Abstract: A document index generating system and method are provided. The system comprises at least one processor and a memory storing a sequence of instructions which when executed by the at least one processor configure the at least one processor to perform the method. The method comprises preprocessing a plurality of pages into a collection of data structures, classifying each preprocessed page into at least one document type, segmenting groups of classified pages into documents, and generating a page and document index for the plurality of pages based on the classified pages and documents. Each data structure comprises a representation of data for a page of the plurality of pages. The representation comprises at least one region on the page.

Abstract: Disclosed herein are methods and systems to generate and communicate interactive digital receipts. A payment-processing system (PPS) receives first data associated with a payment transaction between a payee and a payor. The PPS is associated with a database that includes a payee profile and a payor profile. The payee profile includes payee employment history, transaction history, and location tags associated with the transactions. The payment transaction is processed. Based on the payee and payor profiles, an interactive digital proof of transaction, including an indication of an availability of a resource or a vacancy, is generated and displayed on a device associated with the payee or the payor. A location of the vacancy indicated is based on the location tags. The PPS receives second data indicating a user interaction with an interactable element of the interactive digital proof of transaction corresponding to the indication of the availability.

Abstract: The present invention is an apparatus for creating an index for conducting a search on a database based on a resource including a text sentence.

Abstract: The disclosure relates to a method and a system for predicting the operation time of sparse matrix vector multiplication. The method comprises constructing a convolutional neural network comprising an input layer, a feature processing layer, a data splicing layer and an output layer for outputting prediction results. The method further comprises acquiring a plurality of groups of sparse matrices with known sparse matrix vector multiplication operation time as sample data, inputting the sample data into the convolutional neural network to train the convolutional neural network, and inputting the sparse matrix to be classified into the trained convolutional neural network to realize the prediction of the operation time of sparse matrix vector multiplication.

Abstract: A device receives document information associated with a document, and receives a request to identify insights in the document information. The device performs, based on the request, natural language processing on the document information to identify words, phrases, and sentences in the document information, and utilizes a first machine learning model with the words, the phrases, and the sentences to identify information indicating abstract insights, concrete insights, and non-insights in the document. The device utilizes a second machine learning model to match the abstract insights with particular concrete insights that are different than the concrete insights, and utilizes a third machine learning model to determine particular insights based on the non-insights. The device generates an insight document that includes the concrete insights, the abstract insights matched with the particular concrete insights, and the particular insights determined based on the non-insights.

Abstract: In an example embodiment, access to a data set in a data lake can be specified using several approaches, based on the metadata and information attached. The metadata may be replicated from the original data source of the underlying data, and additional metadata may be modeled and stored to construct linkage information between data types. This linkage information may be used to automatically grant access to users to additional objects that are linked to objects that the user has explicit access to.

Abstract: In implementations of systems for generating review likelihoods for sets of code, a computing device implements a review system to compile input data based on code data describing information associated with a set of new code to be incorporated into a set of existing code and reviewer data describing information associated with a potential reviewer of sets of code. The review system processes the input data using a machine learning model trained on training data to generate review likelihoods for potential reviewers of sets of code to be selected to review sets of new code. A review likelihood for the potential reviewer of sets of code to be selected to review the set of new code is generated using the machine learning model based on processing the input data. The review system generates an indication of the review likelihood for display in a user interface.

Abstract: A method of monitoring performance of a building system to control ambient conditions within the interior of a structure including: detecting a physiological condition of an individual within the interior of the structure; detecting an ambient condition within the interior of the structure; determining a user activity that is assigned to an area within the interior of the structure where the individual is located; and determining a wellness performance score of the area in response to at least the physiological condition, the ambient condition, and the user activity that is assigned to an area within the interior of the structure where the individual is located.

Abstract: Various systems and methods are presented regarding mapping attributes in a first dataset with attributes in a second dataset. Rather than simply applying a static approach of matching a first attribute in the first dataset with a first attribute in the second dataset, etc., an importance of a particular attribute can be identified to assist in accurate matching versus another attribute that does not have as much importance in the matching process. For example, a DESCRIPTION attribute can have greater importance than a DATATYPE attribute, e.g., as a function of the number of terms available to be matched in a DESCRIPTION than in a DATATYPE field. By identifying the degree of matching of an important attribute, the matched values of lesser important parameters can be dynamically adjusted based on the degree of matching of the important attribute. Such an approach enables vast amounts of datasets to be automatically matched.

