Abstract: Systems and methods for analyzing an unknown sample are disclosed. The system includes at least one subsystem to obtain molecular information about the sample and at least one other subsystem to obtain elemental information about the sample. The system also includes a data collection component to collect and combine the information from the subsystems to create combined analytical information and a multivariate model that relates known attributes to information previously generated with at least two analytical systems that are the same types of systems as the at least two analytical subsystems. A prediction engine applies the multivariate model to the combined analytical information to produce predictions of attributes in the unknown sample.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for an improved text classification model. A text classification system determines a first embedding for a first set of characters in a text, and a second embedding for a second set of characters in the text. The text classification system applies a first coefficient to the first embedding and a second coefficient to the second embedding, yielding a first weighted embedding and a second weighted embedding. The first coefficient is different than the second coefficient. The text classification system determines a weighted average embedding for the text based on the first weighted embedding, the second weighted embedding, the first coefficient and the second coefficient. The text classification system identifies at least a first classification label and a second classification label for the text based on the weighted average embedding for the text.

Abstract: A medical diagnosis support apparatus which provides information for supporting medical diagnosis includes an inference unit which obtains an inference result based on a combination of already input information and each non-input information, an evaluation unit which evaluates each non-input information by using an inference result on the already input information which is obtained by the inference unit and an inference result on the each non-input information which is obtained by the inference unit, and a selection unit which selects non-input information to be presented from the non-input information based on the evaluation obtained by the evaluation unit.

Abstract: Methods and apparatus to facilitate dynamic classification for market research are disclosed. Example disclosed methods include constructing, using a programmed processor based on data for a sample population and a first set of input variables, a self-organizing map classifying the sample population according to a plurality of classes defined in the map using fuzzy class membership. Example disclosed methods include extracting the fuzzy class membership for the sample population from the map. Example disclosed methods include correlating fuzzy class membership with behavior data for the sample population to determine a likely class behavior for the plurality of classes. Example disclosed methods include using fuzzy class membership and the likely class behavior to provide a predictive market output in response to a query.

Abstract: Infusion systems, infusion devices, and related operating methods are provided. An exemplary method of operating an infusion device capable of delivering fluid to a patient involves obtaining, by a control system associated with the infusion device, measurement values indicative of a condition of the patient provided by a sensing device, identifying an event pattern based at least in part on the measurement values for the condition and historical data associated with the patient, generating a notification indicative of the event pattern in response to identifying the event pattern, and adjusting operation of the infusion device to deliver the fluid to the patient in a manner that is influenced by the event pattern in response to receiving user input confirming the event pattern.

Abstract: A text stream source is accessed that includes a plurality of text content items. Unique word groupings are determined for the plurality of text content items. A burst detection algorithm is executed to determine word groupings that are currently bursting and that started within a specified time period. Based on the word groupings, an issue is determined based on identifying a set of texts forming at least one clique.

Abstract: A method of processing input data using a computing system. The method comprises obtaining association data which relates a kernel in a convolutional neural network to one or more known data patterns; conducting analysis of input data for the convolutional neural network to identify whether a region of input data corresponds to at least one of the one or more known data patterns; and determining whether to process the region of input data with the kernel in the convolutional neural network based on the analysis and the association data.

Abstract: A computer-implemented method, system, and computer program product are provided for activity recognition. The method includes receiving, by a processor, a plurality of videos, the plurality of videos including labeled videos and unlabeled videos. The method also includes extracting, by the processor with a feature extraction convolutional neural network (CNN), frame features for frames from each of the plurality of videos. The method additionally includes estimating, by the processor with a feature aggregation system, a vector representation for one of the plurality of videos responsive to the frame features. The method further includes classifying, by the processor, an activity from the vector representation. The method also includes controlling an operation of a processor-based machine to react in accordance with the activity.

Abstract: There is described a computing device and method in a digital medium environment for custom auto tagging of multiple objects. The computing device includes an object detection network and multiple image classification networks. An image is received at the object detection network and includes multiple visual objects. First feature maps are applied to the image at the object detection network and generate object regions associated with the visual objects. The object regions are assigned to the multiple image classification networks, and each image classification network is assigned to a particular object region. The second feature maps are applied to each object region at each image classification network, and each image classification network outputs one or more classes associated with a visual object corresponding to each object region.

