Abstract: Systems and methods are provided for implementing confidence enhancement for responses by document-based large language models (“LLMs”) or other AI/ML systems. A first prompt is generated based on data items that are previously received or accessed. The first prompt is used by a first LLM or AI/ML system to extract requested information from the data items. One or more citations are generated and presented within a structured object together with a representation of the extracted information, in some cases, as output from a second LLM or AI/ML system. In some cases, the citations and/or the representation may be verified by a third LLM or AI/ML system, and reliability indicators may be generated for the citations and/or the representation based on determined accuracy of the citations and/or the representation. In this manner, the common issue of hallucinations may be mitigated.

Abstract: An image generation system enables user input during the process of training a generative model to influence the model's ability to generate new images with desired visual features. A source generative model for a source domain is fine-tuned using training images in a target domain to provide an adapted generative model for the target domain. Interpretable factors are determined for the source generative model and the adapted generative model. A user interface is provided that enables a user to select one or more interpretable factors. The user-selected interpretable factor(s) are used to generate a user-adapted generative model, for instance, by using a loss function based on the user-selected interpretable factor(s). The user-adapted generative model can be used to create new images in the target domain.

Abstract: A method, system, and computer program product is provided for tokenizing document citations. The method may include tokenizing each string of a plurality of strings into at least one citation token representing at least one citation parameter, resulting in a plurality of citation tokens, grouping the plurality of citation tokens into a plurality of token groups, each token group of the plurality of token groups including at least one citation token representing a separate citation in the at least one textual document, assigning metadata to each token group of the plurality of token groups, and generating a normalized citation for each token group of the plurality of token groups based on the metadata.

Abstract: A method for processing an image of a physical document to show a redacted portion including: identifying a tag associated with the redacted portion and including first user rights; obtaining, using the identified tag, a digital copy of the physical document including a non-redacted form of the redacted portion; receiving, from an external device, second user rights; determining that the second user rights match the first user rights; outputting, based on the determination, information indicating that the non-redacted form of the redacted portion is able to be shown; receiving, in response to the non-redacted form being able to be shown, an instruction to display the non-redacted form; and displaying, based on the instruction and using a projector onto a surface a predetermined distance from the physical document, the non-redacted form of the redacted portion.

Abstract: When processing a request containing personal information, personal information may be needed to respond to the request, but it may be desired to limit storage of personal information for privacy reasons. To accomplish both objectives, text of a message may be processed using multiple levels of redaction. A first level of redaction may replace digits of the text with a token so that sensitive numbers, such as credit card numbers or social security numbers are no longer present. A second level of redaction may replace one or more words of the text with a label indicating the text that was present, such as by replacing an address with a label indicating that an address was present or by replacing a credit card number with a label indicating that a credit card number was present.

Abstract: A system for dynamically displaying specific sections of a file depending on a user identity is provided. The system utilizes access control data to enable an author to generate and share a file with a number of consumers and have each recipient view a customized set of sections of the file depending on access permissions associated with each recipient. The file can be in any format, e.g., a word processing document, presentation document, a media file, or any other file having a number of sections. A section of a file can be any definitive unit of data, such as a page, slide, tab, worksheet, video segment, audio segment, etc. Permissions can be based on a user's permission level, work history, skill level, role in an organization, title, etc. The system can also prevent access to certain sections of a file depending on the permissions associated with a consumer.

Abstract: The disclosed embodiments include a computer-implemented method to facilitate generating expense reports. The embodiments include causing display of a user interface on a computing device (e.g., smartphone). The user interface presents an expense report form including control elements (e.g., text entry boxes). The method further includes presenting suggestions as inputs for a selected control element such that any suggestion that is formulated based on any journey taken by the user is prioritized for display over any generic suggestion that is not formulated based on a journey taken by the user.

