Kyocera Document Solutions Inc.

Allan Sahagun

Jacek Joseph Matysiak

Christian Olmstead Holmes

Michaela M Guerrera

Sandra Da Silva

Disclosed are a method for real-time dynamic web page display enhancement and a computing apparatus configured to implement said method. The method includes requesting at least one web page code file using a web browser, extracting the at least one style tag and the at least one variable attribute from the at least one web page code file using an extraction module, sending a request signal from the extraction module to an attribute database, returning from the attribute database to a user interface controller a response signal, sending a present user interface signal from the user interface controller to the web browser, accepting at least one selection signal from the web user through the at least one display control of the user interface to the web browser, and generating an enhanced web page.

Fine-grained control of visual display and scaling attributes

A method of evolving web pages or forms to better accord with usability metrics involves generating a heat map encoding of user interaction with a web page or electronic form, transforming the heat map with a machine neural network or other machine learning algorithm into at least one visual element placement prioritization for the web page or electronic form, and applying the visual element placement prioritization to modify a layout of the web page or electronic form.

Machine learning optimization of machine user interfaces

Systems and methods relate generally to image-to-text recognition. In an example thereof, a device captures an image and generates image data and associated meta data. A parser parses the image data and the meta data into sub-image data and sub-meta data, respectively. A recognizer renders the sub-image data into strings for one or more identified objects in the sub-image data. A mapper-controller maps the sub-image data in association with the sub-meta data to generate a data structure having positional information with respect to the one or more identified objects. A dictionary store is accessed by a natural language processing engine responsive to the strings. The natural language processing engine converts the strings into a natural language expression for the strings and the positional information obtained from the data structure.

Image-to-text recognition for a sequence of images

Methods and apparatus for validating paper forms are provided. A node can receive paper-form data from a paper form that has first and second data items (DIs). The node can: determine first and second metadata for the first and second DIs respectively, determine respective first and second validation entities (VEs) to validate respective values of the first and second DIs based on the respective first and second metadata, where the first and second VEs can differ, provide a user interface (UI) including a display of the first DI, receive a validation status for the first DI via the first UI from the first VE, select a first distributed storage system (DSS) associated with the first DI, and record the value of the first DI and the validation status in the first DSS. The node can generate an output related to the paper-form data based on the first DSS.

Method to create a secure distributed data validation system using a distributed storage system and artificial intelligence

Method(s) and apparatus(es) relating generally to an electronic device having a display and a touch-sensitive input device are disclosed. In such a method, a first keypad is displayed on the display. Obtained is sensed information from the touch-sensitive input device responsive to user input in association with the first keypad. The user input is determined to be for a second keypad different from the first keypad. A corresponding input to the user input is determined using the sensed information in association with the second keypad. The corresponding input is displayed on the display.

Suggestion of alternate user input using a different user interface

Methods and apparatus for storing trackable actions in a ledger are provided. A computing device acting as a node can receive a notification of a trackable action. The trackable action can relate to a printer-related transaction and/or an entry-or-exit transaction. The node can generate a block hash value using a hash function operating on data that includes at least part of the notification. The node can add a new block to a ledger, the new block including: the block hash value, a reference to a previous-block hash value of a previous block in the ledger, and the data that includes at least part of the notification of the trackable action. The node can receive a query related to the ledger. In response to the query, the node can provide an output that includes information about the trackable action.

Deploying multiple nodes for creation of blockchains for trackable actions

System and method relating generally to an electronic device are described. In such a method, content is accessed by the electronic device to display the accessed content on at least a portion of a screen. At least one original dimension of the accessed content is determined to exceed at least one threshold dimension corresponding thereto in order to display the accessed content with the at least one original dimension on at least the portion of the screen. Responsive to a determination that the at least one original dimension exceeds the at least one threshold dimension, a subset of the accessed content is obtained with subset dimensions thereof each less than or equal to corresponding display region dimensions including the at least one threshold dimension to display the subset on at least the portion of the screen. The subset is displayed on at least the portion of the screen.

Image handling to select a subject of an image to display and conceal a remainder of the image

Suggestion of alternate user input using different user interface

The present disclosure is directed to systems, methods, and devices that enable the revising of Optical Character Recognition (OCR) data by indexing and displaying potential error locations within the OCR data. The primary method for revising the OCR data includes a terminal device indexing, displaying, receiving editing operations for, and editing the OCR data. The terminal device is configured to revise OCR data and includes an OCR review element, which, in some embodiments, is a software stored on a non-transitory, computer-readable medium, that is executed by a processing unit to cause the terminal device to index, display, receive editing operations for, and edit the OCR data.

Growing community of inventors

Oakland, CA, United States of America

Allan Sahagun