculated based on rotation data of the wearable device; transforming, by the one or more processors, the sensor data into a consistent coordinate system based on the orientation of the wearable device, wherein transforming the sensor data includes modifying the sensor data based on the rotation data; executing, by the one or more processors, an algorithm to generate a baseline value for the activity based on aggregated activity data of a plurality of similar pets, wherein the plurality of similar pets comprises pet data of a same pet breed, a same pet age, or a same pet weight as the pet; predicting, by the one or more processors, one or more health indicators corresponding to the pet based on the transformed sensor data, wherein the one or more health indicators include one or more metrics associated with the activity; executing, by the one or more processors, the algorithm on the one or more health indicators to generate a wellness assessment of the pet, wherein the wellness assessment includes an energy expenditure wellness value of the pet determined based on the time value the pet performed the activity at the intensity point compared to a goal intensity point, wherein the goal intensity point is calculated based on the baseline value for the activity and the received intensity point for the pet; determining, by the one or more processors, a pet recommendation by inputting the wellness assessment of the pet into a prediction module trained on previous pet data corresponding to the pet, wherein the pet recommendation includes a medical recommendation or a product recommendation; and transmitting, by the one or more processors, an alert that includes the pet recommendation to a user interface of a user device.
2. 2 . The method of claim 1 , wherein the one or more sensors further comprise one or more of an actuator, a gyroscope, a magnetometer, a microphone, or a pressure sensor.
3. 3 . The method of claim 1 , wherein detecting the orientation of the wearable device further comprises: training, by the one or more processors, a convolutional neural network with training data to determine an orientation of the wearable device on a pet collar, wherein the training data is associated with a known orientation of the wearable device.
4. 4 . The method of claim 1 , wherein generating the wellness assessment of the pet further comprises: training, by the one or more processors, the prediction module based on one or more of health status data, demographic information, genetic data, location, weather information of the location, or environment data of the location.
5. 5 . The method of claim 1 , further comprising: comparing, by the one or more processors, at least one of the predicted health indicators to at least one stored corresponding health indicator; and detecting, by the one or more processors, a threshold difference between the at least one predicted health indicator and the at least one stored corresponding health indicator; wherein the wellness assessment further comprises the detected threshold difference between the at least one predicted health indicator and the at least one stored corresponding health indicator.
6. 6 . The method of claim 1 , wherein the method further comprises: rescaling, by the one or more processors, one or more of the metrics into a predetermined range; and generating, by the one or more processors, the one or more energy expenditure wellness values based on the one or more rescaled metrics.
7. 7 . The method of claim 1 , wherein the one or more health indicators are associated with one or more weights, respectively, wherein the method further comprises: generating, by the one or more processors, the one or more energy expenditure wellness values based on the one or more weights.
8. 8 . The method of claim 1 , wherein the activity comprises one or more of: a posture comprising one or more of a lying down posture, a sitting posture, a standing posture, a walking posture, or a vigorous posture; or a behavior comprising one or more of a drinking behavior, an eating behavior, a licking an object behavior, a self-licking behavior, a petting behavior, a rubbing behavior, a scratching behavior, a shaking behavior, or a sniffing behavior.
9. 9 . The method of claim 1 , wherein the medical recommendation corresponds to a medical condition including at least one of: a dermatological condition, an ear infection, arthritis, a cardiac episode, a gastrointestinal condition, malaise, a tooth fracture, a cruciate ligament tear, or a pancreatic episode.
10. 10 . The method of claim 1 , wherein the wellness assessment comprises one or more alerts of a possible medical condition, wherein the method further comprises: generating an estimated timeline for the possible medical condition; and presenting, via the user interface on the user device, the estimated timeline.