Abstract: Methods for providing contextual video recommendations within a video game are provided. In one aspect, a method includes executing an application that uses a rendering engine. The method also includes determining that a video recommendation threshold has been met. The method also includes providing a current contextual state of the application to a server such that the server selects a video from a plurality of videos based on the provided current contextual state and an index, wherein the index includes output from a vision model applied on the plurality of videos, and wherein the vision model is trained on footage generated by the rendering engine. The method also includes receiving a reference to the selected video from the server. The method also includes providing for display, via the reference, the selected video within a user interface of the application. Systems and machine-readable media are also provided.

Abstract: Various technologies described herein pertain to controlling an autonomous vehicle to suppress data corresponding to predefined static objects in a radar output generated by a radar sensor system. A computing system of the autonomous vehicle retrieves prior data for a geographic location from a prior radar space map. The prior radar space map includes prior data for geographic locations in an environment corresponding to whether predefined static objects to be suppressed in radar outputs are located at the geographic locations. The computing system generates a score representative of a likelihood of a tracked object being at the geographic location based on data from the radar output for the geographic location, data from an output of a second sensor system for the geographic location, and the prior data for the geographic location from the prior radar space map. An engine, braking system, and/or steering system are controlled based on the score.

Abstract: A method of generating the knowledge base used for a programmable fuzzy controller comprising the steps of determining the relevant input and output variables to be controlled; creating artificial potential fields for each of said variables; sampling each of said potential fields in order to generate fuzzy membership functions; compiling said fuzzy membership functions into fuzzy sets; and mapping inputs fuzzy set to output fuzzy sets through a rule base. The relevant input and output variables are including: minimum, maximum, and equilibrium values; an importance weight; a non-linearity value; a control direction; and information as to whether said variable is an input or output variable. Further provided is a programmable fuzzy controller whose fuzzy knowledge base is obtained by the method described.

Abstract: A system includes a processor and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to gather usage data of a tape drive during usage thereof and create and/or update a usage model based on the usage data. The logic is configured to determine that the usage model has reached a predefined confidence level and perform an action for extending a life of the tape drive in response to determining that the usage model has reached the predefined confidence level.

Abstract: A system for monitoring user engagement, comprising at least one hardware processor, configured to: receive from a plurality of sensors information about a sequence of interactions of a user with a software application during a time interval, the information comprising, for each of the sequence of interactions, a plurality of sensor output values of a plurality of engagement metrics reflecting the user's emotional attachment to the software application; compute a sequence of linearly uncorrelated principle components based on an outcome of principal component analysis (PCA) of the plurality of sensor output values of the plurality of engagement metrics; and select a first component from the sequence of linearly uncorrelated principle components to be a user engagement index representing engagement of the user with the application during the time interval according to the plurality of engagement metrics.

Abstract: A system is described for analyzing plays of a sporting event based on body-pose information in conjunction with real-world positional tracking data. The system permits segmentation of sporting event plays into discrete time periods and the labeling of appropriate body-pose characteristics for each period. The system allows for comparison and fine-grained analysis of plays with respect to either a series of body-pose vertices that exist in continuous space (i.e., skeleton) or map directly to attributes, using the positional tracking data and play information to account for contextual differences. To enable analysis for the former, the system performs a projection to 3D space, followed by a spatiotemporal alignment step. Through the system, the importance of particular body-pose motions or specific attributes to the success of particular sporting event plays is quantified.

Abstract: A method is for creating a classification unit for the automatic classification of materials. An embodiment of the method includes provision of a learning computing device; provision of a start classification unit; provision of a reference image set including spectral reference recordings with annotated materials; and training of the classification unit with the reference recording set. Furthermore, a classification method is for the automatic classification of materials in an image recording. An embodiment of the classification method includes provision of a trained classification unit; provision of a spectral image recording; examination of the image recording for materials via the classification unit; and identification of the determined materials. Furthermore, a classification unit, a learning computing device, a control device and a medical imaging system are disclosed.

Abstract: Various technologies described herein pertain to generating an occupancy grid movie for utilization in motion planning for the autonomous vehicle. The occupancy grid movie can be generated for a given time and can include time-stepped occupancy grids for future times that are at predefined time intervals from the given time. The time-stepped occupancy grids include cells corresponding to regions in an environment surrounding the autonomous vehicle. Probabilities can be assigned to the cells specifying likelihoods that the regions corresponding to the cells are occupied at the future times. Moreover, cached query objects that respectively specify indices of cells of a grid occupied by a representation of an autonomous vehicle at corresponding orientations are described herein. An occupancy grid for the environment surrounding the autonomous vehicle can be queried to determine whether cells of the occupancy grid are occupied utilizing a cached query object from the cache query objects.

