Entity understanding and resolution system
AssigneeFetch Rewards, LLC
InventorsAlec Gil Stashevsky, Melanie Anne Riley, Peter Colin Campbell
Life of this patent
Estimating the term…
Abstract
Technologies for machine learning-based entity understanding and resolution are disclosed. Data for training an entity resolution model is collected to learn semantic relationships associated with entity names. The entity names are provided in a domain of documents that follow the semantic conventions differently from natural language semantic conventions. The data includes entries each specifying an entity name and a label. The entity resolution model is trained using the data to learn and generalizes the semantic relationships and is deployed to serve requests for resolving an entity name from text extract from a document image.
Claims20
A computer-implemented method for matching text input to a retailer entity name in a receipt, comprising:
- collecting data for training an entity resolution model initially trained on a first domain to learn semantic relationships associated with entity names provided in a domain of retailer receipts, wherein the data for training the entity resolution model includes a plurality of entries, each entry specifying at least a retailer entity name and a label describing a measure associated with the retailer entity name;
- building the entity resolution model using the collected data by performing a supervised learning technique to adapt the entity resolution model to learn and generalize the semantic relationships;
- deploying the entity resolution model to serve requests for resolving an entity name from text extracted from a retailer receipt;
- and
- providing an active learning interface to refine the entity resolution model.
A computer-implemented method for matching text input to an entity name in a document image, comprising:
- collecting data for training an entity resolution model to learn semantic relationships associated with entity names provided in a domain of documents that follow semantic conventions differently from natural language semantic conventions, wherein the data for training the entity resolution model includes a plurality of entries, each entry specifying at least an entity name and a label describing a measure associated with the entity name;
- training the entity resolution model using the collected data to learn and generalize the semantic relationships;
- and
- deploying the entity resolution model to serve requests for resolving an entity name from text extracted from a document image.
A system, comprising:
- one or more processors, and
- a memory storing a plurality of instructions, which, when executed by the one or more processors, causes the system to:
- collect data for training an entity resolution model to learn semantic relationships associated with entity names provided in a domain of documents that follow semantic conventions differently from natural language semantic conventions, wherein the data for training the entity resolution model includes a plurality of entries, each entry specifying at least an entity name and a label describing a measure associated with the entity name;
- train the entity resolution model using the collected data to learn and generalize the semantic relationships;
- and
- deploy the entity resolution model to serve requests for resolving an entity name from text extracted from a document image.
Dependencies are inferred from the claim text.