Abstract: A method may include obtaining multiple operations configured to be performed in a serial fashion to implement a function. In some embodiments, each operation may be performed with respect to a parameter and an input. The method may also include obtaining an indication of multiple resources configured to perform the operations and a duration for each of the multiple resources to perform each of the multiple operations individually. The method may also include modeling, as a binary optimization, a scheduling of the resources to perform the multiple operations that reduces a total duration to perform the multiple operations based on the duration for each of the multiple resources to perform each of the multiple operations individually. The method may further include solving the binary optimization to determine a schedule of the multiple resources and performing, by the multiple resources, the multiple operations according to the schedule to implement the function.

Abstract: A receiving unit (310) receives a message transmitted from any one of the users that are talk targets. The interpreter (341) attempts to interpret, as an answer to a question, the message received by the receiving unit (310). A collector (342) collects, upon success of the attempt made by the interpreter (341), the interpreted answer as the answer from the user who sends the message. When a predetermined requirement is satisfied in a state where a yet-to-respond user whose answer is not yet collected by the collector (342) is present, an inquiry transmitter (321) transmits an inquiry about the question to at least the yet-to-respond user among the users. A result transmitter (322), after the answers are collected from all of the users, transmits to the users a message indicating a result obtained by tallying the answers.

Abstract: Embodiments for relationship graph expansion and extraction from a collection of unstructured text data by a processor. A query relating to one or more concepts may be received. The query may be expanded according to a logical reasoning operation and a domain ontology having a set of logical rules. A relationship graph between one or more concepts from a plurality of unstructured text data may be extracted based on an expanded query according to a domain ontology and the set of logical rules.

Abstract: In implementations of systems for suggesting content components, a computing device implements a design system to receive input data describing a feature of a content component to be included in a hypertext markup language (HTML) document. The design system represents that feature of the content component as a document object model (DOM) element and determines a hash value for the DOM element using locality-sensitive hashing. Manhattan distances are computed between the has value and has values described by a segment of content component data. The hash values were determined using the locality-sensitive hashing for DOM elements extracted from a corpus of HTML documents. The design system generates indications, for display in a user interface, of candidate content components for inclusion in the HTML document based on the Manhattan distances.

Abstract: A method, system and computer-usable medium for performing a security analysis operation within a security environment, comprising: monitoring electronically-observable user behavior about a particular entity; maintaining a state about the particular entity, the state representing a context of a particular event; converting the electronically-observable user behavior into electronic information representing the electronically-observable user behavior; generating a user behavior profile based upon the electronic information representing the electronically-observable user behavior; and, analyzing the event using the state of the entity and the user behavior profile.

Abstract: Technologies are provided for determining an individual's likelihood of relapsing into prior behavior subsequent to a treatment for a mental health or addiction disorder, and in some instances predicting a likelihood time frame for such a relapse. Target subjects having a risk of addiction relapse, non-adherence to a treatment program, or absconding, may be automatically identified based on a multiplicative-regression model for relative survival (MRS) that is developed for predicting risk or likelihood of relapse or non-adherence. Further, in some embodiments, a leading indicator of near-term future abnormalities may be provided thereby proactively notifying supervisory personnel responsible for the person and providing such personnel with timely notice to enable effective corrective, preventive, or trend-modifying maneuvers to be undertaken.

Abstract: Methods and systems are provided for creating a calendar event using context. A natural language expression including at least one of words, terms, and phrases of text may be received at a calendar event creation module from an application. The calendar event creation module may identify one or more slots in the text of the natural language expression related to the calendar event using a first grammar module and a second grammar module. The one or more slots identified by the first grammar module and the second grammar module that indicate a calendar event may be compared to determine whether there is a match between the one or more identified slots. If a match is found, at least one calendar event using the one or more slots identified by the first grammar module and the second grammar module may be created.

Abstract: A query-focused faceted structure generation method, system, and computer program product for generating a query-focused faceted structure from a taxonomy for searching a document corpus, including augmenting taxonomy types with new instances where the instances comprise entities within a proximity of existing instances of taxonomy types in a local embedding of entities parsed from the document corpus, ranking each instance in the augmented taxonomy with respect to its type as a function of both a distance from an instance to a query in a global embedding vector space of the entities trained from the document corpus and a distance of an instance to a type in the local embedding, and ranking the taxonomy types using expanded instances in the document corpus for each type.

