Abstract: A method for rendering context based information on a user interface includes receiving a user request to extract the context based information from a database. The database includes a plurality of documents and the request includes at least one search criteria required to determine a context of the user request. The method includes generating a list of documents corresponding to the context of the user request and rendering on a viewing portion of the user interface the list of documents corresponding to the context of the user request.

Abstract: Security Information and Event Management tools, log management tools, log analysis tools, and other event data management tools are enhanced. Enhancements harvest entity extraction rules from queries, query results, and other examples involving the extraction of field values from large amounts of data, and help perform entity extraction efficiently. Entity extraction operations locate IP addresses, usernames, and other field values that are embedded in logs or data streams, for example, and populate object properties with extracted values. Previously used extraction rules are applied in new contexts with different users, different data sources, or both. An entity extraction rules database serves as a model that contains rules specifying parsing mechanisms. Parsing mechanisms may include regular expressions, separation character definitions, and may process particular file formats or object notation formats or markup language formats.

Abstract: Methods and systems for enriching an information system containing information about companies with additional competitor information. The information system, which could be a database, a knowledge base, or a knowledge graph, is assumed to contain information about a plurality of single companies, the information comprising data such as industry codes, competitors, and possibly also keywords for each company. The disclosed methods determine new competitor pairs by combining (i) the generation of new competitor candidate pairs by inference from existing competitors and other company-specific knowledge with (ii) the validation of such competitor candidates pairs by checking for joint occurrence in documents of a document repository.

Abstract: A failure prediction system is provided. The system includes a model-based signature generator generating feature vectors from individual attributes of multi-variate time series data based on sequence importance and attribute importance. The system further includes a knowledge database storing feature vectors corresponding to a set of different failure types. The system also includes a set of similarity detectors. Each detect any of the feature vectors generated by the model-based signature generator that are similar to any of the feature vectors corresponding to a respective one of the different failure types stored in the knowledge database based on a similarity threshold and output the respective one of the different failure types and a likely time period when the respective one of the different failure types will occur.

Abstract: A system, method, and/or device may receive a plurality of terms in a natural language of a user. The plurality of terms may relate to at least one domain of an enterprise of domains. The plurality of terms may be stored as text. For a (e.g., each) term of the plurality of terms, one or more domain levels may be determined in which the term is associated. The domain levels (e.g., each of the domain levels) may be associated with a specificity. From the domain levels, a most specific domain level having a highest degree of specificity may be identified. The term may be associated with a domain-specific term associated with the term at the most specific domain level. The domain-specific term associated with the term may be stored.

Abstract: The present disclosure relates to different techniques of controlling an agricultural system, as for example a controlled agricultural system, an agricultural light fixture and a method for agricultural management. Furthermore, the disclosure relates to an agricultural system, which comprises a plurality of processing lines for growing plants of a given plant type, wherein a first processing line in the plurality of processing lines is configured to move a first plurality of plants through the agricultural system along a route; and apply a first growth condition to the first plurality of plants to satisfy a first active agent parameter for the first plurality of plants.

Abstract: At least some aspects of the present disclosure are directed to systems and methods of an agronomic condition prediction and alerts engine. In some cases, the engine receives a set of field data and the set of field data includes one or more of geospatial data, crop data, user data, agronomic data, and weather data. In some cases, the engine retrieves a set of agronomic profile data from an agronomic data repository, where each of the set of agronomic profile data representing an agronomic condition and comprising one or more of geospatial profile, crop profile, pest profile, agronomic profile, user data profile, and weather profile corresponding to the agronomic condition. In some embodiments, the engine applies a multivariable processing to the set of field data using the set of agronomic profile data and generates an agronomic condition indicator indicative of one or more agronomic conditions.

Abstract: Embodiments for graph computing are provided. A graph including a plurality explicit nodes and at least one implicit node is generated. A first of the plurality of explicit nodes and a second of the plurality of explicit nodes are traversed between utilizing deductive reasoning. A third of the plurality of explicit nodes and a fourth of the plurality of explicit nodes are traversed between through the at least one implicit node utilizing inductive reasoning.

