Granted Patent B2

US 12,611,066 · App. 18/208,100 · Granted Apr 28, 2026

Inventor: Glen Harrison Ruggiero (Charlestown, MA)

Assignee: SharkNinja Operating LLC

A47J43/085A47J43/046A47J2043/0733

Abstract

Claims (72)

1 . A blender comprising:

a controllable component coupled to one or more components configured to process one or more food items, wherein the controllable component comprises a motor;

a monitoring device configured to detect at least one property associated with the processing of the one or more food items during a first period of time, wherein a first series of detection signals are generated from the at least one property detected over the first period of time, and wherein the first series of detection signals comprises a time series of values of power consumption of the motor while processing of the one or more food items during the first period of time;

a memory configured to store a first plurality of food item vectors, each food item vector defining values for a plurality of features in a multi-dimensional feature space, each of the first plurality of food item vectors being associated with a type of food item; and

a controller, configured to control operations of the controllable component, is further configured to:

receive the time series of values of power consumption of the motor;

calculate a detection vector based on the time series of values of power consumption of the motor, the detection vector defining feature values for a plurality of features in the multi-dimensional feature space;

in response to calculating the detection vector, identify one or more types of food items associated with the detection vector, wherein, when identifying the one or more types of food items associated with the detection vector, the controller is configured to:

determine a location of the detection vector in the multi-dimensional feature space relative to positions of one or more of the first plurality of food item vectors, respectively, in the multi-dimensional feature space

compare the location of the detection vector with a location of one or more of the first plurality of food item vectors within a multi-dimensional feature space; and

determine one or more food item vectors of the plurality of food item vectors that are closest to the detection vector in the multi-dimensional feature space, wherein the one or more food item vectors corresponds to the one or more types of food items;

in response to identifying the one or more types of food items:

determine one or more actions based at least in part on the one or more types of food items; and

determine a second period of time based on the location of one or more of the first plurality of food item vectors with respect to the detection vector; and

control operation of the controllable component based at least in part on the-one or more actions, wherein, when controlling operation of the controllable component, the controller is configured to:

operate the controllable component for the second period of time based on the one or more types of food items.

2 . The blender of claim 1 , wherein the controllable component includes the motor and the operating the motor includes rotating the motor.

3 . The blender of claim 1 , wherein the identifying of the food item includes performing a K-NN analysis.

4 . The blender of claim 1 , wherein the monitoring device includes at least one of a current sensor, voltage sensor, motor speed sensor, pressure sensor, and temperature sensor.

5 . The blender of claim 1 , wherein calculating the detection vector includes calculating one or more feature values defining the detection vector, and

wherein a first of the one or more feature values is a gradient of a curve defined by the first series of detection signals.

6 . The blender of claim 1 , wherein detecting the at least one property associated with the processing of the one or more food items during the first period of time includes detecting at least one of a current or voltage associated with operation of the controllable component over the first period of time.

7 . The blender of claim 1 , wherein detecting at least one property associated with the processing of the one or more food items includes determining a type and/or size of the one or more components, and

wherein the controller is configured to control the controllable component based at least in part on the type and/or size of one of the components.

8 . The blender of claim 1 , wherein the controller is further configured to identify the one or more types of food items associated with the detection vector by determining the position of the detection vector in the multi-dimensional feature space with respect to positions of two or more of the first plurality of food item vectors in the multi-dimensional feature space.

9 . The blender of claim 8 , wherein the controller is configured to control the operation based on applying a weight factor to each of the two or more of the first plurality of food item vectors, the weight factor being based on at least one of a distance of a food item vector from the detection vector, a frequency of determining a type of food item, or a type of container used during food processing.

10 . The blender of claim 1 , wherein the controller is further configured to:

classify a first subset of the one or more food item vectors as a first category of food items; and

control the controllable component based at least in part on determining that the position of the detection vector in the multi-dimensional feature space is within a first area of the multi-dimensional feature space associated with the first category of food items.

11 . The blender of claim 10 , wherein the controller is further configured to:

classify a second subset of the one or more food items vectors as a second category of food items; and

control the controllable component based at least in part on determining that the position of the detection vector in the multi-dimensional feature space is within a second area of the multi-dimensional feature space associated with the second category of food items.

12 . The blender of claim 1 , wherein each of a feature values for a plurality of features in the multi-dimensional feature space are selected from a group including: a peak value detected for the at least one property in the first series of signals, a drop between values detected for the at least one property in the first series of signals, a standard deviation of values detected for the at least one property in the first series of signals, and a value detected for the at least one property at a particular point in time in the first series of signals.