Abstract: A method for sharing a digital image between a first user terminal and at least one second user terminal over a communications network. The method includes: displaying on the second terminal a “degraded image”, the degraded image being obtained from a “first image” by digital processing of the first image, the digital processing visually concealing content of the first image; and following detection of an interaction of a user with the screen of the second terminal: defining a zone of interaction of the degraded image depending on the location of the interaction on the screen; obtaining a portion of the first image corresponding to the determined zone of the degraded image; and displaying on the screen of the second terminal the portion of the first image in the place of the corresponding area of the degraded image, throughout the duration of the interaction of the user with the screen.

Abstract: Embodiments of systems and method for assistance in document composition in the context of a document editor are disclosed. Specifically, embodiments may utilize a document definition syntax that allows a user to define a document that includes a set of document sections with identifiers and definitions. A client document compositor may be integrated with the document editor and communicate with a document composition platform to obtain a data section for substitution in the document in place of a document section.

Abstract: A method, computer program and system for performing a find and replace editing operation of a text starting from a couple of initial find and replace expressions provided by the user, applying each rule defining admissible inflected forms of the initial find expression and the initial replace expression, to the initial find and replace expressions to identify all the derived couples of find and replace expressions. The find expression and the replace expression of the derived couples correspond to inflected forms of the initial find and replace expressions. Then, for each match in the text of the find expression of the derived couples, proposing to the user the derived couples for replacement in the text.

Abstract: A neural network may be used to remove personal information from text (such as names, addresses, credit card numbers, or social security numbers), and replace the personal information with a label indicating the type or class of the removed information. The neural network may comprise multiple layers that compute a context vector for words of the text, compute label scores for words of the text using the context vectors, and select a label for each word using the label scores. Words corresponding to certain labels may be replaced with a label, such as replacing the digits of a credit card number with a label <cc_number>. The redacted text may then be presented to a person or stored for later processing.

Abstract: Sensitive information displayed on a screen is protected against leakage and loss. A section of a bitmap containing sensitive information is defined as a protection region. A protection marker identifying the protection region is embedded into the bitmap. The defined protection region is divided into multiple sub-regions, and a separate sub-region protection marker is embedded in each sub-region of the original protection region. The defining, embedding and dividing are performed before the bitmap is copied to the screen buffer. When content that was displayed on the screen has been captured, for example by screen capturing software, the captured content is parsed. All sub-region protection markers embedded in the captured content are detected, and a real protection region in the captured content is calculated, based on information in the detected sub-region protection markers. The sensitive information in the captured content is erased.

Abstract: A computer-implemented method executed in a computational device to reserve a room in a building of a campus includes receiving input from a user identifying features associated with a room, retrieving floorplan level mapping information based on the input, retrieving floorplan level security information based on the input, generating a list of potential reservation locations based on the floorplan level mapping information and the floorplan level security information, and rendering at least a portion of the list of potential reservation locations to a screen.

Abstract: The present invention describes a system and method for tokenization of data. The system includes a receiver configured to receive a request for tokenization. The request for tokenization comprises an input data to be tokenized. The system also includes a parser configured to determine one or more datatype from the input data. The system further includes a trained artificial neural network to generate a token for the input data based on a tokenization technique corresponding to the datatype of the input data.

Abstract: A method comprises receiving a first user communication, accessing a directory entry associated with the user, accessing, by a processor, a database stored in a memory that includes content designated as private that is associated with the user in the directory, determining with the processor whether the first user communication includes content designated as private that is associated with the user, generating a second user communication by removing the content designated as private that is associated with the user from the first user communication, and sending the second user communication to an electronic personal assistant.

Abstract: Personal information is retrieved from at least one data source and personal information associated with a first individual is identified. A document is generated that is a version of a first document, wherein the personal information associated with the first individual cannot be discerned.

Abstract: Technologies for predictive texting on a communication device includes determining an identity of a recipient of a textual communication and determining a suggested textual phrase based on a user selected textual character and the identity of the recipient. The suggested textual phrase may be embodied as a single word or a collection of words. The communication device may store a recipient-based predictive text dictionary that correlates user selected textual characters to suggested textual phrases based on the identity of the recipient. In this way, the suggested textual phrase for a particular character or collection of characters may change based on the identity of the recipient.

