US 8,949,242 B1Granted

Semantic document analysis

AssigneeGoogle Inc.

InventorsZhen Lin, Keith Stevens

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for semantic document analysis. In one aspect, methods include the actions of segmenting a document into segments; generating semantic representations, each corresponding to one of the segments; determining a corresponding segment score for one or more of the segments based on the corresponding semantic representation, such that each segment score represents a change in the corresponding segment; comparing each segment score to a threshold score, such that the threshold score represents an expectation of change for the document; and identifying segments having segment scores that indicate the change in the corresponding segment deviates from the expectation of change for the document based on the comparison.

Claims25

Dependent claims

A method performed by data processing apparatus, the method comprising:

receiving a first version of a document;
segmenting the first version of the document into a plurality of segments;
generating first semantic representations, each first semantic representation corresponding to a respective segment in the first version of the document;
receiving a second version of the document;
generating second semantic representations, each second semantic representation corresponding to a respective segment in the second version of the document;
determining a respective segment score for each of one or more of the segments based on the second semantic representation for the segment in the second version of the document and the first semantic representation for the segment in the first version of the document, wherein the segment score represents a probability that the segment has changed from the first version of the document to the second version of the document at a same rate as an average segment in the document;
determining, for each of the one or more segments and based on the segment score for the segment, whether a change in the segment deviates from an expectation of change for the document from the first version of the document to the second version of the document;
and
identifying segments having a change that deviates from the expectation of change for the document.

6 more elements

A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:

receiving a first version of a document;
segmenting the first version of the document into a plurality of segments;
generating first semantic representations, each first semantic representation corresponding to a respective segment in the first version of the document;
receiving a second version of the document;
generating second semantic representations, each second semantic representation corresponding to a respective segment in the second version of the document;
determining a respective segment score for each of one or more of the segments based on the semantic representation for the segment in the second version of the document and the first semantic representation for the segment in the first version of the document, wherein the segment score represents a probability that the segment has changed from the first version of the document to the second version of the document at a same rate as an average segment in the document;
determining, for each of the one or more segments and based on the segment score for the segment, whether a change in the segment deviates from an expectation of change for the document from the first version of the document to the second version of the document;
and
identifying segments having a change that deviates from the expectation of change for the document.

6 more elements

A system comprising:

one or more computers operable to perform operations comprising:
receiving a first version of a document;
segmenting the first version of the document into a plurality of segments;
generating first semantic representations, each first semantic representation corresponding to a respective segment in the first version of the document;
receiving a second version of the document;
generating second semantic representations, each second semantic representation corresponding to a respective segment in the second version of the document;
determining a respective segment score for each of one or more of the segments based on the second semantic representation for the segment in the second version of the document and the first semantic representation for the segment in the first version of the document, wherein the segment score represents a probability that the segment has changed from the first version of the document to the second version of the document at a same rate as an average segment in the document;
determining, for each of the one or more segments and based on the segment score for the segment, whether a change in the segment deviates from an expectation of change for the document from the first version of the document to the second version of the document;
and
identifying segments having a change that deviates from the expectation of change for the document.

7 more elements

Dependencies are inferred from the claim text.