IP Library Granted Patent US 11,797,551
Granted Patent B2
US 11,797,551 · App. 17/310,439 · Granted Oct 24, 2023

Document retrieval apparatus, document retrieval system, document retrieval program, and document retrieval method

Inventors: Takuya Minami (Tokyo, JP); Yu Kawahara (Tokyo, JP); Shimpei Takemoto (Tokyo, JP); Eriko Takeda (Tokyo, JP); Yoshishige Okuno (Tokyo, JP)
Assignee: RESONAC CORPORATION
G06F16/2468G06F16/93G06V30/347G06V30/416G06V30/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,797,551
App. No.
17/310,439
Granted
Oct 24, 2023
Kind
B2
Abstract

A document retrieval apparatus includes a processor which receives an input of a keyword, acquires an author's name and a document file from a digital document database which stores document files of text data obtained by performing a character recognition process with respect to document image data of handwritten documents, and names of authors who wrote the handwritten documents, references an associating keyword database which stores information associating the authors' names, keywords, and associating keywords, to acquire an associating keyword of the input keyword, from the received input keyword and the acquired author's name, searches the acquired document file, using the input keyword and the acquired associating keyword, and outputs a search result of the searching.

Claims (93)

1. A document retrieval apparatus comprising:

a storage device configured to store a program; and

a processor configured to execute the program, and perform a process including

receiving an input of a keyword;

acquiring an author's name and a document file from a digital document database which stores document files of text data obtained by performing a character recognition process with respect to document image data of handwritten documents, and names of authors who wrote the handwritten documents;

referencing an associating keyword database which stores information associating the authors' names, keywords, and associating keywords, to acquire an associating keyword of the input keyword, from the received input keyword and the acquired author's name;

searching the acquired document file, using the input keyword and the acquired associating keyword; and

outputting a search result of the searching.

2. The document retrieval apparatus as claimed in claim 1 , wherein the processor performs the process further including

acquiring and outputting a document file and associated document image data, from a document image database which stores the document image data of the handwritten documents,

wherein the outputting outputs text data including the input keyword or the associating keyword, from the document file, as the search result, and

wherein, when a part of the text data is selected, the acquiring and outputting acquires and outputs document image data associated with a document file including the selected part of the text data.

3. The document retrieval apparatus as claimed in claim 2 , wherein

information stored in the associating keyword database includes the associating keyword or a keyword regarded as a search keyword of the fuzzy search, the author's name acquired by the acquiring, the keyword received by the receiving, and a selection number,

and the processor performs the process further including

updating the selection number and storing the updated selection number in the associating keyword database, when the part of the text data output as a result of the search using the associating keyword or the fuzzy search is selected from the search result.

4. The document retrieval apparatus as claimed in claim 2 , wherein

the searching performs a fuzzy search using each of the input keyword and the associating keyword, and

the outputting includes a result of the fuzzy search in the search result.

5. The document retrieval apparatus as claimed in claim 4 , wherein

information stored in the associating keyword database includes the associating keyword or a keyword regarded as a search keyword of the fuzzy search, the author's name acquired by the acquiring, the keyword received by the receiving, and a selection number,

and the processor performs the process further including

updating the selection number and storing the updated selection number in the associating keyword database, when the part of the text data output as a result of the search using the associating keyword or the fuzzy search is selected from the search result.

6. The document retrieval apparatus as claimed in claim 1 , wherein

the searching performs a fuzzy search using each of the input keyword and the associating keyword, and

the outputting includes a result of the fuzzy search in the search result.

7. The document retrieval apparatus as claimed in claim 3 , wherein the processor performs the process further including

causing a prediction model to learn; and

storing the prediction model in the storage device,

wherein the causing causes the prediction model to learn using updated associating information stored by the updating as learning data, and the storage device stores the learned prediction model,

wherein the learned prediction model predicts and outputs the associating keyword when the input keyword and the acquired author's name are input, and

wherein the searching searches the document file acquired by the acquiring, using the input keyword and the predicted associating keyword.

8. The document retrieval apparatus as claimed in claim 7 , wherein the processor performs the process further including

holding, when the text data is selected from the search result, associating information associating the keyword generated from the input keyword included in the selected text data, the author's name, and the input keywords, wherein

the causing causes the prediction model to learn using an associating information group, formed by the associating information, as the learning data,

the storage device stores the learned prediction model,

after the learned prediction model is stored in the storage device, the learned prediction model predicts and outputs an associating keyword when the input keyword and the acquired author's name are input, and

the searching searches the document file acquired by the acquiring, using the input keyword and the predicted associating keyword.

9. The document retrieval apparatus as claimed in claim 1 , wherein the processor performs the process further including

causing a prediction model to learn; and

storing the prediction model in the storage device,

wherein the causing causes the prediction model to learn using the information stored in the associating keyword database as learning data, and the storage device to store the learned prediction model,

wherein the learned prediction model predicts and outputs an associating keyword when the input keyword and the acquired author's name are input, and

wherein the searching searches the document file acquired by the acquiring, using the input keyword and the predicted associating keyword.

