Abstract: Herein is a probabilistic indexing technique for searching semi-structured text documents in columnar storage formats such as Parquet, using columnar input/output (I/O) avoidance, and needing minimal storage overhead. In an embodiment, a computer associates columns with text strings that occur in semi-structured documents. Text words that occur in the text strings are detected. Respectively for each text word, a bitmap, of a plurality of bitmaps, that contains a respective bit for each column is generated. Based on at least one of the bitmaps, some of the columns or some of the semi-structured documents are accessed.

Abstract: Embodiments provide systems, methods, and non-transitory computer storage media for providing search result images based on associations of keywords and depth-levels of an image. In embodiments, depth-levels of an image are identified using depth-map information of the image to identify depth-segments of the image. The depth-segments are analyzed to determine keywords associated with each depth-segment based on objects, features, or content in each depth-segment. An image depth-level data structure is generated by matching keywords generated for the entire image with the keywords at each depth-level and assigning the depth-level to the keyword in the image depth-level data structure for the entire image. The image depth-level data structure may be queried for images that contain keywords and depth-level information that match the keywords and depth-level information specified in a search query.

Abstract: Technology is described herein for parsing an ink document having a plurality of ink strokes. The technology performs stroke-level processing on the plurality of ink strokes to produce stroke-level information, the stroke-level information identifying at least one characteristic associated with each ink stroke. The technology also performs object-level processing on individual objects within the ink document to produce object-level information, the object-level information identifying one or more groupings of ink strokes in the ink document. The technology then parses the ink document into constituent parts based on the stroke-level information and the object-level information. In some implementations, the technology converts the ink stroke data into an ink image. The stroke-level processing and/or the object-level processing may operate on the ink image using one or more neural networks.

Abstract: There is a need for more effective and efficient document processing solution. Accordingly, various embodiments of the present invention introduce various document processing optimization solutions. In one example, a method includes identifying a plurality of input pages each associated with a related input document of a plurality of input documents; for each input page of the plurality of input pages, generating a segmented page; processing each segmented page using a trained encoder model to generate a fixed-dimensional representation of the input page; determining, based at least in part on each fixed-dimensional representation, a plurality of document clusters; determining a plurality of processing groups, where each processing group is associated with one or more related document clusters of the plurality of document clusters; and performing the document processing optimization based at least in part on the plurality of processing groups.

Abstract: A method of extracting data from documents is provided. The method comprises receiving input of a number of documents and input of a schema of data items available for extraction from the documents. The documents are parsed into a machine-readable representation, and data items in the machine-readable representation are identified according to the schema. Interpretations of data items are propagated within the documents to disambiguate identified data items, and identified data items are matched with other data items in the documents according to the schema. Only identified data items that include a minimal set of interpretations specified by the schema are extracted.

Abstract: A method and apparatus for detecting text regions in an image, a device, and a medium are provided. The method may include: detecting, based on feature representation of an image, a first text region in the image, where the first text region covers a text in the image, a region occupied by the text being of a certain shape; determining, based on a feature block of the first text region, text geometry information associated with the text, where the text geometry information includes a text centerline of the text and distance information of the centerline from the upper and lower borders of the text; and adjusting, based on the text geometry information associated with the text, the first text region to a second text region, where the second text region also covers the text and is smaller than the first text region.

Abstract: An artificial intelligence engine architecture for generating candidate drugs is disclosed. In one embodiment, a method includes generating, via a creator module, a candidate drug compound including a sequence of a candidate drug compound, including the candidate drug compound as a node in a knowledge graph; generating, via a descriptor module, a description of the candidate drug compound at the node in the knowledge graph, wherein the description comprises drug compound structural information, drug compound activity information, and drug compound semantic information; based on the description, performing, via a scientist module, a benchmark analysis of a parameter of the creator module; and modifying, based on the benchmark analysis, the creator module to change the parameter in a desired way during a subsequent benchmark analysis.