Abstract: The present invention relates to the architecture of a quantum RAM, a method for using classical data in quantum computing by inputting the classical data as quantum data, and a system and method of operating a quantum database using the architecture. Quantum computing can achieve an exponential speed-up in some applications using a large parallel process provided by a quantum database in which information can be superposed. The present invention proposes an efficient quantum database architecture and protocol that can record and search for classical information with a quantum circuit.

Abstract: There is provided an anomaly diagnosis method performed by an anomaly diagnosis apparatus that diagnosis to determine whether an observed value composed of values of variables representing a state of a monitoring target obtained by observing the monitoring target is anomalous. The anomaly diagnosis apparatus includes a processor and a memory. The memory stores an anomaly detection model generated by learning using observed values. The processor acquires group information indicating one or more groups each constituted by a combination of at least two mutually-related variables, acquires the observed value, determines whether the observed value is anomalous by employing the anomaly detection model read from the memory, and in a case where the observed value is determined to be anomalous, identifies a group causing an anomaly among the one or more groups in the observed value.

Abstract: A processing core for the efficient execution of a directed graph is disclosed. The processing core includes a memory and a first and a second data tile stored in the memory. The first and second data tiles include a first and a second set of data elements stored contiguously in the memory. The processing core also includes metadata relationally stored with the first data tile in the memory. The processing core also includes an execution engine, a control unit, and an instruction. Execution of the instruction uses the execution engine, a first data element in the first set of data elements, and a second data element in the second set of data elements. The control unit conditions execution of the instruction using the metadata. A standard execution of the instruction generates a standard output. A conditional execution of the instruction operation generates a conditionally executed output.

Abstract: The disclosure discloses a method for obtaining formation parameters of a gas hydrate reservoir through well testing interpretation, which comprises: (1) establishing a physical model for well testing interpretation of the gas hydrate reservoir according to multiphase flow, hydrate dissociation, secondary hydrate formation and heat transfer exhibited in the well testing process of the gas hydrate reservoir; (2) establishing a mathematical model for well testing interpretation of the gas hydrate reservoir; (3) conducting spatial discretization and temporal discretization on the mathematical model, and adopting a finite volume method to obtain a numerical solution of bottom-hole pressure; (4) calculating a bottom-hole pressure variation curve and a production rate variation curve in the well testing process of the hydrate reservoir, and drawing theoretical curves of bottom-hole pressure difference and pressure difference derivative; and (5) matching a measured pressure curve with the theoretical curve to obtain

Abstract: Data includes data with labels and data without labels. For data without labels a fuzzy rules system assigns pseudo labels. A computer processes the data with labels using a first cognitive neural network; processes the data with pseudo labels using a second cognitive neural network; and produces system outcomes by combining the results of the first and second cognitive neural networks. The computer obtains feedback on the system outcomes, and modifies parameters of the fuzzy rule system in response to the feedback.

Abstract: Techniques for generating domain and client-specific application program interface recommendations are provided. In one example, a computer-implemented method comprises modifying, by a device operatively coupled to a processor, a description of a client application program interface by removing text data associated with the description of the client application program interface, resulting in a modified description of the client application program interface. The computer-implemented method can further comprise analyzing, by the device, a performance associated with the client application program interface to generate an ontology based on a semantic similarity between the modified description of the client application program interface and one or more previous descriptions of one or more previous client application program interfaces.

Abstract: A network device accesses a server via a network to collect information from a user and to verify identification of the user. Financial information of the user is accessed from one or more sources other than the user. An indicator of financial responsibility is assigned to the user based on the collected information and the accessed financial information of the user. The indicator of financial responsibility is disclosed to other persons under conditions selected by the user by communicating the indicator of financial responsibility via the network to one or more network devices.

Abstract: The present approach relates to improving query performance in a database context. Examples of query improvement are described in the context of certain query patterns, one or more of which may be observed in a given query. When a given query pattern is observed, changes may be made to the query at the application or database level to improve performance of the respective query. Query improvements may be performed in a manner transparent to the user.