Abstract: Automatically generating a rule set implementation is disclosed. A set of rules is accessed. For each non-const rule in the set of rules, one or more implication directed acyclic graphs (DAGs) are constructed. The non-const rule directly causes at least one external output or at least one external action. The one or more implication DAGs specify rule conditions, including one or more observable rule conditions. Implication DAGs that are constructed for the set of rules are compiled to obtain a compiled result that is configured to evaluate rule conditions associated with the set of rules and determine one or more actions when at least one of the rule conditions evaluates to true. The compiled result is output.

Abstract: Disclosed herein are system, method, and computer program product embodiments for extracting customer relationship management (CRM) data from an on-premises database for testing with a cloud-based CRM. The extraction approach simplifies, through the use of a wizard, the selection of relevant customer records and their extraction, along with any dependencies on other records. The extracted records can then be uploaded to the cloud-based CRM for evaluation.

Abstract: A system to manage power consumption from a grid includes a building switchgear; an energy storage system (ESS) coupled to the building switchgear to selectively provide power in response to a customer power demand to prevent a customer grid power consumption from spiking and peaking at grid imbalance highest cost on peak times; an energy management system (EMS) to operate the ESS from behind-the-meter; and a data distribution service (DDS) coupled to the EMS forming a DDS-EMS network to provide a global data space servicing EMS edge publishers and subscribers.

Abstract: Embodiments herein provide an on-device method for enhancing user experience in an electronic device. The method includes monitoring a plurality of parameters associated with an operation of the electronic device. The method includes identifying an anomaly associated with the electronic device based on the plurality of parameters associated with the operation of the electronic device and identifying a class of anomaly to which the anomaly associated with the electronic device belongs using a first on-device model. Further, the method includes presenting at least one question associated with the identified class of anomaly to user of the electronic device using on a second on-device model and receiving at least one user input for the at least one question. Furthermore, the method includes performing at least one action for enhancing the user experience based on the at least one user input for the at least one question.

Abstract: A control method of a server is provided. The method includes acquiring code information about a program, identifying at least one error with respect to a code style included in the code information based on a predetermined code style rule, acquiring at least one error information with respect to the identified code style, and modifying the code style by inputting the code information and the error information to an artificial intelligence model in which the code style rule is trained.

Abstract: A computer-implemented method of managing questions and answers on a computer-hosted service. The method includes a computing device receiving text based tax question and answer pairings and inputting the tax question and answer pairings into a content model executed by the device and outputting a content score for each tax question and answer pairing based on the model. The content score comprises a number within a range. One end of the range corresponds to product content and another end of the range corresponds to general tax content. The device outputs an answer quality score for the tax question and answer pairings based at least in part on the content score and votes assigned to each respective question and answer pair, wherein votes comprises up votes and down votes. The device may generate a FAQ list stored in a database based at least in part on the answer quality score.

Abstract: Systems, apparatuses, and methods for more effectively preparing for and responding to cybersecurity threats directed at people or at groups of people. A segmentation process is described that evaluates multiple characteristics of a person that may make them a potential target or that may make a cybersecurity attack on that person more likely to be successful. Based on the segmentation, a security analyst can apply an appropriate risk reduction or security protocol to each person or group of similarly situated people to reduce the likelihood of an attack and/or the likelihood of a successful attack.

Abstract: A human-powered vehicle component includes an input device, to which first information related to at least one of a human-powered vehicle, a rider of the human-powered vehicle, and environment of the human-powered vehicle is input. The human-powered vehicle component further comprises an electric actuator and an artificial intelligence processor configured to generate second information for controlling the electric actuator in accordance with the first information input to the input device.

Abstract: A method for rendering context based information on a user interface includes receiving a user request to extract the context based information from a database. The database includes a plurality of documents and the request includes at least one search criteria required to determine a context of the user request. The method includes generating a list of documents corresponding to the context of the user request and rendering on a viewing portion of the user interface the list of documents corresponding to the context of the user request.