Abstract: A method of testing an optical network with an optical time-domain reflectometer includes determining a reference power of the optical time-domain reflectometer based on a power level of a reflected light pulse reflected from an optical reflector. After determining the reference power, the method includes connecting the optical time-domain reflectometer to one end of the optical network and connecting the optical reflector to an opposite end of the optical network. The method also includes determining a return power through the optical network based on a power level of a reflected light pulse reflected through the optical network from the optical reflector to the optical time-domain reflectometer. The method further includes determining a loss of the optical network based on the reference power and the return power.

Abstract: An Artificial Intelligence (AI) based data transformation system receives a process document and automatically generates processor-executable code which enables automatic execution of a process as detailed within the process document. Various structural elements of the process documents are identified and the data from the document is clustered based on common parameters which can include the structural elements or textual data from the process document. The contextual information including conditional and non-conditional statements along with the entities and entity attributes are also obtained. The domain knowledge is superimposed on the contextual information to generate flows that represent procedures which make up the process to be automated. Platform specific code for the automatic execution of the process is automatically generated from the flows.

Abstract: Provided is a method of obtaining state data indicating a state of a user. The method includes: obtaining estimation models for obtaining pieces of state data existing in a plurality of layers from sensor data obtained by a sensor; obtaining at least one piece of sensor data; obtaining state data of a lower layer from the at least one piece of sensor data, based on the estimation models; and obtaining state data of a higher layer from the state data of the lower layer, based on the estimation models.

Abstract: A method for analysis of problems is described, comprising receiving values for a plurality of input parameters specifying a problem, analyzing the values of the plurality of input parameters with a fuzzy expert system thereby calculating a fuzzy result, including a value of a linguistic variable and a crisp value, and determining a priority of the problem, wherein the priority is determined based on the value of the linguistic variable and the crisp value of the fuzzy result. Furthermore, a corresponding problem analysis system is provided.

Abstract: Radiation therapy treatment planning methods facilitate predicting achievable dose distributions by training a prediction model for clinical DVH curves based on simplified DVH curves obtained using standardized methods. Machine learning applied on pairs of clinical and simplified DVH curves enables predicting actual clinical DVH curves based on simplified DVH curves.

Abstract: A medical information processing apparatus includes processing circuitry. The processing circuitry acquires information concerning a similar patient similar to a designated patient. The processing circuitry acquires a value representing a first treatment effect and a value representing a first side-effect based on the acquired information concerning the similar patient. The processing circuitry generates a map image in which a mark representing the similar patient is arranged based on the value representing the first treatment effect and the value representing the first side-effect.

Abstract: Methods, apparatus, and processor-readable storage media for document indexing with cluster computing are provided herein. An example computer-implemented method includes obtaining and monitoring a list of document identifiers corresponding to documents to be indexed as part of an indexing process across at least a portion of a computing cluster; initiating the indexing processing based on one or more inputs; iteratively requesting at least one of the document identifiers; obtaining, from across at least a portion of the computing cluster, a document corresponding to a document identifier provided in response to the request; and carrying out one or more functions related to the indexing process on the obtained document.

Abstract: A method for providing an advertisement using a keyword of music content. The method includes storing information on musicians, and one or more tags corresponding to each of the musicians in a first database, storing information on music pieces, and one or more tags corresponding to each of the music pieces in a second database, storing information on music contents in a third database, acquiring tags corresponding to a musician and music piece corresponding to each of the music contents stored in the third database from the first database and the second database, storing the acquired tags in the third database, searching for the music contents stored in the third database using a first keyword as matching one of the one or more tags keywords stored in the third database, allocating the advertisement to the selected music contents.

Abstract: System, methods, and other embodiments described herein relate to an improved approach to reverse engineering binary code through the use of machine learning and image processing. In one embodiment, a method includes, in response to receiving, as an electronic input, a code segment of code that is represented in a binary format, transforming the segment into an image to visually represent the binary format of the segment. The method includes generating, as an electronic output from a classifier, a segment indicator that is based, at least in part, on the image and that specifies source code corresponding to the segment in order to reverse engineer the segment into the source code using the classifier.

