A document authenticity identification method is provided. A dynamic anti-counterfeiting point is detected in each document image of a subset of a plurality of document images. A static anti-counterfeiting point is detected in a document image of the plurality of document images. A static anti-counterfeiting point feature is generated based on image feature information of the static anti-counterfeiting point that is extracted from the document image. A dynamic anti-counterfeiting point feature is generated based on image feature information of the dynamic anti-counterfeiting point and variation feature information of the dynamic anti-counterfeiting point. A first authenticity result corresponding to the static anti-counterfeiting point is determined based on the static anti-counterfeiting point feature. A second authenticity result corresponding to the dynamic anti-counterfeiting point is determined based on the dynamic anti-counterfeiting point feature. Authenticity of the document is determined based on the first authenticity result and the second authenticity result.

A system and method are provided wherein, in at least one form, artificial intelligence is used to identify objects in a document to be considered for metallic rendering or printing on a substrate. Then, the options for printing, including the considerations for rendering in metallic toner or ink, are, in at least one form, presented to the user for acceptance or rejection before the actual printing is initiated.

Systems and methods are used to generate contact type predictions that route user customer service requests within a support platform. The contact type predictions are generated using a hybrid model that includes a deep learning component and a business logic component. The deep learning component may generate a multi-channel output based on text features and context features. The multi-channel output is modified based on one or more business rules to generate the contact type predictions.

Systems and methods are used to generate contact type predictions that route user customer service requests within a support platform. The contact type predictions are generated using a hybrid model that includes a deep learning component and a business logic component. The deep learning component may generate a multi-channel output based on text features and context features. The multi-channel output is modified based on one or more business rules to generate the contact type predictions.

A system for format-agnostic document ingestion including a document ingestion server and a database is disclosed. The server is configured to receive an image of a document comprising text in an unknown format, convert the image, using OCR, into a plurality of text elements a content, a size, and an absolute position. The server is also configured to retrieve data detectors from the database, each associated with a data type anticipated to be in the document, and comprising at least one identifier and direction, and at least one validation criteria. The server is also configured to identify a potential descriptor by comparing the content of each text element with the at least one identifier, and then determine if the text element pointed to by the data detector meets the validation criteria. Finally, the server is configured to associate the validated text element with the data detector, and store the content.

Provided is an image processing apparatus that improves the performance when performing image processing accompanying an analysis. An image acquisition unit acquires processing image data for performing processing. A normal image processing unit performs normal image processing for normal output on the processing image data acquired by the image acquisition unit and outputs the normal image data. An analysis image processing unit performs analysis image processing accompanied by analysis in parallel with the normal image processing by the normal image processing unit and outputs the analysis image data. A merge processing unit merges the normal image data output by the normal image processing unit and the analysis image data output by the analysis image processing unit and outputs print data for printing.

Provided is an image processing apparatus that improves the performance when performing image processing accompanying an analysis. An image acquisition unit acquires processing image data for performing processing. A normal image processing unit performs normal image processing for normal output on the processing image data acquired by the image acquisition unit and outputs the normal image data. An analysis image processing unit performs analysis image processing accompanied by analysis in parallel with the normal image processing by the normal image processing unit and outputs the analysis image data. A merge processing unit merges the normal image data output by the normal image processing unit and the analysis image data output by the analysis image processing unit and outputs print data for printing.

In a method for distributed upload of documents an upload email address is assigned to a user and associated with a searchable document database accessible by the user via a user device and a network. Sender acceptance criteria are established for the upload email address. An email addressed to the upload email address and having a sender email address is received from an email sender via the network. A determination is made as to whether the received email meets sender acceptance criteria. Responsive to a determination that the email meets sender acceptance criteria, documents attached to the email are identified. Each identified document is associated with a document record comprising a document identifier and a sender identifier associated with the email sender and is stored in the searchable document database with the document record.

Disclosed techniques provide just-in-time error detection and correction within a multi-edit session. The multi-edit session may have a scope definition across a subset of devices within a network, each device having a set of network configuration parameters. The system may be implemented, in part, by obtaining a restricted grammar language (RGL) rule set derived from devices on the network within and outside of the edit scope. After detecting an indication of an edit to configuration information, the techniques may compare the edit (e.g., unsaved or saved change) to the RGL. Based on detection of a suspect entry, information may be presented to a user of the multi-edit session. The information may include suggestions or corrections relative to user edits (e.g., just-in-time). The suggestions or corrections may be derived using the RGL based on consistency of the proposed edit with respect to information utilized to generate the RGL.

A Computer Vision (CV) model generated by a Machine Learning (ML) system may be retrained for more accurate computer image analysis in Robotic Process Automation (RPA). A designer application may receive a selection of a misidentified or non-identified graphical component in an image form a user, determine representative data of an area of the image that includes the selection, and transmit the representative data and the image to an image database. A reviewer may execute the CV model, or cause the CV model to be executed, to confirm that the error exists, and if so, send the image and a correct label to an ML system for retraining. While the CV model is being retrained, an alternative image recognition model may be used to identify the misidentified or non-identified graphical component.