Document reading device, document reading method, and program

Abstract

To efficiently perform visual confirmation work by reducing a waiting time during which a user who visually confirms characters input to a document in paperwork waits in a readout time when the document is optically read.SOLUTION: A document reader is configured to: acquire mage data of a reading target document in which a plurality of reading areas each showing at least one of one or more characters or numerals are provided; classify each of the plurality of reading areas into a plurality of different groups; perform processing of optically reading at least one of characters or numerals in the reading areas included in the groups according to a reading sequence allocated to each of the plurality of different groups; and perform processing for outputting a result of the reading processing for each of the groups of the reading areas.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a document reading device, a document reading method, and a program. [Background technology]

[0002] In many cases of office work, a user such as an operator visually checks characters entered into a document to check for errors. There is a demand for improving the efficiency of document checking work in such office work. Related technology is disclosed in Patent Document 1.

[0003] Patent Document 1 discloses a technique for displaying a plurality of character candidates on a display unit in an order based on evaluation points. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2019 / 097690 Summary of the Invention [Problem to be solved by the invention]

[0005] In the above-mentioned administrative processing, users who visually check the characters entered on a document have to wait while the document is optically read, but there is a need to shorten this time and work more efficiently.

[0006] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a document reading device, a document reading method, and a program that solve the above-mentioned problems. [Means for solving the problem]

[0007] According to a first aspect of the present invention, a document reading device comprises a document image acquisition means for acquiring image data of a document to be read, which has a plurality of reading areas each showing at least one character or number; a classification means for classifying each of the plurality of reading areas into a plurality of different sets; a reading means for performing an optical reading process of at least one of the characters or numbers in the reading areas included in each of the plurality of different sets in accordance with a reading order assigned to that set; and an output means for outputting the results of the reading process for each of the sets.

[0008] According to a second aspect of the present invention, a document reading method acquires image data of a document to be read, which has a plurality of reading areas each showing at least one character or number, classifies each of the plurality of reading areas into a plurality of different sets, performs an optical reading process of at least one of the characters or numbers in the reading areas included in each of the plurality of different sets according to a reading order assigned to each of the plurality of different sets, and performs an output process of the results of the reading process for each of the sets.

[0009] According to a third aspect of the present invention, the program causes a computer of a document reading device to function as a document image acquisition means for acquiring image data of a document to be read, which has a plurality of reading areas each showing at least one character or number; a classification means for classifying each of the plurality of reading areas into a plurality of different sets; a reading means for performing an optical reading process of at least one of the characters or numbers in the reading areas included in each of the plurality of different sets in accordance with a reading order assigned to the set; and an output means for outputting the results of the reading process for each of the sets. [Effects of the Invention]

[0010] According to the present invention, a user who visually checks characters entered into a document during office work can shorten the waiting time required for the document to be optically read, thereby enabling the visual check to be performed efficiently. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a schematic configuration diagram of a document reading device system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a hardware configuration diagram of the document reading device according to the present embodiment. [Figure 3] 1 is a functional block diagram of a document reading device according to an embodiment of the present invention; [Figure 4] FIG. 2 is a diagram illustrating an example of a data table stored in a database according to the present embodiment. [Figure 5] 10 is a graph showing the relationship between the number of read items in a document to be read and the amount of processing according to the present embodiment. [Figure 6] FIG. 4 is a diagram showing a processing flow of the document reading device according to the present embodiment. [Figure 7] FIG. 2 is a first diagram showing a document to be read and a display example according to the present embodiment. [Figure 8] FIG. 10 is a second diagram showing a document to be read and a display example according to the present embodiment. [Figure 9] FIG. 1 is a diagram showing a minimum configuration of a document reading device according to an embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing a processing flow by a document reading device with a minimum configuration according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] A document reading system according to an embodiment of the present invention will now be described with reference to the drawings. FIG. 1 is a schematic diagram of the document reading system according to the embodiment. As shown in this diagram, the document reading system 100 is configured by connecting a document reading device 1 and a reader 2 via a communication cable. The document reading device 1 acquires image data of the document to be read optically read by the reader 2, and reads characters recorded on the document to be read using an OCR (Optical Character Recognition) function. The document to be read has multiple reading areas each showing a set of one or more characters. Each of these reading areas will be called a reading item.

