US 12,093,292 B2
Document retrieval device
Yu Kawahara, Tokyo (JP); Takuya Minami, Tokyo (JP); Yu Okano, Tokyo (JP); Hiroko Takashi, Tokyo (JP); and Yoshishige Okuno, Tokyo (JP)
Assigned to Resonac Corporation, Tokyo (JP)
Appl. No. 18/245,061
Filed by Resonac Corporation, Tokyo (JP)
PCT Filed Sep. 7, 2021, PCT No. PCT/JP2021/032807
§ 371(c)(1), (2) Date Mar. 13, 2023,
PCT Pub. No. WO2022/059556, PCT Pub. Date Mar. 24, 2022.
Claims priority of application No. 2020-155507 (JP), filed on Sep. 16, 2020.
Prior Publication US 2023/0359653 A1, Nov. 9, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/332 (2019.01); G06F 16/338 (2019.01)
CPC G06F 16/332 (2019.01) [G06F 16/338 (2019.01)] 10 Claims
OG exemplary drawing
 
1. A document retrieval device comprising:
a misidentification table storing
a correctly identified character string that is presented as first text data by a user input, the first text data corresponding to individual handwritten characters, and
a misidentified character string that is second text data obtained by incorrectly recognizing the individual handwritten characters; and
a processor configured to
obtain a search character string, and
retrieve the search character string from both a document and a character string that is obtained by changing the misidentified character string included in the document to the correctly identified character string,
wherein the processor is configured to
compare a digitalized character string with a second character string, the digitalized character string being presented by a second user input, and corresponding to target handwritten text to be recognized using optical character recognition, and the second character string being obtained by recognizing the target handwritten text using the optical character recognition,
determine a difference between the digitalized character string and the second character string, based on a result of comparison, and
register, for each combination of content words, the correctly identified character string and the misidentified character string in association with characters of the digitalized character string and the second character string that are related to the difference, in the misidentification table.