Abstract: A method for rendering context based information on a user interface includes receiving a user request to extract the context based information from a database. The database includes a 5 plurality of documents and the request includes at least one search criteria required to determine a context of the user request. The method includes generating a list of documents corresponding to the context of the user request and rendering on a viewing portion of the user interface the list of documents corresponding to the context of the user request.

Abstract: The disclosure provides a natural language processing (NLP) model arranged to operate on two lexicons, where one lexicon is a sub-set of the other lexicon. The NLP model can be arranged to generate output based on the sub-set lexicon and exit processing of the NLP model, to potentially save computation cycles.

Abstract: Disclosed is a method, a device and equipment for fusing different instances describing the same entity. The method includes: acquiring a connection diagram comprising a plurality of instances, where different nodes in the connection diagram represent different instances, and connection lines between the nodes represent instance relations between the instances corresponding to the nodes; based on the instance relations, identifying different instances describing the same entity in the connection diagram, fusing the nodes corresponding to the identified instances, and updating the connection diagram.

Abstract: Embodiments disclosed herein relate to methods, systems, and computer programs for automatically determining an outcome associated with a reasoning graph, based on one or more data sets. The methods, systems, and computer programs compare hash values associated with different data sets to determine if they match to assign the outcome associated with a pre-existing hash to the later provided hash and data set associated therewith.

Abstract: A model maintenance device according to an embodiment performs maintenance of a model for pattern recognition used in label estimation of target data for recognition. The model maintenance device includes a generating unit, an evaluating unit, and an updating determining unit. The generating unit generates a new model using learning data. The evaluating unit evaluates the performance of the new model using evaluation data classified into a first group, from among evaluation data classified into a plurality of groups, and calculates a first performance evaluation value; and evaluates performance of the new model using evaluation data classified into a second group, from among the evaluation data classified into a plurality of groups, and calculates a second performance evaluation value. Based on the first performance evaluation value and the second performance evaluation value, the updating determining unit determines whether or not the existing model should be updated with the new model.

Abstract: A human-powered vehicle control device includes an artificial intelligence processor, an operation device, and a communication device. The artificial intelligence processor is configured to generate second information for controlling an electric component of a human-powered vehicle in accordance with first information related to at least one of the human-powered vehicle, a rider of the human-powered vehicle, and an environment of the human-powered vehicle. The operation device operates the electric component. The communication device is configured to communicate with an external device. The artificial intelligence processor is configured to change a process for generating the second information in accordance with the first information and an operation of the operation device. The communication device is configured to transmit third information related to a process for generating the second information to the external device.

Abstract: An electronic device includes an artificial intelligence processor that is configured to generate second information for controlling an electric component including at least one of a drive unit that applies propulsion force to a human-powered vehicle, an electric adjustable seatpost, and an electric suspension in accordance with first information related to at least one of the human-powered vehicle, a rider of the human-powered vehicle, and an environment of the human-powered vehicle. The artificial intelligence processor changes a process for generating the second information in accordance with the first information and in accordance with an operation of a first operation unit for operating the at least one of the drive unit, the electric adjustable seatpost, and the electric suspension.

Abstract: A system, program product, and method for use with an artificial intelligence (AI) platform to dynamically amend a knowledge base responsive to query evaluating and processing. A received or detected query is subject to natural language processing to identify, annotate, and map one or more query tokens against a knowledge base. The query tokens are evaluated against the knowledge base to identify one or more query tokens absent from the knowledge base and leverage a neural network to predict a probability relationship between the query tokens absent from the knowledge base and one or more tokens populated in the knowledge base. The natural language (NL) query is translated to a structured query language (SQL) and the SQL query is executed and evaluated, and the knowledge base is selectively and dynamically amended subject to the SQL evaluation.