Abstract: Disclosed are an electronic device and an electronic device control method that can use address information on the basis of an inputted string. The disclosed electronic device is provided with: a memory (44) that stores an address book that has names and address information; input keys (14) for inputting strings; a display unit (21) that displays both an input string inputted via the input keys (14) and a conversion candidate string which is a conversion candidate for the input string; a search execution unit (46) that searches the address book on the basis of an input string inputted via the input keys (14); and a control unit (45) that has the display unit (21) display, as a conversion candidate string, a name or address information that corresponds to the input string and was searched for by the search execution unit (46).

Abstract: Techniques are described for an automated grammar teaching system that displays sentences and allows a user to identify subject-verb agreement errors within the sentences, if any. The sentences may be presented as single sentences or as part of a paragraph. The user may be asked to determine whether the sentences are correct or incorrect, to identify the locations of verbs that should agree with a subject of the sentence, to identify the core noun that determines whether the subject is singular or plural, and to provide a new verb that agrees with the subject. To guide the user, user responses may trigger the display of remediation information, which may include identifying one or more grammar elements of the sentences that are relevant to identifying the subject-verb agreement errors. New sentences in the teaching system may be selected based on historical data maintained for the user.

Abstract: A grammar teaching system provides adaptive practice to build students' grammar skills with respect to verb tense errors. The system displays a sentence to a user, and allows the user to identify the locations of verbs within the sentence and tenses of the identified verbs. The system reinforces correct designations of verbs using visual cues. If a user incorrectly identifies a term as a verb within a sentence, then the system displays information to help the user understand the nature of the incorrectly designated term. The system allows the user to determine whether the sentence includes a verb tense error and to select a particular verb in the sentence to replace in order to correct any verb tense error. The system allows the user to obtain help in correcting a verb tense error by providing optional tasks that step the user through the reasoning needed to correct the error.

Abstract: Techniques are described for an automated grammar teaching system that displays sentences and allows a user to identify preposition errors within the sentences, if any. The sentences may be presented as single sentences or as part of a paragraph. The user may be asked to determine whether the sentences are correct or incorrect, to identify the locations of missing or incorrect prepositions, to provide a new correct preposition, and to identify a correct preposition usage category for the new preposition. To guide the user, an incorrect user response may trigger the display of remediation information, which may include identifying one or more grammar elements of the sentences that are relevant to identifying the preposition errors. New sentences in the teaching system may be selected based on historical data maintained for the user.

Abstract: An apparatus comprising a controller, wherein said controller is arranged to receive touch input identifying an original string; receive a multi-touch input gesture comprising a first and a second touch point in which a distance between a first touch point and a second touch point is changed and to replace said identified original string with a replacement string in response thereto.

Abstract: A system and a method for loading and displaying content from a plurality of content sources on a user computer is disclosed. The content is placed on a web document having a first web page and at least one other web page. The contents in the first web page are loaded and displayed on the user computer and the contents of the other web pages are loaded in cache and displayed on the first web page after the contents have been fully loaded.

Abstract: A computer receives user preferences. The computer receives a document, wherein the document includes an image. The computer determines that the image contains embedded text. The computer determines that the embedded text does not satisfy the received user preferences. The computer modifies the embedded text to satisfy user preferences.

Abstract: A computer program product is provided and includes a non-transitory tangible storage medium readable by a processing circuit and on which instructions are stored for execution by the processing circuit for performing a method. The method includes enabling retrieval of a keyboard pressed sequence of characters of a first type, permitting a re-selection of characters of a second type, which are associated with the keyboard pressed sequence of the characters of the first type and permitting modification of the keyboard pressed sequence of the characters of the first type to initiate a search for and retrieval of characters of the second type.

