Abstract: Described herein is a system that transmits and combines local models, that individually comprise a set of local parameters computed via stochastic gradient descent (SGD), into a global model that comprises a set of global model parameters. The local models are computed in parallel at different geographic locations along with symbolic representations. Network transmission of the local models and the symbolic representations, rather than transmission of the large training data subsets processed to compute the local models and symbolic representations, conserves resources and decreases latency. The global model can then be used as a model to determine a likelihood of a course of action being successful for an organization. For example, the course of action can be a purchase of a security or a business operation strategy. In another example, the course of action can be a type of medical treatment for a patient.

Abstract: The present application provides a method for simultaneously translating the language of a smart in-vehicle system and the related product, wherein the method comprises the steps of: a smart in-vehicle device receiving the first language to be played; the smart in-vehicle device acquiring the first voice of a navigation software, wherein the first voice is the second language, and constructing the input data at the current time t of a cyclic neural network according to the first voice; and inputting the input data to the preset the cyclic neural network for calculation to obtain output result, the second voice corresponding to the first language is obtained according to the output result, and the second voice is played.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of recurrent neural networks to generate media consumption predictions and providing media content to a target audience. For example, the disclosed system can train a plurality of long short-term memory neural networks for a plurality of users based on historical media consumption data over a plurality of time periods. In one or more embodiments, the disclosed system identifies a target audience including a subset of users and the corresponding neural networks. The disclosed system can then utilize the neural networks of the subset of users to generate a plurality of predictions for a future time period for the users. In some embodiments, the disclosed system then combines the predictions for the users to generate a media consumption prediction for the target audience for the future time period.

Abstract: A computer-implemented real-time visualization method, system, and computer program product including determining a current sentiment and a current state of a user from user data, creating at least one layer including at least one of an image and an animation based on at least one of an aggregation and a combination of the current sentiment and the current state of the user, and compiling the at least one layer into a single image or a single animation for display on an image display medium.

Abstract: Data sources containing a plurality of health information is combined throughout a plurality of travelers. Profile vectors are created from each individual member of the traveling party and a group profile vector is built as a representative whole of the traveling parties interests. Potential travel destinations vectors are clustered and mapped with dimensions comprised in the group profile vector. A recommended vacation or travel destination itinerary is proposed based on the highest overlaying dimensional score between the group profile vector and potential travel destinations.

Abstract: A system predicts user intent to take an action and delivers content items to the user that match that intent. A plurality of features or attributes for each tracking pixel in a set of tracking pixels can be acquired based on content items and landing pages associated with each tracking pixel. For example, features for a tracking pixel can be determined based on information associated with a content item that enabled a user to access a landing page from which the tracking pixel was fired or triggered. In this example, features for the tracking pixel can also be determined based on information associated with the landing page. The features for the tracking pixels can be utilized to train a machine learning model. The machine learning model can be trained to predict whether or not a particular user intends to produce a conversion (e.g., make a purchase).

Abstract: A computerized system and method to detect ransomware cyber-attacks is described. The approach entails analyzing the features associated with a file access event by a process operating on a computing device, to ascertain whether the process is associated with a ransomware cyber-attack.

Abstract: Aggregate vectors corresponding to non-textual information/data are provided in a multi-dimensional space. A computing entity access a plurality of instances of medical information comprising medical codes. The computing entity generates one or more medical sentences from the plurality of instances of medical information. Each medical sentence comprises one or more medical codes. The computing entity generates an embedding vector dictionary comprising a plurality of multi-dimensional vectors based on a medical embedding model trained using machine learning and the one or more medical sentences. Each multi-dimensional vector corresponds to a medical code. The computing entity generates a plurality of aggregate vectors based on the embedding vector dictionary and analyzes at least a portion of the plurality of aggregate vectors to identify two or more aggregate vectors that are similar or different based on a distance between the two or more aggregate vectors in the multi-dimensional space.

Abstract: A system to reduce the number of factors that need to be considered in generating a prediction function includes an access module and a function generator module. The access module accesses a reduced set of factors derived from an original set of factors based at least in part on correlations between the factors of the original set. The function generator module generates, based on the reduced set of factors and a data set associated therewith, a plurality of potential prediction functions that operate on the data set to predict a result, evaluates performance of each one from the plurality of potential prediction functions, and selects a solution prediction function based on the evaluated.

Abstract: A monitoring system for a heating, ventilation, and air conditioning (HVAC) system of a building receives, from a monitoring device located at the building, a frequency domain representation and a time domain current value that are based on an aggregate current supplied to a plurality of components of an indoor air handler of the HVAC system. The monitoring system assesses, based on the received frequency domain representation and time domain current value, whether a first fault has occurred in a first component of the plurality of components of the indoor air handler and whether a second fault has occurred in a second component of the plurality of components of the indoor air handler. The monitoring system generates and transmits an alert in response to assessing occurrence of at least one of the first fault and the second fault. The monitoring system is located remotely from the building.