Abstract: A method for detecting structural surface cracks based on image features, support vector machines and Bayesian data fusion, including: 1) acquisition of a video of a structural surface and establishment of an image library; 2) calculation of texture features of the image frames by local binary patterns; 3) scanning and grouping for image patches of cracks on the image frames using two-stage support vector machine; 4) Bayesian data fusion and decision. The video image detection acquires images of many areas where human beings are difficult to reach; computers are adopted to identify cracks on surfaces of the structural elements, which can greatly reduce the identification workload and labor cost, and increase the crack detection rate. The invention has a better adaptability to the light strength on the structural surface, thus providing better identification for cracks.

Abstract: A self-monitoring time series database system is described. A time series database system receives an alert trigger condition associated with multiple time series data points corresponding to multiple subsystems of the time series database system. The time series database system aggregates the multiple time series data points in an internal time series data point that is internal to the time series database system. The time series database system evaluates whether the internal time series data point meets the alert trigger condition. The time series database system outputs an alert notification associated with the internal time series data point and the alert trigger condition if the internal time series data point meets the alert trigger condition.

Abstract: Embodiments herein disclose a method and system for authenticating users of an electronic device. In an example, data pertaining to a user of the electronic device is collected for authentication. The data is data indicative of an interaction behavior of the user with the electronic device. A deviation of the collected data from a behavior model of the user is checked. To generate the behavior model, data from multiple users is collected to create the behavior model corresponding to each of the users, each behavior model is indicative of data uncommon between the user corresponding to the behavior model and other users in the plurality of users to separate the user corresponding to the behavior model from other users in the multiple users. Further, an access control policy is enforced on the electronic device, based on the deviation of the collected data from the behavior model of the user.

Abstract: A time series database system receives a trigger condition associated with time series data points corresponding to subsystems of the system. The system aggregates the time series data points associated with a first time into a first internal time series data point. The system aggregates the time series data points associated with a second time into a second internal time series data point if the first internal time series data point does not meet the trigger condition. The system calculates a projected internal time series data point based on the first internal time series data point and the second internal time series data point if the second internal time series data point does not meet the trigger condition. The system outputs a projected alert notification associated with the projected internal time series data point and the trigger condition if the projected internal time series data point meets the trigger condition.

Abstract: This disclosure relates generally to data processing, and more particularly to a system and a method for mapping heterogeneous data sources. For a product being sold globally, there might be one global database listing characteristics of the product, and from various System and method for mapping attributes of entities are disclosed. In an embodiment, the system uses a combination of Supervised Bayesian Model (SBM) and an Unsupervised Textual Similarity (UTS) model for data analysis. A weighted ensemble of the SBM and the UTS is used, wherein the ensemble is weighted based on a confidence measure. The system, by performing data processing, identifies data match between different data sources (a local databases and a corresponding global database) being compared, and based on matching data found, performs mapping between the local databases and the global database.

Abstract: System and method for an active learning system including a sensor obtains data from a scene including a set of images having objects. A memory to store active learning data including an object detector trained for detecting objects in images. A processor in communication with the memory, is configured to detect a semantic class and a location of at least one object in an image selected from the set of images using the object detector to produce a detection metric as a combination of an uncertainty of the object detector about the semantic class of the object in the image (classification) and an uncertainty of the object detector about the location of the object in the image (localization). Using an output interface or a display type device, in communication with the processor, to display the image for human labeling when the detection metric is above a threshold.

Abstract: Computer implemented methods for access control for a restricted resource in a computer system and related methods train a hierarchical temporal memory and use cryptocurrency allocations and blockchain records to determine whether resource consumers are authorized or unauthorized to access the restricted resource.

Abstract: A system, method and program product for providing cascade prediction. A system is disclosed having: a computing system for receiving observed cascade data, wherein the observed cascade data includes a set of nodes impacted prior to a preliminary time; a sub-cascade processing engine that determines a sub-cascade size of each node in the set of nodes; survival analysis system that utilizes a networked Weibull regression to determine a survival rate of each node in the set of nodes; and a calculation system that applies the survival rate to the sub-cascade size of each node in the set of nodes to generate a predicted cascade size at a future time.

Abstract: Systems and methods are disclosed for enabling Internet users to schedule recordings of electronic programming content. One method includes displaying on a web page, over the Internet, a user interface element associated with an advertisement for electronic programming content; wherein selection of the user interface element, by a user of a web browsing device, initiates a recording device of the user, separate from the web browsing device, to schedule a recording of the electronic programming content. Another method for enabling Internet users to request television content includes displaying on a web page, over the Internet, a user interface element associated with an advertisement for television content; wherein a user's selection of the user interface element initiates a request for the advertised television content from a carrier that provides television service to the user.

