Abstract: A method for constructing an efficient product surface defect detection model based on network collaborative pruning is provided. According to an initial product surface defect detection model, the method provides a network-based collaborative pruning method and constructs the efficient product surface defect detection model. On a premise of ensuring an accuracy of a product defect detection method, a product surface defect detection time is reduced to satisfy manufacturer's requirements on the product surface defect detection time and accuracy of product surface defects.

Abstract: A document processing apparatus includes a processor configured to receive purpose information indicating a purpose of creating a document, extract item definition information corresponding to the purpose indicated by the received purpose information from item definition information stored in a memory for the item definition information in which one or more items to be posted in the document are defined in correspondence with the purpose of creating the document, extract an item value corresponding to each item defined in the extracted item definition information from item information stored in a memory for the item information including the item value of each item, and assign the extracted item value in each predetermined area of the document to create the document.

Abstract: A cause-effect sentence analysis device including: a cause-effect sentence extraction unit configured to extract a cause-effect sentence including a cause expression and an effect expression from a text; an acquisition unit configured to acquire information indicating a reference expression for analyzing the degree of similarity; a similarity degree analysis unit, for a cause-effect sentence extracted by the cause-effect sentence extraction unit, configured to calculate a cause similarity degree, namely, the degree of similarity between the reference expression and the cause expression included in the cause-effect sentence, and an effect similarity degree, namely, the degree of similarity between the reference expression and the effect expression; and a desired cause-effect sentence extraction unit for extracting a cause-effect sentence in which one of the cause expression and the effect expression included in the cause-effect sentence is similar to the reference expression and the other is not similar to the

Abstract: Systems and methods for guided personal identity based actions are provided. In example embodiments, a user-specified action from a first user device of a first user is received. The user-specified action pertains to the first user and uses data of the first user when performed. The user-specified action is linked to an identifier. An indication of the identifier is received from a second user device of a second user. In response to receiving the indication of the identifier, the user-specified action linked to the identifier is identified, the data of the first user is accessed, a user interface that includes an option to perform the user-specified action using the data of the first user is generated, and the generated user interface is presented on the second user device.

Abstract: Methods and apparatuses are described for automatic validation of a hybrid digital document. A server computing device downloads a hybrid digital document from a remote computing device, the hybrid digital document comprising an image content file and a hypertext content file. The server computing device determines content validation rules based upon one or more attributes associated with the hybrid digital document. The server computing device converts the image content file to a text content file. The server computing device validates one or more data elements in the text content file using the content validation rules. The server computing device validates one or more data elements in the hypertext content file using the content validation rules. The server computing device transmits a notification to the remote computing device indicating an outcome of the data elements validation.

Abstract: A processor may receive structured data. The structured data may include one or more columns and associated column names. The processor may analyze the structured data. Analyzing the structured data may include gathering a requisite set of keywords from the associated column names across all columns and/or a sample of column cells. The processor may access a corpus of documents. Each of the documents in the corpus may be associated with a respective keyword. The processor may search the corpus of documents based on the requisite set of keywords. The processor may summarize one or more documents associated with the requisite set of keywords.

Abstract: A validation document while responding to a customer's demand is efficiently created. A server creates a first sample document upon receiving, from a terminal device, a request for creation of the first sample document including an inspection item targeted for a first device. The terminal device receives an operation of inputting the parameter value to the first sample document, and transmits the inputted parameter value to the server. The server creates a first validation document on the basis of the parameter value received from the terminal device and on the basis of the first sample document.

Abstract: A computer-implemented method for handwritten text line wrapping includes: obtaining, from a user, at least two words of handwritten text on a screen; determining an original bounding box for the at least two words; creating at least one line-break character for the at least two words; determining at least one baseline for the at least two words; determining a new bounding box for the at least two words based on the at least one baseline; generating, on the screen, a text box; moving, on the screen, at least one of the at least two words from a first line of at least one line of handwritten text to a second line of the at least one line of handwritten text, wherein the second line of handwritten text fits within the text box; and adjusting at least one gap between the at least one line of handwritten text.

Abstract: A technique for more efficiently integrating external content for web page display is disclosed. The technique includes identifying a plurality of page features for displaying a web page, selecting a corresponding content resolver from a plurality of content resolvers stored in the memory for each of the identified page features. The selecting may be in accordance with the end user device. The technique may also include rendering the web page for display on the end user device in accordance with one or more parameters specified in the corresponding content resolver.

Abstract: A control device that is communicably connected to a user terminal includes a controller, in which the controller is configured to set a virtual space, select one or more virtual spots from a plurality of candidate locations in the virtual space in accordance with associated values with a plurality of users belonging to a real specific region, install a virtual renewable energy power plant at the selected virtual spot in the virtual space, generate image information in which information regarding a real renewable energy power plant that is installed at a real spot corresponding to the selected virtual spot is displayed in association with the installed virtual renewable energy power plant, and transmit the image information to the user terminal.