Abstract: Systems, methods and products for accessing a set of electronic document templates, identifying instances of common document content such as content items which are semantically similar, and generating component templates containing the common content. Semantically similar content may be identified by analyzing content for factors such as expressed sentiment, included keyphrases, recognizable entities, expressed topics, assigning values to content based on these factors, and determining similarity based on comparisons of the assigned values. Component templates may also be generated based on types of content that include identical text or images, content that has a predefined level of similarity rather than being identical, content that has common rules, scripting logic or variables, metadata, etc. The component templates may be generated automatically, or in response to user instructions.

Abstract: A method, system, and computer program product are disclosed. The method includes processing an audio signal that includes speech data and transcribing the speech data to generate text data. The method also includes identifying a vulnerable portion of the text data and, in response, applying adversarial text to the text data to generate robust text data. Adversarial noise corresponding to the robust text data is generated and applied to the speech data.

Abstract: A computer-implemented method for an improved management of artifact information is provided, particularly for facilitating finding a searched artifact information item in a plurality of artifact documents.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for a learning platform that employs machine learning to identify patterns that describe meaningful subgroups of patients associated with a particular disease, distinct characteristics of each subgroup, and implications of belonging to a specific subgroup in terms of developing into a more severe disease state for patient journey mapping. The system may include a mapping server that includes a medical-event embedding engine that embeds electronic health records into vectors, a clustering engine that identifies clusters of patients with similar patient journeys by operating on the output of the medical-event embedding engine, and a cluster profiling engine that identifies distinguishing medical events for each identified cluster by operating on the output of the clustering engine.

Abstract: Provided are an information processing apparatus and an information processing method capable of supporting work of giving a classification to a group of sentences. The information processing apparatus includes a presentation unit that presents a sentence included in a cluster of interest among clusters generated by clustering a sentence set in a sentence selection region, and a reception unit that receives selection of the sentence constituting a group of sentences from the sentences presented in the sentence selection region.

Abstract: The disclosed methods and systems provide computer-assisted guided review of unstructured data to generate a structured data output based on customizable template rules. In embodiments, an unstructured file is received, and a predefined template is selected. The predefined template includes a plurality of fields, each field corresponding to a field of the structured report. The predefined template also defines extraction rules for each field of the predefined template, and the extraction rules define parameters for identifying unstructured data relevant to the associated field. The extraction rules are applied to the unstructured file to identify data relevant to the field associated with the corresponding extraction rule, and the data identified as relevant is confirmed. Confirming the relevant data includes determining to refine the relevant data based on a condition, and modifying the extraction rule associated with the field to refine the relevant data.

Abstract: A data processing method in the form of a data compression method is provided in which a plurality of integers are accessed. Each of the plurality of integers is split to generate a first plurality of numbers respectively paired with a second plurality of numbers. A first tuple is generated based on the first plurality of numbers. A second tuple is generated based on the second plurality of numbers and the first plurality of numbers. The first tuple and the second tuple are stored. A system and computer readable medium enabling the data processing method are further provided.

Abstract: An extractive summarization model provides extraction and classification of research assertions, or claims, made by a documented body of research such as a scientific paper or article. Modern electronic publication and dissemination allows tremendous capability for researching and scrutinizing previous documented efforts for further research and study. Accordingly, a substantial volume of material is easily obtained in response to research efforts. The extractive summarization model provides a summarization of this scientific literature by identifying and classifying asserted claims made by a particular research document. Researchers may quickly identify relevant documents based on the extracted claims asserted by the document, facilitating substantive review.

Abstract: According to one embodiment, a communication data log processing apparatus includes a processor including hardware. The processor receives communication data contained in a communication data log as a log of the communication data containing a speech sentence and meta information. The processor determines a section to which the received communication data should belong based on the speech sentence and the meta information.

