Abstract: Disclosed is a domain filter capable of determining an n-gram distance between a seed domain and each of a plurality of candidate domains. The domain filter loads a seed domain n-gram for the seed domain and a candidate domain n-gram for each candidate domain in memory, compares the seed domain n-gram and the candidate domain n-gram to identify any identical grams, removes any identical grams from the seed domain n-gram, and determines how many grams are left in the seed domain n-gram, representing the n-gram distance between the seed domain and the candidate domain. The domain filter then compares n-gram distances thus determined with a predetermined threshold, eliminates any candidate domain having an n-gram distance from the seed domain that exceeds the predetermined threshold, and provides remaining candidate domains to a downstream computing facility such as a user interface or an analytical module operating in an enterprise computing environment.

Abstract: The present invention relates to a method for revising an error, wherein a user inputs a desired character string for revision so as to calculate a correlation between the desired character string for revision and previously inputted character strings, so that a character string with a high correlation is replaced with the desired character string for revision. A characteristic configuration of the present invention is in a step for deciding a correlation.

Abstract: Disclosed is an approach of on-device partial recognition that includes performing partial recognition on an image of a document captured by a mobile device to detect and/or recognize a specific area (e.g., barcodes, non-relevant text, etc.) and filling the recognized area with a solid color. Because the solid color area has a maximum compression ratio, this approach can lead to image size reduction and increased network throughput for client-server based data recognition where further processing such as advanced data extraction is performed at the server side. The approach can be enforced with neural network algorithms to exclude non-relevant information (e.g., logos, phrases, words, etc.).

Abstract: Based on a candidate set of translations produced by a neural network based machine learning model, a mapping data structure such as a statistical phrase table is generated. The mapping data structure is analyzed to obtain a quality metric of the neural network based model. One or more operations are initiated based on the quality metric.

Abstract: Embodiments include techniques for channeling elements in an analytics engine environment, techniques include analyzing a current process, and identifying critical data element types associated with the current process. The techniques also include receiving a real-time data stream including a plurality of data elements, and pre-filtering the plurality of data elements, wherein the pre-filtering determines one or more of the plurality of data elements are associated with the critical data element type. The technique includes selecting a channel of a plurality of channels to fast-path the one or more of the plurality of data elements based at least in part on the pre-filtering, and increasing a confidence level corresponding to the current process and the critical data element type based on a state of the current process.

Abstract: Systems and methods for assigning word fragments to lines of text in optical character recognition (OCR) extracted data can include at least one processor obtaining a plurality of word fragments from OCR generated data associated with an image. The at least one processor can determine vertical coordinates of each of the word fragments in the image. The at least one processor can cluster the plurality of word fragments into one or more clusters of word fragments based on the vertical coordinates of the plurality of word fragments. The at least one processor can assign each word fragment of a respective cluster to a corresponding text line based on the clustering.

Abstract: A structured data processing system includes hardware processors and a memory in communication with the hardware processors. The memory stores a data structure and an execution environment. The data structure includes an electronic document. The execution environment includes a data extraction solver configured to perform operations including identifying a particular page of the electronic document; performing an optical character recognition (OCR) on the page to determine a plurality of alphanumeric text strings on the page; determining a type of the page; determining a layout of the page; determining at least one table on the page based at least in part on the determined type of the page and the determined layout of the page; and extracting a plurality of data from the determined table on the page.

Abstract: Embodiments include techniques for channeling elements in an analytics engine environment, techniques include analyzing a current process, and identifying critical data element types associated with the current process. The techniques also include receiving a real-time data stream including a plurality of data elements, and pre-filtering the plurality of data elements, wherein the pre-filtering determines one or more of the plurality of data elements are associated with the critical data element type. The technique includes selecting a channel of a plurality of channels to fast-path the one or more of the plurality of data elements based at least in part on the pre-filtering, and increasing a confidence level corresponding to the current process and the critical data element type based on a state of the current process.

