WO2023101636A2 - A document reading system - Google Patents

A document reading system Download PDF

Info

Publication number
WO2023101636A2
WO2023101636A2 PCT/TR2022/050896 TR2022050896W WO2023101636A2 WO 2023101636 A2 WO2023101636 A2 WO 2023101636A2 TR 2022050896 W TR2022050896 W TR 2022050896W WO 2023101636 A2 WO2023101636 A2 WO 2023101636A2
Authority
WO
WIPO (PCT)
Prior art keywords
documents
server
database
document
data
Prior art date
Application number
PCT/TR2022/050896
Other languages
French (fr)
Other versions
WO2023101636A3 (en
Inventor
Sabri DEMIR
Mehmet Berk CAVDAR
Nurullah KUS
Original Assignee
Dogus Bilgi Islem Ve Teknoloji Hiz. A.S.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from TR2021/018731 external-priority patent/TR2021018731A1/en
Application filed by Dogus Bilgi Islem Ve Teknoloji Hiz. A.S. filed Critical Dogus Bilgi Islem Ve Teknoloji Hiz. A.S.
Publication of WO2023101636A2 publication Critical patent/WO2023101636A2/en
Publication of WO2023101636A3 publication Critical patent/WO2023101636A3/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G06F40/174—Form filling; Merging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition

Definitions

  • the present invention relates to a system which enables to automatically recognize document types of documents obtained and scanned from any external source, by means of smart image recognition techniques; to obtain and then save the requested fields within scanned documents.
  • OCR Optical Character Recognition
  • image recognition is an artificial intelligence technology used in order to automatically identify and categorize objects, places, people, texts and actions in images.
  • OCR or image recognition technologies enables to convert scanned documents into processable digital files; it is not possible to receive documents, select the requested fields from the document or transfer them to different sources.
  • the United States patent document no. US10796080 discloses a system for executing artificial intelligence-based document processing transactions.
  • discrepancies needed in the document are determined from contents of a request that is received from the process initiated by the user to ensure that at least one document is automatically created with respect to a process, and the documents that are loaded by users; documents required for the process are automatically selected; and discrepancies needed within the document are created upon being automatically determined from within the documents.
  • requests and documents are received by means of an objective setting engine and then they are examined by an optical character recognition unit, a compiler, a discrepancy identification unit and a natural language processing unit; characters included in documents are determined by the optical character recognition unit and discrepancies are determined by the discrepancy identification unit; discrepancies are added into documents upon being compiled by the compiler.
  • An objective of the present invention is to realize a system which enables to automatically recognize document types of documents obtained from any external source periodically, by means of smart image recognition techniques; to obtain and then save the requested fields within scanned documents.
  • Figure l is a schematic view of the inventive system.
  • at least one database (2) which is configured to keep the obtained documents under record in it together with the document definitions and such that the parts received from documents are associated with the documents
  • at least one server (3) which can establish communication with the
  • the database (2) included in the inventive system (1) is in communication with the server (3) and is configured to be managed by the server (3).
  • the database (2) is configured to keep the keyword and/or document definitions, that are related to the text fields to be extracted from documents, under record in it.
  • the said database (2) is configured to keep the documents, that are obtained by the server (3), under record in it together with the detected document definitions.
  • the database (2) is also configured to keep the text fields, that are detected on identified documents, under record in it.
  • the server (3) included in the inventive system (1) is configured to establish communication with remote servers such as document server (A), instant messaging application (B) and chat application (C) by using any remote communication protocol included in the state of the art and to realize data exchange over this communication established.
  • the said server (3) is configured to manage the database (2) by means of transactions such as performing new data recording into the database (2), deleting the recorded data within the database (2) or changing the recorded data within the database (2) and updating the recorded data within the database (2) and to access the recorded data within the database (2).
  • the server (3) is configured to run at least one artificial intelligence that can perform data processing or document reading, on it.
  • the said server (3) is configured to receive documents to be identified and processed from external servers such as document server (A), instant messaging application (B) and chat application (C) by being triggered at certain periods.
  • the server (3) is configured to receive and then process document images from application servers such as document server (A), instant messaging application (B) and chat application (C), in base64 format that is a coding scheme enabling to transmit and store binary data only in media that use ASCII characters.
  • the server (3) is configured to receive and then process the documents to be processed from external servers such as document server (A), instant messaging application (B) and chat application (C), by logging in to systems of external servers (A, B, C) by means of a robotic process automation that automatizes the processes being carried out in base64 format or manually over a web service by means of an API (Application Programming Interface).
  • the server (3) is configured to process the documents received from external servers such as document server (A), instant messaging application (B) and chat application (C), by means of an artificial intelligence algorithm being run on it and to identify the said documents.
  • the server (3) is configured to process and identify the documents received from external servers (A,B,C), by means of an artificial intelligence algorithm such as Inception V3 that is a convolutional neural network enabling image analysis and obj ect detection.
  • the said server (3) is configured to detect text fields on a document by performing optical character recognition on identified documents and to ensure that texts are extracted in text fields.
  • the said server (3) is configured to detect fields and data comprising pre-determined subject, word, expression and/or data by means of natural language processing and regular expression methods in accordance with keywords or definitions, that are kept under record on texts extracted from identified documents, and to parse the said text fields and then save them to the database (2).
  • the server (3) is configured to transmit the text fields, that are extracted from document and documents saved to the database (2), to the related units at request and/or by using any communication means periodically.
  • inventive system (1) it is ensured that documents received automatically at certain periods are processed by means of artificial intelligence techniques and thereby the said documents are identified and saved by obtaining the requested fields in the documents.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Character Discrimination (AREA)
  • Facsimile Scanning Arrangements (AREA)