Abstract: A method for determining an academic impact, including: pre-processing a citing paper to obtain pre-processed data; determining a category of an impact, on the citing paper, of each reference paper and ranking of contribution, to the citing paper, of each reference paper, according to the pre-processed data; determining a local influential factor, on the citing paper, of each reference paper, according to the category of the impact and the ranking of the contribution of each reference paper; and determining a global influential factor of each reference paper according to a global influential factor of the citing paper and the local influential factor.

Abstract: Disclosed herein are system, method, and computer program product embodiments for linking data records in memory. The system, method, and computer program product includes accessing a first record stored in memory, the first record holding information describing a first person and accessing at least one additional record stored in memory, the additional records holding information describing additional persons. The method continues by parsing the information of the first record and additional record and assigning the parsed information to predefined categories within the respective records. After assigning the information into categories, a similarity score between categorical information in the first record and categorical information of additional records is determined. A category of an additional record is then modified based on the similarity score, so the additional record is associated with the first person.

Abstract: A method and server for ranking digital documents for a query are disclosed. T server hosts a search engine associated with an inverted index. The method includes accessing inverted index for retrieving query-independent data for a first document-term pair and a second document-term pair, where the query-independent data is indicative of (i) a term-specific occurrence of the first term in content of the document and (ii) a term-specific occurrence of the second term in the content of the document. The method includes generating a query-dependent feature using the query-independent data and which is indicative of a group occurrence of the first term with the second term in the content of the document. The method includes generating a ranking feature for the given document based on at least the first term, the second term, and the query-dependent feature, and ranking the given document based on at least the ranking feature.

Abstract: Systems, devices, and methods discussed herein provide improved autonomous agent applications that are configured to generate automated answers to a question using summarized logical forms (SLFs). A myriad of techniques may be utilized to generate one or more summarized logical forms for an answer, where the summarized logical form(s) identifies the main entities/informative portions of the answer. Instead of indexing the whole of the answer as in conventional methods, an answer can be indexed using the summarized logical forms. A subsequent query may be converted to logical form to generate a query representation which can be compared to one or more SLFs of a set of answers. If an SLF of an answer matches the query representation, the answer may be provided in response to the question. By indexing the answer with its informative portions, the speed and accuracy of identifying the answer is improved.

Abstract: Systems and methods for providing a document are described. In one described method, a document comprising a portion selected by a first member of a social network is hosted for the first member. The portion is dynamically updated with content. An audience criterion for the portion and a type of relationship between the first member and a second member of the social network are identified. If the type of relationship between the first member and the second member satisfies the audience criterion, the second member is provided access to at least the portion.

Abstract: A system and method for determining an embedding for a document (e.g. representing the document in vector space) by determining for the document a preliminary document embedding; determining for the document a document topic embedding based on a set of nearest topics to the preliminary document embedding; determining for each phrase in the document a topic relevancy score based on the document topic embedding and the embedding associated with the phrase; using a ranking algorithm to determine a saliency score for each phrase in the document, each saliency score based on the topic relevancy score for the phrase, and an inverse frequency score for the phrase; and calculating an embedding for the document using the saliency scores and embedding, for the phrases in the document.

Abstract: Disclosed herein are systems and methods to efficiently execute predictions models to identify future values associated with various nodes. The systems and methods described herein retrieve a set of nodes and execute various clustering algorithms in order to segment the nodes into different clusters. The systems and methods described herein also describe generating one or more prediction models, such as time-series models, for each cluster of nodes. When a node with unknown/limited data and attributes is identified, the methods and systems described herein first identify a cluster most similar the new node, identify a corresponding prediction model, and execute the identified prediction model to calculate future attribute of the new node.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for determining clusters of similar digital documents using unique document signatures. Specifically, the disclosed system processes digital text in a digital document to tokenize character strings (e.g., words) in the digital document by combining a subset of character values and string lengths in the character strings. Additionally, the disclosed system generates a document signature for the digital document by combining subsets of tokens generated for the digital document into a token sequence indicative of the digital text in the digital document. The disclosed system determines a cluster of similar digital documents including the digital document by comparing the document signature of the digital document to document signatures corresponding to a plurality of digital documents.