Abstract: In accordance with one or more aspects of a dynamic soft keyboard, a user input is received via a soft keyboard having multiple keys. Information describing a current input environment for the soft keyboard is obtained, and a determination is made as to which one or more keys of the multiple keys was intended to be selected by the user input. This determination is made based at least in part on the current input environment.

Abstract: Certain embodiments involve transforming an electronic document into a tagged electronic document. For instance, an electronic document processing application generates a tagged electronic document from an input electronic document. The electronic document processing application accesses one or more feature maps that identify, via a set of object-recognition rules, identified objects in the electronic document. The electronic document processing application also obtains a heat map of the electronic document that represents attributes in a pixel-wise manner. The electronic document processing application computes a tag by applying a fusion deep learning model to the one or more feature maps and the heat map. The electronic document processing application generates the tagged electronic document by applying the tag to the electronic document.

Abstract: According to one embodiment, a dialogue system includes a setting apparatus and a processing apparatus. The setting apparatus sets in advance a plurality of words that are in impossible combination relationships to each other. The processing apparatus acquires speech of a user, and when a speech recognition result of an object included in the speech includes a word combination included in the plurality of words that are in impossible combination relationships to each other, output a notification to the user that processing of the object cannot be carried out.

Abstract: A method for training a locally interpretable model includes obtaining a set of training samples and training a black-box model using the set of training samples. The method also includes generating, using the trained black-box model and the set of training samples, a set of auxiliary training samples and training a baseline interpretable model using the set of auxiliary training samples. The method also includes training, using the set of auxiliary training samples and baseline interpretable model, an instance-wise weight estimator model. For each auxiliary training sample in the set of auxiliary training samples, the method also includes determining, using the trained instance-wise weight estimator model, a selection probability for the auxiliary training sample. The method also includes selecting, based on the selection probabilities, a subset of auxiliary training samples and training the locally interpretable model using the subset of auxiliary training samples.

Abstract: An information processing apparatus includes a processor configured to obtain, for each character of plural characters recognized from an image, (a) position of the character in the image, (b) size of the character, and (c) confidence level of a character recognition result of the character; and determine whether to regard the character as a noise based on a distance between the character and its nearest character, the size of the character, and the confidence level of the character recognition result of the character.

Abstract: Embodiments described herein automatically classifies numerical expressions from a textual document and designates a context to understand each numerical expression. Specifically, numerical expressions from a textual context are classified as nominal or cardinal. For cardinal numerical expressions that carry a quantitative meaning, inference terms are determined from the textual context to associate with the cardinal numerical expressions. The numerical expressions are then translated to a format of a numerical value and stored with metadata indicating the unit scale or the meaning of the numerical value.

Abstract: Systems and methods for executing a robotic process automation (RPA) workflow are provided. The RPA workflow is executed by a first robot. The execution of the RPA workflow is suspended by the first robot. A current context of the RPA workflow is serialized at a time of the suspension and the current context of the RPA workflow is stored. The execution of the RPA workflow is resumed by a second robot based on a triggering condition by retrieving the current context of the RPA workflow. The first robot and the second robot may be the same robot or different robots.

Abstract: Content fragments aligned to content criteria enable rich sets of multimodal content to be generated based on specified content criteria, such as content needs pertaining to various content delivery platforms and scenarios. For instance, the described techniques take a set of content (e.g., text, images, etc.) along with a specified content criteria (e.g., business/user need) and creates content fragment variants that are tailored to the content criteria with respect to both the information presented as well as the style of the content presented.

Abstract: A network analyzer includes a storage and a processor to provide an answer to inquiry including an inquiry statement and device log. The storage stores first information indicating relation between a previously received inquiry statement and an answer for the inquiry statement and second information indicating relation between previously received device log and an answer for the device log. The processor selects a first answer candidate for a new inquiry statement and calculates a first degree of certainty of the first answer candidate based on the first information. The processor selects a second answer candidate for new device log corresponding to the new inquiry statement and calculates a second degree of certainty of the second answer candidate based on the second information. The processor determines an answer based on the first answer candidate, the first degree of certainty, the second answer candidate, and the second degree of certainty.