10. The document retrieval apparatus as claimed in claim 1 , wherein the associating keyword is a character string including an erroneously recognized character as a result of performing the character recognition process with respect to the keyword associated with the associating keyword.

11. A document retrieval system comprising:

a document retrieval apparatus; and

a terminal device,

wherein the document retrieval apparatus includes

a storage device configured to store a program; and

a processor configured to execute the program, and perform a process including

receiving an input of a keyword;

acquiring an author's name and a document file from a digital document database which stores document files of text data obtained by performing a character recognition process with respect to document image data of handwritten documents, and names of authors who wrote the handwritten documents;

referencing an associating keyword database which stores information associating the authors' names, keywords, and associating keywords, to acquire an associating keyword of the input keyword, from the received input keyword and the acquired author's name;

searching the acquired document file, using the input keyword and the acquired associating keyword; and

outputting a search result of the searching.

12. The document retrieval system as claimed in claim 11 , wherein the processor of the document retrieval apparatus performs the process further including

acquiring and outputting a document file and associated document image data, from a document image database which stores the document image data of the handwritten documents,

wherein the outputting outputs text data including the input keyword or the associating keyword, from the document file, as the search result, and

wherein, when a part of the text data is selected, the acquiring and outputting acquires and outputs document image data associated with a document file including the selected part of the text data.

13. The document retrieval system as claimed in claim 12 , wherein

information stored in the associating keyword database includes the associating keyword or a keyword regarded as a search keyword of the fuzzy search, the author's name acquired by the acquiring, the keyword received by the receiving, and a selection number,

and the processor performs the process further including

updating the selection number and storing the updated selection number in the associating keyword database, when the part of the text data output as a result of the search using the associating keyword or the fuzzy search is selected from the search result.

14. The document retrieval system as claimed in claim 11 , wherein

the searching performs a fuzzy search using each of the input keyword and the associating keyword, and

the outputting includes a result of the fuzzy search in the search result.

15. A non-transitory computer-readable recording medium having stored therein a document retrieval program which, when executed by a computer, causes the computer to perform a process comprising:

receiving an input of a keyword;

acquiring an author's name and a document file from a digital document database which stores document files of text data obtained by performing a character recognition process with respect to document image data of handwritten documents, and names of authors who wrote the handwritten documents;

referencing an associating keyword database which stores information associating the authors' names, keywords, and associating keywords, to acquire an associating keyword of the input keyword, from the received input keyword and the acquired author's name;

searching the acquired document file, using the input keyword and the acquired associating keyword; and

outputting a search result of the searching.

16. The non-transitory computer-readable recording medium as claimed in claim 15 , wherein the document retrieval program which, when executed by the computer, causes the computer to perform a process further comprising:

acquiring and outputting a document file and associated document image data, from a document image database which stores the document image data of the handwritten documents,

wherein the outputting outputs text data including the input keyword or the associating keyword, from the document file, as the search result, and

wherein, when a part of the text data is selected, the acquiring and outputting acquires and outputs document image data associated with a document file including the selected part of the text data.

17. The non-transitory computer-readable recording medium as claimed in claim 15 , wherein

the searching performs a fuzzy search using each of the input keyword and the associating keyword, and

the outputting includes a result of the fuzzy search in the search result.

18. A document retrieval method to be implemented by a computer which performs procedures comprising:

receiving an input of a keyword;

acquiring an author's name and a document file from a digital document database which stores document files of text data obtained by performing a character recognition process with respect to document image data of handwritten documents, and names of authors who wrote the handwritten documents;

referencing an associating keyword database which stores information associating the authors' names, keywords, and associating keywords, to acquire an associating keyword of the input keyword, from the received input keyword and the acquired author's name;

searching the acquired document file, using the input keyword and the acquired associating keyword; and

outputting a search result of the searching.

19. The document retrieval method as claimed in claim 18 , wherein the computer performs the procedures further comprising:

acquiring and outputting a document file and associated document image data, from a document image database which stores the document image data of the handwritten documents,

wherein the outputting outputs text data including the input keyword or the associating keyword, from the document file, as the search result, and

wherein, when a part of the text data is selected, the acquiring and outputting acquires and outputs document image data associated with a document file including the selected part of the text data.

20. The document retrieval method as claimed in claim 18 , wherein

the searching performs a fuzzy search using each of the input keyword and the associating keyword, and

the outputting includes a result of the fuzzy search in the search result.

Assignments (3)
CHANGE OF ADDRESS Recorded Feb 14, 2024
From: RESONAC CORPORATION
To: RESONAC CORPORATION
Reel/Frame 066599/0037 →
DECLARATION OF SUCCESSION Recorded Mar 8, 2023
From: SHOWA DENKO K.K.
To: RESONAC CORPORATION
Reel/Frame 063011/0157 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 3, 2021
From: MINAMI, TAKUYA; KAWAHARA, YU; TAKEMOTO, SHIMPEI; TAKEDA, ERIKO; OKUNO, YOSHISHIGE
To: SHOWA DENKO K.K.
Reel/Frame 057064/0621 →