Information processing apparatus, information processing method, and storage medium

1 . An information processing apparatus comprising:

one or more memories storing instructions; and

one or more processors executing the instructions:

(1) to obtain scanned images consisting of multiple pages by scanning a plurality of different documents collectively;

(2) to determine a break between the different documents in the scanned images;

(3) in a case when a first document indicated by the page preceding the break and a second document indicated by the page following the break in the scanned images do not satisfy a predetermined condition indicating related documents, to divide the scanned images at the break to generate files so that the first document and the second document are separated;

(4) in a case when the first document and the second document, that is not the same document as the first document, satisfy the predetermined condition, to combine the first document indicated by the page preceding the break and the second document indicated by the page following the break; and

(5) generate a filename for each of one or more files generated from the scanned images by using at least a character string indicating a type of a document corresponding to the file,

wherein, based on a result of comparing a character string indicating a first item included in the first document with a character string indicating a second item included in the second document, the one or more processors further execute the instructions to determine whether the predetermined condition is satisfied,

wherein the first item is a named entity included in the first document, and wherein the second item is a named entity included in the second document, and

wherein the comparing is carried out using a trained model.

2 . The information processing apparatus according to claim 1 , wherein the one or more processors further execute the instructions to extract a character string indicating a predetermined item from each page in the scanned images, and

wherein, in the comparing, the extracted character string indicating the first item on a page corresponding to the first document is compared with the extracted character string indicating the second item on a page corresponding to the second document.

3 . The information processing apparatus according to claim 1 , wherein the first item and the second item are determined in accordance with a pair of a type of the first document and a type of the second document.

4 . The information processing apparatus according to claim 1 , wherein, in a case when the character string indicating the first item and the character string indicating the second item are different from each other, the scanned images are divided at the break to generate files so that the first document and the second document are separated, and

wherein in a case when the character string indicating the first item and the character string indicating the second item are the same, the first document and the second document are combined to generate a file so that the first document and the second document are included in one file.

5 . The information processing apparatus according to claim 1 , wherein the one or more processors further execute the instructions:

to generate files by dividing the scanned images at the break; and

to combine two files, in a case when the two files, in which a last page of one file of the two files and a first page of the other file of the two files, satisfy the predetermined condition, the last page and the first page being adjacent pages in the scanned images.

6 . The information processing apparatus according to claim 1 , wherein the scanned images are images in a PDF format obtained by scanning the plurality of documents by a page unit.

7 . The information processing apparatus according to claim 1 , wherein the one or more processors further execute the instructions to determine whether or not an interval between two adjacent pages selected from the scanned images is the break.

8 . The information processing apparatus according to claim 1 , wherein the filename is generated by further using a predetermined character string included in a page of the generated file.

9 . The information processing apparatus according to claim 1 , wherein the one or more processors further execute the instructions to manage a value for identifying the file generated so that two or more documents are included in one file and a configuration of types of the two or more documents in association with each other.

10 . The information processing apparatus according to claim 9 , wherein the one or more processors further execute the instructions:

to obtain the configuration of the types of the two or more documents associated with the same value as the value for identifying a file as a processing target from the managed data; and

to notify a user in a case when the obtained configuration of the types of the two or more documents and a configuration of types of documents of the file as the processing target are different from each other.

11 . The information processing apparatus according to claim 1 , wherein the predetermined condition includes one or more of the following conditions:

(1) a condition that the first document is an estimate form and the second document is a purchase order,

(2) a condition that the first document is a delivery slip and the second document is a bill,

(3) a condition that the first document is a bill and the second document is a receipt, and

(4) a condition that the first document is an application form and the second document is a receipt.

12 . An information processing method comprising:

obtaining scanned images consisting of multiple pages by scanning a plurality of documents collectively;

determining a break between different documents in the scanned images;

in a case when a first document indicated by the page preceding the break and a second document indicated by the page following the break in the scanned images do not satisfy a predetermined condition indicating related documents, dividing the scanned images at the break to generate files so that the first document and the second document are separated;

in a case when the first document and the second document, that is not the same document as the first document, satisfy the predetermined condition, combining the first document indicated by the page preceding the break and the second document indicated by the page following the break; and

generating a filename for each of one or more files generated from the scanned images by using at least a character string indicating a type of a document corresponding to the file,

wherein, based on a result of comparing a character string indicating a first item included in the first document with a character string indicating a second item included in the second document, it is determined whether the predetermined condition is satisfied,

wherein the first item is a named entity included in the first document, and wherein the second item is a named entity included in the second document, and

wherein the comparing is carried out using a trained model.

13 . A non-transitory computer-readable storage medium storing a program that causes a computer to perform an information processing method, the information processing method comprising:

obtaining scanned images consisting of multiple pages by scanning a plurality of documents collectively;

determining a break between different documents in the scanned images;

in a case when a first document indicated by the page preceding the break and a second document indicated by the page following the break in the scanned images do not satisfy a predetermined condition indicating related documents, dividing the scanned images at the break to generate files so that the first document and the second document are separated;

in a case when the first document and the second document, that is not the same document as the first document, satisfy the predetermined condition, combining the first document indicated by the page preceding the break and the second document indicated by the page following the break; and

generating a filename for each of one or more files generated from the scanned images by using at least a character string indicating a type of a document corresponding to the file,

wherein, based on a result of comparing a character string indicating a first item included in the first document with a character string indicating a second item included in the second document, it is determined whether the predetermined condition is satisfied,

wherein the first item is a named entity included in the first document, and wherein the second item is a named entity included in the second document, and

wherein the comparing is carried out using a trained model.