Back to results
US 11,900,276 B2Granted
Distributed relationship reasoning engine for generating hypothesis about relations between aspects of objects in response to an inquiry
AssigneeNant Holdings IP, LLC
InventorPatrick Soon-Shiong
Life of this patent
Estimating the term…
Abstract
A reasoning engine is disclosed. Contemplated reasoning engines acquire data relating to one or more aspects of various environments. Inference engines within the reasoning engines review the acquire data, historical or current, to generate one or more hypotheses about how the aspects of the environments might be correlated, if at all. The reasoning engine can attempt to validate the hypotheses through controlling acquisition of the environment data.
Claims24
A computer implemented method of providing recommendations based on observed objects in an environment, the method comprising:
- receiving, via a data interface, sensor data representing a digital representation of a scene of the environment having at least one object;
- recognizing target objects from aspects of the at least one object represented in the digital representation and based on data features derived from the digital representation, the recognized target objects having object attributes;
- selecting at least one reasoning rule set as a function of the aspects of the at least one object represented in the digital representation and the object attributes of the recognized target objects, wherein the at least one reasoning rule set is selected based on mapping at least the object attributes of the recognized target objects to concept maps comprising pointers to types of reasoning;
- generating at least one hypothesis according to the selected at least one reasoning rule set, the at least one hypothesis representing a correlation among the recognized target objects;
- and
- presenting to a user, via a user interface, a recommendation relating to the recognized target objects and derived at least in part from the at least one hypothesis.
3 more elements
A computer-based reasoning system for providing recommendations based on observed objects in an environment, comprising:
- at least one computer-readable memory storing determination software instructions and alert software instructions;
- at least one processor coupled with the at least one computer-readable memory and that, upon execution of the determination software instructions, operates as a data interface to receive sensor data representing a digital representation of a scene of the environment having at least one object;
- at least one processor coupled with the at least one computer-readable memory and that, upon execution of the determination software instructions, operates as at least one inference engine coupled within the data interface, to:
- recognize target objects from aspects of the at least one object represented in the digital representation and based on data features derived from the digital representation, the recognized target objects having object attributes;
- select at least one reasoning rule set as a function of the aspects of the at least one object represented in the digital representation and the object attributes of the recognized target objects, wherein the at least one reasoning rule set is selected based on mapping at least the object attributes of the recognized target objects to concept maps comprising pointers to types of reasoning;
- generate at least one hypothesis according to the selected at least one reasoning rule set, the at least one hypothesis representing a correlation among the recognized target objects;
- and
- at least one processor coupled with the at least one computer-readable memory and that, upon execution of the determination software instructions, operates as a user interface to present to a user a recommendation relating to the recognized target objects and derived at least in part from the at least one hypothesis.
5 more elements
A computer program product embedded in a non-transitory computer readable medium comprising instructions executable by a computer processor to perform operations comprising:
- receiving, via a data interface, sensor data representing a digital representation of a scene of the environment having at least one object;
- recognizing target objects from aspects of the at least one object represented in the digital representation and based on data features derived from the digital representation, the recognized target objects having object attributes;
- selecting at least one reasoning rule set as a function of the aspects of the at least one object represented in the digital representation and the object attributes of the recognized target objects, wherein the at least one reasoning rule set is selected based on mapping at least the object attributes of the recognized target objects to concept maps comprising pointers to types of reasoning;
- generating at least one hypothesis according to the selected at least one reasoning rule set, the at least one hypothesis representing a correlation among the recognized target objects;
- and
- presenting to a user, via a user interface, a recommendation relating to the recognized target objects and derived at least in part from the at least one hypothesis.
3 more elements
Dependencies are inferred from the claim text.