Item name normalization
Assigneee-centives, Inc.
InventorArkady Borkovsky
Life of this patent
Estimating the term…
Abstract
A computer-implemented approach for processing search queries generally involves normalizing names and descriptions of items. The various forms of a name or description of an item is referred to as an item name variant. The normalized form of the name or description of an item is referred to as a normalized item name. Item name variants that are similar are grouped together to form clusters. Each cluster of item name variants is mapped to a normalized item name. A dictionary of normalized item names are created by storing: 1) the item name variant, 2) the information that is obtained from the item name source and which is associated with the item name variant, and 3) the mapping information that maps the item name variant to the corresponding normalized item name.
Claims20
A method for normalizing item names, the method comprising the computer-implemented steps of:
- determining one or more clusters of item name variants, wherein the item name variants are extracted from an initial set of records and wherein each cluster is a cluster of similar item name variants;
- determining a normalized item name that is logically associated with each cluster;
- mapping the item name variants in each cluster to the normalized item name that is logically associated with the cluster to create an initial set of mapping information;
- and
- creating a dictionary that stores at least the initial set of mapping information.
A computer-readable medium for normalizing item names, the computer-readable medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of:
- determining one or more clusters of item name variants, wherein the item name variants are extracted from an initial set of records and wherein each cluster is a cluster of similar item name variants;
- determining a normalized item name that is logically associated with each cluster;
- mapping the item name variants in each cluster to the normalized item name that is logically associated with the cluster to create an initial set of mapping information;
- and
- creating a dictionary that stores at least the initial set of mapping information.
An apparatus comprising a query processing mechanism for normalizing item names, the query processing mechanism being configured to:
- determining one or more clusters of item name variants, wherein the item name variants are extracted from an initial set of records and wherein each cluster is a cluster of similar item name variants;
- determining a normalized item name that is logically associated with each cluster;
- mapping the item name variants in each cluster to the normalized item name that is logically associated with the cluster to create an initial set of mapping information;
- and
- creating a dictionary that stores at least the initial set of mapping information each cluster.
Dependencies are inferred from the claim text.