Abstract

The present invention relates to a system (1) which enables to automatically recognize document types of documents obtained and scanned from any external source, by means of smart image recognition techniques; to obtain and then save the requested fields within scanned documents.

Description

A DOCUMENT READING SYSTEM
Technical Field
The present invention relates to a system which enables to automatically recognize document types of documents obtained and scanned from any external source, by means of smart image recognition techniques; to obtain and then save the requested fields within scanned documents.
Background of the Invention
In order to carry out transaction on printed papers/ documents in digital environment or to transfer data from the said documents, it is required to transfer documents to digital media. Today, printed documents can be transferred to digital media upon being written, scanned or rendered in digital media manually. Transfer of documents to digital media is commonly used in all sectors and it is quite important in terms of saving of time and resource. However, incorrect data are transferred to system based on user error during transfer of documents to digital media manually.
In the state of the art, various systems are used in order to avoid user errors in transfer of printed documents to digital media. Some of the systems developed are technologies such as OCR (Optical Character Recognition) which enables to convert types of documents such as scanned paper documents, PDF files, or pictures taken by a digital camera into editable and searchable data, or image recognition which is an artificial intelligence technology used in order to automatically identify and categorize objects, places, people, texts and actions in images. Although use of OCR or image recognition technologies enables to convert scanned documents into processable digital files; it is not possible to receive documents, select the requested fields from the document or transfer them to different sources. Therefore, considering the studies and the deficiencies in the state of art, there is a need for a system which enables to automatically recognize document types of documents obtained and scanned from any external source, by means of smart image recognition techniques; to obtain and then save the requested fields within scanned documents; and transmit them to different sources.
The United States patent document no. US10796080, an application in the state of the art, discloses a system for executing artificial intelligence-based document processing transactions. In the system of the said invention; discrepancies needed in the document are determined from contents of a request that is received from the process initiated by the user to ensure that at least one document is automatically created with respect to a process, and the documents that are loaded by users; documents required for the process are automatically selected; and discrepancies needed within the document are created upon being automatically determined from within the documents. In the said invention, requests and documents are received by means of an objective setting engine and then they are examined by an optical character recognition unit, a compiler, a discrepancy identification unit and a natural language processing unit; characters included in documents are determined by the optical character recognition unit and discrepancies are determined by the discrepancy identification unit; discrepancies are added into documents upon being compiled by the compiler.
Summary of the Invention
An objective of the present invention is to realize a system which enables to automatically recognize document types of documents obtained from any external source periodically, by means of smart image recognition techniques; to obtain and then save the requested fields within scanned documents.
Detailed Description of the Invention “A Document Reading System” realized to fulfil the objective of the present invention is shown in the figure attached, in which:
Figure l is a schematic view of the inventive system.
The components illustrated in the figure are individually numbered, where the numbers refer to the following:
1. System
2. Database
3. Server
A. Document server
B. Instant messaging application
C. Chat application
The inventive system (1) which enables to obtain documents from an external source periodically; to automatically recognize document types of documents obtained, by means of smart image recognition techniques; to receive and then save the requested fields within scanned documents comprises: at least one database (2) which is configured to keep the obtained documents under record in it together with the document definitions and such that the parts received from documents are associated with the documents; at least one server (3) which can establish communication with the database (2) such that it will realize data exchange; manage the data within the database (2); is configured to establish communication with eternal servers (A,B,C) and to realize data exchange by using any remote communication protocol; to receive documents by being triggered at certain periods and/or upon certain events; to identify the received documents; to obtain texts by detecting the text fields on the identified documents; to extract the related fields by detecting the requested fields in the obtained text fields and to save them to the database (2).