Abstract: A method for operating an electronic device with a display includes: displaying a virtual keypad on a screen of the display; receiving one or more characters from a user through the virtual keypad; displaying the one or more characters on the screen; displaying one or more recommended words at a location close to the virtual keypad on the screen based on at least some of the one or more characters; displaying a first key on the screen; maintaining the one or more characters on the screen when a user input for selecting the first key is received; and removing the recommended words from the screen. Furthermore, other embodiments can be made.

Abstract: A method includes incorporating a local service within a user's device, accessing at least one external service via the user's device; starting a service request for the at least one external service from an input area of the user's device, causing the local service to determine at least one possible completion for the service request based on the input to the at least one external service, and providing the at least one possible completion to the input area of the user's device, wherein the local service consults at least one user context before providing the at least one possible completion to the input area of the user's device.

Abstract: An information processing apparatus for representing at least one candidate for a character string to be input based on at least one input character includes an acquisition unit configured to obtain situation information which represents the situation in which the information processing apparatus exists based on the information detected by the at least one sensor. The information processing apparatus further includes a prediction unit configured to predict at least one character string to be input based on the at least one character input by a user operation, a storage unit configured to store two or more character strings with each of the two or more character strings being associated with situation information which represents the situation in which the character string is used and a representation unit configured to represent at least one character string predicted by the prediction unit.

Abstract: An exemplary method includes a virtual interface adjustment system detecting, based on user input data associated with user input received by way of a virtual interface of a user device, an erroneous input pattern that includes at least one unintentional input, determining, based on the erroneous input pattern, an adjustment procedure configured to adjust the virtual interface to avert future unintentional inputs that correspond to the at least one unintentional input of the erroneous input pattern, determining an adjustment procedure trigger for the adjustment procedure, activating the adjustment procedure trigger, detecting, after the activating, an occurrence of the adjustment procedure trigger, and executing, in response to the detecting of the occurrence of the adjustment procedure trigger, the adjustment procedure to avert the future unintentional inputs that correspond to the at least one unintentional input of the erroneous input pattern. Corresponding methods and systems are also described.

Abstract: A transcript interface for displaying a plurality of words of a transcript in a text editor can be provided and configured to receive a command to edit the transcript. Limited edits to data corresponding to the transcript can be made in response to commands received via the user interface module. For example, edits may be limited to selection of a single word in the text editor for editing via a given command. The edit may affect an adjacent word in some instances, such as when two adjacent words are merged. In some embodiments, data corresponding to the selected word of the transcript is changed to reflect the edit without changing data defining the relative timing of those words of the transcript that are not adjacent to the selected word.

Abstract: Disclosed is a system and method for suggesting messages that are automatically learned, personalized and diversified by leveraging messages sent by a large number of users in order to provide message completions that are as engaging as possible. The disclosed systems and methods learn from recurrent messages sent to a recipient, and suggest message completions based upon user behavior. The systems and methods compute a ranked list of suggested message completions after every key stroke or character input, and if the list satisfies a given confidence threshold, it is returned and displayed to the user.

Abstract: Described herein are techniques for rendering additional keys on a display of an electronic device based on one or more characteristics of a user's selection of another key. After rendering the additional keys, the user may thereafter select one of the additional keys now available and rendered on the display.

Abstract: A computer-based detection tool for detecting whether content within a given document is common to content within a plurality of other, existing documents, the detection tool comprising: a character string recognizer for recognizing character strings in the content of the given document; a character string distinguisher for distinguishing main character strings and auxiliary character strings in the recognized character strings by reference to a closed list of main character strings; an encoder for encoding the content of the given document by assigning one or more digits to each main character string and one or more digits to auxiliary character strings; and a matcher for matching a plurality of n-digit streams from within the encoded content with any corresponding n-digit streams within previously-encoded content of the one or more other documents. The character strings may be encoded as a bit-stream.