[0013] FIG. 2 is a diagram showing the hardware configuration of the document reading device according to this embodiment. As shown in Figure 2, the document reading device 1 is a computer equipped with various hardware components such as a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, an HDD (Hard Disk Drive) 104, a communication module 105, and a database 106.

[0014] FIG. 3 is a functional block diagram of the document reading device according to this embodiment. The document reading device 1 executes a document reading program, which causes the document reading device 1 to perform the functions of a control unit 11, a document image acquisition unit 12, a document type identification unit 13, a classification unit 14, a reading unit 15, and a display unit 16.

[0015] The control unit 11 controls each functional unit. The document image acquisition unit 12 acquires image data of a document to be read, which has a plurality of reading areas each showing at least one of one or more characters or numbers. The document type identification unit 13 identifies the type of the document to be read. The classification unit 14 classifies each of the plurality of reading areas (reading items) into a plurality of different groups (sets). The reading unit 15 performs optical reading processing of at least one of each character and each number in the reading items included in a plurality of different groups (sets) in accordance with the reading order assigned to each of the groups (sets). The display unit 16 displays the results of the reading process for each of a plurality of different groups (sets).

[0016] FIG. 4 is a diagram showing an example of a data table stored in the database. The database 106 stores a classification table and an order table. The classification table stores read items for each grouping, which is a classification of one or more read items set in the document to be read indicated by the document ID, linked to the document ID, which is identification information for identifying the type of document. The sequence table stores the reading sequence for each group set for the document to be read, linked to the document ID. These classification tables and order tables may be data tables created by an administrator, or may be data tables generated automatically.

[0017] FIG. 5 is a graph showing the relationship between the number of read items in a document to be read and the amount of processing. The graph in Figure 5 shows the total time (seconds) to process all items and the number of items processed per unit time (items / second) for each number of items in the document to be read. For example, if the document to be read has three items, items 1 through 3, the total time to process all three items, items 1 through 3, is 2.1 seconds, and the number of items processed per unit time when all three items in the document to be read are OCR-read is 1.4. Also, if the document to be read has nine items, items 1 through 9, the total time to process all nine items, items 1 through 9, is 4.5 seconds, and the number of items processed per unit time when all nine items in the document to be read are OCR-read is 2.

[0018] In this way, the total time required to process all items and the number of items processed per unit time when OCR reading of all items is processed differ depending on the number of reading items provided in the document to be read. The administrator may classify the reading items into multiple different groups based on the total time required to process all items for each document to be read and the number of items processed per unit time when OCR reading of all items is processed, determine the reading order for each classified group, and create a classification table and an order table to record in database 106.

[0019] Furthermore, the types of characters entered in the reading items provided on the document to be read vary, including Arabic numerals, kanji, hiragana, katakana, and the alphabet, and the total time required to process all items for each document to be read and the number of items processed per unit time when OCR reading of all items is processed differ depending on the type of characters and the number of characters included in the reading items.The administrator may classify the reading items into multiple different groups based on the total time required to process all items and the number of items processed per unit time when OCR reading of all items is processed, depending on the type of characters and the number of characters for each document to be read, determine the reading order for each classified group, and create a classification table and an order table to record in database 106.

[0020] Furthermore, if the confirmation order for each reading item set on the document to be read has been determined in advance, the administrator may classify the reading items into multiple different groups based on that confirmation order, determine the reading order for each of the classified groups, and create a classification table and an order table to record in database 106.

[0021] As an example, suppose a document to be scanned has 10 scanning items, from item 1 to item 10, and the character types for the scanning items, from item 1 to item 10, are numbers, numbers, kanji, kanji, numbers, numbers, kanji, kanji, kanji, kanji. The administrator checks the graph shown in Figure 4 as basic data and confirms that the time to confirm numbers is 1.0 second per scanning item and the time to confirm kanji is 2.0 seconds per scanning item. In order to minimize the total work time, the administrator considers how to classify the scanning items in such a document to be scanned and in what order to perform OCR processing. For example, the administrator may classify the documents to be scanned into four groups: "First group 01 (first scanning item), second group 02 (second scanning item to fourth scanning item), third group 03 (fifth scanning item to seventh scanning item), and fourth group 04 (eighth scanning item to tenth scanning item)," and consider that the shortest time would be to repeat the OCR processing and display of the scanning results.The administrator creates a classification table and an order table based on the results of this consideration.