The database (2) included in the inventive system (1) is in communication with the server (3) and is configured to be managed by the server (3). In a preferred embodiment of the invention, the database (2) is configured to keep the keyword and/or document definitions, that are related to the text fields to be extracted from documents, under record in it. The said database (2) is configured to keep the documents, that are obtained by the server (3), under record in it together with the detected document definitions. The database (2) is also configured to keep the text fields, that are detected on identified documents, under record in it.
The server (3) included in the inventive system (1) is configured to establish communication with remote servers such as document server (A), instant messaging application (B) and chat application (C) by using any remote communication protocol included in the state of the art and to realize data exchange over this communication established. The said server (3) is configured to manage the database (2) by means of transactions such as performing new data recording into the database (2), deleting the recorded data within the database (2) or changing the recorded data within the database (2) and updating the recorded data within the database (2) and to access the recorded data within the database (2). In a preferred embodiment of the invention, the server (3) is configured to run at least one artificial intelligence that can perform data processing or document reading, on it. The said server (3) is configured to receive documents to be identified and processed from external servers such as document server (A), instant messaging application (B) and chat application (C) by being triggered at certain periods. In one embodiment of the invention, the server (3) is configured to receive and then process document images from application servers such as document server (A), instant messaging application (B) and chat application (C), in base64 format that is a coding scheme enabling to transmit and store binary data only in media that use ASCII characters. In a different embodiment of the invention, the server (3) is configured to receive and then process the documents to be processed from external servers such as document server (A), instant messaging application (B) and chat application (C), by logging in to systems of external servers (A, B, C) by means of a robotic process automation that automatizes the processes being carried out in base64 format or manually over a web service by means of an API (Application Programming Interface). The server (3) is configured to process the documents received from external servers such as document server (A), instant messaging application (B) and chat application (C), by means of an artificial intelligence algorithm being run on it and to identify the said documents. In a preferred embodiment of the invention, the server (3) is configured to process and identify the documents received from external servers (A,B,C), by means of an artificial intelligence algorithm such as Inception V3 that is a convolutional neural network enabling image analysis and obj ect detection. The said server (3) is configured to detect text fields on a document by performing optical character recognition on identified documents and to ensure that texts are extracted in text fields. The said server (3) is configured to detect fields and data comprising pre-determined subject, word, expression and/or data by means of natural language processing and regular expression methods in accordance with keywords or definitions, that are kept under record on texts extracted from identified documents, and to parse the said text fields and then save them to the database (2). The server (3) is configured to transmit the text fields, that are extracted from document and documents saved to the database (2), to the related units at request and/or by using any communication means periodically.
Industrial Application of the Invention
In the inventive system (1), it is ensured that documents received automatically at certain periods are processed by means of artificial intelligence techniques and thereby the said documents are identified and saved by obtaining the requested fields in the documents. Within these basic concepts; it is possible to develop various embodiments of the inventive “Document Reading System (1)”; the invention cannot be limited to examples disclosed herein and it is essentially according to claims.