Abstract: A system and method for domain aware document classification and information extraction from consumer documents are disclosed. A particular embodiment is configured to: establish, by use of a data processor and a data network, a data connection with at least one applicant platform; receive an upload of documents from the applicant platform via the data network; classify each document as being of a particular document type; determine an information extraction strategy based on a document type classification of a particular document; and extract information from the particular document based on the information extraction strategy.

Abstract: Certain aspects of the disclosure pertain to inferring a candidate entity associated with a transaction with a machine learning model. An organization identifier and description associated with a transaction can be received as input. In response, an entity embedding, comprising a vector for each entity of an organization based on the organization identifier, can be retrieved from storage. A machine learning model can be invoked with the entity embedding and description. The machine learning model can be trained to infer a transaction embedding from the description and compute a similarity score between the transaction embedding and each vector of the entity embedding. A candidate entity with a similarity score satisfying a threshold can be identified and returned. The candidate entity with the highest similarity score can be identified in certain aspects.

Abstract: An experimentation platform controls testing of features by an application server. Based on a user identifier, the experimentation platform determines which feature should be provided, and the application server provides the corresponding version of a user interface. If the user behavior data shows that using a tested feature results in an improvement, the tested feature will be adopted. To determine whether or not an improvement is observed, a statistically significant amount of data is gathered. The experimentation platform gathers data regarding user behavior for the feature versions and, in response, adjusts the frequency at which each version is served. Providing the proposed version to an increased percentage of users decreases the total number of page serves required to gather statistically significant data. The experimentation platform may provide an updated projected time to completion of testing based on the changed percentage of users receiving the proposed version.

Abstract: An automatic terminology linking system includes a candidate generator configured to identify candidate nodes for each terminology that is to be linked to a node of the knowledge base. A pseudo-candidate generator is configured to identify pseudo-candidate nodes for candidate-less terminologies. A candidate scorer is configured to respectively score the candidate nodes and the pseudo-candidate nodes by collective inference using occurrence statistics and co-occurrence statistics for these nodes. The pseudo-candidate generator is configured to identify knowledge base nodes that are semantically-related to candidate-less terminology as the pseudo-candidate nodes for the candidate-less terminology.

Abstract: In implementations of systems for identifying templates based on fonts, a computing device implements an identification system to receive input data describing a selection of a font included in a collection of fonts. The identification system generates an embedding that represents the font in a latent space using a machine learning model trained on training data to generate embeddings for digital templates in the latent space based on intent phrases associated with the digital templates and embeddings for fonts in the latent space based on intent phrases associated with the fonts. A digital template included in a collection of digital templates is identified based on the embedding that represents the font and an embedding that represents the digital template in the latent space. The identification system generates an indication of the digital template for display in a user interface.

Abstract: In implementations of systems for assistive digital form authoring, a computing device implements an authoring system to receive input data describing a search input associated with a digital form. The authoring system generates an input embedding vector that represents the search input in a latent space using a machine learning model trained on training data to generate embedding vectors in the latent space. A candidate embedding vector included in a group of candidate embedding vectors is identified based on a distance between the input embedding vector and the candidate embedding vector in the latent space. The authoring system generates an indication of a search output associated with the digital form for display in a user interface based on the candidate embedding vector.

Abstract: Systems and methods for generating encoded text representations of spoken utterances are disclosed. Audio data is received for a spoken utterance and analyzed to identify a nonverbal characteristic, such as a sentiment, a speaking rate, or a volume. An encoded text representation of the spoken utterance is generated, comprising a text transcription and a visual representation of the nonverbal characteristic. The visual representation comprises a geometric element, such as a graph or shape, or a variation in a text attribute, such as font, font size, or color. Analysis of the audio data and/or generation of the encoded text representation can be performed using machine learning.

Abstract: Methods and systems for structuring, storing and displaying time series data in a user interface. One system includes processors executing instructions to determine, from time series data from a first sensor, a first subset of time series data for the first batch from the first start time and the first end time, determine, from the time series data from the first sensor, a second subset of time series data for the second batch from the second start time and the second end time, generate a time series user interface comprising a chart, the chart including a first plot for the first subset of time series data and a second plot for the second subset of time series data, the first plot being aligned to the second plot, and cause presentation of the time series user interface.

Abstract: A method, system, and apparatus—using conventional web browsers with no custom software installation—for enabling a user to share at least one portion of content is disclosed. The user selected portions of content, or references to them, are stored in a repository and are made available for subsequent viewing to a potentially larger universe of users. Neither group: the users selecting the portions of content, nor the users viewing the previously selected portions of content, need to install any special software to avail all these benefits. The invention discloses automatically creating and embedding a portion of content from an internet document into another document. Using the teachings from this invention publishers can share their content across the internet in a manner so as to get increased exposure, back links, branding, advertising, and virality—and a plethora of other benefits.

Abstract: A method for removing text noise according to an embodiment of the present disclosure includes inspecting quality of the text, correcting the text based on a result of inspection; selecting a noise candidate based on each type of sentences included in the corrected text, wherein the noise candidate is selected for each sentence included in the text and removing at least some of the sentences included in the noise candidate based on the purpose of the text.