Abstract: A method, system and computer program product for calibrating a quantum error mitigation technique with appropriate settings. Calibrations of the quantum error mitigation technique corresponding to combinations of noise factors and extrapolation functions that when applied to quantum circuits that represent the target quantum circuit achieve an expectation value that is close to a zero-noise value within a threshold degree of accuracy are saved. A calibration (combination of noise factors and an extrapolation function) is then selected from the saved calibrations based on the depth of the target quantum circuit. The quantum error mitigation technique is then calibrated based on the selected calibration. The calibrated quantum error mitigation technique is then performed on the target quantum circuit. In this manner, a quantum error mitigation technique is automatically calibrated with the appropriate settings to achieve a zero-noise value by the target quantum circuit without requiring multiple iterations.

Abstract: The present disclosure provides a method for generating a recommendation model, a content recommendation method, and a content recommendation apparatus, and an electronic device, and relates to an artificial intelligence field and a deep learning field. The method for generating a recommendation model includes: obtaining a graph training sample set; inputting the graph training sample set into a machine learning model to train the machine learning model, in which the machine learning model includes at least one low-rank graph convolutional network, and the low-rank graph convolutional network includes a complete weight matrix composed of a first low-rank matrix and a second low-rank matrix; in which a training objective of the low-rank graph convolutional network includes a first parameter item, a second parameter item and a non-convex low-rank item; and in responding to detecting that a training end condition is met, determining the machine learning model as a recommendation model.

Abstract: In an encoder and a decoder for Region Based Intra Block Copy, the encoder may be configured for block-based encoding a picture into a data stream, and the decoder may be configured for block-based decoding a picture from a data stream. The encoder and decoder may further be configured to determine for a current block of the picture a difference between a first predetermined block and a second predetermined block inside a block search area. The encoder may encode the difference into the data stream and the decoder may derive the difference from the data stream. According to the innovative principle, the encoder and the decoder may be configured to partition the block search area into multiple block search regions.

Abstract: A pervasive user experience capable of integrating robo-advising with human advising is discussed. Conversations and other inputs may be actively captured to identify issues with which the system may be able to assist. Inputs from multiple conversations separated in time may be correlated to identify relevant needs and goals. Recommendations and strategies may be developed and presented to the customer. When it is determined that human advising is appropriate for one or more issues, the customer may be connected to an advisor for assistance with particular issues. Transitions may be facilitated to allow customers to more efficiently return to robo-advising until human advising is again deemed appropriate.

Abstract: One embodiment of a method includes predicting one or more three-dimensional (3D) mesh representations based on a plurality of digital images, wherein the one or more 3D mesh representations are refined by minimizing at least one difference between the one or more 3D mesh representations and the plurality of digital images.

Abstract: A computer-implemented method, a computer system and a computer program product generate a contextual display for a mobile computing device. The method includes identifying a task for the mobile computing device, wherein the task comprises a set of applications on the mobile computing device. The method also includes obtaining application usage data for each application in the set of applications and determining an application context for the task based on the application usage data and the set of applications, wherein the application context includes usage requirements for each application. In addition, the method includes generating a tile view for each application in the set of applications, wherein each tile view is laid out based on the usage requirements. Lastly, the method includes displaying a task view on the mobile computing device, wherein the task view is generated by laying out the tile views based on the usage requirements.

Abstract: A system and method of creating electronic characters in one or more electronic formats, selectively customizing the characters, and presenting them via electronic channels in response to satisfaction of one or more programmable conditions is disclosed. The system enables entities to competitively bid to customize the personality and/or other attribute of a character. For example, a character may be presented via an electronic channel to an audience (e.g., one or more end users who view, listen to, or otherwise experience a character through an electronic channel). An entity may bid on altering that character's personality and/or other attribute. If the entity's bid is selected by the system (e.g., over other bids that also compete to alter one or more attributes of that character), the system customizes the character's personality and/or other attribute according to the winning bid's customization, and presents the customized character via the electronic channel to the audience.

Abstract: Techniques related to object detection using an adaptive convolutional neural network (CNN) are discussed. Such techniques include applying one of multiple configurations of the CNN to input image data in response to an available computational resources for processing the input image data.