[0022] The document reading device 1 then identifies a classification table recorded in the database 106 based on the ID of the document to be read, and classifies the multiple reading items into multiple different groups based on the classification table. The document reading device 1 also identifies an order table recorded in the database 106 based on the ID of the document to be read, and performs optical reading processing on a set of characters of the reading items included in the group in accordance with the reading order assigned to each of the multiple different groups based on the order table.

[0023] The document reading device 1 performs OCR processing on the reading items included in the first group in accordance with the order table to read characters, and then outputs the characters. This allows the user to check the reading results of the reading items included in the first group in order. The document reading device 1 also performs OCR processing on the reading items included in the second group in accordance with the order table to read characters, and then outputs the characters. This allows the user to check the reading results of the reading items included in the second group in order. The document reading device 1 performs OCR processing on all reading items of the document to be read in accordance with the order table.

[0024] According to this process, while the document reading device 1 is performing OCR processing on a certain group, the user can visually check the reading results of the group of reading items that was previously OCR processed. As a result, the time taken for the document reading device 1 to perform OCR processing on the group of reading items and the time taken for the user to visually check the reading results of the reading items read in the previous OCR processing are parallel, so that the time taken to perform OCR processing on all reading items of the document to be read and for the user to visually check the reading results can be shortened.

[0025] In other words, the user does not have to wait until the document reading device 1 completes OCR processing for all reading items of the document to be read, and the user can visually check the reading items that were read in the reading order first. This allows the document reading device 1 to perform OCR processing for all reading items of the document to be read, thereby shortening the time until the user can visually check the reading results.

[0026] FIG. 6 is a diagram showing a processing flow of the document reading device. Next, the processing flow of the document reading device will be explained step by step. First, the user places the document to be read in the reader 2 and instructs the reader 2 or the document reading device 1 to start reading. Based on the instruction to start reading from the user or based on the instruction to start reading from the document reading device 1, the reader 2 optically reads the document to be read and generates image data. The reader 2 transmits the image data to the document reading device 1.

[0027] The document image acquisition unit 12 acquires image data of the document to be read (step S101). The control unit 11 outputs the image data to the document type identification unit 13. The document type identification unit 13 identifies the document ID based on one or more pieces of information contained in the image data, such as characters, images, code information, and the description format of ruled lines (step S102). For example, the document type identification unit 13 may identify the document ID by reading it encoded in a two-dimensional code. Alternatively, the document type identification unit 13 may identify the ID by reading numbers written on the document to be read from the image data. The document type identification unit 13 outputs the document ID to the control unit 11. The control unit 11 outputs the document ID to the classification unit 14 and the reading unit 15.

[0028] The classification unit 14 acquires the document ID. The classification unit 14 acquires classification information recorded in the classification table of the database 106 in association with the document ID (step S103). The classification information is information indicating which read items of the document to be read indicated by the document ID are included in which group. In other words, the classification information includes at least an identifier indicating the group and identifiers of the read items included in that group. Note that the classification information further includes coordinate information on the area indicated by each read item in the document to be read. The classification unit 14 outputs the classification information acquired based on the document ID to the reading unit 15.

[0029] The reading unit 15 acquires the order information recorded in the order table of the database 106 in association with the document ID (step S104). The order information is information indicating which group of documents classified in the document to be read indicated by the document ID and in what order to read them. In other words, the order information includes at least an order number and an identifier of the group to be read in that order.

[0030] The reading unit 15 acquires the identifier of the group in Order 1 from the order information, and acquires the reading items included in the group from the classification information based on the group identifier (step S105). The reading unit 15 acquires the coordinates within the document of the reading area of ​​each reading item in Order 1 from the classification information. The reading unit 15 performs OCR processing on the characters of the reading items in the document to be read based on the coordinates, and reads the characters (step S106). If the group in Order 1 includes multiple reading items, the reading unit 15 performs OCR processing on the characters of these multiple reading items. The reading unit 15 outputs the reading results of each reading item included in the group in Order 1 to the control unit 11. The control unit 11 instructs the display unit 16 to output the reading results. The display unit 16 displays the reading results of each reading item included in the group in Order 1 (step S107).