Abstract: Sourcing is a practice of locating and selecting entities based on set criteria. Determining most appropriate supplier entities at the lowest cost can develop a competitive advantage. However, existing sourcing techniques lack effective ways to target best suppliers for right part bundling and to efficiently optimize sourcing cost for sustained savings. Present disclosure leverages machine learning and optimization methods with technology data to provide a computationally efficient solution. Relationships between parts and corresponding attributes are obtained for parts bundling and best supplier locations are mapped for selected part bundles. A sourcing cost minimizer is used in conjunction with an iterative process to grow or limit supplier capacity by constraining award amount, bundle mix, or number of supplier entities based on multiple alternative scenarios being defined to systemically minimize cost and manage risks driven by changes in customer demand or manufacturing location.

Abstract: A sentence generation method is provided for an electronic device. The method includes obtaining an input sequence, encoding the input sequence to obtain a sentence eigenvector, decoding the sentence eigenvector to obtain a first predetermined quantity of candidate sentence sequences, clustering the first predetermined quantity of candidate sentence sequences to obtain sentence sequence sets of at least two types, screening out a second predetermined quantity of candidate sentence sequences from the sentence sequence sets of at least two types, the second predetermined quantity of candidate sentence sequences including at least two sentence feature types, and determining an output sequence corresponding to the input sequence according to the second predetermined quantity of candidate sentence sequences.

Abstract: This disclosure enables various technologies that can (1) learn new synonyms for a given concept without manual curation techniques, (2) relate (e.g., map) some, many, most, or all raw named entity recognition outputs (e.g., “United States”, “United States of America”) to ontological concepts (e.g., ISO-3166 country code: “USA”), (3) account for false positives from a prior named entity recognition process, or (4) aggregate some, many, most, or all named entity recognition results from machine learning or rules based approaches to provide a best of breed hybrid approach (e.g., synergistic effect).

Abstract: The problem of ever-increasing huge volume of unstructured data, mainly documents, and within that the scanned documents, needs to have a solution to expedite the overall turnaround time in document centric business processing. Majority of these documents often do not strictly follow a specific format or a template, and creating a generic OCR solution, which would work on any kind of document format is needed to enhance overall efficacy of processes. Embodiments of the present disclosure provide system and method that extract tabular and text information from scanned documents. More specifically, method and system are provided to extract user filled tabular data, textual information, selected radio-buttons and checked checkboxes, stamps, barcodes from scanned copies of any filled form with or without any template being pre-defined or without any prior knowledge about format of input forms. The system converts extracted information in a structured form for further for analytics and reporting.

Abstract: Techniques for generating formatting tags for textual content obtained from a source electronic document are disclosed. A system parses a digital file to obtain information about characters in an electronic document. The system applies tags to text generated based on the textual content of the electronic document by creating segments of textually-consecutive characters and applying corresponding text formatting style tags to the segments. The system further identifies segments of text overlapping bounding boxes in the electronic document. The system generates textual content including a segment of text and a corresponding hyperlink associated with the segment of text. The system further generates textual content by selectively applying line breaks from the source electronic document in the textual content.

Abstract: A learning apparatus according to an embodiment has a feature generation means configured to take a search query, a first document related to the search query, and a second document that is not related to the search query as input, and generate a feature of the search query, a feature of the first document, and a feature of the second document, by using model parameters of a neural network, and an update means configured to take the feature of the search query, the feature of the first document, and the feature of the second document as input, and update the model parameters by using an error function including a cost function that is a differentiable approximation function of an L0 norm.

Abstract: According to implementations of the subject matter described herein, there is provided a solution for generating a summary of a document. In this solution, feature information of pages comprised in a document is extracted, which characterizes at least one type of content contained in each page. Respective importance of the pages is determined at least based on the extracted feature information. A summary of the document is generated for the document by selecting a predetermined number of pages less than the number of the pages based on the respective importance. Through the solution, instead of providing all the pages, pages containing important content may be determined automatically to serve as the summary of the document. This summary allows the user to learn quickly main content of the document, shorten the time consumed in browsing all documents and/or facilitate location of a document of interest as soon as possible.