Abstract: This application provides a method, a terminal-side device, and a cloud-side device for data processing and a terminal-cloud collaboration system. The method includes: sending, by the terminal-side device, a request message to the cloud-side device; receiving, by the terminal-side device, a second neural network model that is obtained by compressing a first neural network model and that is sent by the cloud-side device, where the first neural network model is a neural network model on the cloud-side device that is used to process the cognitive computing task, and a hardware resource required when the second neural network model runs on the terminal-side device is within an available hardware resource capability range of the terminal-side device; and processing, by the terminal-side device, the cognitive computing task based on the second neural network model.

Abstract: Methods and systems for selecting a machine learning algorithm are described. In one embodiment, one or more factors to be used by a plurality of machine learning algorithms in predicting a value of a required pharmacy element of a prescription are identified, each of the plurality of machine learning algorithms are trained to predict the value of the required pharmacy element using a first subset of previously received prescriptions, respective success rates for each of the plurality of machine learning algorithms at predicting respective known values of respective known required pharmacy elements for each of a second subset of the previously received prescriptions are determined, and a first of the plurality of machine learning algorithms having a highest success rate is selected to predict the value of the required pharmacy element of the prescription for a first predetermined period.

Abstract: A system and method for automatically predicting deviation on a metric of a use-case and deriving interconnections between metrics for generating action recommendations is provided. The system includes a deviation management system 104 which captures data from a plurality of external sources and internal sources and comprises of a deviation management platform 106 and a deviation management environment 108. The system includes various computation modules which work the deviation management platform 106 to provide a deviation management service to a set of clients that are associated with that service. The service and its users are specific to use-case, wherein the use-case is specified by a client device 116 inside the system. The system comprises of external data which is horizontal across a plurality of deviation management services and internal data which is specific to every deviation management service.

Abstract: A system may receive a query for a patient evaluation. The system may then receive historical patient information or hospital data, current medical information, patient information, and testing information. The system may then use the received information to generate a set of rules using a neural network and uses the rules to process an evaluation for the patient.

Abstract: A method for generating a classification model using a training data set. An iterative procedure for training an ANN model, in which an iteration includes selecting a small sample of training data from a source of training data, training the model using the sample, using the model in inference mode over a larger sample of the training data, and reviewing the results of the inferencing. The results can be evaluated to determine whether the model is satisfactory, and if it does not meet specified criteria, then cycles of sampling, training, inferencing and reviewing results (STIR cycles) are repeated in an iterative process until the criteria are met. A classification engine trained as described herein is provided.

Abstract: A depth-based object-detection convolutional neural network is disclosed. The depth-based object-detection convolutional neural network described herein incorporates a base network and additional structure. The base network is configured to receive a depth image formatted as RGB image data as input, and compute output data indicative of at least one feature of an object in the RGB image data. The additional structure is configured to receive the output data of the base network as input, and compute predictions of the location of a region in the received depth image that includes the object and of a class of the object as output. An object detection device incorporating the depth-based object-detection convolutional neural network is operable in real time using an embedded GPU.

Abstract: A home cost analysis server is configured to train an image processing program to identify features of homes, receive user input including a prospective home, and access a first database storing metadata and images associated with homes, including the prospective home, available for purchase. The server is also configured to input images of the prospective home to the machine-learned image processing program, which outputs a feature of the prospective home, access a second database storing historical ancillary costs, and perform a lookup in the second database to retrieve comparable historical ancillary costs associated homes having a comparable feature to the outputted feature. The server is further configured to analyze the metadata associated with the prospective home, the outputted feature, and the comparable historical ancillary costs to determine ancillary home costs associated with the prospective home, and display the ancillary home costs and an overall monthly cost for the prospective home.

Abstract: A method may include obtaining interactions between users and items, and calculating, for each edge in a bipartite graph, an edge weight using an inverse of the degree of a user node connected to the edge and an inverse of the degree of an item node connected to the edge. The bipartite graph includes user nodes corresponding to the users and item nodes corresponding to the items. The method may further include identifying paths each including an edge connecting the target user node and a common item node, an edge connecting a neighboring user node and the common item node, and an edge connecting the neighboring user node and a neighboring item node. The method may further include calculating, using the edge weights calculated for the edges, scores for the paths, and recommending, to the target user and using the scores for the paths, a recommended item.