11. 11 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to: receive sensor data associated with a pet captured by one or more sensors, wherein the one or more sensors are associated with a wearable device worn by or attached to the pet, the sensor data including: a time value corresponding to when the pet performed an activity, and an intensity point corresponding to when the pet performed the activity- detect an orientation of the wearable device, wherein the orientation is calculated based on rotation data of the wearable device; transform the sensor data into a consistent coordinate system based on the orientation of the wearable device, wherein transforming the sensor data includes modifying the sensor data based on the rotation data; execute an algorithm to generate a baseline value for the activity based on aggregated activity data of a plurality of similar pets, wherein the plurality of similar pets comprises pet data of a same pet breed, a same pet age, or a same pet weight as the pet; predict one or more health indicators corresponding to the pet based on the transformed sensor data, wherein the one or more health indicators include one or more metrics associated with the activity; execute the algorithm on the one or more health indicators to generate a wellness assessment of the pet, wherein the wellness assessment includes an energy expenditure wellness value of the pet determined based on the time value the pet performed the activity at the intensity point compared to a goal intensity point, wherein the goal intensity point is calculated based on the baseline value for the activity and the received intensity point for the pet; determine a pet recommendation by inputting the wellness assessment of the pet into a prediction module trained on previous pet data corresponding to the pet, wherein the pet recommendation includes a medical recommendation or a product recommendation; and transmit an alert that includes the pet recommendation to a user interface of a user device.
12. 12 . A system comprising: one or more processors; and a memory storing instructions that, when executed by the one or more processors, cause the processors to: receive sensor data associated with a pet captured by one or more sensors, wherein the one or more sensors are associated with a wearable device worn by or attached to the pet, the sensor data including: a time value corresponding to when the pet performed an activity, and an intensity point corresponding to when the pet performed the activity- detect an orientation of the wearable device, wherein the orientation is calculated based on rotation data of the wearable device; transform the sensor data into a consistent coordinate system based on the orientation of the wearable device, wherein transforming the sensor data includes modifying the sensor data based on the rotation data; execute an algorithm to generate a baseline value for the activity based on aggregated activity data of a plurality of similar pets, wherein the plurality of similar pets comprises pet data of a same pet breed, a same pet age, or a same pet weight as the pet; predict one or more health indicators corresponding to the pet based on the transformed sensor data, wherein the one or more health indicators include one or more metrics associated with the activity; execute the algorithm on the one or more health indicators to generate a wellness assessment of the pet, wherein the wellness assessment includes an energy expenditure wellness value of the pet determined based on the time value the pet performed the activity at the intensity point compared to a goal intensity point, wherein the goal intensity point is calculated based on the baseline value for the activity and the received intensity point for the pet; determine a pet recommendation by inputting the wellness assessment of the pet into a prediction module trained on previous pet data corresponding to the pet, wherein the pet recommendation includes a medical recommendation or a product recommendation; and transmit an alert that includes the pet recommendation to a user interface of a user device.
13. 13 . The system of claim 12 , wherein the one or more sensors further comprise one or more of an actuator, a gyroscope, a magnetometer, a microphone, or a pressure sensor.
14. 14 . The system of claim 12 , wherein the instructions, when executed, further cause the one or more processors to: train a convolutional neural network with training data to determine an orientation of the wearable device on the pet collar, wherein the training data is associated with a known orientation of the wearable device.
15. 15 . The system of claim 12 , wherein the instructions, when executed, further cause the one or more processors to: train the prediction module based on one or more of health status data, demographic information data, genetic data, location data, weather information data of the location, or environment data of the location.
16. 16 . The system of claim 12 , wherein the instructions, when executed, further cause the one or more processors to: compare at least one of the predicted health indicators to at least one stored corresponding health indicator; and detect a threshold difference between the at least one predicted health indicator and the at least one stored corresponding health indicator; wherein the wellness assessment further comprises the detected threshold difference between the at least one predicted health indicator and the at least one stored corresponding health indicator.
17. 17 . The system of claim 12 , wherein the instructions, when executed, further cause the one or more processors to: rescale one or more of the metrics into a predetermined range; and generate the one or more energy expenditure wellness values based on the one or more rescaled metrics.
18. 18 . The system of claim 12 , wherein the one or more health indicators are associated with one or more weights, respectively, wherein the instructions, when executed, further cause the one or more processors to: generate the one or more energy expenditure wellness values based on the one or more weights.
19. 19 . The system of claim 12 , wherein the activity comprises one or more of: a posture comprising one or more of a lying down posture, a sitting posture, a standing posture, a walking posture, or a vigorous posture; or a behavior comprising one or more of a drinking behavior, an eating behavior, a licking an object behavior, a self-licking behavior, a petting behavior, a rubbing behavior, a scratching behavior, a shaking behavior, or a sniffing behavior.