Abstract: A system for prospectively identifying media characteristics for inclusion in media content is disclosed. A neural network database including media characteristic information and feature information may associate relationships among the media characteristic information and feature information. Personal characteristic information associated with target media consumers may be used to select a subset of the neural network database. A first set of nodes, representing selected feature information, may be activated. The node interactions may be calculated to detect the activation of a second set of nodes, the second set of nodes representing media characteristic information. Generally, a node is activated when an activation value of the node exceeds a threshold value. Media characteristic information may be identified for inclusion in media content based on the second set of nodes.

Abstract: A method and system for identifying and prioritizing business useful insights from hidden patterns. This invention relates to data mining techniques and more particularly to identify and prioritize insights from a plurality of insights present in a large set of data. Insight exploration is a method and system that enables the user to generate actionable insights, prioritize them for a given data. This falls broadly within the field of data mining. The primary achievement of this invention is to take a rule in if-then format and then systematically process them to identify actionable information from them. In that process, the system automatically prioritizes the rules, generates other rules and analyzes the path that leads to desired behavioral changes.

Abstract: A device extracts data files from different data sources, and processes the data files to generate data from the data files. The device trains a first artificial intelligence model and a second artificial intelligence model based on historical data parameters, wherein the historical data parameters are associated with historical data previously processed by the device. The device utilizes the trained first artificial intelligence model and the data to generate data parameters for the data, and utilizes the trained second artificial intelligence model, the data, and the data parameters to generate a data structure configuration. The device generates a data structure for the data based on the data parameters and the data structure configuration, stores the data in the data structure, and provides a user interface for accessing the data structure.

Abstract: In some examples, a computing device may receive hierarchical data having a hierarchical structure including a plurality of levels. The computing device may determine a plurality of features based at least in part on the hierarchical data, and may select a subset of the features at a first level as candidates for consolidating to a next higher level in the hierarchical structure. The computing device may determine that a predicted loss of information from consolidating the subset of features is less than a threshold, and may revise the hierarchical structure to include a consolidated feature at the next higher level, rather than the subset of features. In some examples, a statistical model may be trained based on the revised hierarchical structure and used at least partially to make a determination, send a notification, and/or control a device.

Abstract: A system, for filtering and fusing multi-source ontologies. The system includes a tangible processing controller unit and non-transitory computer-readable storage device in communication with the tangible processing controller unit. The storage device includes a first receiving unit that, when executed by the tangible processing control unit, receives a plurality of ontologies, each ontology having a set of rules and a class structure with a plurality of data classes. The storage device also includes a second receiving unit that, when executed, receives data. The device also includes a comparison unit that compares the data classes from the plurality of ontologies, and a merging unit that merges the data classes that are identical or consistent into a new data class. The storage device also includes a discarding unit that discards the data classes that are inconsistent. The storage device also includes a new-set-generation unit that generates a new set of class structure.

Abstract: The present disclosure provides systems and methods that use machine-learned models, such as deep neural networks, to predict and prevent adverse conditions at structural assets. One example method includes obtaining data descriptive of a plurality of images that depict at least a portion of a geographic area that contains a first structural asset. The plurality of images include at least a first image captured at a first time and a second image captured at a second time that is different than the first time. The method includes inputting data descriptive of at least the first image, the first time, the second image, and the second time into a condition prediction model. The method includes receiving, as an output of the condition prediction model, at least one prediction regarding the occurrence of an adverse condition at the first structural asset during one or more future time periods.

Abstract: Information extraction and annotation systems and methods for use in annotating and determining annotation instances are provided herein. Exemplary methods include receiving training documents having annotated words, identifying a predetermined number of characters preceding and following each annotated word for each of the training documents to determine a context for each of the annotated words, performing an alignment of an annotated word and its context with characters in the target document, identifying common sequences, and assigning annotations to words in the target document when common sequences are found.