Abstract: An apparatus of operating a computational network is configured to determine a low-rank approximation for one or more layers of the computational network based at least in part on a set of residual targets. A set of candidate rank vectors corresponding to the set of residual targets may be determined. Each of the candidate rank vectors may be evaluated using an objective function. A candidate rank vector may be selected and used to determine the low rank approximation. The computational network may be compressed based on the low-rank approximation. In turn the computational network may be operated using the one or more compressed layers.

Abstract: Systems, methods, and computer-readable media for achieving privacy for both data and an algorithm that operates on the data. A system can involve receiving an algorithm from an algorithm provider and receiving data from a data provider, dividing the algorithm into a first algorithm subset and a second algorithm subset and dividing the data into a first data subset and a second data subset, sending the first algorithm subset and the first data subset to the algorithm provider and sending the second algorithm subset and the second data subset to the data provider, receiving a first partial result from the algorithm provider based on the first algorithm subset and first data subset and receiving a second partial result from the data provider based on the second algorithm subset and the second data subset, and determining a combined result based on the first partial result and the second partial result.

Abstract: Systems, devices, and methods are provided for detecting anomalous events from categorical data using autoencoders. A system may receive a data set associated with actions requested within the computing environment, wherein the data set includes first categorical data indicative of anomalous activity in the computing environment. The system may train an autoencoder to reconstruct approximations of requests associated with the computing environment based on the received data set, wherein training the autoencoder includes using a beta divergence and a maximum mean discrepancy divergence. The trained system may receive a request to invoke an action within the computing environment, may generate a reconstruction of the request to invoke the action using the trained autoencoder, may determine a normalcy score based on a probability that the reconstruction of the request exists in the training data set, and, based on the calculated normalcy score, may determine whether requests indicate anomalous data.

Abstract: Methods and systems for selecting a machine learning algorithm are described. In one embodiment, one or more factors to be used by a plurality of machine learning algorithms in predicting a value of a required pharmacy element of a prescription are identified, each of the plurality of machine learning algorithms are trained to predict the value of the required pharmacy element using a first subset of previously received prescriptions, respective success rates for each of the plurality of machine learning algorithms at predicting respective known values of respective known required pharmacy elements for each of a second subset of the previously received prescriptions are determined, and a first of the plurality of machine learning algorithms having a highest success rate is selected to predict the value of the required pharmacy element of the prescription for a first predetermined period.

Abstract: In a system for knowledge system management, the system includes: a processor; and a memory coupled to the processor, wherein the memory has stored thereon instructions that, when executed by the processor, cause the processor to: receive a question from a customer; determine whether to not the question satisfies a first criterion for obtaining an automated response to the question; in response to determining that the question satisfies the first criterion, transmit the question to a knowledge system for generating automated responses to questions; receive the automated response to the question from the knowledge system; determine whether or not the automated response satisfies a second criterion for providing the automated response to the customer; and in response to determining that the automated response satisfies the second criterion, transmit the automated response to an electronic device operated by the customer.

Abstract: Innovations in adaptive encoding and decoding for units of a video sequence can improve coding efficiency when switching between color spaces during encoding and decoding. For example, some of the innovations relate to adjustment of quantization or scaling when an encoder switches color spaces between units within a video sequence during encoding. Other innovations relate to adjustment of inverse quantization or scaling when a decoder switches color spaces between units within a video sequence during decoding.

Abstract: Methods and hardware implementations for performing a motion search based on an estimated complexity of a block. The block is obtained from a first frame. A reference window is obtained from a second frame. For each partition type of N partition types, the block is partitioned into a plurality of partitioned blocks in accordance with the partition type. For each partitioned block of the plurality of partitioned blocks, a frequency transform of the partitioned block is computed, a complexity subvalue is computed for the partitioned block based on the frequency transform, and the complexity subvalue is accumulated into a complexity value for the partition type. M partition types are selected from the N partition types based on the N complexity values. A motion vector between the block and the reference window is determined for each partition type of the M partition types.

