A generation method implemented by a computer, the generation method including: acquiring, by a processor circuit of the computer, read information generated from a reading result that is a document image obtained by imaging a paper document; and generating, by the processor circuit, an electronic document with a signature image that includes the electronic document and the signature image by adding the signature image obtained by imaging a signature written or stamped on the paper document to an electronic document that corresponds to the acquired read information.

A generation method implemented by a computer, the generation method including: acquiring, by a processor circuit of the computer, read information generated from a reading result that is a document image obtained by imaging a paper document; and generating, by the processor circuit, an electronic document with a signature image that includes the electronic document and the signature image by adding the signature image obtained by imaging a signature written or stamped on the paper document to an electronic document that corresponds to the acquired read information.

Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

Examples provide a self-supervised language model for document-to-document similarity scoring and ranking long documents of arbitrary length in an absence of similarity labels. In a first stage of a two-staged hierarchical scoring, a sentence similarity matrix is created for each paragraph in the candidate document. A sentence similarity score is calculated based on the sentence similarity matrix. In the second stage, a paragraph similarity matrix is constructed based on aggregated sentence similarity scores associated with the first candidate document. A total similarity score for the document is calculated based on the normalize the paragraph similarity matrix for each candidate document in a collection of documents. The model is trained using a masked language model and intra-and-inter document sampling. The documents are ranked based on the similarity scores for the documents.

A system and method for classifying digital images is presented. The method includes extracting a plurality of descriptive data items of a transaction evidence from a digital image indicating a plurality of purchased items; searching in data source for informative data based on the extracted plurality of descriptive data items, wherein the informative data includes a price; determining a correlated amount for each of at least one of the plurality of descriptive data items, wherein the correlated amount determined for one of the descriptive data items defines a paid price for the descriptive data item; determining, based on at least one expense type classification rule, a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and each of the correlated amount; and classifying the digital image based on the primary expense type.

A system and method for classifying digital images is presented. The method includes extracting a plurality of descriptive data items of a transaction evidence from a digital image indicating a plurality of purchased items; searching in data source for informative data based on the extracted plurality of descriptive data items, wherein the informative data includes a price; determining a correlated amount for each of at least one of the plurality of descriptive data items, wherein the correlated amount determined for one of the descriptive data items defines a paid price for the descriptive data item; determining, based on at least one expense type classification rule, a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and each of the correlated amount; and classifying the digital image based on the primary expense type.

A method and system are used for managing and classifying electronic document images. Each of the electronic document images is divided into an array of image segments. The method extracts image features from each of the image segments to obtain numerical coefficients for each of the image segments. The numerical coefficients are compared with each other to generate sub-codes. A classification code is determined as a combination of the sub-codes. The classification codes of a plurality of electronic document images can be stored in a database for further analysis. Based on the classification codes, similarity rates between at two document images can be determined.

A translation support device includes a storage device and a control device. The storage device stores therein an original document file in which original document data is recorded, and a translated document file in which translated document data, representing a translated document translated from an original document represented by the original document data, is recorded. The control device includes a processor, and acts as a detector and a generator, when the processor executes a control program. The detector detects, through comparison between the original document file and the translated document file, a same portion contained in common in both of the files, as an untranslated portion. The generator generates untranslated portion information indicating the untranslated portion.

The invention relates to the field of providing a trusted environment for executing an analogue-digital signature. The claimed document-signing device in the form of a stylus includes a protective compartment, in which the following are disposed: a microcontroller with a programme code; a memory with a secret digital signature key; and additionally inertial sensors, which are connected to the microcontroller; a lens; and a camera, which is also connected to the microcontroller. A wireless interface is used in order to communicate with a computer. The inertial sensors serve to verify the handwritten signature of the user, while the lens and camera serve to carry out a comparison with the text of an electronic document uploaded via the wireless interface. In this way it is ensured that verified information enters the trusted environment of the stylus.

Systems and methods for identifying a presence of a completed document are disclosed. The system may receive an image file from a client device associated with a first document, identify one or more image regions within the image file corresponding to a presence of one or more extractable data entries, selectively extract the one or more extractable data entries, and determine whether the one or more extractable data entries match one or more stored data entries. When the one or more extractable data entries match, the system may determine the status of the first document as completed. When the one or more extractable data entries do not match, the system may proactively replace one or more inconsistent extractable data entries with corresponding stored data entries to form a corrected first document, and generate a request for a client to verify the corrected first document.