Abstract: A method of indicating to an operator of a work vehicle a relative location of an object, an object indication system, and a work vehicle are provided. The method includes sensing the object with one or more sensors positioned at one or more sensor positions on the work vehicle and activating one or more indicators positioned at one or more indicator positions relative to the operator based on the sensing of the object with the one or more sensors. Each sensor position directionally corresponds to one or more of the indicator positions.

Abstract: An apparatus in one embodiment comprises at least one processing platform including a plurality of processing devices. The processing platform is configured to receive a request to execute one or more predictive models for generating a delivery date, to initiate execution of the one or more predictive models responsive to the request, and to invoke a plurality of machine learning algorithms using data from a plurality of data sources when executing the one or more predictive models. The processing platform is further configured to capture the data from the plurality of data sources and organize the data into a sparse matrix, to automatically generate the delivery date, and to automatically transmit the delivery date to one or more user devices.

Abstract: A knowledge driven architecture for information system lifecycle development is disclosed. The architecture includes a knowledgebase repository including a knowledge engine to store a first set of knowledge models associated with an information system development; an upstream subsystem to feed a second set of knowledge models to the knowledge engine and update the knowledge engine with a final set of knowledge models; a downstream subsystem to provide one or more features corresponding to the information system development to a user.

Abstract: The present disclosure describes methods, devices, and non-transitory computer readable storage medium for managing lifecycle of a knowledge base (KB) in chatbot systems. The method includes receiving an update request and updating a current-version KB as a new current-version KB. The method also includes receiving a first test request from a knowledge point (KP) operator and determining whether the new current-version KB passes a first test; and in response to the determination that the new current-version KB passes the first test, submitting the new current-version KB as a new submit-version KB. The method further includes receiving a second test request from a KP manager and determining whether the new submit-version KB passes a second test; and in response to the determination that the new submit-version KB passes the second test, storing an original production-version KB as a pervious-version KB and submitting the new submit-version KB as a new production-version KB.

Abstract: A POI recommendation method based on the graph database includes: acquiring an ID and positioning information of a target user; according to the ID and the positioning information of the target user, acquiring a feature vector of the target user, a friend intimacy coefficient of the target user and a target POI set from a target graph database, wherein the target POI set is a set composed of POIs within a preset distance range queried according to the positioning information; according to the target POI set, acquiring a feature matrix of a user set with related POI consumption records from the target graph database, wherein the related POI consumption records are consumption records associated with any POI in the target POI set; and according to the friend intimacy coefficient, the feature vector of the target user and the feature matrix, determining a target POI from the target POI set.

Abstract: Provided is a robot that includes: a first sensor having a first output and configured to sense state of a robot or an environment of the robot; a first hardware machine-learning accelerator coupled to the first output of the first sensor and configured to transform information sensed by the first sensor into a first latent-space representation; a second sensor having a second output and configured to sense state of the robot or the environment of the robot; a second hardware machine-learning accelerator configured to transform information sensed by the second sensor into a second latent-space representation; and a processor configured to control the robot based on both the first latent-space representation and the second latent-space representation.

Abstract: Systems and methods for controlling and implementing a concurrent multi-agent BDI architecture to control complex systems in real time and exhibiting high parallelism. The system comprises BDI agent modules storing a BDI state of the whole system, an emotional and an internal the BDI agent modules and a world model. Each BDI agent module concurrently evaluates the activation of its potential goals and prioritizes its intentions. Each BDI agent module may be hardware-implemented, software-implemented or hybrid-domain-implemented, depending on whether they are executed on application-specific hardware, general purpose hardware or a combination thereof. The domain of each BDI agent might be migrated in real time during operation, optimizing resources and improving performance.

Abstract: Aspects of the invention include generating a vector representation of a root node of the error based on a hierarchical topology of a computing system; generating a respective vector representations of each subject matter expert of a plurality of subject matter experts based at least in part on the hierarchical topology; selecting a subject matter expert based at least in part on the vector representation of root cause of the error; and uploading a diagnostic software to the computing system.