Abstract: A system and method for representing query elements in an artificial neural network. The method includes generating a translation table based on a plurality of query elements, wherein the translation table maps a plurality of vectors to the plurality of query elements, wherein each of the plurality of vectors is mapped to at least one query element of the plurality of query elements, wherein a number of distinct query elements among the plurality of query elements is greater than a number of distinct vectors among the plurality of vectors.

Abstract: An artificial intelligence device for learning a de-identified speech signal includes a memory configured to store a speech recognition model, a microphone configured to acquire an original speech signal, and a processor configured to perform de-identification with respect to the acquired original speech signal and perform speech recognition with respect to the de-identified speech signal through the speech recognition model.

Abstract: Methods, systems, articles of manufacture and apparatus to privatize consumer data are disclosed. A disclosed example apparatus includes a consumer data acquirer to collect original data corresponding to (a) confidential information associated with consumers and (b) behavior information associated with the consumers, and a data obfuscator. The data obfuscator is to determine a degree to which the original data is to be obfuscated and a type of obfuscation to be applied to the original data based on the original data, generate obfuscation adjustments of the original data based on the degree and the type, and generate an obfuscation model based on the obfuscation adjustments.

Abstract: A method for magnetic resonance imaging reconstructs images that have reduced under-sampling artifacts from highly accelerated multi-spectral imaging acquisitions. The method includes performing by a magnetic resonance imaging (MRI) apparatus an accelerated multi-spectral imaging (MSI) acquisition within a field of view of the MRI apparatus, where the sampling trajectories of different spectral bins in the acquisition are different; and reconstructing bin images using neural network priors learned from training data as regularization to reduce under-sampling artifacts.

Abstract: A method and system of generating an adjustment parameter value for a control parameter to enhance a new image, which includes configuring a neural network, trained to restore image quality for a derivative image, to that of an earlier version of the derivative image, to generate as an output the adjustment parameter value, for the control parameter in response to input of data derived from the new image, and changing a control parameter of the new image, by generating the adjustment parameter value by calculating an inverse of the output value, and applying the adjustment parameter value to the control parameter of the new image so as to generate an enhanced image.

Abstract: Some embodiments of a virtual coaching platform can analyze user and coach characteristics to determine suggested coaching partnerships. Some virtual coaching platform embodiments can implement whole-person dimensionalities used to track progress and provide coaching resources and guidance. In some implementations, the virtual coaching platform can provide six whole-person dimensions including: centered, aware, agile, includes, elevates, and drives. Some virtual coaching platform embodiments can select a subset of the dimensionalities to update using determined associations between a user and the dimensionalities. Some virtual coaching platform embodiments can implement a motivational matrix to assess a user in a readiness versus clarity domain and provide coaching suggestions based on a corresponding type.

Abstract: A method and system is provided for identifying patters in datasets by identifying delimited regions of feature-space in which patterns occur. The delimited regions are then combined into an ensemble able to make predictions based on the identified regions of feature-space. The method may be used for classification, for regression, for auto-encoding, for simulation, and for other applications of pattern detection.

Abstract: Aspects described herein relate to various methods, systems and apparatuses that may improve the accuracy of object classifications and object boundary definitions for a semantic segmentation technique. For example, the semantic segmentation technique may be based on a hierarchy of two or more layers. The two or more layers may include neural networks that analyze image data at different resolution scales. Each layer of the hierarchy may determine object boundary features and object class features. Each layer of the hierarchy may share its object boundary features and/or its object class features with one or more other layers in the hierarchy. In turn, each of other layers of the hierarchy may determine its object boundary features and/or its object class features based on the shared features.

Abstract: Systems, methods, apparatuses, and computer program products to generate, by a computing model, a transformed dataset based on a first dataset comprising numeric values, the computing model to convert the numeric values from a first format to a second format, generate a training dataset comprising the first dataset as an input dataset and the transformed dataset as an output dataset, train an autoencoder comprising a latent vector to transform the input dataset from the first format to the second format, determine, by a statistical model based on an output of the trained autoencoder and the input dataset, an accuracy of the trained autoencoder, and determine that the accuracy of the trained autoencoder exceeds a threshold accuracy.

