# US 2017/0286767 A1 · Method and apparatus for finding differences in documents > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0286767 A1 - Document ID: US20170286767A1 - Status: Published application - Kind: A1 - Application number: 15/623,254 - Filed: 2017-06-14 - Published: 2017-10-05 - Earliest claimed: 2013-12-18 - Assignees: ABBYY Development LLC - Applicants: ABBYY Development LLC - Inventors: Vasily Vladimirovich Panferov; Andrey Anatolievich Isaev; Catherine Yurievna Bobrova; Olga Zhukovskaya - Web page: https://patentgrep.com/patent/US20170286767A1 ## CPC - G06V 30/418: Document matching, e.g. of document images - G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text - G06V 30/10: Character recognition - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Systems and methods for finding and presenting differences between documents are provided. One method includes identifying one or more differences between a first document and at least one second document. The method further includes determining each of the one or more differences to be either a significant difference or an insignificant difference. The method further includes providing a first identification of the significant differences and a second identification of the insignificant differences. ## Claims ### Claim 1 A method comprising: identifying, using a computing device comprising one or more processors, one or more differences between a first document and a second document; determining, using the computing device, each of the one or more differences between the first document and the second document to be either a significant difference or an insignificant difference; providing a first identification of the significant differences; and providing a second identification of the insignificant differences. ### Claim 2 (depends on 1) The method of claim 1, wherein providing the second identification comprises at least one of indicating that the insignificant differences are to be hidden, or providing the insignificant differences in a different manner than a manner in which the identification of the significant differences is provided. ### Claim 3 (depends on 1) The method of claim 1, further comprising: performing optical character recognition on the first document and the at least one second document; wherein identifying the one or more differences between the first document and the at least one second document comprises identifying at least one of the one or more differences based on the optical character recognition. ### Claim 4 (depends on 3) The method of claim 3, wherein: identifying the one or more differences comprises identifying one or more OCR-related differences likely to have resulted from the optical character recognition; and determining each of the one or more differences to be either a significant difference or an insignificant difference comprises determining the one or more OCR-related differences to be insignificant differences. ### Claim 5 (depends on 4) The method of claim 4, wherein identifying the one or more OCR-related differences comprises, for at least a first difference of the one or more differences: comparing a first set of hypotheses of recognition for the first difference in the first document with a second set of hypotheses of recognition for the first difference in the at least one second document, wherein the first set of hypotheses of recognition and the second set of hypotheses of recognition comprise a plurality of candidates identified by the optical character recognition as potentially corresponding to the first difference; and identifying the first difference as one of the one or more OCR-related differences when the first set of hypotheses of recognition includes a same candidate as the second set of hypotheses of recognition. ### Claim 6 (depends on 1) The method of claim 1, wherein determining each of the one or more differences to be either a significant difference or an insignificant difference comprises, for at least a first difference of the one or more differences: determining a first width of a first blank space associated with the first difference in the first document; determining a second width of a second blank space associated with the first difference in the at least one second document; and determining the first difference to be either a significant difference or an insignificant difference based on a comparison of the first width and the second width. ### Claim 7 (depends on 6) The method of claim 6, wherein determining the first difference to be either a significant difference or an insignificant difference based on the comparison of the first width and the second width comprises determining the first difference to be a significant difference when a difference between the first width and the second width exceeds a threshold value. ### Claim 8 (depends on 1) The method of claim 1, wherein determining each of the one or more differences to be either a significant difference or an insignificant difference comprises, for at least a first difference of the one or more differences: determining the first difference to be associated with a line break; determining a distance from a last character to a right text edge in a line before the line break for at least one of the first document and the at least one second document; and determining the first difference to be a significant difference when the distance exceeds a threshold value. ### Claim 9 (depends on 1) The method of claim 1, wherein providing an identification of the significant differences comprises: providing a list of the significant differences; and responsive to receiving a selection of a significant difference from the list of the significant differences, providing a visualization of the significant difference in the first document and the at least one second document. ### Claim 10 (depends on 1) The method of claim 1, further comprising classifying each of the significant differences according to one of a plurality of difference types, wherein providing an identification of the significant differences comprises providing an indication of the difference type for each of the significant differences. ### Claim 11 (depends on 1) The method of claim 1, further comprising providing an option to display both the identification of the significant differences and the identification of the insignificant differences. ### Claim 12 A system comprising: at least one computing device operably coupled to at least one memory and configured to: identify one or more differences between a first document and a second document; determine each of the one or more differences between the first document and the second document to be either a significant difference or an insignificant difference; provide a first identification of the significant differences; and provide a second identification of the insignificant differences. ### Claim 13 (depends on 12) The system of claim 12, wherein to provide the second identification, the at least one computing device is to at least one of hide the insignificant differences, or provide an identification of the insignificant differences in a different manner than a manner in which