Abstract: The social networking system monitors implicit interactions between a user and objects of the social networking system with which the user has not established a connection. Based on the implicit interactions between the user and an object, the social networking system identifies a soft connection between the user and the object. The social networking system may then identify soft connections to include in a candidate list of soft connections to recommend to the user. The social networking system may also extract signals from the set of candidate list of soft connections, and may use the extracted signals to rank the soft connections in the list of candidate soft connections. The social networking system may then recommend soft connections to the user based on the rank associated with the soft connections in the candidate list of soft connections.

Abstract: Techniques are described for classifying seasonal patterns in a time series. In an embodiment, a set of time series data is decomposed to generate a noise signal and a dense signal, where the noise signal includes a plurality of sparse features from the set of time series data and the dense signal includes a plurality of dense features from the set of time series data. A set of one or more sparse features from the noise signal is selected for retention. After selecting the sparse features, a modified set of time series data is generated by combining the set of one or more sparse features with a set of one or more dense features from the plurality of dense features. At least one seasonal pattern is identified from the modified set of time series data. A summary for the seasonal pattern may then be generated and stored.

Abstract: A hardware database privacy device is communicatively coupled to a private database system. The hardware database privacy device receives a request from a client device to perform a query of the private database system and identifies a level of differential privacy corresponding to the request. The identified level of differential privacy includes privacy parameters (?,?) indicating the degree of information released about the private database system. The hardware database privacy device identifies a set of operations to be performed on the set of data that corresponds to the requested query. After the set of data is accessed, the set of operations is modified based on the identified level of differential privacy such that a performance of the modified set of operations produces a result set that is (?,?)-differentially private.

Abstract: Systems and methods are disclosed for structuring unstructured machine-generated content. In one implementation, unstructured content is received and processed to identify a first content segment. Parameter(s) within the first content segment are identified and classified. A content segment skeleton that reflects an arrangement of the first content segment is generated. Based on the classifying of the parameter(s), the parameter(s) are extracted s from the first content segment into a structured content element in a structured content format, with the structured content element including a representation of the content segment skeleton. Based on the structured format, a query adapter is generated. Queries are executed via the query adapter and the structured format.

Abstract: Quantum computing is a computational paradigm for solving (exactly or approximately) difficult combinatorial optimization problems. One degree of freedom that is available is the so-called annealing schedule, which defines how the quantum computation evolves from the start of the computation to the end of the computation. This schedule is defined by anneal offsets, which can be different for each quantum bit (qubit) in the quantum computer. The choice of annealing schedule can have a dramatic impact on the performance of the computer. In this disclosure we provide a method for selecting and/or modifying the annealing schedule based on the problem to be solved.

Abstract: A request from a client is received to generate a differentially private random forest classifier trained using a set of restricted data. The differentially private random forest classifier is generated in response to the request. Generating the differentially private random forest classifier includes determining a number of decision trees and generating the determined number of decision trees. Generating a decision tree includes generating a set of splits based on the restricted data, determining an information gain for each split, selecting a split from the set using an exponential mechanism, and adding the split to the decision tree. The differentially private random forest classifier is provided to the client.

Abstract: A system and method for identifying botnets. The method includes determining a network event proximity based on collected network data, where the network data relates to at least one network device; determining time density of the network data; determining trend patterns of the network data; and determining, based on the network event proximity, time density, and trend patterns, when a botnet activity is present within the network data.

Abstract: Systems and methods are described for selecting content item identifiers for display. The system may identify a set of content items that are likely to be requested in the future based on a history of content item requests. The system then selects a first plurality of content categories using a category selection neural net and selects a first set of recommended content items for the first plurality of content categories. The system increases a reward score for the first plurality of content categories based on receiving a request for a content item that is included in the first set of recommended content items. The system also decreases the reward score for the first plurality of content categories based on determining that the requested content item is included in the set of content items that are likely to be requested in the future. The neural net is trained based on the reward score of the first plurality of content categories to reinforce reward score maximization.