Abstract: A method, computer system, and a computer program product for building and applying fuzzy term partitions is provided. The present invention may include building a fuzzy category taxonomy. The present invention may also include implementing the built fuzzy category taxonomy into a fuzzy category classifier. The present invention may then include building a fuzzy term extractor. The present invention may further include building a fuzzy term association map. The present invention may also include processing a plurality of words stored on a database. The present invention may then include extracting a fuzzy term from the processed plurality of words. The present invention may further include associating the extracted fuzzy term with a plurality of context data. The present invention may also include producing a context data partition for the extracted fuzzy term. The present invention may then include applying a weight to the extracted fuzzy term.

Abstract: The described technology relates to electronic continuous trading systems, and matching data records representing inventories with variant characteristics such as, variant length, variant data types, etc. Example implementations provide for generating instrument descriptors that include unitary-valued attributes and set-valued attributes, and the use of both types of attributes in trade decision making.

Abstract: Described is a system for predicting the behavior of an autonomous system. The system identifies a taxonomic state of a motion condition of an autonomous vehicle based on a spatiotemporal location of the autonomous vehicle and elements of a driving scenario. Behavior of the autonomous vehicle is predicted based on the taxonomic state of the motion condition. The autonomous vehicle makes and implements a driving operation decision based on the predicted behavior.

Abstract: In one embodiment, a method includes receiving a request to generate k words that each approximates a representation of a relationship between two concepts, where the request includes two input n-grams that each represent one of the two concepts, accessing a table of word vector relationships, where the table includes a plurality of unique n-grams and their corresponding word vectors, looking up word vectors corresponding to each of the two input n-grams using the table, calculating an average vector of the word vectors corresponding to the two input n-grams, selecting, using the table and based on a similarity metric, k word vectors closest to the average vector in the embedding space, identifying, for each of the selected word vectors, a corresponding n-gram by looking up the selected word vector in the table, and sending a response message, the response message comprising the identified n-grams.

Abstract: In one embodiment, a method includes receiving a request to generate a two-dimensional visualization of public sentiments regarding a particular subject, where the request includes an input n-gram representing the particular subject, constructing a first corpus of text by collecting text containing the input n-gram from a plurality of user-created content objects in the online social network, identifying a list of unique n-grams appearing in the first corpus of text, generating a table comprising unique n-grams in the list and their corresponding word vectors using a word embedding model, condensing the d-dimensional word vectors in the table into a two-dimensional word vectors; and sending, as a response to the request, instructions to display n-grams in the table on a two-dimensional display space, where each n-gram is placed at a location of the corresponding condensed word vector.

Abstract: A computing device for expert case-based natural language learning includes a blackboard database, a top level mapper, and a bottom level case-based inference engine, and a bottom level translator. The blackboard database is configured to store context information corresponding to case semantics associated with natural language sentential forms. The case semantics include situation semantics and action semantics. The top level mapper is configured to query the blackboard database for the context information, map the situation semantics to the action semantics using the context information to form new case semantics, and store the new case semantics in a bottom level case database. The bottom level case-based inference engine is configured to match an input natural language sentential form to a matching case semantic stored in the bottom level case database. The bottom level translator is configured to translate the matching case semantic into natural language sentential form.

Abstract: The present invention provides an importance-level calculation device, etc., with which it is possible to present an alert indicating network abnormality to an operator so as to enable the operator to determine the alert more efficiently. An importance-level calculation device is provided with an importance-level calculation unit which, when a first alert is notified in response to detection of an abnormality in a communication network to be monitored, computes an importance level of the first alert, based on a characteristic that is included in communication information that has caused the first alert but is not included in communication information related to one or more second alerts having been notified prior to the first alert.

Abstract: Methods to, responsive to receiving a case by a deep question answering (deep QA) system, identify, in a corpus of information, a first variable for which a value was not specified in the case, compute an importance score for the first variable based on a concept in the corpus, wherein the concept is associated with the first variable, and upon determining that the importance score exceeds an importance threshold, determine that specifying a value for the first variable increases a confidence score of a response returned by the deep QA system beyond a confidence threshold.