[0031] The reading unit 15 determines whether processing has been completed for all groups (step S108). The reading unit 15 repeats the above-described processing from step S105 until OCR processing has been performed on each read item included in all groups. The control unit 11 ends the processing when OCR processing has been performed on each read item included in all groups.

[0032] FIG. 7 is a first diagram showing a document to be read and a display example. The document 6 to be read is provided with seven read items, namely, read items 61 to 67. The classification table is set so that, linked to the ID of the document 6 to be read, the first group 601 includes read items 61 and 62, the second group 602 includes read items 63 and 64, and the third group 603 includes read items 65, 66, and 67. In this situation, in the first OCR process (S1), the document reading device 1 performs OCR processing on the read items 61 and 62 set as the first group based on the order information, and displays them on the display screen 600. In the next OCR process (S2), the document reading device 1 performs OCR processing on the read items 63 and 64 set as the second group based on the order information, and displays them on the display screen 600. In the next OCR process (S3), the document reading device 1 performs OCR processing on the read items 65, 66, and 67 that are set as the third group based on the order information, and displays them on the display screen 600.

[0033] FIG. 8 is a second diagram showing a document to be read and a display example. The following is a specific example of read items when the document to be read is a transfer request form 7. The transfer request form 7 has eight read items, 71 to 78. These eight read items are the transfer destination account number 71, the amount (transfer amount) 72, the name of the account from which the transfer is made 73, the address 74 of the account holder of the account from which the transfer is made, a transaction number 75 for identifying the transfer transaction, the store code 76 of the account from which the transfer is made, and the account number 77 of the account from which the transfer is made. The classification table is set up so that, linked to the ID of the transfer request form 7, the first group 701 includes the read items of the account number 71, the amount 72, and the name 73, the second group 702 includes the address 74, the third group 703 includes the transaction number 75, the fourth group 704 includes the read items of the store code 76 and the account number 77, and the fifth group 705 includes the internal number 78. In this situation, in the first OCR process, the document reading device 1 performs OCR processing on each of the read items, account number 71, amount 72, and name 73, set in the first group 701 based on the order information, and displays them on the display screen 700. In the next OCR process, the document reading device 1 performs OCR processing on the read item, address 74, set in the second group based on the order information, and displays them on the display screen 700. In the next OCR process, the document reading device 1 performs OCR processing on the read item, process number 75, set in the third group based on the order information, and displays them on the display screen 700. In the next OCR process, the document reading device 1 performs OCR processing on the read items, store code 76 and account number 77, set in the fourth group based on the order information, and displays them on the display screen 700. In the next OCR process, the document reading device 1 performs OCR processing on the read item, internal number 78, set in the fifth group based on the order information, and displays them on the display screen 700.

[0034] According to the above process, when a user instructs the document reading device 1 to perform a reading process on the reading items included in the document to be read, the document reading device 1 performs OCR processing on each group indicated by the classification information and displays the results. This allows the user to visually confirm the OCR processing results for some of the reading items before the OCR processing for all of the reading items is completed. Furthermore, according to the above process, each reading item is OCR processed and displayed for each group in the desired order based on the order table. This allows the user to visually confirm the reading results in order of the reading items with the highest priority in the business process. Furthermore, according to the above process, the time required for the document reading device 1 to perform OCR processing on a group of reading items and the time required for the user to visually confirm the reading results of the reading items read in the previous OCR processing are parallel, so that the time required for the document to be read to perform OCR processing on all reading items and for the user to visually confirm the reading results can be shortened.

[0035] The display unit 16 of the document reading device 1 may display a management screen on the display of the document reading device 1 based on a user operation. The management screen may include a setting screen for the sequence table and a setting screen for the classification table. The user may use the setting screen in the management screen displayed on the display to change the setting of the sequence recorded in the sequence table or the setting of the group of reading items recorded in the classification table. When the document reading device 1 receives a request to change the reading items corresponding to each group of the classification table based on the setting screen in the management screen, the document reading device 1 changes the classification table based on the request. Alternatively, when the document reading device 1 receives a request to change the order corresponding to each group of the sequence table based on the setting screen in the management screen, the document reading device 1 changes the sequence table based on the request. The document reading device 1 may receive a change request while the device is operating and change the setting of the classification table or the sequence table as described above.