Abstract: A first graph is generated from a text data set, with graph nodes representing named entities in the data set and edges representing relationships between the named entities, and with edge weights indicating confidence levels. At least one cycle of the graph may be designated as inconsistent using a rule set. An edge may be selected for deletion from the first graph based on its presence in an inconsistent cycle, the cycle's weight, and/or on the edge weight. A representation of relationships indicated in the modified graph is provided programmatically.

Abstract: An electronic apparatus and a control method thereof are provided. The control method includes: receiving video data; acquiring a plurality of feature information representing an object from the received video data using a plurality of filters; detecting the object included in the video data using feature information, among the plurality of feature information, acquired by at least two of the plurality of filters; and providing information on the detected object. As a result, the electronic apparatus can accurately detect surrounding vehicles and pedestrians even under a general road condition, dark road conditions (such as at night time and bad weather), or the like.

Abstract: A reinforcement learning processor specifically configured to train reinforcement learning agents in the AI systems by the way of implementing an application-specific instruction set is disclosed. The application-specific instruction set incorporates ‘Single Instruction Multiple Agents (SIMA)’ instructions. SIMA type instructions are specifically designed to be implemented simultaneously on a plurality of reinforcement learning agents which interact with corresponding reinforcement learning environments. The SIMA type instructions are specifically configured to receive either a reinforcement learning agent ID or a reinforcement learning environment ID as the operand. The reinforcement learning processor is designed for parallelism in reinforcement learning operations. The reinforcement learning processor executing of a plurality of threads associated with an operation or task in parallel.

Abstract: Systems and methods for automated sequencing database generation are disclosed herein. The system can include memory that can include a content library database; a graph database; and a model database. The system can include a user device and at least one server. The at least one server can: receive a content aggregation from the content library database; identify content components of the content aggregation based on a natural language processing analysis of at least a portion of the content aggregation; identify explicit sequencing of the content components; generate an intermediate content graph based on the explicit sequencing of the content components; generate a final content graph from the intermediate content graph based on implicit sequencing of the content components; and store the final content graph within the graph database.

Abstract: A method of producing dynamic controllable data composites from two or more data segments includes: building or training one or more function mappers to map between one or more extracted feature envelopes sets from the original data and one or more general parametric representations of the data; combining the extracted feature envelopes or the function mappers using two or more audio segments; and feeding the extracted feature envelopes or combined feature envelopes to the function mappers to obtain synthesis parameters to drive a synthesis process.

Abstract: A neural network training method based on training data, includes receiving training data including sequential data, and selecting a reference hidden node from hidden nodes in a neural network. The method further includes training the neural network based on remaining hidden nodes obtained by excluding the reference hidden node from the hidden nodes, and based on the training data, the remaining hidden nodes being connected with hidden nodes in a different time interval, and a connection between the reference hidden node and the hidden nodes in the different time interval being ignored.

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods of determining quantitative values representative of user action automaticity. Example methods may include determining a first request for a first user interface from a user device, determining a user identifier associated with the first request, and determining user interaction history data using the user identifier. Example methods may include determining a first selectable option for presentation in a first position at the first user interface using the user interaction history, determining a second selectable option for presentation in a second position at the first user interface, generating the first user interface, and sending the first user interface to the user device.

Abstract: Various systems and methods for implementing unsupervised or reinforcement learning operations for a neuron weight used in a neural network are described. In an example, the learning operations include processing a spike train input at a neuron of a spiking neural network, applying a synaptic weight, and observing spike events occurring before and after the neuron processing based on respective spike traces. A synaptic weight update process operates to generate a new value of the synaptic weight based upon the spike traces, configuration values, and a reference weight value. A reference weight update process also operates to generate a new value of the reference value for significant changes to the synaptic weight. Reinforcement may be provided in some examples to implement changes to the reference weight in reduced time. In some examples, the techniques may be implemented in a neuromorphic hardware implementation of the spiking neural network.

Abstract: An electronic communications method includes receiving, by a device, an electronic communication. The electronic communications method further includes analyzing, by the device, the electronic communications. The electronic communications method further includes generating, by the device, an electronic authentication certificate. The electronic communications method further includes sending a second electronic communication to another device that indicates that an electronic authentication certificate is generated for a particular electronic entity.

Abstract: Computer vision systems and methods for optimized computer vision using deep neural networks and Lipschitz analysis are provided. The system receives signals or data related to visual imagery, such as data from a camera, and feed-forwards the signals/data through the multiple layers of a convolutional neural network (CNN). At one or more layers of the CNN, the system determines at least one Bessel bound of that layer. The system then determines a Lipschitz bound based on the one or more Bessel bounds. The system then applies the Lipschitz bound to the signals. Once the Lipschitz bound is applied, the system can feed-forward the signals to other processes of the layer or to a further layer.