20. 20 . The system of claim 12 , wherein the medical recommendation corresponds to a medical condition including at least one of: a dermatological condition, an ear infection, arthritis, a cardiac episode, a gastrointestinal condition, malaise, a tooth fracture, a cruciate ligament tear, or a pancreatic episode.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a U.S. National Stage Patent Application under 35 U.S.C. § 371 of International Patent Application No. PCT/US2022/025368, filed Apr. 19, 2022, which claims the benefit, under 35 U.S.C. § 119(e), of U.S. Provisional Patent Application No. 63/176,812, filed 19 Apr. 2021, both of which are incorporated herein by reference. TECHNICAL FIELD The embodiments described in the disclosure relate to monitoring of pet activity. For example, some non-limiting embodiments relate to monitoring of pet activity to help detect a health condition of a pet. BACKGROUND Mobile devices and/or wearable devices have been fitted with various hardware and software components that can help track or monitor human activity. The data resulting from the monitored activity can be collected, analyzed, and displayed. For example, a mobile device and/or wearable devices can be used to track the number of steps or the heart rate of a human during a given period of time. The number of steps or heart rate can then be displayed on a user graphic interface of the mobile device or wearable device. Beyond human monitoring, the ever-growing emphasis on pet safety and health has resulted in an increased need to monitor pet behavior. Accordingly, there is an ongoing demand in the pet product industry for a system and/or method for monitoring pet activity. SUMMARY OF PARTICULAR EMBODIMENTS The purpose and advantages of the disclosed subject matter will be set forth in and apparent from the description that follows, as well as will be learned by practice of the disclosed subject matter. Additional advantages of the disclosed subject matter will be realized and attained by the methods and systems particularly pointed out in the written description and claims hereof, as well as from the appended drawings. To achieve these and other advantages, and in accordance with the purpose of the disclosed subject matter, as embodied and broadly described, the disclosed subject matter presents systems, methods, and apparatuses that can be used to collect, receive and/or analyze data. For example, certain non-limiting embodiments can be used to monitor and track pet activity. In certain non-limiting embodiments, the disclosure describes a method for monitoring pet activity and determining pet wellness accordingly. The method includes determining one or more health indicators of a pet based on collected, received and/or analyzed data. The method also includes performing a wellness assessment of the pet based on the one or more health indicators of the pet. In addition, the method includes displaying one or more notifications to a pet owner based on the wellness assessment of the pet at a mobile device. In certain non-limiting embodiments, one or more computing systems can access sensor data captured by one or more sensors. The sensor data can be associated with a first pet. The computing systems can then detect, based on the sensor data, one or more activities of the first pet within a specified time period. The computing systems can then determine, based on one or more of the activities, one or more health indicators of the first pet. In certain non-limiting embodiments, the one or more health indicators can be based on one or more metrics associated with the one or more of the activities. The computing systems can further generate a wellness assessment of the first pet based on the one or more health indicators. The wellness assessment can comprise one or more of a wellness score or an alert of a possible medical condition from a plurality of medical conditions. In certain non-limiting embodiments, the computing systems can then send, to a user device, instructions for presenting the wellness assessment of the first pet to a user. In certain non-limiting embodiments, one or more computer-readable non-transitory storage media embodying software is operable when executed to access sensor data captured by one or more sensors. The sensor data can be associated with a first pet. The computer-readable non-transitory storage media embodying software is further operable when executed to detect, based on the sensor data, one or more activities of the first pet within a specified time period. The computer-readable non-transitory storage media embodying software is further operable when executed to determine, based on one or more of the activities, one or more health indicators of the first pet. In some embodiments, the one or more health indicators can be based on one or more metrics associated with the one or more of the activities. The computer-readable non-transitory storage media embodying software is further operable when executed to generate a wellness assessment of the first pet based on the one or more health indicators. In some embodiments, the wellness assessment can comprise one or more of a wellness score or an alert of a possible medical condition from a plurality of medical conditions. The computer-readab