US 2013/0085902 A1 · Automated account reconciliation method

Abstract

Disclosed is a generalized method for automated account reconciliation capable of matching transactions in one accounting dataset to transactions in another accounting dataset with little initial data preparation. The method is highly flexible in that it does not require source data in a particular format, can accept both structured and unstructured (e.g. Descriptive text) data as input, is not domain- or language-dependent, and requires little to no training or user-provided heuristics. The method is also adjustable depending on a user's tolerance of error. Based on probability and information theory, computational linguistics, and statistics, the method can complete accounting reconciliation problems in significantly less time than is possible manually, and with just as high accuracy. Especially for large reconciliation problems, the method can save an overwhelming portion of the cost associated with this kind of task in the past.

Claims20

Dependent claims

A computer implemented generalized method for automated account reconciliation, comprising:

a method capable of automatically matching items in one dataset with items in another dataset;
a component to extract features of each item for which reconciliation is to be attempted;
a component to weight features according to their distinctiveness to each item;
a component to list pairs of items which are candidates for reconciliation;
a component to calculate the pair wise similarities for each candidate pair;
and a component to rule in (reconcile) or rule out each pair.

3 more elements

An improved computer implemented generalized method for automated account reconciliation, comprising:

a method capable of automatically matching items in one dataset with items in another dataset;
a component to extract features of each item for which reconciliation is to be attempted, said component capable of extracting words from unstructured text data where the text is in any human language;
a component to weight features according to their distinctiveness to each item, said component capable of applying to any human language or feature set and said component resilient to typographical or encoding errors in the source data;
a component to list pairs of items which are candidates for reconciliation, said component capable of modification to allow certain candidates not to be considered based on specified heuristics (a blocking component);
a component to calculate the pair wise similarities for each candidate pair regardless of the feature set defining the transactions;
and a component to rule in (reconcile) or rule out each pair.

3 more elements

Dependencies are inferred from the claim text.

Automated account reconciliation method

Life of this patent

Automated account reconciliation method

Life of this patent

Abstract

Claims20