Abstract: According to an aspect of some embodiments of the present invention there is provided a computer implemented method for detecting at least one anomaly in a dataset, comprising: managing a dataset including a plurality of data entities each including at least one value; receiving a semantic model that defines associations between two or more data entities; forming a plurality of multi dimensional data instances, each multi dimensional data instance formed from at least one of a permutation and a combination of a set of data entities from the plurality of data entities according to the semantic model; analyzing the multi dimensional data instances to detect at least one anomalous value, the anomalous value representing a statistically significant deviation according to a deviation requirement, of one or more values from a set of values of the multi dimensional data instances; and providing the detected at least one anomalous value.

Abstract: Example implementations may relate to an occupancy sensing system. For example, the occupancy sensing system may collect connection data and traffic data related to electronic devices that connect to the networking device. The occupancy sensing system may determine a number of resident devices and a number of high-traffic devices, based on the connection data or the traffic data. The occupancy sensing system may determine a number of the electronic devices that are coactive within an analysis time window, and may constrain the number of coactive electronic devices to a range from the number of high-traffic devices to the number of resident devices to generate an occupancy value.

Abstract: The objective of the invention is the computer-assisted selection of the optimal machine component for a use. In the selection, empirical values are collected to create a continuously improving system. To achieve this, the inventive method includes determining properties of the machine component and their corresponding influence quantities, possible uses for the machine component, and the influence quantities to be considered in the use-specific selection and design of the machine component. The method also includes receiving statements relating to the influence quantities and determining, influence quantity interactions. The method further includes formulating the influence quantities, feeding the use and associated influence quantities as inputs into a selection algorithm to select the machine component that is optimally suitable for the use, and supplying the selected machine component.

Abstract: A method and system for identifying users for advertising. Users and attributes are identified. First web sites provided by ISPs accessed by the users are identified. First data received from the ISPs include content of the first web sites and user time spent thereon. The first data is analyzed to determine first attribute values indicative of interest in each attribute by each user. Second data received from ISPs include content of second web sites and user time spent thereon. Second attribute values are derived from questionnaires completed by the users, which indicate interest in each attribute by each user. Third attribute values are determined by combining the first attribute values with the second attribute values for each user. The third attribute values are processed to identify users to which a product or service may be advertised. The identified users are communicated to a provider of the product or service.

Abstract: Mechanisms are provided to implement a self-training engine of a question and answer system. The self-training engine pairs an unanswered natural language question with portions of an electronic document to generate an unlabeled data set. The self-training engine trains a model based on a labeled data set comprising a finite number of question and answer pair data structures and applies the model to the unlabeled data set to identify an answer from the portions of the electronic document to the unanswered natural language question. The self-training engine modifies the labeled data set to include the identified answer and corresponding unanswered natural language question as an additional question and answer pair data structure. The self-training engine then trains the model based on the modified labeled data set.

Abstract: Methods and apparatus to calculate granular data of a region based on another region for media audience measurement are disclosed. An example method for calculating, via a processor, granular data of a region includes determining aggregate behavioral data associated with a media audience measurement of a target region. The example method includes determining, via the processor, aggregate demographics data of the target region. The example method includes determining, via the processor, granular data of a source region. The example method includes calculating, via the processor, granular data of the target region to measure a media audience of the target region by apportioning the aggregate demographics data and the aggregate behavioral data of the target region based on the granular data of the source region.

Abstract: Systems and methods are provided for managing information networks. A delta causality matrix is generated based on newly discovered topology changes in an information network. The delta causality matrix specifies changes in problem-symptom relationships of a causality matrix associated with constituent objects in a previous topology of the information network. The delta causality matrix is utilized to modify at least one context which comprises a first set of related symptoms and problems associated with the constituent objects in the previous topology of the information network. The modified context includes a second set of related symptoms and problems associated with constituent objects of the modified topology of the information network. An event correlation operation is performed utilizing the modified context and active symptoms detected in the information network, to determine at least one problem which has a symptom signature that corresponds to the set of current symptoms.

Abstract: The present disclosure provides a semantic understanding based emoji input method and device, and relates to the input method technology field. The method includes: obtaining a text content according to an input sequence; performing word segmentation on the text content, and extracting text features based on the word segmentation result; constructing an input vector using the text features, performing classification using an emotion classification model to determine an emotion label of the text content; based on a correspondence relationship between the emotion label and emojis of various themes, respectively obtaining an emoji corresponding to the emotion label from each of the various themes; sorting the obtained emojis of the various themes, and displaying the sorted emojis as candidate options in a client. The disclosed invention facilitates users to input an emoji, enhances emoji input efficiency, and provides users with rich and wide scope of emoji resources.