Apparatus and method for matching line item textual entries with individual image objects from a file with multiple image objects
A computer implemented method includes receiving a document with line item textual entries and an attachment containing images of different objects characterizing different transactions. The images of the different objects are split into individual image objects. Attributes from the individual image objects are extracted. The line item textual entries are matched with the individual image objects to form matched image objects. The matched image objects include ambiguous matches with multiple individual image objects assigned to a single line item textual entry or a single individual image object assigned to multiple line item textual entries. An assignment model is applied to resolve the ambiguous matches. The assignment model defines priority constraints, assigns pairs of line item textual entries and individual image objects that meet highest priority constraints, removes highest priority constraints when ambiguous matches remain, and repeats these operations until no ambiguous matches remain. One-to-one matches of line item textual entries and individual image objects are returned.
1. A computer implemented method, comprising:
receiving a document with line item textual entries and an attachment containing images of different objects characterizing different transactions;
splitting the images of the different objects into individual image objects;
extracting attributes from the individual image objects;
matching the line item textual entries with the individual image objects to form matched image objects, wherein the matched image objects include ambiguous matches with multiple individual image objects assigned to a single line item textual entry or a single individual image object assigned to multiple line item textual entries; and
applying assignment model matching to resolve the ambiguous matches, wherein the assignment module matching includes:
defining priority constraints,
assigning pairs of line item textual entries and individual image objects that meet highest priority constraints,
removing highest priority constraints when ambiguous matches remain,
repeating the assigning and removing operations until no ambiguous matches remain, and
returning one-to-one matches of line item textual entries and individual image objects.
2. The computer implemented method of claim 1 wherein splitting the images of the different objects into individual image objects utilizes a deep learning model trained on image objects where visual edges or boundaries are not present.
3. The computer implemented method of claim 1 wherein splitting the images of the different objects into individual image objects utilizes a deep learning model trained on different image objects with different spatial orientations.
4. The computer implemented method of claim 1 wherein splitting the images of the different objects into individual image objects transpires when an image object to background pixel contrast exceeds a specified threshold.
5. The computer implemented method of claim 1 further comprising grouping together travel itinerary individual image objects characterizing a single trip.
6. The computer implemented method of claim 1 wherein extracting includes itemizing different types of charges within a single image object.
7. The computer implemented method of claim 1 further comprising extracting merchant information from the individual image objects.
8. The computer implemented method of claim 1 further comprising assigning the individual image objects to expense type classifications.
9. The computer implemented method of claim 1 further comprising extracting transaction amount information from the individual image objects.
10. The computer implemented method of claim 1 further comprising extracting dates from the individual image objects.
11. The computer implemented method of claim 1 wherein the matched image objects include confidence scores, each confidence score characterizing the strength of a coupling between a line item textual entry and an individual image object.