the identification of the significant differences is provided. ### Claim 14 (depends on 12) The system of claim 12, wherein the at least one computing device is configured to: perform optical character recognition on the first document and the at least one second document; and identify at least one of the one or more differences based on the optical character recognition. ### Claim 15 (depends on 14) The system of claim 14, wherein the at least one computing device is configured to: identify one or more OCR-related differences likely to have resulted from the optical character recognition; and determine the one or more OCR-related differences to be insignificant differences. ### Claim 16 (depends on 15) The system of claim 15, wherein the at least one computing device is configured, for at least a first difference of the one or more differences, to: compare a first set of hypotheses of recognition for the first difference in the first document with a second set of hypotheses of recognition for the first difference in the at least one second document, wherein the first set of hypotheses of recognition and the second set of hypotheses of recognition comprise a plurality of candidates identified by the optical character recognition as potentially corresponding to the first difference; and identify the first difference as one of the one or more OCR-related differences when the first set of hypotheses of recognition includes a same candidate as the second set of hypotheses of recognition. ### Claim 17 (depends on 12) The system of claim 12, wherein the at least one computing device is configured, for at least a first difference of the one or more differences, to: determine a first width of a first blank space associated with the first difference in the first document; determine a second width of a second blank space associated with the first difference in the at least one second document; and determine the first difference to be either a significant difference or an insignificant difference based on a comparison of the first width and the second width. ### Claim 18 (depends on 17) The system of claim 17, wherein the at least one computing device is configured to determine the first difference to be a significant difference when a difference between the first width and the second width exceeds a threshold value. ### Claim 19 (depends on 12) The system of claim 12, wherein the at least one computing device is configured, for at least a first difference of the one or more differences, to: determine the first difference to be associated with a line break; determine a distance from a last character to a right text edge in a line before the line break for at least one of the first document and the at least one second document; and determine the first difference to be a significant difference when the distance exceeds a threshold value. ### Claim 20 (depends on 12) The system of claim 12, wherein the at least one computing device is configured to: provide a list of the significant differences; and responsive to receiving a selection of a significant difference from the list of the significant differences, provide a visualization of the significant difference in the first document and the at least one second document. ### Claim 21 (depends on 12) The system of claim 12, wherein the at least one computing device is configured to classify each of the significant differences according to one of a plurality of difference types and provide an indication of the difference type for each of the significant differences. ### Claim 22 A computer-readable storage medium having instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising: performing optical character recognition on a first document and a second document; identifying one or more differences between the first document and the second document based at least in part on the optical character recognition; determining each of the one or more differences between the first document and the second document to be either a significant difference or an insignificant difference; providing a first identification of the significant differences; and providing a second identification of the insignificant differences. ### Claim 23 (depends on 22) The computer-readable storage medium of claim 22, wherein providing the second identification comprises at least one of indicating that the insignificant differences are to be hidden, or providing the insignificant differences in a different manner than a manner in which the identification of the significant differences is provided. ### Claim 24 (depends on 22) The computer-readable storage medium of claim 22, wherein: identifying the one or more differences comprises identifying one or more OCR-related differences likely to have resulted from the optical character recognition; and determining each of the one or more differences to be either a significant difference or an insignificant difference comprises determining the one or more OCR-related differences to be insignificant differences. ### Claim 25 (depends on 24) The computer-readable storage medium of claim 24, wherein identifying the one or more OCR-related differences comprises, for at least a first difference of the one or more differences: comparing a first set of hypotheses of recognition for the first difference in the first document with a second set of hypotheses of recognition for the first difference in the at least one second document, wherein the first set of hypotheses of recognition and the second set of hypotheses of recognition comprise a plurality of candidates identified by the optical character recognition as potentially corresponding to the first difference; and identifying the first difference as one of the one or more OCR-related differences when the first set of hypotheses of recognition includes a same candidate as the second set of hypotheses of recognition. ### Claim 26 (depends on 22) The computer-readable storage medium of claim 22, wherein determining each of the one or more differences to be either a significant difference or an insignificant difference comprises, for at least a first difference of the one or more differences: determining a first width of a first blank space associated with the first difference in the first document; determining a second width of a second blank space associated with the first difference in the at least one second document; and determining the first difference to be a significant difference when a difference between the first width and the second width exceeds a threshold value. ### Claim 27 (depends on 22) The computer-readable storage medium of claim 22, wherein determining each of the one or more differences to be either a significant difference or an insignificant difference comprises, for at least a first difference of the one or more differences: determining the first difference to be associated with a line break; determining a distance from a last character to a right text edge in a line before the line break for at least one of the first document and the at least one second document; and determining the first difference to be a significant difference when the distance exceeds a threshold value.