Abstract: Systems and computer program products to, responsive to receiving a case by a deep question answering (deep QA) system, identify, in a corpus of information, a first variable for which a value was not specified in the case, compute an importance score for the first variable based on a concept in the corpus, wherein the concept is associated with the first variable, and upon determining that the importance score exceeds an importance threshold, determine that specifying a value for the first variable increases a confidence score of a response returned by the deep QA system beyond a confidence threshold.

Abstract: A method, computer system, and a computer program product for building and applying fuzzy term partitions is provided. The present invention may include building a fuzzy category taxonomy. The present invention may also include implementing the built fuzzy category taxonomy into a fuzzy category classifier. The present invention may then include building a fuzzy term extractor. The present invention may further include building a fuzzy term association map. The present invention may also include processing a plurality of words stored on a database. The present invention may then include extracting a fuzzy term from the processed plurality of words. The present invention may further include associating the extracted fuzzy term with a plurality of context data. The present invention may also include producing a context data partition for the extracted fuzzy term. The present invention may then include applying a weight to the extracted fuzzy term.

Abstract: A method includes retrieving, by executing a scored content generator, a web content collection. The web content collection includes first metadata associated with the web content collection as a whole, content items, and second metadata associated with the content items. The second metadata also includes metrics characterizing (i) the content items and (ii) at least a portion of the web content collection. Executing a scored content generator, and based on the metrics, a content item performance score is calculated for each of the retrieved content items. Each content item performance score characterizes a level of user interaction with the content items. Data encapsulating the content item performance scores is provided to a first computing system.

Abstract: In some example embodiments, an indication of a selected data point of a current visualization can be received. A context of the selected data point can be determined based on a dimension of the data point, and explanation candidates can be generated based on the context of the selected data point. Each exploration candidate can have a different dimension context that is within the context of the selected data point and a corresponding value for the dimension context. For each one of the explanation candidates, a corresponding score can be generated based on a difference between the value for the explanation candidate and an average value of all the values of the explanation candidates. The explanation candidates can be ranked based on the scores. At least one of the explanation candidates can be selected based on the ranking, and selectable explanation(s) for the selected explanation candidate(s) can be displayed.

Abstract: A data extraction and analysis system and tool is disclosed herein. The data extraction and analysis system and tool can include memory containing a comparison database, a factor database, and a model database that can include a multilevel model. The data extraction and analysis system and tool can include a content management server. The content management server can receive a request identifying a species and a variable and can retrieve data to generate a statistical model. Based on the statistical model, the content management server can identify and recommend an option to the requestor.

Abstract: A network security analysis system performs anomaly detection with low false positives by implementing a multiple perspective analysis of network data. The analysis system implements natural language processing techniques to examine the content of network and time series data to identify anomalies within new activity.

Abstract: A control device for a vehicle heater includes: a camera; a heater configured to heat a portion of the window glass located in front of the camera; a temperature sensor configured to acquire a camera temperature; an illuminance acquisition unit configured to acquire an illuminance outside the vehicle; and a control unit configured to determine that a control prohibition condition to prohibit execution of the heater energization control is satisfied when the camera temperature is equal to or larger than a prohibition threshold temperature, execute the heater energization control when execution of the heater energization control is requested, prevent execution of the heater energization control when the control prohibition condition is satisfied, and when the illuminance is lower than a threshold illuminance, set the prohibition threshold temperature to be lower than when the illuminance is equal to or larger than the threshold illuminance.

Abstract: A system for facilitating creation of a patient treatment plan includes components configured to receive at least one feature associated with patient data and search a database of previously planned radiation treatments to identify one or more matching plans from the database based on the at least one feature. Parameters corresponding to the identified matching treatment plans may be used to facilitate creation of the patient treatment plan.

Abstract: Methods, systems, and computer program products for determining seeds for targeted notifications through online social networks are provided herein. A computer-implemented method includes analyzing user mobility data associated with multiple users of a social network to identify spatio-temporal relationships among the users; computing, for each of the users, a value representing the user's level of influence in relation to other users, wherein the value is based on the spatio-temporal relationships and a product and/or service to be identified in a spread of information within the social network; segmenting the users into groups based on the computed value for each user, wherein a first group comprises each user associated with a computed value above a given threshold, and wherein a second group comprises each user associated with a computed value below the given threshold; and selecting one or more users from the first group to initiate the spread of information.