Abstract: For saliency mapping, a machine-learned classifier is used to classify input data. A perturbation encoder is trained and/or applied for saliency mapping of the machine-learned classifier. The training and/or application (testing) of the perturbation encoder uses less than all feature maps of the machine-learned classifier, such as selecting different feature maps of different hidden layers in a multiscale approach. The subset used is selected based on gradients from back-projection. The training of the perturbation encoder may be unsupervised, such as using an entropy score, or semi-supervised, such as using the entropy score and a difference of a perturbation mask from a ground truth segmentation.

Abstract: Images stored in an information repository are prepared for browsing. For each image in the repository, text in the repository is mined to extract snippets of text about the image which are semantically relevant to the image, and for each of these snippets of text, keyterms are detected in the snippet of text which represent either concepts that are related to the image or entities that are related to the image, and the snippet of text and keyterms are associated with the image. Each keyterm that is associated with each image in the repository is hyperlinked to each other image in the repository that has this keyterm associated therewith. A graphical user interface allows a user to browse the images in the repository by using their associated snippets of text and hyperlinked keyterms.

Abstract: A method for dynamically detecting and converting a context-sensitive information in a first language and a first format to a second language and a second format that is understandable to an end user based on a user-specified setting is provided. The method may use a built-in camera of a computing device to dynamically detect and capture an image frame of context-sensitive information. The method may use Optical character recognition (OCR), as well as contextual information such as GPS data available from a mobile computing device, to automatically translate and reformat the context-sensitive information in real-time so a user may understand it unambiguously.

Abstract: A method and device for page displaying, a terminal, and a storage medium are provided according to an implementation of the present disclosure. The present disclosure is related to the technical field of terminals. The method includes the following. A user configuration interface is displayed, where the user configuration interface includes a first area and a second area, and on the first area selectable operation modes are displayed. A selection operation on the first area is received, and at least one target operation mode is determined from the selectable operation modes in response to the selection operation. Information associated with the at least one target operation mode is displayed on the second area.

Abstract: Provided is an image reading apparatus capable of eliminating the need for a user to correct a character portion that cannot be recognized by OCR and improve the operation burden on the user. A non-word detecting unit detects a non-word that is not considered to be a word among a plurality of words constituting the text in a document. A determining unit determines whether or not a compound word obtained by combining the non-word with at least one of the word immediately before the non-word and the word immediately after the non-word in that arrangement order is a word. A character correcting unit identifies the text portion corresponding to the compound word in the text in the document as a failed character recognition portion, and corrects the text of the failed character recognition portion to the text of the compound word.

Abstract: An information processing apparatus includes a selection unit that, when a target document is recognized, selects a first mode in which a latest version of a recognition dictionary is applied, or a second mode in which a version of the recognition dictionary is applied, the version of the recognition dictionary having a highest correct answer rate among plural versions different from the latest version, the correct answer rate being obtained from a recognition result and a confirmation or correction result of each of plural documents.

Abstract: Techniques for simulating human interface interaction resilient to user interface changes are presented. Automated analysis is performed on an image of a user interface of a computer program that is to be a target of simulated user interactions, and that determines the location and interaction purpose of a particular control on the user interface. An interaction package is read, and it indicates one or more interaction purposes that are to be carried out through interactions with the user interface of the computer program. Interaction with the user interface is simulated to carry out the one or more interaction purposes, where the particular interaction purpose is among the one of the one or more interaction purposes and simulating user interactions includes simulating user interaction with the particular control, based on the determined location and particular interaction purpose.

