Back to results
US 12,718,524 B2Granted
Artificial intelligence for animal identification based on animal behavior
AssigneeToshiba Global Commerce Solutions, Inc.
InventorsEvgeny Shevtsov, John Pistone, Philip S. Brown, Leon T. Cain, II, Vladyslav Kolbasin
Life of this patent
Estimating the term…
Abstract
Techniques for animal identification based on animal behavior. A first video depicting a first animal associated with a user during a first visit to an enterprise location is received. One or more attributes pertaining to the first animal or to the user are received. A first behavior of the first animal as depicted in the first video is extracted and encoded into a first behavioral representation. One or more machine learning models are trained to identify the first animal based on the first behavioral representation and the one or more attributes.
Claims20
A computer-implemented method comprising:
- receiving a first video depicting a first animal associated with a user during a first visit, by the user, to a first enterprise location, the first animal being of a given type, wherein the first video is captured to facilitate enrolling the first animal in an identification program;
- receiving one or more attributes during the first visit, wherein the one or more attributes pertain to the first animal;
- associating the first animal with the user, wherein an indication of the association is stored;
- extracting a first behavior of the first animal as depicted in the first video, wherein the first behavior comprises a measure of physical action and movement exerted by the first animal within a physical proximity and during a predetermined reference period of time;
- encoding the first behavior comprising the measure of physical action and movement exerted by the first animal within the physical proximity and during the predetermined reference period of time into the first behavioral representation;
- training one or more machine learning models to uniquely identify the first animal based on the first behavioral representation and the one or more attributes;
- receiving one or more images depicting a second animal during a second visit, by the user, to a second enterprise location, wherein the second visit is subsequent in time to the first visit, wherein the first and second enterprise locations are selected from the same enterprise location or different enterprise locations;
- determining, by an application using the one or more machine learning models and based on the one or more images, that the first and second animals are the same animal;
- and
- responsive to determining that the first and second animals are the same animal, identifying the user based on the association, and wherein identifying the user facilitates a transaction pertaining to the same animal at the second enterprise location.
7 more elements
A non-transitory computer-readable medium containing a program executable to perform an operation comprising:
- receiving a first video depicting a first animal associated with a user during a first visit, by the user, to a first enterprise location, the first animal being of a given type, wherein the first video is captured to facilitate enrolling the first animal in an identification program;
- receiving one or more attributes during the first visit, wherein the one or more attributes pertain to the first animal;
- associating the first animal with the user, wherein an indication of the association is stored;
- extracting a first behavior of the first animal as depicted in the first video, wherein the first behavior comprises a measure of physical action and movement exerted by the first animal within a physical proximity and during a predetermined reference period of time;
- encoding the first behavior comprising the measure of physical action and movement exerted by the first animal within the physical proximity and during the predetermined reference period of time into the first behavioral representation;
- training one or more machine learning models to uniquely identify the first animal based on the first behavioral representation and the one or more attributes;
- receiving one or more images depicting a second animal during a second visit, by the user, to a second enterprise location, wherein the second visit is subsequent in time to the first visit, wherein the first and second enterprise locations are selected from the same enterprise location or different enterprise locations;
- and
- upon determining, by the program using the one or more machine learning models and based on the one or more images, that the first and second animals are the same animal, identifying the user based on the association, and wherein identifying the user facilitates a transaction pertaining to the same animal at the second enterprise location.
6 more elements
A system comprising:
- one or more computer processors;
- and
- a memory containing a program executable by the one or more computer processors to perform an operation comprising:
- receiving a first video depicting a first animal associated with a user during a first visit, by the user, to a first enterprise location, the first animal being of a given type, wherein the first video is captured to facilitate enrolling the first animal in an identification program;
- receiving one or more attributes during the first visit, wherein the one or more attributes pertain to the first animal;
- associating the first animal with the user, wherein an indication of the association is stored;
- extracting a first behavior of the first animal as depicted in the first video, wherein the first behavior comprises a measure of physical action and movement exerted by the first animal within a physical proximity and during a predetermined reference period of time;
- encoding the first behavior comprising the measure of physical action and movement exerted by the first animal within the physical proximity and during the predetermined reference period of time into the first behavioral representation;
- training one or more machine learning models to uniquely identify the first animal based on the first behavioral representation and the one or more attributes;
- receiving one or more images depicting a second animal during a second visit, by the user, to a second enterprise location, wherein the second visit is subsequent in time to the first visit, wherein the first and second enterprise locations are selected from the same enterprise location or different enterprise locations;
- and
- upon determining, by the program using the one or more machine learning models and based on the one or more images, that the first and second animals are the same animal, identifying the user based on the association, and wherein identifying the user facilitates a transaction pertaining to the same animal at the second enterprise location.
9 more elements
Dependencies are inferred from the claim text.