Abstract: The present technology relates to an arithmetic processing device and an arithmetic processing method that enable the reduction of a circuit area while lowering power consumption, in performing more reliable arithmetic operations of a neural network. In arithmetic operations of the neural network, the arithmetic processing device makes a specific part of bits of a weighting coefficient and input data used for the arithmetic operations redundant such that redundancy of the specific part of bits becomes larger than redundancy of remaining bits except the specific part of bits, thereby being able to reduce the circuit area while lowering the power consumption in performing reliable arithmetic operations of the neural network. The present technology can be applied to, for example, an arithmetic processing device configured to perform arithmetic operations of a neural network.

Abstract: The innovation disclosed and claimed herein, in one aspect thereof, comprises systems and methods of intelligent learning and management of networked architectures. The innovation maps a networked architecture. The networked architecture includes elements having software elements and hardware elements interconnected in a common environment. The innovation determines data sources associated with the set of elements using the identifiers. The innovation compiles data associated with the set of elements into a knowledgebase. The innovation utilizes machine learning to analyze information from the data sources. The innovation determines a configuration for at least one element in the environment based on the mapping. The innovation executes the configuration based on the configuration.

Abstract: An interactive system makes use of a concise user representation, for example, in the process of making predictions of a user's next action. In some examples, the concise user representation is computed from a larger amount of user data, which is processed using a transformation trained using a Generative Adversarial Network (GAN) approach.

Abstract: Methods, systems and computer program products memorize multiple inputs into an artificial neuron that includes multiple dendrites each having multiple dendrite compartments. Operations include computing coincidence detection as distal synapse activation that flows from more proximal ones of the dendrite compartments to a soma of the artificial neuron, generating a dendritic action potential responsive to the coincidence detection from a non-zero activation value input received at a corresponding one of the dendrite compartments that includes a non-zero receptivity, and responsive to generating the dendritic action potential, decrementing the activation value and the receptivity and passing the decremented activation value to a next one of the dendrite compartments.

Abstract: Embodiments disclosed herein involve techniques for automatically retouching photos. A neural network is trained to generate a skin quality map from an input photo. The input photo is separated into high and low frequency layers which are separately processed. A high frequency path automatically retouches the high frequency layer using a neural network that accepts the skin quality map as an input. A low frequency path automatically retouches the low frequency layer using a color transformation generated by a second neural network and the skin quality map. The retouched high and low frequency layers are combined to generate the final output. In some embodiments, a training set for any or all of the networks is enhanced by applying a modification to an original image from a pair of retouched photos in the training set to improve the resulting performance of trained networks over different input conditions.

Abstract: A method and system for forecasting a histogram in a database system is provided. The method includes determining that database table statistics and historical statistical histograms associated with specified subject matter have been previously retrieved. The database table statistics and historical statistical histograms are retrieved and determined to be frequency based histograms. Historical target values associated with the historical statistical histograms are identified and new target values associated with the historical target values are identified. A value identifying a number of occurrences for identified target values comprising the new target values and the historical target values is forecast and database table histograms comprising the identified target values are stored.

Abstract: Computer program products, methods, systems, apparatus, and computing entities for extracting lab result data from lab reports are provided. In one example embodiment, an example computing device receives a lab report. The computing device identifies one or more relevant portions of the lab report. The computing device then generates parsed lab report data from only the identified one or more relevant portions of the lab report. Subsequently, the computing device extracts patient information and lab results from the parsed lab report data. Using various embodiments of the present invention, patient information and lab results can be efficiently extracted for incorporation into structured data sets maintained, for example, by a healthcare company.

Abstract: Systems and methods are provided for predicting treatment-regimen-related outcomes (e.g., risks of regimen-related toxicities). A predictive model is determined for predicting treatment-regimen-related outcomes and applied to a plurality of datasets. An ensemble algorithm is applied on result data generated from the application of the predictive model. Treatment-regimen-related outcomes are predicted using the predictive model. A combination of machine learning prediction and patient preference assessment is provided for enabling informed consent and precise treatment decisions.