Abstract: A method for automatically selecting one of a plurality of recognition algorithms for a handwritten input of alphanumeric characters and/or gestures into a selected input field displayed on a screen using a touch-sensitive input apparatus comprises carrying out optical character recognition in a region of the screen which comprises at least the input field and the immediate environment of the input field, or carrying out voice recognition for a voice instruction acoustically output after the selected input field has been displayed. Terms describing field types are searched for in the result of the optical character recognition or the voice recognition, and a recognition algorithm which is adapted to a field type found in the result of the optical character recognition or the voice recognition is selected.

Abstract: Disclosed is an effective domain name defense solution in which a domain name string may be provided to or obtained by a computer embodying a visual domain analyzer. The domain name string may be rendered or otherwise converted to an image. An optical character recognition function may be applied to the image to read out a text string which can then be compared with a protected domain name to determine whether the text string generated by the optical character recognition function from the image converted from the domain name string is similar to or matches the protected domain name. This visual domain analysis can be dynamically applied in an online process or proactively applied in an offline process to hundreds of millions of domain names.

Abstract: A non-interactive screen sharing session executing within a computing device can be identified. The device can be communicatively linked to different computing devices of the screen sharing session. The contents of the remote screen buffer can be analyzed to determine a graphical representation of a Uniform Resource Locator (URL) within the contents prior to presenting the contents of the buffer within the device. A visible information item can be extracted and a non-visible reference can be established from the representation. An area surrounding the representation including a position and dimensions of the representation within the contents can be determined. The representation of the URL can be replaced with an interactive element in real-time. The element can include the visible and non-visible reference. The contents of the buffer can be presented within an interface associated with the session of the device, responsive to the replacing.

Abstract: The present invention provides a search capability to allow a user to easily locate a preference control, file, folder, control, or other system resource or data item associated with a search result. In one embodiment, a user enters a search term (or a portion thereof) in a search field associated with one or more resource types that may be searched. The user may be presented with a pop-up menu containing a list of likely matches. The user selects the desired preference control from the pop-up menu, and the corresponding preference pane, or other container, containing the selected data item, control, or other resource is displayed. In one aspect, as the user enters the search term (or portion thereof), certain icons are highlighted. Specifically, those icons that represent containers containing matching data items (such as preference panes having controls that match the search term) are highlighted.

Abstract: A search area is set on a recognition target image, cutout areas are set at a plurality of positions in the search area, images corresponding to the plurality of set cutout areas are extracted, similarities of candidate characters obtained by comparison between the extracted images and dictionary data is weighted in accordance with the positions of the cutout areas. In such a manner, evaluation values of the candidate characters are obtained, and a candidate character with the highest evaluation value among the obtained candidate characters is output as a recognition result. Further, a search area relating to a next character is set based on position information about the cutout area corresponding to the recognition result.

Abstract: As disclosed herein, a method for generating a natural language processing query includes receiving one or more documents, wherein each document comprises a set of words, processing the one or more documents and the sets of words to provide a document content matrix V, a word feature matrix W, and a document feature matrix H, forecasting values for each entry of the word feature matrix and the document feature matrix over a selected time interval and a selected set of domains to provide a forecasted word feature matrix W? and a forecasted document feature matrix H?, calculating a set of coefficients for forecasted document feature matrix H? such that V=W? *H?, determining a rank for each word of the sets of words according to the calculated set of coefficients, and generating one or more queries according to the determined ranks for each word of the set of words.

Abstract: An image processing apparatus includes a controller configured to execute: acquiring objective image data representing an objective image which includes a first character and a second character; analyzing first partial image data and specifying the first character in an image represented by the first partial image data; and generating processed image data representing a processed image which includes the first character and the second character by using the objective image data. The objective image data includes the first partial image data in a bitmap format which represents the image including the first character and second partial image data in a vector format which represents an image including the second character. The processed image data includes: first processed data representing an image including the first character; and second processed data representing an image including the second character.

Abstract: Computer-implemented systems and methods are provided for suggesting emoticons for insertion into text based on an analysis of sentiment in the text. An example method includes: determining a first sentiment of text in a text field; selecting first text from the text field in proximity to a current position of an input cursor in the text field; identifying one or more candidate emoticons wherein each candidate emoticon is associated with a respective score indicating relevance to the first text and the first sentiment based on, at least, historical user selections of emoticons for insertion in proximity to respective second text having a respective second sentiment; providing one or more candidate emoticons having respective highest scores for user selection; and receiving user selection of one or more of the provided emoticons and inserting the selected emoticons into the text field at the current position of the input cursor.

