Abstract: A computer-implemented method for utilizing external knowledge and memory networks in a question-answering system includes receiving, from a search engine of a question-answering system, one or more search results based on a search query associated with a question submitted via a user interface associated with a computing device, analyzing the one or more search results to generate search evidence as a source of external knowledge for generating an answer to the question, the search evidence including one or more titles and one or more corresponding text snippets, encoding the search evidence and the search query to generate vectors stored in a memory network, obtaining a final vector representation based on the encoding, and decoding the final vector representation to obtain the answer to the question.

Abstract: Techniques for augmenting relational databases with graph database capabilities are described. A graph database query requesting data from a graph database is received. The graph database includes a plurality of vertices and a plurality of edges. The graph database query is translated into a relational database query using one or more computer processors. The relational database query references a vertex table and an edge table in a relational database. Result data corresponding with the graph database query is retrieved from the relational database by executing the relational database query against the relational database.

Abstract: Techniques are described that facilitate automatically distinguishing between different expressions of a same or similar emotion. In one embodiment, a computer-implemented is provided that comprises partitioning, by a device operatively coupled to a processor, a data set comprising facial expression data into different clusters of the facial expression data based on one or more distinguishing features respectively associated with the different clusters, wherein the facial expression data reflects facial expressions respectively expressed by people. The computer-implemented method can further comprise performing, by the device, a multi-task learning process to determine a final number of the different clusters for the data set using a multi-task learning process that is dependent on an output of an emotion classification model that classifies emotion types respectively associated with the facial expressions.

Abstract: The invention relates to a submersible-type humidifier that adding water from upper portion, comprising a lower water tank and a top cover connected thereto, the lower water tank and the top cover are detachably connected, an electric appliance chamber is arranged in inner chamber of the top cover, an air blower and a display control panel are arranged inside the electric appliance chamber, an energy gathering atomization pipe is provided on bottom of the top cover, an ventilation portion is provided on outer side of the energy gathering atomization pipe, air blower is connected to the ventilation portion, inner chamber of the energy gathering atomization pipe is respectively connected with the ventilation portion and mist outlet of the top cover, an atomization component is provided on bottom of the energy gathering atomization pipe, the atomization component and the air blower are respectively electrically connected to the display control panel.

Abstract: A computer-implemented method for clinical decision support is provided according to an embodiment of the present disclosure. In the method, patient information can be obtained that comprises at least one clinical condition. A graph can be searched for at least one rule matching the at least one clinical condition. The graph represents a plurality of rule sets. The rule set comprises one or more rule. The rule can be indicated with a path comprising at least one first node and a second node. The first node can indicate a clinical condition, and the second node can indicate a clinical conclusion. Then, a clinical conclusion can be determined based on the at least one path in response that the at least one path matching the at least one clinical condition is searched out.

Abstract: The present invention discloses a method for optimizing sensor network node location in a geological CO2 storage area. In the method, by analyzing data in a monitoring area, such as geological data, geographical data, and meteorological data, analyzing influence factors of a CO2 leakage event and determining a sensitivity partition, designing different coverage control schemes of monitoring sensor network nodes, or intensively or sparsely arranging sensor monitoring nodes, a coverage network is described and optimally expressed on the basis of Delaunay triangulation. In the method for optimizing sensor network node location in a geological carbon dioxide storage area, the arrangement density of wireless sensor network nodes can be dynamically adjusted according to geological and geographical features of a detection area, and the arrangement optimization of a dynamic monitoring sensor network for coal seam carbon dioxide injection area leakage can be realized.

Abstract: Techniques are provided for generating recommended query terms that are specialized to a topic of desired information based on a query associated with a user. In one example, a computer-implemented method comprising selecting, by a system operatively coupled to a processor, a coarse cluster of corpus terms having a defined relatedness to a query associated with a user from a plurality of coarse clusters of corpus terms; and determining, by the system, a plurality of candidate terms from search results associated with the query. The computer-implemented method can also comprise determining, by the system, at least one recommended query term based on refined clusters of the coarse cluster, the candidate terms, and the query; and displaying, by the system, the at least one recommended query term on a display device associated with the query.

