Method for comparing content of two document files, and method for training a graph neural network structure to implement the same
AssigneeFoxit Software Inc.
InventorsPo-Fang Hsu, Chi-Ching Wei
Life of this patent
Estimating the term…
Abstract
A method for comparing content of two document files each having a plurality of content blocks is provided. The method is to be implemented by an electronic device and includes the steps of: performing, for the each of the content blocks in each of the document files, a pre-process operation so as to obtain a plurality of properties associated with the content block; comparing, for each content block from one of the document files, the properties thereof with the properties of each of the plurality of content blocks of the other one of the document files; and generating a comparison result based on the operations of the comparing.
Claims18
A method for comparing content of two document files each having a plurality of content blocks, the method to be implemented by an electronic device and comprising the steps of:
- a) performing, for each of the content blocks in each of the document files, a pre-process operation so as to obtain a plurality of properties associated with the content block;
- b) comparing, for each content block from one of the document files, the properties of the content block with the properties of each of the plurality of content blocks of the other one of the document files;
- c) generating a comparison result based on the operations of step b);
- d) receiving the two document files;
- and
- e) in response to receipt of the two document files, identifying, for each of the document files, the plurality of content blocks.
A method for training a graph neural network (GNN) structure to compare content of two document files, the method comprising:
- constructing an initial GNN structure that includes a plurality of layers;
- preparing a plurality of training datasets, each of the training datasets including two source files, each of the source files including a plurality of content blocks;
- supplying the plurality of training datasets into the initial GNN structure as input, so as to train the initial GNN structure to obtain a trained GNN structure that is configured to compare, for each content block from one of the document files, properties of the content block with the properties of each of a plurality of content blocks of the other one of the document files.
Dependencies are inferred from the claim text.