Abstract: A printing apparatus comprises: a processor configured to create print data for printing at least one printable character so as to arrange the printable character along a widthwise direction of the print medium based on input data input by a user; and a printhead configured to print on the print medium in accordance with the print data, wherein the processor compares an overall print length of overall data obtained by adding margins to a front end and a rear end of the printable character with a first length of an elongated print medium in the widthwise direction, and, the processor creates the print data including a mark indicating an end portion of the overall data when the overall print length is shorter than the first length.

Abstract: A method including the steps of: receiving a search query containing search terms from a user device; retrieving from one or more data storage devices, search configuration information in response to the received search query, wherein the search configuration information comprises a designated field set; generating a plurality of query partitions based on the received search query; generating one or more internal query clauses based on all possible combinations of sub-phrases of the plurality of query partitions and fields from the designated field set; executing a query on a database based on the one or more internal query clauses; generating query results based on the executed query; calculating match metrics for all query results; determining query results having match metrics that satisfy configured match constraints as legitimate matches; and detecting patterns based on corresponding matched terms and fields of the legitimate matches.

Abstract: An image processing apparatus includes a controller configured to execute: acquiring objective image data representing an objective image which includes a first character and a second character; analyzing first partial image data and specifying the first character in an image represented by the first partial image data; and generating processed image data representing a processed image which includes the first character and the second character by using the objective image data. The objective image data includes the first partial image data in a bitmap format which represents the image including the first character and second partial image data in a vector format which represents an image including the second character. The processed image data includes: first processed data representing an image including the first character; and second processed data representing an image including the second character.

Abstract: A method that includes generating, in a query pre-processor, a set of pre-computed materialized sub-graphs by executing a pre-processing dynamic random-walk based search for a bin of terms. The method also includes receiving, in a query processor, a search query having at least one search query term. In response to receiving the search query, the method includes accessing the set of pre-computed materialized sub-graphs. The accessing includes accessing a text index based on the search query term to retrieve a corresponding term group identifier and accessing the corresponding pre-computed materialized sub-graph based on the term group identifier. The method also includes executing a dynamic random-walk based search on only the corresponding pre-computed materialized sub-graph and based on the executing, retrieving nodes in the dataset and transmitting the nodes as results of the query.

Abstract: Disclosed is a data driven error model that is based on error patterns found at the morphemes level. A model is generated by error-correct patterns generator and is stored in an error-correct patterns database (ECPD). The ECPD is used in conjunction with a correction candidates' generator (CCG) to provide a list of correction candidates for a given error word. The error model can learn the types and forms of the language patterns from an annotated corpus. The error model can be used to analyze the type of error and can provide candidates corrections for wide ranges of Arabic spelling errors.

Abstract: One or more embodiments relate to an object indexing method, object indexing device and object indexing system. An object indexing method may include an initializing step of dividing at least one first data container and at least one second data container, and initializing respectively the first and the second data containers by using a first data indexer and a second data indexer; a first indexing step of adding the input feature vector of a specific object into a first data container currently being filled by using the first data indexer; and a second indexing step, when the data size in the first data container being filled has reached a threshold, selecting another first data container as the first data container currently being filled, and in the case of executing the first indexing step, converting bulk data in the first data container previously being filled into one available second data container.

Abstract: A machine translation method and a machine translation apparatus using a neural network model are provided. The machine translation apparatus extracts information associated with a keyword from a source sentence, obtains a supplement sentence associated with the source sentence based on the extracted information associated with the keyword, acquires a first vector value from the source sentence and a second vector value from the supplement sentence using neural network model-based encoders, and outputs a target sentence corresponding to a translation of the source sentence based on any one or any combination of the first vector value and the second vector value using a neural network model-based decoder.