Abstract: Embodiments of the present disclosure disclose a method, apparatus, device, and readable storage medium for image-based data processing. The method comprises: acquiring an image and a to-be-processed text; extracting features of a plurality of objects in the image, and extracting a feature of the text; fusing the features of the plurality of objects into a fused feature of the image based on a matching degree between the feature of the text and a feature of each object of the plurality of objects; and processing the text based on the fused feature of the image and the feature of the text. Embodiments of the present disclosure can accurately learn an association relationship between a text and each object in an image, and improve the processing accuracy.

Abstract: Mechanisms are provided for implementing a candidate answer variant engine. The mechanisms receive an indication of a structured portion of content in a corpus, generate a plurality of groupings of elements of the structured portion of content, and generate, for each grouping of elements in the plurality of groupings of elements, and for each element in the grouping of elements, a corresponding grouping vector representation, corresponding to the element. The mechanisms, for each grouping vector representation of each grouping of elements in the plurality of groupings of elements perform a similarity measure calculation between the grouping vector representation and a vector representation of an input question, and select an element corresponding to the grouping vector representation for inclusion as a candidate answer variant based on results of the similarity measure calculation. The mechanisms perform question answering operations based on an analysis of one or more candidate answer variants.

Abstract: A method for matching a license plate number, comprises: obtaining a first license plate number to be matched; obtaining a license plate number library, wherein the license plate number library includes at least one second license plate number; calculating, based on a visual similarity of characters, a difficult degree in editing a character string required to converting between each second license plate number and the first license plate number; and determining, according to the difficult degree in editing a character string, at least one second license plate number matched with the first license plate number.

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: A computer-implemented method includes training a classification model to produce a mapping from a set of feature vectors to a set of confidence levels. Each feature vector describes a respective term, and each confidence level indicates a likelihood that the respective term is a keyword. A plurality of program artifacts are tokenized into a plurality of terms. For each term in the plurality of terms, a respective feature vector is determined for describing the term, based on the plurality of program artifacts. For each term in the plurality of terms, based on the respective feature vector, using the mapping, a respective confidence level is determined for indicating a likelihood that the term is a keyword of the plurality of program artifacts.

Abstract: Detection of typed and/or pasted text, caret tracking, and active element detection for a computing system are disclosed. The location on the screen associated with a computing system where the user has been typing or pasting text, potentially including hot keys or other keys that do not cause visible characters to appear, can be identified and the physical position on the screen where typing or pasting occurred can be provided based on the current resolution of where one or more characters appeared, where the cursor was blinking, or both. This can be done by identifying locations on the screen where changes occurred and performing text recognition and/or caret detection on these locations. The physical position of the typing or pasting activity allows determination of an active or focused element in an application displayed on the screen.

Abstract: An image forming apparatus includes a receiving part that receives multiple page images including a first page image and a second page image, a medium carrying part that carries the recording media, and an image forming part that forms images on the recording media carried by the medium carrying part based on the first and second page images processed by the image processing part. The image processing part determines one edge region of the first page image, which has the highest image density among four edge regions on the first page image, changes the orientation of the first page image such that the one edge region having the highest image density is arranged to be at the trailing side of the first page image, and changes the orientation of the second page image to the same orientation as that of the first page image.

Abstract: An image encoding method, decoding method and corresponding device, and intraframe pixel prediction method.

Abstract: Methods and systems for maximizing data utility efficiency to maximize dynamic application of content in a database as applied to a validation are disclosed herein. A system for maximizing data utility efficiency to maximize dynamic application of content in a database as applied to a validation can include a memory having a first database containing information identifying a plurality of topics and a second database containing a plurality of content items. The system can further include a server that can maximize data utility efficiency by identifying multipurpose content items.

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: A system for converting an image of an unstructured table into a structured table is provided. The system may comprise a memory storing machine readable instructions. The system may include a processor to receive an image of a unstructured table and convert the image of the unstructured table into a structured table. Converting the image of the unstructured table into the structured table may include providing cell mapping and low confidence determination to highlight potentially misconverted content. The low confidence determination may be based on a first input and a second input. The processor may export the structured table, upon validation, to an application that supports structured tables.