Claims

CLAIMS A system (1) which enables to obtain documents from an external source periodically; to automatically recognize document types of documents obtained, by means of smart image recognition techniques; to receive and then save the requested fields within scanned documents; comprising at least one database (2) which is configured to keep the obtained documents under record in it together with the document definitions and such that the parts received from documents are associated with the documents; and characterized by at least one server (3) which can establish communication with the database (2) such that it will realize data exchange; manage the data within the database (2); is configured to establish communication with eternal servers (A,B,C) and to realize data exchange by using any remote communication protocol; to receive documents by being triggered at certain periods and/or upon certain events; to identify the received documents; to obtain texts by detecting the text fields on the identified documents; to extract the related fields by detecting the requested fields in the obtained text fields and to save them to the database (2). A system (1) according to Claim 1 ; characterized by the database (2) which is in communication with the server (3) and is configured to be managed by the server (3). A system (1) according to Claim 1 or 2; characterized by the database (2) which is configured to keep the keyword and/or document definitions, that are related to the text fields to be extracted from documents, under record in it.
7
4. A system (1) according to any of the preceding claims; characterized by the database (2) which is configured to keep the documents, that are obtained by the server (3), under record in it together with the detected document definitions.
5. A system (1) according to any of the preceding claims; characterized by the database (2) which is configured to keep the text fields, that are detected on identified documents, under record in it.
6. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to establish communication with remote servers such as document server (A), instant messaging application (B) and chat application (C) by using any remote communication protocol and to realize data exchange over this communication established.
7. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to manage the database (2) by means of transactions such as performing new data recording into the database (2), deleting the recorded data within the database (2) or changing the recorded data within the database (2) and updating the recorded data within the database (2) and to access the recorded data within the database (2).
8. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to run at least one artificial intelligence that can perform data processing or document reading, on it.
9. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to receive documents to be identified and processed from external servers such as document server (A), instant messaging application (B) and chat application (C) by being triggered at certain periods.
8 A system (1) according to Claim 9; characterized by the server (3) which is configured to receive and then process document images from application servers such as document server (A), instant messaging application (B) and chat application (C), in base64 format that is a coding scheme enabling to transmit and store binary data only in media that use ASCII characters. A system (1) according to Claim 9; characterized by the server (3) which is configured to receive and then process the documents to be processed from external servers such as document server (A), instant messaging application (B) and chat application (C), by logging in to systems of external servers (A, B, C) by means of a robotic process automation that automatizes the processes being carried out in base64 format or manually over a web service by means of an API. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to process the documents received from external servers such as document server (A), instant messaging application (B) and chat application (C), by means of an artificial intelligence algorithm being run on it and to identify the said documents. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to process and identify the documents received from external servers (A,B,C), by means of an artificial intelligence algorithm such as Inception V3 that is a convolutional neural network enabling image analysis and object detection. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to detect text fields on the document by performing optical character recognition on identified documents and to ensure that texts are extracted in text fields.
9
15. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to detect fields and data comprising predetermined subject, word, expression and/or data by means of natural language processing and regular expression methods in accordance with keywords or definitions, that are kept under record on texts extracted from identified documents, and to parse the said text fields and then save them to the database (2). 16. A system (1) according to any of the preceding claims; characterized by the server (3) which is configured to transmit the text fields, that are extracted from document and documents saved to the database (2), to the related units at request and/or by using any communication means periodically.
10
PCT/TR2022/050896 2021-11-30 2022-08-23 A document reading system WO2023101636A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TR2021/018731 TR2021018731A1 (en) 2021-11-30 A DOCUMENT READING SYSTEM
TR2021018731 2021-11-30

Publications (2)

Publication Number Publication Date
WO2023101636A2 true WO2023101636A2 (en) 2023-06-08
WO2023101636A3 WO2023101636A3 (en) 2023-07-27

Family

ID=86613199

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/TR2022/050896 WO2023101636A2 (en) 2021-11-30 2022-08-23 A document reading system

Country Status (1)

Country Link
WO (1) WO2023101636A2 (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11170055B2 (en) * 2018-12-28 2021-11-09 Open Text Sa Ulc Artificial intelligence augmented document capture and processing systems and methods
US11328524B2 (en) * 2019-07-08 2022-05-10 UiPath Inc. Systems and methods for automatic data extraction from document images

Also Published As

Publication number Publication date
WO2023101636A3 (en) 2023-07-27

Similar Documents

Publication Publication Date Title
US11816165B2 (en) Identification of fields in documents with neural networks without templates
US20230206000A1 (en) Data-driven structure extraction from text documents
US11055527B2 (en) System and method for information extraction with character level features
US20210366055A1 (en) Systems and methods for generating accurate transaction data and manipulation
US9836520B2 (en) System and method for automatically validating classified data objects
AU2019419891B2 (en) System and method for spatial encoding and feature generators for enhancing information extraction
CN112464927B (en) Information extraction method, device and system
US11880435B2 (en) Determination of intermediate representations of discovered document structures
US20220374473A1 (en) System for graph-based clustering of documents
US20230177267A1 (en) Automated classification and interpretation of life science documents
EP4141818A1 (en) Document digitization, transformation and validation
Sunder et al. One-shot information extraction from document images using neuro-deductive program synthesis
US9952942B2 (en) System for distributed data processing with auto-recovery
WO2023101636A2 (en) A document reading system
Stančić et al. Optimisation of archival processes involving digitisation of typewritten documents
CN105913071A (en) Information processing device, information processing system and information processing method
CN105389378A (en) System for integrating separate data
US20220405499A1 (en) Method and system for extracting information from a document
CN115146583A (en) Self-host structured extraction and association method and device for terms and storage medium
US11363162B2 (en) System and method for automated organization of scanned text documents
US10522246B2 (en) Concepts for extracting lab data
CN113901817A (en) Document classification method and device, computer equipment and storage medium
Pattnaik et al. A Framework to Detect Digital Text Using Android Based Smartphone
Shahin et al. Deploying Optical Character Recognition to Improve Material Handling and Processing
KR102345481B1 (en) Method and system for deciding keyword related with stock item based on artificial intelligence