Abstract: Systems and methods for determining one or more topics that may be associated and/or grounded with a node of a taxonomy to facilitate the creation and/or modification of the taxonomy. The one or more topics can be determined by generating two layers of associations and/or groundings. In a first layer, tokens can be associated and/or grounded in a corpus of queries, and in a second layer, topics can be associated and/or grounded in the tokens. The topics can then be associated with and/or grounded in nodes of a taxonomy which can facilitate access to content items stored and maintained by an online service. Further, in exemplary implementations where the content items include associations and/or mappings to the corpus of queries, the nodes of the taxonomy (which are associated with one or more topics) can be transitively mapped to the content items.

Abstract: Disclosed are implementations for ranking a feed in a social network. In one aspect, a method of generating a feed includes identifying a group of users associated with a first user, identify notifications for the first user based on the group of users, determine one or more actions that may result from each of the identified notifications, rank the notifications based on the one or more determined actions; and display the notifications to the first user according to the ranking.

Abstract: This application relates to targeted search of backup data. A data storage system can provide a targeted search of backup data based on events associated with the backup data. Upon receiving a search query that identifies an event stored in an event database, the data storage system can determine an event location and an event time associated with the identified event by accessing the event database and output a search result including a portion of the backup data that is associated with the event location and the event time.

Abstract: An example method includes receiving and preprocessing a query request prior to execution of a query. Through preprocessing, a probability that execution of the query would yield a result set similar to at least a portion of results stored in a repeated query result repository is obtained. In response to the probability satisfying a probability threshold, a portion of results is retrieved from the repository. The example method further includes causing transmission of a response to the query request, the response comprising the portion of results.

Abstract: Techniques are described herein for determining an information gain score for one or more documents of interest to the user and present information from the documents based on the information gain score. An information gain score for a given document is indicative of additional information that is included in the document beyond information contained in documents that were previously viewed by the user. In some implementations, the information gain score may be determined for one or more documents by applying data from the documents across a machine learning model to generate an information gain score. Based on the information gain scores of a set of documents, the documents can be provided to the user in a manner that reflects the likely information gain that can be attained by the user if the user were to view the documents.

Abstract: A method for predicting matching degree between a resume and a post, and a related device are provided in this disclosure. In the method for predicting the matching degree between the resume and the post, and the related device according to this disclosure, firstly the semi-structured keys and values in post information and resume information and their source are obtained. Then, the matching degree between the resume information and the post information is predicted by a prediction model including a cascaded pre-trained language model, a Transformer encoder and a single label classification model, based on the keys and values of a respective post information and resume information attribute, and corresponding source representations. Thus, by comprehensively searching internal interaction and external interaction of semi-structured multivariate attributes in person-post matching, the matching result is more accurate.

Abstract: Performing a mutual exclusion data class analysis is provided. A data class group of a plurality of data class groups that a matching data class is a member of is identified. The matching data class matches data in a plurality of rows of a column in a data asset. Data classes included in the data class group that the matching data class is a member of are identified. A mutual exclusion data class is filtered from the data class group to form a filtered data class group for the column. The filtered data class group is run against the column of the data asset decreasing processing time and resource utilization of a computer.

Abstract: This disclosure describes a technique to determine whether a client computing device accessing an API is masquerading its device type (i.e., pretending to be a device that it is not). To this end, and according to this disclosure, the client performs certain processing requested by the server to reveal its actual processing capabilities and thereby its true device type, whereupon—once the server learns the true nature of the client device—it can take appropriate actions to mitigate or prevent further damage. To this end, during the API transaction the server returns information to the client device that causes the client device to perform certain computations or actions. The resulting activity is captured on the client computing and then transmitted back to the server, which then analyzes the data to inform its decision about the true client device type.

Abstract: An example first network device includes a control unit configured to execute at least one application and a forwarding unit. The forwarding unit includes an interface configured to receive packets, at least one packet processor operably coupled to a memory, and a forwarding path, wherein at least a portion of the forwarding path is stored in the memory and is executable by the at least one packet processor. The forwarding unit is configured to receive an advertisement originated by a second network device in a network, wherein the advertisement specifies a second micro segment identifier (SID), and store, in a destination lookup table, a route entry comprising a first micro SID associated with the first network device and the second micro SID.

