Methods and systems for artificial intelligence (AI)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.

To extract necessary information, documents are received and classified, converted to text, and stored in a database. A request for information is then received, and relevant documents and/or document passages are selected from the stored documents. The needed information is then extracted from the relevant documents. The various processes use one or more artificial intelligence (AI), image processing, and/or natural language processing (NLP) techniques as well as knowledge-based and rule-based techniques.

To extract necessary information, documents are received and classified, converted to text, and stored in a database. A request for information is then received, and relevant documents and/or document passages are selected from the stored documents. The needed information is then extracted from the relevant documents. The various processes use one or more artificial intelligence (AI), image processing, and/or natural language processing (NLP) techniques as well as knowledge-based and rule-based techniques.

Techniques for processing an image of a check captured using a mobile device are provided. The check image is processed to determine whether the check can be deposited at a bank via a mobile deposit process. The system can identify regions of the check—such as the endorsement area—to determine if the check has been properly endorsed. The system can be implemented on a mobile device and/or a server, where the mobile device routes the check image to the server for processing. If the check cannot be deposited, a rejection is forwarded in real time to the mobile device for possible correction.

There is provided a prediction device that analyzes a chart image indicating price fluctuations of a financial instrument and predicts a future price of the financial instrument, the prediction device including an image acquiring unit that acquires a prediction target image to be a prediction target of the future price, an outputting unit that inputs the prediction target image to a learned model and outputs type data serving as a type of a chart included in the prediction target image from the learned model, and a predicting unit that outputs a predicted value of the future price based on a price after a lapse of a predetermined period from the type data.

A distributed learning method of a server managing an ID card recognition model includes releasing an ID card recognition model performing at least one convolution operation on an ID card image captured in a user terminal so that the user terminal uses the ID card recognition model, receiving update information of the ID card recognition model generated according to an ID card recognition result of the released ID card recognition model, and verifying the update information received from the user terminal and updating the ID card recognition model using the verified update information.

A distributed learning method of a server managing an ID card recognition model includes releasing an ID card recognition model performing at least one convolution operation on an ID card image captured in a user terminal so that the user terminal uses the ID card recognition model, receiving update information of the ID card recognition model generated according to an ID card recognition result of the released ID card recognition model, and verifying the update information received from the user terminal and updating the ID card recognition model using the verified update information.

Systems, devices, methods, and instructions for travel document validation, including receiving data for one or more travel documents, generating a set of features for artificial intelligence model training, validating, and testing, upon receiving data for a plurality of travel documents, data from a first subset of travel documents is used to train an artificial intelligence model, a second subset of travel documents is used to validate the artificial intelligence model, and a third subset of travel documents is used to test the artificial intelligence model.

Systems, devices, methods, and instructions for travel document validation, including receiving data for one or more travel documents, generating a set of features for artificial intelligence model training, validating, and testing, upon receiving data for a plurality of travel documents, data from a first subset of travel documents is used to train an artificial intelligence model, a second subset of travel documents is used to validate the artificial intelligence model, and a third subset of travel documents is used to test the artificial intelligence model.

An information processing apparatus (10) registers a set of item names corresponding to an item name field associated with an item value field in a predetermined business form and identifies an association of an item name field with an item value field included in the business form to be processed based on the registered set of item names.