Back to results
US 12,417,649 B2Granted
Table information extraction and mapping to other documents
AssigneeBILL Operations, LLC
InventorsNatalia Berestovsky, Stefano Andrea Romano, Ricardo Antonio Fernandez, Joseph Michael Price
Life of this patent
Estimating the term…
Abstract
The accuracy of existing machine learning models, software technologies, and computers are improved by using one or more machine learning models to map data inside structural elements, such as rows or columns, as found within a document to data objects of other documents, where the data objects are at least partially indicative of candidate categories that the data can belong to.
Claims20
A computerized system comprising:
- one or more processors;
- and
- computer storage memory having computer-executable instructions stored thereon which, when executed by the one or more processors, implement a method comprising:
- receiving a first document associated with a user;
- determining a table within the first document;
- extracting a plurality of structural elements from the table, a first structural element comprising a first cost of a first good or service and a second structural element comprising a second cost of a second good or service;
- determining, via at least natural language processing (NLP), a first similarity score between a first set of words and a data object, the first set of words describing the first good or service and being included in the first structural element, the data object at least partially describes, in natural language and at a second document associated with the user, a first candidate category that the first set of words belong to, the candidate category not describing the first good or service but describing a good or service type that the first good or service belongs to, the first similarity score at least partially indicates semantic similarity between a first word, of the first set of words, and a second word in the data object;
- determining, via a least the NLP, a second similarity score between a second set of words and the data object, the second set of words describing the second good or service and being included in the second structural element, the second similarity score at least partially indicates semantic similarity between a third word of the second set of words and the second word in the data object;
- based at least in part on the first similarity score meeting a similarity threshold and the second similarity score not meeting the similarity threshold, applying an operation on the first cost but not the second cost resulting in an output cost;
- and
- based at least in part on the applying of the operation and the first similarity score meeting a threshold for the data object, copying the data object from the second document to a third document and providing the output cost at the third document in association with the data object.
8 more elements
A computer-implemented method comprising:
- receiving a first document associated with a user;
- determining a table within the first document;
- extracting a plurality of structural elements from the table, a first structural element comprising a first cost of a first good or service and a second structural element comprising a second cost of a second good or service;
- determining, via at least Natural language processing (NLP), a first similarity score between a first set of words and a data object, the first set of words describing the first good or service and being included in the first structural element, the data object at least partially indicates a first candidate category that the first set of words belong to, the candidate category not describing the first good or service but describing a good or service type that the first good or service belongs to, the first similarity score at least partially indicates semantic similarity between a first word, of the first set of words, and a second word in the data object;
- determining, via at least the NLP, a second similarity score between a second set of words and the data object, the second set of words describing the second good or service and being included in the second structural element;
- based at least in part on whether the first similarity score and the second similarity score meets a similarity threshold, applying an operation on at least one of the first cost or the second cost resulting in an output cost;
- and
- based at least in part on the applying of the operation and whether the first similarity score and the second similarity score meets the similarity threshold, copying the data object from the second document to a third document and providing the output cost at the third document.
5 more elements
One or more non-transitory computer readable storage mediums having computer-executable instructions embodied thereon that, when executed, by one or more processors, cause the one or more processors to perform a method, the method comprising:
- receiving a plurality of documents associated with a user, each document describes, via one or more identifiers, one or more categories of item expenses;
- subsequent to the receiving, receiving a first document associated with the user, the first document not being among the plurality of documents;
- determining a table within the first document, wherein the table describes individual expenses of at least one of:
- multiple goods or multiple services;
- extracting a plurality of structural elements from the table, a first structural element comprising a first cost of at least one of a first good or a first service and a second structural element comprising a second cost of at least one of a second good or a second service;
- determining, via a least Natural Language Processing (NLP), a first similarity score between a first set of words and a data object, the first set of words describes, in natural language, at least one of the first good or first service and being included in the first structural element, the data object at least partially describes, in natural language, a candidate category that the first set of words belong to, the candidate category not describing at least one of the first good or the first service but describing at least one of a good type or a service type that the first good or first service belongs to, the first similarity score at least partially indicates a semantic similarity between a first word, of the first set of words, and a second word in the data object;
- based at least in part on the first similarity score meeting a similarity threshold, applying an operation on the first cost resulting in an output cost;
- and
- based at least in part on the applying of the operation and the first similarity score meeting the similarity threshold, generating a third document that includes the data object from the second document and the output cost.
6 more elements
Dependencies are inferred from the claim text.