Abstract: A method for magnetic resonance imaging (MRI) scans a field of view and acquires sub-sampled multi-channel k-space data U. An imaging model A is estimated. Sub-sampled multi-channel k-space data U is divided into sub-sampled k-space patches, each of which is processed using a deep convolutional neural network (ConvNet) to produce corresponding fully-sampled k-space patches, which are assembled to form fully-sampled k-space data V, which is transformed to image space using the imaging model adjoint Aadj to produce an image domain MRI image. The processing of each k-space patch ui preferably includes applying the k-space patch ui as input to the ConvNet to infer an image space bandpass-filtered image yi, where the ConvNet comprises repeated de-noising blocks and data-consistency blocks; and estimating the fully-sampled k-space patch vi from the image space bandpass-filtered image yi using the imaging model A and a mask matrix.

Abstract: Examples of techniques for optimal storage of load data for lifetime prediction for a piece of equipment used in a well operation are disclosed. In one example implementation according to aspects of the present disclosure, a method may include: using a lifetime model for the piece of equipment used in the well operation; discretizing, by a processing device, a load data spectrum into one or more buckets, the one or more buckets having a bucket size, wherein the bucket size of at least one bucket is based on one of the lifetime model and a distribution of load data; collecting load data of the piece of equipment; assigning, by the processing device, the collected load data to the one or more buckets of the load data spectrum; and storing, by the processing device, the collected load data assigned to the one or more buckets to a memory.

Abstract: Systems, methods, and computer program products to perform an operation comprising receiving a request to generate a personalized emblem for a user, receiving data associated with the user from a plurality of data sources, extracting a plurality of data elements describing the user from the data associated with the user based on an extraction rule, selecting a first emblem template based on the plurality of extracted data elements and a template selection rule, modifying at least one attribute of the first emblem template based on a first extracted data element of the plurality of data elements, and generating the personalized emblem for the user by placing each of the plurality of extracted data elements in a respective location on the modified first emblem template based on a plurality of emblem layout rules.

Abstract: A motion estimator that divides an image into a plurality of blocks and estimates motion information including a motion vector of each block includes: independent processing units, a dependent processing unit, and a motion vector buffer. The independent processing units can operate in parallel, search for a motion vector of each block using a reference image and a current image without using motion information on neighboring blocks, and record the motion vector in the motion vector buffer. The dependent processing unit determines whether or not to change motion information on a processing target block by referring to motion information on neighboring blocks held in the motion vector buffer, and when it is determined that it is necessary to change the motion information, the dependent processing unit performs processing for recording the changed motion information in the motion information buffer and outputting the changed motion information to outside.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

Abstract: A method for generating a musical composition based on user input is described. A first set of musical characteristics is extracted from a first input musical piece. The first set of music characteristics is prepared as an input vector into an unsupervised neural net comprised of a plurality of computing layers by perturbing the first set of musical characteristics according to a user intent expressed in the user input to create a perturbed vector. The perturbed vector is input into the first set of nodes of the unsupervised neural net. The unsupervised neural net is operated to calculate an output vector from a highest set of nodes. The output vector is used to create an output musical piece.

Abstract: This disclosure relates to drug delivery methods and related products. In some aspects, a method includes selecting a drug vial combination by comparing a prescribed drug dosage to a dosing schedule, and delivering substantially all of the first drug from each of the selected drug vials to a patient by operating a pump of a drug delivery device to which the drug vials are connected.

Abstract: According to one aspect of the invention, target data comprising observations is received. A neural network comprising input neurons, output neurons, hidden neurons, skip-layer connections, and non-skip-layer connections is used to analyze the target data based on an overall objective function that comprises a linear regression part, the neural network's unregularized objective function, and a regularization term. An overall optimized first vector value of a first vector and an overall optimized second vector value of a second vector are determined based on the target data and the overall objective function. The first vector comprises skip-layer weights for the skip-layer connections and output neuron biases, whereas the second vector comprises non-skip-layer weights for the non-skip-layer connections.

Abstract: Techniques are described for displaying help articles, for a web page, that are related to the context of the web page. A help article provider has access to a database of help articles, each of which are associated with target-context data that may include content identifiers for the help article and/or user profile attributes for users that the help article targets. The help article provider identifies content identifiers for a viewed web page based on one or more of: metadata and a URL for the web page. The help article provider searches the help article database using the identified content identifiers. The help article provider may filter the help articles based on an authenticated user's attributes. An ordered list of the identified help articles is displayed, with the most relevant or important help articles displayed at or near the top of the list.