Abstract: A method and system are provided for optical character recognition (OCR) of multi-language content. The method includes extracting a text portion from an image received from a user-computing device. The text portion comprises a plurality of keywords associated with a plurality of languages. The method further includes segmenting the plurality of keywords into a plurality of layers. Each layer of the plurality of layers comprises one or more keywords which are associated with a language. The method further comprise generating an OCR output of each of the plurality of layers based on the language associated with the one or more keywords in each of the plurality of layers. The method further comprises generating an electronic document of the received image based on the generated OCR output of each of the plurality of layers. The method further includes transmitting the generated electronic document to the user-computing device.

Abstract: A hardware and software facility for classifying media content units using keywords from a structured vocabulary. Metadata associated with each media content unit is segmented into a series of descriptive phrases. The descriptive phrases are mapped to keywords in a structured vocabulary, and the identified keywords associated with the media content units. Descriptive phrases that are not found in the structured vocabulary are tracked as candidate phrases for later addition to the structured vocabulary. A keyword index to the media content units may be constructed. The index is used to identify specific media content units that are responsive to search queries in a reliable and accurate fashion.

Abstract: A system for annotating frames in a media stream 114 includes a pattern recognition system (PRS) 108 to generate PRS output metadata for a frame; an archive 106 for storing ground truth metadata (GTM); a device to merge the GTM and PRS output metadata and thereby generate proposed annotation data (PAD) 110; and a user interface 109 for use by the human annotator HA 118. The user interface 104 includes an editor 111 and an input device 107 used by the HA 118 to approve GTM for the frame. An optimization system 105 receives the approved GTM and metadata output by the PRS 108, and adjusts input parameters for the PRS to minimize a distance metric corresponding to a difference between the GTM and PRS output metadata.

Abstract: Network session identification information is received. The network session identification information is associated with a destination IP address and a destination network port. An available source network port for a new session to be established for a source IP address is determined based on the destination IP address and the destination network port.

Abstract: Computer-implemented systems and methods are provided for suggesting emoticons for insertion into text based on an analysis of sentiment in the text. An example method includes: determining a first sentiment of text in a text field; selecting first text from the text field in proximity to a current position of an input cursor in the text field; identifying one or more candidate emoticons wherein each candidate emoticon is associated with a respective score indicating relevance to the first text and the first sentiment based on, at least, historical user selections of emoticons for insertion in proximity to respective second text having a respective second sentiment; providing one or more candidate emoticons having respective highest scores for user selection; and receiving user selection of one or more of the provided emoticons and inserting the selected emoticons into the text field at the current position of the input cursor.

Abstract: In a method of creating similar sentences from an entered original, one or more second phrases having the same meaning as a first phrase, which is part of the original, are extracted from a first database; an N-gram value is calculated according to a context dependence value, in a second database, corresponding to the one or more second phrases; one or more contiguous third phrases that include a number of second phrases equivalent to the N-gram value are extracted from one or more sentences obtained by replacing, in the original, the first phrase with the one or more second phrases; the appearance frequency of the one or more third phrases in a third database is calculated; and if the calculated appearance frequency is determined to be larger than or equal to a threshold, the one or more sentences are used as similar sentences of the original and are externally output.

Abstract: Data representing an image is received by an image recognition system. An image recognition system generates an image classification output distribution for a plurality of image features based on analysis of the data representing the image and training data stored for the image recognition system. One or more filters are applied to the image classification output distribution to obtain an updated image classification output distribution. A highest confidence value is selected from the updated image classification output distribution. A selected image feature associated with the highest confidence value is identified from the plurality of image features. Information associated with the selected image feature is obtained from a database and communicated to the user's device by the image recognition system.

Abstract: Method, apparatus, and program means for performing a string comparison operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store a result of a comparison between each data element of a first and second operand corresponding to a first and second text string, respectively.

Abstract: Various embodiments provide a method that comprises receiving a set of segments from a text field, analyzing the set of segments to determine at least one of a target subtext or a target meaning associated with the set of segments, and identifying a set of candidate emoticons where each candidate emoticon in the set of candidate emoticons has an association between the candidate emoticon and at least one of the target subtext or the target meaning. The method may further comprise presenting the set of candidate emoticons for entry selection at a current position of an input cursor, receiving an entry selection for a set of selected emoticons from the set of candidate emoticons, and inserting the set of selected emoticons into the text field at the current position of the input cursor.