Abstract: An image analysis apparatus includes an extraction section, an acquisition section, an exclusion section, and a recognition section. The extraction section extracts, from a target image, a text area including a character. The acquisition section acquires a predetermined target-object condition. The predetermined target-object condition defines a target object. The exclusion section searches for the target object in the text area and excludes the target object from a target of character recognition. The text area is extracted by the extraction section. The target object satisfies the predetermined target-object condition. The recognition section performs character recognition on the text area. The text area is an area from which the target object is excluded.

Abstract: An information processing apparatus includes a first extraction part that extracts a value corresponding to a first item, which is an item indicative of a deadline, from a result of character recognition with respect to an image acquired by reading a document which includes an item and a value corresponding to the item; a generation part that generates a second character string of a date format indicative of a date of the deadline based on the result of the character recognition in a case where the value extracted by the first extraction part is a first character string other than the date format; and an output part that outputs the generated second character string as the value corresponding to the first item.

Abstract: A method for automatically detecting errors in at least one data entry in a database, the at least one data entry including an input string of characters that do not match at least one predefined string of characters. The method includes generating a first image map; generating at least one classification parameter by comparing the first image map to a second image map, the second image map based at least partially on the predefined string of characters; determining that the input string of characters correlates to the predefined string of characters; and modifying the at least one data entry to match the predefined string of characters in response to determining that the input string of characters correlates to the predefined string of characters. Various other methods and systems for automatically detecting errors in at least one data entry in a database are also disclosed.

Abstract: A method is described for selecting and displaying, on or through a television signal receiver apparatus capable of connecting to Internet and of pointing to URL's, television programs transmitted through an Internet network, said method comprises the step of associating at least one URL, or Uniform Resource Locator, corresponding to streaming audio/video of a specific television program, with the same television program of an EPG, or Electronic Program Guide, received by said apparatus via television broadcast, and wherein said association requires that said URL be stored into a memory-type processing circuit of the apparatus to create a link between said specific television program received through said Internet network and the same specific television program of said EPG received by said television receiver apparatus via television broadcast.

Abstract: An apparatus of the invention determines whether or not new scanned image data is similar to past scanned image data based on character string areas and a table area extracted from the new scanned image data, specifies a character string area used to obtain information set to the past scanned image data determined to be similar, detects a target area as a processing target out of the character string areas extracted from the new scanned image data based on the specified character string area, the table included in the past scanned image data determined to be similar, and the table included in the new scanned image data, performs character recognition processing on the detected target area, and sets information to the new scanned image data by using a character obtained as a result of the character recognition processing.

Abstract: The present document describes a system and method for providing augmented reality interactions with printed media, whereby a user looking at a printed media (physical or electronic) with their portable computing device may view augmented reality interactions on their portable device to enrich the media being viewed. The method includes recognizing pages and using interaction capabilities offered atop the page once recognized. The system is also configured to perform an image recognition process which allows for a very quick detection of a preregistered image from the database which matches the image of the page viewed by the user in order to extract the assets associated with the prestored image and send them to the portable device for display.

Abstract: Implementations generally relate to importing data and presenting the data in a user interface (UI). In some implementations, a method includes capturing an image of an object using a camera, where the object includes text. The method further includes recognizing the text. The method further includes generating a data structure that includes the text. The method further includes generating a graphical image that represents at least a portion of the text. The method further includes displaying the graphical image in a UI in a display screen of a client device.

Abstract: A computer-implemented method of tagging a text, comprises: determining a value for each of a plurality of locations in a first vector; processing (402), by a trained first neural network component, the first vector to generate a second vector; processing (404), at a trained second neural network component, the second vector to generate a probability score for each of at least ten predetermined tags; determining (406) if each probability score meets a criterion; if the criterion is met, assigning (408) the tag corresponding to the probability score to the text. Each of the locations may correspond to a respective predetermined word, each value relating to existence and/or frequency of the corresponding word in the text, and the number of locations may be between 600 and 20000. The number of locations in the second vector may be fewer than the number of locations in the first vector and is from 100 to 5000.