Abstract: A method for predicting an unfavorable outcome for a patient admitted to a hospital, e.g., with a COVID-19 infection is described. Attributes from an electronic health record for the patient are obtained including at least findings obtained at admission, basic patient characteristics, and laboratory data. The attributes are supplied to a classifier implemented in a programmed computer which is trained to predict a risk of the unfavorable outcome. The classifier is arranged as a hierarchical combination of (a) an initial binary classifier stratifying the patient into either a high risk group or a low risk group, and (b) child classifiers further classifying the patient in a lowest risk group or a highest risk group depending how the initial binary classifier stratified the patient as either a member of the high risk or low risk group.

Abstract: A work machine receives a thematic map that maps values of a variable to different geographic locations at a worksite. Control zones are dynamically identified on the thematic map and actuator settings are dynamically identified for each control zone. A position of the work machine is sensed, and actuators on the work machine are controlled based upon the control zones that the work machine is in, or is entering, and based upon the settings corresponding to the control zone. These control zones and settings are dynamically adjusted based on in situ (field) data collected by sensors on the work machine.

Abstract: This disclosure provides a knowledge base system and method for curating both factual and logical knowledge while using a common data storage repository. According to an exemplary embodiment, a knowledge base stores complied Boolean information which represents factual knowledge and logic for interpreting the factual knowledge. Combining the knowledge base, i.e., functional logic knowledge (FLK) repository, with a logic evaluator creates a knowledge abstraction layer.

Abstract: A machine-learning method for training a decision-making model includes: obtaining a rationale vector group for a rationale included in a labeled natural language text file; assembling an effective vector group for the labeled natural language text file by connecting the rationale vector groups for the rationales using a specific order; and executing a supervised classification algorithm to train the decision-making model using the effective vector group and a target decision for the natural language text file. The decision-making model is trained to be configured to label an unlabeled natural language text file using one of a plurality of potential decisions that serves as a target decision.

Abstract: Methods, apparatus, and system determine if a data class in a plurality of data classes is separable, such as by determining an average intra-class similarity within each data class, inter-class similarity across all data classes in the plurality of data classes, and determining separability based on the average intra-class similarity relative to the inter-class similarity. Data classes determined to be highly variable may be removed. Pair(s) of data classes not separable from one another may be combined into one class or one of the data classes may be dropped. A hardware accelerator, which may comprise artificial neurons, accelerate performance of the data analysis.

Abstract: An accelerator includes: a memory configured to store input data; a plurality of shift buffers each configured to shift input data received sequentially from the memory in each cycle, and in response to input data being stored in each of internal elements of the shift buffer, output the stored input data to a processing element (PE) array; a plurality of backup buffers each configured to store input data received sequentially from the memory and transfer the stored input data to one of the shift buffers; and the PE array configured to perform an operation on input data received from one or more of the shift buffers and on a corresponding kernel.

Abstract: A system is disclosed for generating a graphical user interface (GUI) for network management automation. The GUI is a data view that provides functionality for monitoring and controlling devices in a network using a dynamic golden baseline.

Abstract: Neural stimulation is provided according to a closed loop algorithm to treat sleep disordered breathing (SDB), including obstructive sleep apnea (OSA). The closed loop algorithm is executed by a system comprising a processor (which can be within the neural stimulator). The closed loop algorithm includes monitoring physiological data (e.g., EMG data) recorded by a sensor implanted adjacent to an anterior lingual muscle; identifying a trigger within the physiological data, wherein the trigger is identified as a biomarker for a condition related to sleep (e.g., inspiration); and applying a rule-based classification (which can learn) to the trigger to determine whether one or more parameters of a stimulation should be altered based on the biomarker.

Abstract: Concepts may be associated with each other based on information provided by data sources. Entities may be associated based on the information provided by the data sources and characteristics of the entities. A concept graph may be generated based on the concepts such that each edge in the concept graph corresponds to a relationship between two or more associated concepts. A data graph may be generated based on the concept graph and the entities such that each node in the data graph corresponds to a concept or an entity and the edges in the data graph correspond to relationships between two or more concepts and such that other relationships between two or more associated concepts are absent from the concept graph. In response to a query, traversing the data graph to determine entities that are related to the query and providing a report that includes those entities.