Abstract: The invention provides methods and apparatus for securing personalized or sensitive information appearing in digital images. Digital images containing information to be secured is processed and divided into a plurality of image cells. At least one image cell from the plurality of image cells is selected and redacted or altered to render the information to be secured with the selected image cells indecipherable. The invention also provides methods and apparatus for transmitting or streaming unredacted image cells alone or in combination with redacted image cells for secured viewing on a user browser or computer.

Abstract: A method and system to secure the display of advertisements on web browsers. A method according to an embodiment includes: interpreting a markup file in a virtual machine, converting displayable elements of the markup file to one or a plurality of images and constructing a modified markup file comprising the at least one image file and a scripting language code adapted to cause a user terminal upon which it is executed to transmit coordinate information defining the position of a user-controlled cursor and action information defining a clicking action.

Abstract: A support apparatus, computer-implemented method, and article of manufacture for supporting a processing of a character string in a document. The support apparatus includes: a document storage unit; a designation reception unit; a document acquisition unit; a historical-information storage unit; a reference-information generator; and a presentation unit. The method includes: receiving designation from a user; acquiring a document from the document storage device based on the designation by the user; reading pieces of historical information related to the acquired document from the historical-information storage device, and thereby generating reference information for helping the user to select a processing of the character string in the document; and presenting, to the user, a screen for receiving the designation of the processing of the character string in the acquired document, together with the reference information.

Abstract: Non-destructive manipulation of images in a web development environment (WDE) is disclosed. The WDE provides an image preview component for operating on the original source image data of an image desired for placement on a web page under development in the WDE. Image manipulation tools, such as cropping and scaling, are provided in the image preview component allowing the designer to adjust the appearance of the original source image data that will be presented by the web image object placed on the design canvas of the WDE. The web image objects are defined having a link to the original source image data by maintaining the display modification instructions used to manipulate the original image defined by the original source image data into the display of the web image object.

Abstract: A method for correcting service manual textual inconsistencies. Extracting textual procedures from service documents stored in a memory of a service document storage device. Each term of an extracted textual procedure terminology is compared to a correlating target name terminology for identifying any matching terms by a processor. An overlap similarity is computed as a function of the identified matching terms from the extracted textual procedure terminology and the correlating target name terminology. A determination is made whether the overlap similarity is greater than a predetermined similarity threshold. The service documents are modified to change the extracted textual procedure terminology to the correlating target name terminology in response to the overlap similarity being greater than the predetermined similarity threshold and the extracted textual procedure terminology not exactly matching the correlating target name terminology.

Abstract: A computer system for preparing a document which includes multiple elements having a common noun and being differentiated by a reference indicia with each combination of primary and secondary adjectives by automatically scanning the document for each combination of the primary and secondary adjectives and inserting all of the reference indicia following the common noun in response to a scanning processor detecting the occurrence of the common noun unmodified by an adjective to reference the unmodified common noun with all of the reference indicia for the elements throughout the document without attaching the reference indicia to occurrences of the common noun modified by one of the adjectives.

Abstract: A typing error correction method and a device implementing the same method are provided. A correction method includes the following: every time when a user inputs characters, a correlation between the newly input characters and the character substrings of the already input words having the same length as the newly input characters is calculated; in case the correlation exceeds a predetermined value, such character substring of already input word is registered in a correction candidate list; in case there is only one correction candidate in the list, the candidate substring in the list is replaced by the newly input characters according to correction command; in case there are more than one correction candidates in the list, a user's move command is input for selection, and the selected candidate substring is replaced by the newly input characters.

Abstract: The computer transforms text by receiving a command to insert text into a user interface of an application. The computer extracts one or more words from the text, wherein each of the one or more words is associated with a category relevant to the application. The computer transforms the text to fit a template based on the respective associated categories of the one or more words. The computer inserts the transformed text into the user interface.

Abstract: A computer implemented method, system, and computer program product include one or more processors identifying a dynamic element within framework for building a visual representation of a product concept, the visual representation including one or more of a textual component and a graphical component, the dynamic element associated with a variant list including one or more variant elements; one or more processors identifying one of a longest variant element and a shortest variant element from within the variant list; and one or more processors generating a first instantiation of a visual representation of a product concept including the one of the longest variant element and the shortest variant element as the dynamic element.