Abstract: A message processing device (10) includes an estimator (11), an extractor (12), and an indicator (13). The estimator (11) estimates words understandable to a destination user (1). The extractor (12) extracts, from a message (3) created by a transmission originator user (2), a portion that does not match the words estimated by the estimator (11). The indicator (13) indicates, to the transmission originator user (2), the message (3) with the extracted portion by the extractor (12) being in an emphasized manner.

Abstract: An image recognition approach employs both computer generated and manual image reviews to generate image tags characterizing an image. The computer generated and manual image reviews can be performed sequentially or in parallel. The generated image tags may be provided to a requester in real-time, be used to select an advertisement, and/or be used as the basis of an internet search. In some embodiments generated image tags are used as a basis for an upgraded image review. A confidence of a computer generated image review may be used to determine whether or not to perform a manual image review. Images and their associated image tags are optionally added to an image sequence.

Abstract: Optical character recognition is described in various implementations. In one example implementation, a method may include receiving a plurality of optical character recognition (OCR) outputs provided by a respective plurality of OCR engines, each of the plurality of OCR outputs being representative of text depicted in a portion of an electronic image. The method may also include identifying a document context associated with the electronic image, and generating an output character set by applying a character resolution model to resolve differences among the plurality of OCR outputs. The character resolution model may define a probability of character recognition accuracy for each of the plurality of OCR engines given the identified document context. The method may also include updating the character resolution model to generate an updated character resolution model such that subsequent generating of output character sets are based on the updated character resolution model.

Abstract: According to one embodiment, an electronic apparatus includes a hardware processor. The hardware processor converts a first character in a first image of images in which characters of languages are rendered, into a first character code by using dictionary data for a first language environment, converts the first character into a second character code by using dictionary data for a second language environment, causes a memory to store a pair of the first character code and a first area in the first image corresponding to the first character code, and causes the memory to store a pair of the second character code and a second area in the first image corresponding to the second character code.

Abstract: Technologies for analyzing software similarity include a computing device having access to a collection of sample software. The computing device identifies a number of code segments, such as basic blocks, within the software. The computing device normalizes each code segment by extracting the first data element of each computer instruction within the code segment. The first data element may be the first byte. The computing device calculates a probabilistic feature hash signature for each normalized code segment. The computing device may filter out known-good code segments by comparing signatures with a probabilistic hash filter generated from a collection of known-good software. The computing device calculates a similarity value between each pair of unfiltered, normalized code segments. The computing device generates a graph including the normalized code segments and the similarity values. The computing device may cluster the graph using a force-based clustering algorithm.

Abstract: Various approaches provide for detecting and recognizing text to enable a user to perform various functions or tasks. For example, a user could point a camera at an object with text, in order to capture an image of that object. The camera can be integrated with a portable computing device that is capable of taking the image and processing the image (or providing the image for processing) to recognize, identify, and/or isolate the text in order to send the image of the object as well as recognized text to an application, function, or system, such as an electronic marketplace.

Abstract: A user can emulate touch screen events with motions and gestures that the user performs at a distance from a computing device. A user can utilize specific gestures, such as a pinch gesture, to designate portions of motion that are to be interpreted as input, to differentiate from other portions of the motion. A user can then perform actions such as text input by performing motions with the pinch gesture that correspond to words or other selections recognized by a text input program. A camera-based detection approach can be used to recognize the location of features performing the motions and gestures, such as a hand, finger, and/or thumb of the user.

Abstract: Methods and apparatus, including computer program products, are provided for backfilling. In some example embodiments, there is provided a method that includes receiving, at a receiver, backfill data representative of sensor data stored, at a continuous blood glucose sensor and transmitter assembly, due to a loss of a wireless link between the receiver and the continuous blood glucose sensor and transmitter assembly; generating, at the receiver, at least one of a notification or a graphically distinct indicator for presentation at a display of the receiver, the at least one of the notification or the graphically distinct indicator enabling the backfill data to be graphically distinguished, when presented at the display, from non-backfill data; and generating, at the receiver, a view including the backfill data, the non-backfill data, and the generated at least one of the notification or the graphically distinct indicator. Related systems, methods, and articles of manufacture are also described.