Abstract: The system, method, and computer readable medium described herein provide improvements in the ways that user interfaces present multi-dimensional relationships between data samples to a user. The disclosed user interface framework provides users with a visualization of the complex relationships between data samples having multi-dimensional attributes which allows the users to quickly and intuitively grasp the relationships between data samples for a large number of attributes at a glance and in a single data map visualization.

Abstract: A computing device receives user selection of a data source and a natural language command directed to the data source. The device identifies a first keyword and a second keyword in the natural language command. The first keyword corresponds to a first data field from the data source and the second keyword expresses a limit on a range of data values for the first data field. The device generates a visual specification that specifies the data source, a plurality of visual variables, and a plurality of data fields from the data source, including the first data field. The visual variables determine characteristics of visual marks in a data visualization according to the second keyword, and each of the visual variables is associated with a respective data field of the plurality of data fields. The device generates and displays the data visualization based on the visual specification.

Abstract: A computer-implemented method and system for determining a localization of a digitally-modeled object with respect to a digitally-modeled space and performing volumetric queries. The method including retrieving or creating voxel representations of the object (OV) and of the space, partitioning these representations of the digitally-modeled object into sets of heart (OH) and border (OB) voxels, determining intersections between sets of voxels of the object and of the space, and based on said intersections, determining the localization of the digitally-modeled object with respect to the digitally-modeled space.

Abstract: In some embodiments, a computer system selects a first subset of candidate content items based on their filter scores that are generated based on a partial generalized linear mixed model comprising a baseline model and a user-based model, with the baseline model being a generalized linear model, and the user-based model being a random effects model based on user actions by the target user directed towards reference content items related to the candidate content items. In some embodiments, the computer system then selects a second subset from the first subset based on recommendation scores that are generated based on a full generalized linear mixed model comprising the baseline model, the user-based model, and an item-based model, with the item-based model being a random effects model based on user actions directed towards the candidate online content item by reference users related to the target user.

Abstract: A genomic data decoder may jointly compress and encrypt genomic data alignment information while preserving the privacy of sensitive genomic data elements at retrieval stage. Genomic data alignment information organized as a read-based alignment data stream may be transposed into a position-based alignment data stream. The position-based alignment information may been coded into a reference-based alignment data stream. The reference-based alignment data stream may be encrypted with a combination of order-preserving encryption of the genomic position information and symmetric encryption of the reference-based alignment differential data. Differential encoding and entropy coding schemes may further compress the reference-based alignment data stream. The resulting compressed and encrypted stream may be indexed and stored in a biobank storage unit.

Abstract: Techniques, systems, architectures, and methods for efficient and accurate intelligence gathering comprising the combination of Knowledge Modeling (KM) and Object Based Production (OBP) techniques, in embodiments, leveraging a context data layer within Knowledge Models (KMs) to store connections between models and OBP objects that are representative of any entities, organizations, resources, locations, etc. described within a model.

Abstract: Techniques for generating rules from documentation are described. For example, a method for generating rules may include generating one or more rules from documentation by: extracting a plurality of chunks from the documentation, inferring one or more candidate rules from the extracted chunks, mining the inferred one or more candidate rules to determine at least one of the one or more candidate rules is to be included in rule generation, classifying the at least one mined one or more candidate rules as one or more rules, and extracting information to generate the one or more rules.

Abstract: Online tutorials for websites or software platforms can become out of date quickly once a website or platform has a minor update. Embodiments of the present invention fix this problem by automatically mapping website elements from the original tutorial to elements of the updated website by calculating and determining similar non-exact matches to those elements as the website changes. This gives designers of websites flexibility to perform maintenance and updates to their websites without regularly reprogramming their tutorials ensuring a higher accuracy of educational material for the end-user.