Abstract: Techniques for providing improved optical character recognition (OCR) for receipts are discussed herein. Some embodiments may provide for a system including one or more servers configured to perform receipt image cleanup, logo identification, and text extraction. The image cleanup may include transforming image data of the receipt by using image parameters values that optimize the logo identification, and performing logo identification using a comparison of the image data with training logos associated with merchants. When a merchant is identified, a second image clean up may be performed by using image parameter values optimized for text extraction. A receipt structure may be used to categorize the extracted text. Improved OCR accuracy is also achieved by applying on format rules of the receipt structure to the extracted text.

Abstract: A method for reducing the parameters defining an acquired light field ray which enables only the colour associated with the light field ray to be stored instead of 4 light field co-ordinates (x,y,i,j) and its associated colour.

Abstract: In some embodiments, a computing system computes tags for an electronic document. The computing system identifies sets of objects for the electronic document by applying a set of object-recognition rules to the electronic document, with each object-recognition rule generating a set of identified objects. The computing system generates feature maps that represent a set of identified objects. The computing system generates a heat map that identifies attributes of the electronic document including object candidates of the electronic document by applying a page-segmentation machine-learning model to the electronic document. The computing system computes a tag by applying a fusion deep learning module to the feature map and the heat map to correlate a document object identified by the feature map with an attribute of the electronic document identified by the heat map. The computing system generates the tagged electronic document by applying the tag to the electronic document.

Abstract: Examples relate to identifying randomly generated character strings. In one example, a computing device may: receive a character string that includes two or more characters; identify a number of character transitions included in the character string, each character transition being a change in character type within an n-gram of the character string, where n is a positive integer; and determine, based on the number of character transitions, whether the character string was randomly generated.

Abstract: A message processing method and an electronic device for supporting the same are provided. The electronic device includes a communication interface configured to receive a message including a plurality of pages, and a control module configured to process the received message, wherein, if undefined data exists among data contained in a specific page of the plurality of pages, the control module combines at least a part of data contained in a next page that is sequential to the specific page with the undefined data.

Abstract: Methods and systems to supplement search results returned to a buyer of parts are described. The system receives a first query from a buyer. The first query includes keywords. The system identifies at least one compatibility keyword included in the keywords. The system further infers that the other keywords in the query are item information that describes a part that is sought for on a network-based marketplace. The system further infers the part has a compatibility based on the compatibility keywords. Next, the system searches a data storage device based on the item information and the compatibility keywords to identify a first listing as matched. Finally, the system presents the first listing describing the matched part. The matched part is indicated as compatible by supplementing the presentation of the first listing with the compatibility keywords from the first query.

Abstract: A document processing system is configured to identify, for each accessed electronic document in a first set of multiple electronic documents, a set of identified multi-word phrases determined to be in ordered text information in the accessed electronic document, each multi-word phrase of the set of identified multi-word phrases including adjacent words in the ordered text information; and determine, for each accessed electronic document in the first set of multiple electronic documents, a selected document type from the first set of document types based at least on an analysis of the set of identified multi-word phrases with respect to multi-word-phrase characteristics identified by a first definition and associated with each document type in a first set of document types associated with a first document-set type.

Abstract: A system and a method for verifying authenticity of a physical copy and a digital copy of a document are disclosed. The method comprises registering a document in a repository by storing details related to the document in a location of the repository. A symbology for the document is generated. The symbology is an identifier of the location of the repository comprising the document. The symbology is associated with either a physical or a digital copy of the document. The digital copy of the document is printed to generate a printed copy. The printed copy or the physical copy of the document is scanned to generate a scanned image. The document and the details related to the document present at the location of the repository are accessed. The scanned image is compared with the document stored in the repository to determine the authenticity of either the physical copy or the digital copy of the document.