Abstract: The present invention provides a word input method including the steps of: selectively inputting one or more letters containing the first letter of the word to be inputted; extracting, as a first priority, a word having less letters than a predetermined number, and which coincides with the word to be inputted, in a sequence from the first letter, from words containing one or more letters, from a word storage unit; extracting, as a second priority, a word having less letters than the predetermined number, from words containing one or more letters, from the word storage unit; extracting, as a third priority, a word having more letters than the predetermined number, and which coincides with the word to be inputted, in a sequence from the first letter, from words containing one or more letters, from the word storage unit; extracting, as a fourth priority, a word having more letters than the predetermined number, from words containing one or more letters, from the word storage unit; dividing the words of the first

Abstract: In one example, a method includes outputting, for display at a presence-sensitive display, a graphical user interface including a text display region and a graphical keyboard. The method further includes receiving an indication of a first gesture detected at a location within the text display region, and selecting, based at least in part on the location within the text display region, at least a portion of a character string included in the text display region. The method further includes receiving, while the first gesture is detected at the presence-sensitive display, an indication of at least a portion of a second gesture to select at least one key of the graphical keyboard, and outputting, responsive to receiving an indication of a termination of at least the second gesture, a replacement character string for display within the text display region to replace the portion of the character string.

Abstract: On computing devices, the implementation as a service or as a hosted application responsive to user intent automatically allows for correction of grammatical and stylistic issues in collaboratively or individually created content. The performance of automated fact-checking provides users with amended data and quotations along with the source, based on search engine input. Focused and automation rich productivity solutions provide benefits when an understanding of user intent is available.

Abstract: Techniques pertaining to embedding fonts in a PDF document are disclosed. A processing component executing a PDF application programming interface (API) may be operative to identify each character in a PDF file associated with an un-embedded font. The PDF API may store a bitmap representation for each identified character in the PDF file associated with the un-embedded font. The PDF API may then create a bitmap font character from the bitmap representation for each identified character in the PDF file associated with an un-embedded font and replace each reference to a character in the PDF file associated with an un-embedded font with a reference to its corresponding bitmap font character.

Abstract: Provided is an information processing apparatus including: a detection unit for detecting quotations from a plurality of texts from other texts; a conversion unit for deleting or replacing with predetermined character strings the quotations in a plurality of the texts; and a text mining unit for executing text mining for a plurality of the converted texts.

Abstract: A word prediction system determines probabilities of next words based upon an n-gram analysis of the input words as a user inputs text into a device. The predicted next words can be predicted based upon the last input word(s) and the predicted next words can be displayed on a predicted word portion of the device. Rather than inputting the letters of the next word, a user can easily input a predicted next word that matches the desired next word.

Abstract: In setting, by using a format, a non-display region in image data obtained by an image reading unit, a format location information input unit writes in the image data, an image representing information on access to a format storage unit in an external apparatus where a format to be used has been stored. In displaying the image data, a format location information extraction unit extracts the format location information by extracting the image from the image data. A format obtaining unit obtains the format by accessing the format storage unit based on the information. An image modification unit uses the obtained format to modify the image data such that the designated region is displayed in an invisible manner.

Abstract: To facilitate the use of audio files for annotation purposes, an audio file format, which includes audio data for playback purposes, is augmented with a parallel data channel of line identifiers, or with a map associating time codes for the audio data with line numbers on the original document. The line number-time code information in the audio file is used to navigate within the audio file, and also to associate bookmark links and captured audio annotation files with line numbers of the original text document. An annotation device may provide an output document wherein links to audio and/or text annotation files are embedded at corresponding line numbers. Also, a navigation index may be generated, having links to annotation files and associated document line numbers, as well as bookmark links to selected document line numbers.