Abstract: An information display terminal achieves a suitable display of types of electronic content such as electronic books with a display unit, an operation unit for receiving an operation instruction directed to the information display terminal, and a scroll control unit for controlling the operation for automatic scroll processing of the electronic content displayed on the display unit. An operation instruction instructing initiation of the automatic scroll processing is input to the operation unit, the scroll control unit performs control to initiate automatic scroll processing by which the electronic content displayed on the display unit is displayed in such a manner that the electronic content is moved a predetermined distance per predetermined time period; and when an operation instruction instructing interruption of the automatic scroll processing is input to the operation unit, the scroll control unit performs control to interrupt the automatic scroll processing.

Abstract: An input support apparatus includes a processor and a memory configured to store association information in which a character string decided to be inputted on a screen is associated with coordinates at which the character string is inputted on the screen. The processor configured to execute a process including searching the association information for a character string that corresponds to the coordinates of an operation position on the screen for input operation, and outputting the searched-out character string.

Abstract: A method, system, and computer-readable storage medium for performing content based transitions between images. Image content within each image of a set of images are analyzed to determine at least one respective characteristic metric for each image. A respective transition score for each pair of at least a subset of the images is determined with respect to each transition effect of a plurality of transition effects based on the at least one respective characteristic metric for each image. Transition effects implementing transitions between successive images for a sequence of the images are determined based on the transition scores. An indication of the determined transition effects is stored. The determined transition effects are useable to present the images in a slideshow or other image sequence presentation.

Abstract: Managing network ports is disclosed. Network session identification information is received. The network session identification information is associated with a destination IP address and a destination network port. An available source network port is determined using a data structure that is based on the destination IP address and the destination network port.

Abstract: The present application discloses a method and an apparatus for obtaining structured information in a fixed layout document to improve the structuring speed for information management of a fixed layout document. The method may comprise: determining initial page number information corresponding to current directory entry of the document; segmenting first article content of a page corresponding to the initial page number information into at least one structured-characters-block; searching in each structured-characters-block for a first structured-characters-block which matches with name strings of the current directory entry, and obtaining first position information about where the first structured-characters-block is located in the first article content; and obtaining initial position information of the current directory entry and end position information of the previous directory entry based on the first position information.

Abstract: An improved method for verifying whether a character-recognition technology has correctly identified which characters are represented by character images involves displaying the uncertain character images in place of their respective hypothesis characters in a document being read a verifier. The verifier may mark incorrectly spelled words containing the uncertain character images. Based on the markings, a system adjusts a confidence level associated with the hypothesis about the uncertain character in order to obtain a confirmed hypothesis linked to the uncertain character.

Abstract: A computer processor may receive medical data including a report and an image. The computer processor may analyze the report using natural language processing to identify a condition and a corresponding criterion. The computer processor may also analyze the image using an image processing model to generate an image analysis. The computer processor may determine whether the report has a potential problem by comparing the image analysis to the criterion.

Abstract: Systems, apparatuses and methodologies, for an administrator to configure a flexible document workflow are provided. A workflow creation interface may be provided on a terminal (e.g., via application software) for an administrator to create and register document workflow profiles. Such workflow creation interface may be configured to include a processing location selector to receive selection by the administrator of (i) a processing location amongst plural processing locations or (ii) automatic determination. Such processing location selection may be on a connector-by-connector basis or for the entire workflow. For example, the administrator can register multiple versions of a workflow, to be processed at respective processing locations. As another example, a hybrid workflow can be created in which some workflow connectors or components are performed at one location acid other workflow connectors or components are performed at another location.

Abstract: A similarity between character strings is assessed by identifying first and second character strings as candidate similar character strings, determining a frequency of occurrence for at least one of the first and second character strings from a collection of character strings, and designating the first and second character strings as similar based on the determined frequency of occurrence.

Abstract: A similarity between character strings is assessed by identifying first and second character strings as candidate similar character strings, determining a frequency of occurrence for at least one of the first and second character strings from a collection of character strings, and designating the first and second character strings as similar based on the determined frequency of occurrence.