13 . The blender of claim 1 , wherein, when operating the controllable component for the second period of time, the controller is configured to:

rotate the controllable component for the second period of time.

14 . The blender of claim 13 , wherein the second period of time is less than 30 seconds.

15 . The blender of claim 1 , wherein, when operating the controllable component for the second period of time, the controller is configured to:

rotate the motor for the second period of time; and

stop rotating the motor after the second period of time expires.

16 . A method for blending food items via a controllable component configured to process one or more food items comprising:

operating the controllable component for a first period of time, wherein the controllable component comprises a motor;

detecting, via a monitoring device, at least one property associated with the processing of the one or more food items during the first period of time, wherein a first series of detection signals are generated from the at least one property detected over the first period of time, and wherein the first series of detection signals comprises a time series of values of power consumption of the motor while processing of the one or more food items during the first period of time;

storing, in a memory, a first plurality of food item vectors, each food item vector defining values for a plurality of features in a multi-dimensional feature space, each of the first plurality of food item vectors being associated with a type of food item;

receiving the time series of values of power consumption of the motor;

calculating a detection vector based on the time series of values of power consumption of the motor, the detection vector defining feature values for a plurality of features in the multi-dimensional feature space;

in response to calculating the detection vector, identifying one or more types of food items associated with the detection vector, wherein identifying the one or more types of food items associated with the detection vector comprises:

determining a location of the detection vector in the multi-dimensional feature space relative to positions of one or more of the first plurality of food item vectors, respectively, in the multi-dimensional feature space;

comparing the location of the detection vector with a location of one or more of the first plurality of food item vectors within a multi-dimensional feature space; and

determining one or more food item vectors of the plurality of food item vectors that are closest to the detection vector in the multi-dimensional feature space, wherein the one or more food item vectors corresponds to the one or more types of food items;

in response to identifying the one or more types of food items:

determining one or more actions based at least in part on the one or more types of food items; and

determining a second period of time based on the location of one or more of the first plurality of food item vectors with respect to the detection vector; and

controlling operation of the controllable component based at least in part on the one or more actions, wherein controlling operation of the controllable component comprises:

operating the controllable component for the second period of time based on the one or more types of food items based on the one or more types of food items.

17 . The method of claim 16 , wherein the controllable component includes the motor and operating the motor includes rotating the motor.

18 . The method of claim 16 , wherein the identifying of the food item includes performing a K-NN analysis.

19 . The method of claim 16 , comprising identifying the one or more types of food items associated with the detection vector by determining which one of the first plurality of food item vectors is closest to the detection vector in the multi-dimensional feature space.

20 . A non-transitory computer-readable storage medium storing instructions including a plurality of food processing instructions associated with a food processing sequence which when executed by a computer cause the computer to perform a method for processing food items using a food processor via a controllable component configured to process one or more food items, the method comprising:

operating the controllable component for a first period of time, wherein the controllable component comprises a motor;

detecting, via a monitoring device, at least one property associated with the processing of the one or more food items during the first period of time, wherein a first series of detection signals are generated from the at least one property detected over the first period of time, and wherein the first series of detection signals comprises a time series of values of power consumption of the motor while processing of the one or more food items during the first period of time;

storing, in a memory, a first plurality of food item vectors, each food item vector defining values for a plurality of features in a multi-dimensional feature space, each of the first plurality of food item vectors being associated with a type of food item;

receiving the time series of values of power consumption of the motor;

calculating a detection vector based on the time series of values of power consumption of the motor, the detection vector defining feature values for a plurality of features in the multi-dimensional feature space;

identifying one or more types of food items associated with the detection vector, wherein identifying the one or more types of food items associated with the detection vector comprises:

determining a location of the detection vector in the multi-dimensional feature space relative to positions of one or more of the first plurality of food item vectors, respectively, in the multi-dimensional feature space;

comparing the location of the detection vector with a location of one or more of the first plurality of food item vectors within a multi-dimensional feature space; and

determining one or more food item vectors of the plurality of food item vectors that are closest to the detection vector in the multi-dimensional feature space, wherein the one or more food item vectors corresponds to the one or more types of food items;

in response to identifying the one or more types of food items:

determining one or more actions based at least in part on the one or more types of food items; and

determining a second period of time based on a location of one or more of the first plurality of food item vectors with respect to the detection vector; and

controlling operation of the controllable component based at least in part on the one or more actions, wherein controlling operation of the controllable component comprises:

operating the controllable component for the second period of time based on the one or more types of food items.

Assignments (2)

Continuity (2)

References Cited (88)