Abstract: In a processing system 101, a first processing device 111 obtains first characteristics information indicating a characteristics of users in a first environment, divides the users into first clusters according to the first characteristics information, and transmits, to a second processing device 121, belonging information indicating which of the first clusters each of the users belongs to. The second processing device 121 obtains second characteristics information indicating characteristics of the users in a second environment, and divides the users into second clusters according to the belonging information and the second characteristics information.

Abstract: A system for managing web traffic comprising a meta control operating on a first processor having a first control interface and configured to generate a request for content and to transmit the request for content over a digital data network to a meta control server. The meta control server operating on a second processor and configured to receive the request for content and to select data for one or more second control interfaces as a function of data associated with the first control interface and to transmit the data for the one or more second control interfaces over the digital data network to the first control interface. The first control interface displays the data for the one or more second control interfaces and monitors user activity associated with the data.

Abstract: Content of different formats may be sourced from various data sources such as content servers and ingested into a data integration server by an ingestion broker embodied on a non-transitory computer readable medium. The ingestion broker may normalize the content of different formats into a uniform representation that can be indexed and delivered across multiple digital channels for a variety of applications. The normalized content may be analyzed and semantic metadata may be determined from the normalized content. The normalized content can be semantically enriched by associating the semantic metadata and the like with the content. The semantic metadata can be stored in a semantic index that can be used for searching via the data integration server. During search, the semantic metadata can be instantiated as facets for user navigation and refinement of search criteria and additional semantic relationships can be assigned to the words in the normalized content.

Abstract: The present disclosure is directed to systems and methods that include and/or leverage one or more machine-learned language models that generate intermediate textual analysis (e.g., including usage of structural tools such as APIs) in service of contextual text generation. For example, a computing system can obtain a contextual text string that includes one or more contextual text tokens. The computing system can process the contextual text string with the machine-learned language model to generate one or more intermediate text strings that include one or more intermediate text tokens. The computing system can process the one or more intermediate text strings with the machine-learned language model to generate an output text string comprising one or more output text tokens. The one or more intermediate text strings can include textual analysis of the contextual text string that supports the output text string.

Abstract: A first document is stored in a first format having an ordered sequence of data elements including characters and embedded objects accessible by index location into the ordered sequence. The first document in the first format is converted into a second document in a second format having a second ordered sequence including a subset of the data elements of the first document including the characters but not the embedded objects, such that the index location into the ordered sequence of the characters differs between the first and second documents. The second document is analyzed in the second format as plain text to identify a string of the data elements of interest. A document location of the string of the data elements of interest is represented as a relative location into the second document. The relative location into the second document is mapped into the index location of the first document.

Abstract: According to an embodiment, a storage method includes: a step of generating scan data by scanning of a document with a reading device; a step of acquiring index information that is different from information that is based on the document; and a step of assigning the acquired index information to the scan data and storing the scan data to which the index information is assigned in a storage device.

Abstract: A frequency of occurrence for each term in a training data set is determined in relation to the entire training data set. A relational data structure is generated that associates each term in the training data with its respective frequency. Any term that has a frequency below a threshold frequency is then added to a list of relevant words. When a natural language search query is received, a plurality of terms in the natural language search query are identified and compared with the list of relevant words. If any term of the natural language search query is included in the relevant words list, that term is identified as a keyword. The natural language search query is then interpreted based on any identified keywords.

Abstract: Methods for generating content summaries in a web content management service, wherein in one embodiment a digital page editor and a component browser are launched to enable selection of a first content item. A summary of the first content item is automatically generated according to parameters that may have default values or values set by a user. The parameters may specify a size for the summary as a percentage of the first content item's size, as a particular number of lines, characters or words, as a size for a particular type of device, etc. The automatically generated summary is provided to the digital page editor, which can edit it and add it to the digital page. The summary is stored in a content repository as an independent summary content item with its own metadata.