Abstract: A method in which a plurality of process are configured to hold a block of data destined for other processes, with data repacking circuitry including receiving circuitry configured to receive at least one block of data from a source process of the plurality of processes, the repacking circuitry configured to repack received data in accordance with at least one destination process of the plurality of processes, and sending circuitry configured to send the repacked data to the at least one destination process of the plurality of processes, receiving a set of data for all-to-all data exchange, the set of data being configured as a matrix, the matrix being distributed among the plurality of processes, and transposing the data by each of the plurality of processes sending matrix data from the process to the repacking circuitry, and the repacking circuitry receiving, repacking, and sending the resulting matrix data to destination processes.

Abstract: The present invention relates to a data storage technology, and in particular relates to a data depositing method applicable to a flash memory in a display device. The method comprises: step S1, dividing a first user storage area and a second user storage area from the flash memory, so as to store structured data; and step S2, circularly and alternately storing, according to one pre-set strategy, the structured data between the first user storage area and the second user storage area. According to the method, newly stored data can he found easily, and the problem of data loss caused by erasure and power outage is avoided, and the writing speed is fast and the reliability is high.

Abstract: Methods and systems for processing records include extracting feature vectors from words in an unstructured portion of a record. The feature vectors are weighted based similarity to a topic vector from a structured portion of the record associated with the unstructured portion. The weighted feature vectors are classified using a machine learning model to determine respective probability vectors that assign a probability to each of a set of possible relations for each feature vector. Relations between entities are determined within the record based on the probability vectors. An action is performed responsive to the determined relations.

Abstract: A system for decentralized privacy-preserving clinical data evaluation includes a plurality of sites of a decentralized private network, a memory device for storing program code, and at least one processor device operatively coupled to the memory device and configured to execute program code stored on the memory device to, for each of the local datasets, evaluate the local dataset using each of the local models to obtain one or more features related to a degree of outlierness, determine at least one outlier dataset based on the one or more features, and implement one or more actions based on the determination.

Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.

Abstract: A pattern based audio searching method includes labeling a plurality of source audio data based on patterns to obtain audio label sequences of the source audio data; obtaining, with a processing device, an audio label sequence of target audio data; determining matching degree between the target audio data and the source audio data according to a predetermined matching rule based on the audio label sequence of the target audio data and the audio label sequences of the source audio data; and outputting source audio data having matching degree higher than a predetermined matching threshold as a search result.

Abstract: A computer-implemented method for utilizing external knowledge and memory networks in a question-answering system includes receiving, from a search engine of a question-answering system, one or more search results based on a search query associated with a question submitted via a user interface associated with a computing device, analyzing the one or more search results to generate search evidence as a source of external knowledge for generating an answer to the question, the search evidence including one or more titles and one or more corresponding text snippets, encoding the search evidence and the search query to generate vectors stored in a memory network, obtaining a final vector representation based on the encoding, and decoding the final vector representation to obtain the answer to the question.

Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.

Abstract: A computer-implemented method, system, and computer program product are provided for Autism Spectrum Disorder assessment and intervention. The method includes receiving, by a processor device, behavioral phenomenon from a child. The method also includes generating, by the processor device, a similarity score for the child based on a similarity between the behavioral phenomenon and ASD profiles. The method additionally includes evaluating, by the processor device, the similarity score against applied behavior analysis (ABA) training courses. The method further includes determining, by the processor device, a dynamic ABA protocol from a sorted list of the ABA training courses. The method also includes controlling an operation of an interactive training device to deliver the dynamic ABA protocol to the child.

Abstract: Speech recognition is performed by receiving a speech signal that includes spoken phones. A dynamic time warping procedure is applied to the received speech signal to generate a time-warped signal. The time-warped signal is compared to a plurality of stored reference patterns to identify a set of stored reference patterns that are most similar to the time-warped signal. A candidate hot word is selected from a list using the identified set of stored reference patterns. The selection of the candidate hot word is then refined.

Abstract: A computer implemented method, computer system and computer program product are provided for data classification. According to the method, an original data is received by one or more processing units. A classification of the original data with a trained classifier is determined by one or more processing units, wherein the classifier is trained by a labeled data of different granularity, and the labeled data include at least one defect object.