[0036] FIG. 9 is a diagram showing the minimum configuration of a document reading device according to this embodiment. FIG. 10 is a diagram showing a processing flow by a document reading device with a minimum configuration according to this embodiment. The document reading device 1 includes at least a document image acquisition unit 91, a classification unit 92, a reading unit 93, and an output unit 94. The document image acquisition means 91 acquires image data of a document to be read, which has a plurality of reading areas each showing at least one of one or more characters or numbers (step S201). The classification means 92 classifies each of the plurality of reading areas into a plurality of different sets (step S202). The reading means 93 performs optical reading processing of at least one of the characters and numbers in the reading areas included in the plurality of different sets in accordance with the reading order assigned to each of the sets (step S203). The output means 94 performs output processing of the results of the reading processing for each of a plurality of different sets (step S204).

[0037] Each of the above-mentioned devices has a computer system built in. The steps of each of the above-mentioned processes are stored in the form of a program on a computer-readable recording medium, and the computer reads and executes this program to perform the above-mentioned processes. Here, computer-readable recording medium refers to a magnetic disk, magneto-optical disk, CD-ROM, DVD-ROM, semiconductor memory, etc. Alternatively, the computer program may be distributed to a computer via a communication line, and the computer that receives the program may execute the program.

[0038] The program may also be a program for realizing some of the functions described above, or may be a so-called differential file (differential program) that can realize the functions described above in combination with a program already recorded in the computer system. [Explanation of symbols]

[0039] 1. Document reader 2. Leader 11 Control section 12 Document image acquisition unit 13 Document type identification section 14...Classification section 15 Reading unit 16...Display section

Claims

1. a document image acquisition unit for acquiring image data of a document to be read, the document having a plurality of reading areas each showing at least one of one or more characters or numbers; a classification means for classifying each of the plurality of reading areas into a plurality of different groups; a reading unit that performs optical reading processing of at least one of the characters and the numbers in the reading areas included in each of the plurality of different sets according to a reading order assigned to each of the plurality of different sets; a control means for repeatedly outputting an output instruction for displaying the results of the reading process for each of the sets in the order in which the reading process is completed based on the reading order; a display means for displaying the results of the reading processes on a display screen in the order in which the reading processes are completed based on the output instruction; A document reading device comprising:

2. a type detection means for detecting the type of the document to be read, The classification means acquires a classification method for the set according to the type, and classifies the plurality of reading areas into a plurality of different sets according to the classification method. The document reader according to claim 1 .

3. a type detection means for detecting the type of the document to be read, The reading means acquires the reading order according to the type, and performs optical reading processing of at least one of the characters and numbers in the reading area included in the set according to the reading order. The document reader according to claim 1 .

4. Acquire image data of a document to be read, which has a plurality of reading areas each showing at least one of one or more characters or numbers; classifying each of the plurality of reading areas into a plurality of different sets; performing an optical reading process of at least one of the characters and the numbers in the reading areas included in each of the plurality of different sets according to a reading order assigned to each of the plurality of different sets; outputting an output instruction to display the results of the reading process for each of the sets in a sequential order in which the reading process is completed based on the reading order; displaying the results of the reading processes on a display screen in the order in which the reading processes are completed based on the output instruction; How to read documents.

5. The document reader computer a document image acquisition means for acquiring image data of a document to be read, the document having a plurality of reading areas each showing at least one of one or more characters or numbers; a classification means for classifying each of the plurality of reading areas into a plurality of different sets; a reading means for optically reading at least one of the characters and the numbers in the reading areas included in each of the plurality of different sets in accordance with a reading order assigned to each of the plurality of different sets; a control means for repeatedly outputting an output instruction for displaying the results of the reading process for each of the sets in the order in which the reading process is completed based on the reading order; a display means for displaying the results of the reading processes on a display screen in the order in which the reading processes are completed based on the output instruction; A program that functions as a

Images