Fuzzy inference deduction using rules and hierarchy-based item assignments
AssigneeHealthtrust Purchasing Group, LP
InventorMelanie Anne McMeekan
Life of this patent
Estimating the term…
Abstract
Some embodiments disclosed herein relate to generating fuzzy inferences of procedure types based on fuzzy logic. Membership functions can be used to relate item variables to a degree of correspondence to various item types. Fuzzy rules can specify processing to be conducted using membership values produced by evaluations of membership functions. An output of the processing can include an inference that a content object corresponding to the item variables relates to one or more procedure types. Further, some embodiments disclosed herein relate to querying hierarchical data structures to identify related items. A hierarchical data structure can associate each of a set of procedure types with one or more item types and/or item identifiers or characteristics.
Claims20
A knowledge processing system for querying hierarchical data structures to identify related items, the knowledge processing system comprising:
- an input receiver that accesses a content object that refers to a first item;
- an item-assignment fuzzification engine that identifies, using an extraction technique, a first item identifier corresponding to the first item;
- a variation engine that:
- queries, using one or more processors, a hierarchical item library with the first item identifier, the hierarchical item library identifying:
- a set of procedure types;
- and
- for each procedure type in the set of procedure types:
- a set of item types;
- for each item type in the set of item types, one or more item characteristics or item identifiers;
- and
- identifying, as a result of using machine learning, at least one item type in the set of item types as indicative of a particular procedure type in the set of procedure types;
- and
- receives a query response that identifies:
- a type of item for the first item;
- a procedure type in the set of procedure types;
- and
- a second item identifier associated with the procedure type;
- and
- an output engine that generates an output that identifies a second item that is associated with the second item identifier.
A computer-implemented method for querying hierarchical data structures to identify related items, the method comprising:
- accessing a content object that refers to a first item;
- identifying, using an extraction technique, a first item identifier corresponding to the first item;
- querying, using one or more processors, a hierarchical item library with the first item identifier, the hierarchical item library identifying:
- a set of procedure types;
- and
- for each procedure type in the set of procedure types:
- a set of item types;
- for each item type in the set of item types, one or more item characteristics or item identifiers;
- and
- identifying, as a result of using machine learning, at least one item type in the set of item types as indicative of a particular procedure type in the set of procedure types;
- receiving a query response that identifies:
- a type of item for the first item;
- a procedure type in the set of procedure types;
- and
- a second item identifier associated with the procedure type;
- and
- generating an output that identifies a second item that is associated with the second item identifier.
A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform actions including:
- accessing a content object that refers to a first item;
- identifying, using an extraction technique, a first item identifier corresponding to the first item;
- querying, using one or more processors, a hierarchical item library with the first item identifier, the hierarchical item library identifying:
- a set of procedure types;
- and
- for each procedure type in the set of procedure types:
- a set of item types;
- for each item type in the set of item types, one or more item characteristics or item identifiers;
- and
- identifying, as a result of using machine learning, at least one item type in the set of item types as indicative of a particular procedure type in the set of procedure types;
- receiving a query response that identifies:
- a type of item for the first item;
- a procedure type in the set of procedure types;
- and
- a second item identifier associated with the procedure type;
- and
- generating an output that identifies a second item that is associated with the second item identifier.
Dependencies are inferred from the claim text.