Back to results
US 12,008,600 B2Granted
Sentiments based transaction systems and methods
AssigneeNant Holdings IP, LLC
InventorPatrick Soon-Shiong
Life of this patent
Estimating the term…
Abstract
Systems and methods of facilitating transactions related to targeted or customized commercial offerings based on derived sentiment states are provided. The sentiment states are derived from digital representations such as images, videos and sound recordings.
Claims22
A digital sentiment analysis system comprising:
- at least one computer readable memory storing software instructions;
- and
- at least one processor coupled with the computer readable memory and wherein the processor, upon execution of the software instructions, performs operations to:
- obtain, via a digital sensor, sensor data of an environment, wherein the sensor data comprises at least one digital data modality and at least some data derived by executing a recognition algorithm, wherein the recognition algorithm comprises at least one of the following recognition algorithms:
- a scale-invariant feature transform (SIFT) algorithm, a Fast Retina Key-point (FREAK) algorithm, a DAISY descriptor algorithm, or a Features from Accelerated Segment Test (FAST) algorithm;
- associate one or more sentiment characteristics with at least some of the sensor data, wherein the associating the one or more sentiment characteristics comprises mapping a threshold number or percentage of items present in the sensor data to a sentiment characteristic;
- generate one or more digital models of sentiment states in the environment based on at least some of the sensor data and the one or more sentiment characteristics;
- determine a set of sentiment states relevant to the environment from the one or more digital models of sentiment states;
- and
- facilitate a mobile device to take action based on the set of sentiment states relevant to the environment.
7 more elements
A non-transitory computer readable medium containing program instructions which, when executed by at least one processor and memory, cause the at least one processor to perform one or more steps comprising:
- obtaining, via a digital sensor, sensor data of an environment, wherein the sensor data comprises at least one digital data modality and at least some data derived by executing a recognition algorithm, wherein the recognition algorithm comprises at least one of the following recognition algorithms:
- a scale-invariant feature transform (SIFT) algorithm, a Fast Retina Key-point (FREAK) algorithm, a DAISY descriptor algorithm, or a Features from Accelerated Segment Test (FAST) algorithm;
- associate one or more sentiment characteristics with at least some of the sensor data, wherein the associating the one or more sentiment characteristics comprises mapping a threshold number or percentage of items present in the sensor data to a sentiment characteristic;
- generating one or more digital models of sentiment states in the environment based on at least some of the sensor data and the one or more sentiment characteristics;
- determining a set of sentiment states relevant to the environment from the one or more digital models of sentiment states;
- and
- facilitating a mobile device to take action based on the set of sentiment states relevant to the environment.
4 more elements
A computer-implemented method for digital sentiment analysis, the method comprising:
- obtaining, via a digital sensor, sensor data of an environment, wherein the sensor data comprises at least one digital data modality and at least some data derived by executing a recognition algorithm, wherein the recognition algorithm comprises at least one of the following recognition algorithms:
- a scale-invariant feature transform (SIFT) algorithm, a Fast Retina Key-point (FREAK) algorithm, a DAISY descriptor algorithm, or a Features from Accelerated Segment Test (FAST) algorithm;
- associate one or more sentiment characteristics with at least some of the sensor data, wherein the associating the one or more sentiment characteristics comprises mapping a threshold number or percentage of items present in the sensor data to a sentiment characteristic;
- generating one or more digital models of sentiment states in the environment based on at least some of the sensor data and the one or more sentiment characteristics;
- determining a set of sentiment states relevant to the environment from the one or more digital models of sentiment states;
- and
- facilitating a mobile device to take action based on the set of sentiment states relevant to the environment.
4 more elements
Dependencies are inferred from the claim text.