Abstract: A method for automatic recognition of at least one anatomical landmark in a hollow organ of a patient is provided. The method includes providing an image dataset of the hollow organ, establishing or providing a three-dimensional mesh of a surface of the hollow organ from the image dataset, and determining a centerline of the mesh by skeletization. At least one feature is determined for each of a plurality of points on the centerline. A classifier pre-trained on the at least one feature is used for detecting candidates for the at least one anatomical landmark from the plurality of points. The candidates are grouped together with a distance from one another below a threshold. At least one specification determined from the anatomy of the hollow organ is used for confirming or rejecting the candidates for the at least one anatomical landmark. One or more candidates are defined as an anatomical landmark.

Abstract: A method includes receiving a request for sports programming recommendation, responsive to the receiving step, determining an upcoming program vector and a weighted historical vector, performing a similarity calculation comparing the upcoming program vector and the weighted historical vector to derive a recommendation score, and generating a recommendation based on the recommendation score.

Abstract: A method for distributed graph processing is provided including receiving ingest data from at least one data source, generating, using processing circuitry, a data map comprising a graph of edges between a plurality of data vertices of the ingest data, determining at least two nodes of a cluster, and storing a portion of the ingest data and a portion of the data map at the at least two nodes.

Abstract: Disclosed are various embodiments for identifying segment assignments of users within segments of interest. Historical user behavior associated with users for whom segment assignments within segments of interest is analyzed. Probabilities associating possible segment assignments within a segment of interest with user behavior are calculated. User behavior of anonymous users and/or users for which segment assignments are unknown can be determined along with a confidence score.

Abstract: A method, computer system, and a computer program product for building and applying fuzzy term partitions is provided. The present invention may include building a fuzzy category taxonomy. The present invention may also include implementing the built fuzzy category taxonomy into a fuzzy category classifier. The present invention may then include building a fuzzy term extractor. The present invention may further include building a fuzzy term association map. The present invention may also include processing a plurality of words stored on a database. The present invention may then include extracting a fuzzy term from the processed plurality of words. The present invention may further include associating the extracted fuzzy term with a plurality of context data. The present invention may also include producing a context data partition for the extracted fuzzy term. The present invention may then include applying a weight to the extracted fuzzy term.

Abstract: An endoscopic image diagnosis support system (100) includes: a memory (10) that stores learning images pre-classified into pathological types; and a processor (20) that, given an endoscopic image, performs feature value matching between an image of an identification target region in the endoscopic image and the learning images, to identify the pathological types in the identification target region.

Abstract: Features are disclosed for generating bundles of content items and proactively providing the bundles to client devices. The bundles may be provided to client devices in response to requests for the content page that references the content items in the bundle, or in response to a request for a content page hosted by the same domain as the content items in the bundle. A browser module executing on the client device can extract the referenced content items in the bundle and cache them in a local content cache at the client device prior to the client device receiving and processing a requested content page. As a result, the browser module may have access to cached versions of referenced content items when processing the requested content page even if the referenced content items were not present when the requested content page was requested.

Abstract: Disclosed is a technique for providing a linkage between applications, or other digital content, of an application store by assigning values to users of the digital content with respect to a particular user who is submitting a query for particular digital content. The technique involves receiving a query and identifying a subset of digital content based on the query and a word matching technique. For each identified digital content, users who have installed or downloaded the digital content may be determined. A reputation score, corresponding to a user's influence, and a trust score, corresponding to a degree of separation between the user who submitted the query and other users who have installed the digital content, may be computed for each of the users. A list of recommended applications may be generated based on the word matching technique, the reputation score, and the trust score.

Abstract: In one embodiment, sensor signals corresponding to motions of a client device are received. Activities of a user corresponding to the client device are determined, based on a first analysis algorithm that uses the sensor signals to select activity types, each activity type corresponding to a particular time period. A reference to the selected activity types is sent to the client device. User input indicating whether the reference is correct is received from the client device. Based on the indication, which reflects the accuracy of the first analysis algorithm, a priority between the first analysis algorithm and a second analysis algorithm is determined, based on determining which analysis algorithm is more accurate.