Abstract: An apparatus includes an optical transmitter and/or an optical receiver configured to use one or more artificial neural networks (ANNs) for geometric constellation shaping, the determination of constellation symbols to be transmitted, and/or the determination of the transmitted bit-word(s) or codewords. Each ANN has a plurality of bit-level processing portions connected to a symbol-level processing portion in a manner that enables bitwise processing of constellation-point labels.

Abstract: Provided are a data transmission method for a neural network, and a related product. The method includes the following steps: acquiring a weight specification of weight data stored in a memory, comparing the weight specification with a specification of a write memory in terms of size and determining a comparison result; according to the comparison result, dividing the write memory into a first-in first-out write memory and a multiplexing write memory; according to the comparison result, determining data reading policies of the first-in first-out write memory and the multiplexing write memory; and according to the data reading policies, reading weights from the first-in first-out write memory and the multiplexing write memory and loading the weights to a calculation circuit. The technical solution provided by the present application has the advantages of low power consumption and short calculation time.

Abstract: Methods and systems are disclosed for enumeration of trees in a database environment. Temporary copies of trees are stored in a database accelerator environment, for efficient access by software programs operating within the database layer. Multiple trees can be enumerated concurrently using level-by-level traversal. Nodes are assigned sortable indices through which a tree structure is maintained. Enumeration supports linking from a node of a parent tree to a child tree stored separately. Enumeration supports synthesizing child nodes in order to satisfy constraints on a parent node. Filtering and sorting are supported. The disclosed technology provides unexpectedly superior results, and can be applied in many fields. Variants are disclosed.

Abstract: Provided are operations including: receiving, with one or more processors of a robot, an image of an environment from an imaging device separate from the robot; obtaining, with the one or more processors, raw pixel intensity values of the image; extracting, with the one or more processors, objects and features in the image by grouping pixels with similar raw pixel intensity values, and by identifying areas in the image with greatest change in raw pixel intensity values; determining, with the one or more processors, an area within a map of the environment corresponding with the image by comparing the objects and features of the image with objects and features of the map; and, inferring, with the one or more processors, one or more locations captured in the image based on the location of the area of the map corresponding with the image.

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.

Abstract: A method that may include feeding an input image and downscaled versions of the input image to multiple branches of an object detector calculating, by the multiple branches, candidate bounding boxes; and selecting bounding boxes. The multiple branches comprise multiple shallow neural networks that are followed by multiple region units. Each branch includes a shallow neural network and a region unit. The multiple shallow neural networks are multiple instances of a single trained shallow neural network. The single trained shallow neural network is trained to detect objects having a size that is within a predefined size range and to ignore objects having a size that is outside the predefined size range.

Abstract: Architecture that enables the identification of entities such as people and content in live broadcasts (e.g., streaming content (e.g., video) of live events) and non-live presentations (e.g., movies), in realtime, using recognition processes. This can be accomplished by extracting live data related to a live event. With respect to people entities, filtering can be performed to identify the named (people) entities from the extracted live data, and trending topics discovered as relate to the named entities, as associated with the live event. Multiple images of the named entities that capture the named entities under different conditions are captured for the named entities. The images are then processed to extract and learn facial features (train one or more models), and facial recognition is then performed on faces in the video using the trained model(s).

Abstract: The system for automatic signal measurement includes a device under test, a control circuit, a data processing circuit, and a display device. The device under test includes a test pad area, which has multiple exposed test pads coupled to multiple circuit nodes in the device under test. The control circuit is coupled to the exposed test pads through a clamping fixture. The control circuit receives multiple test signals from the exposed test pads, stores multiple test signals in the memory, and controls a power on/off operation applied to the device under test through the exposed test pads. The data processing circuit is configured to receive the test signals stored in the memory, and determine whether the test signals meet a set of predetermined criteria to generate a verification result. The display device displays a signal waveform of the test signals and the verification result.

Abstract: The disclosure is directed to an ensemble learning prediction apparatus. The apparatus includes a loss module, a diversity module, a sample weight module, and an integrating weight module. The loss module, the diversity module and the sample weight module calculate a loss, a diversity and a sample weight, respectively. An ensemble weight is learned by an object function built by the loss, diversity and the sample weight. The integrating weight module calculates an adaptive ensemble weight by integrating the ensemble weight and previous ensemble weights at a plurality of previous time points.

Abstract: A diagnostic device and diagnostic method for monitoring operation of a technical system with an automation system, wherein values of process variables, which were previously automatically determined as relevant to a diagnosis by analyzing a program for a sequential function chart, are determined when each step of the cycle to be checked is executed and evaluated based on at least one predetermined self-organizing map acquired based on fault-free cycles during a system operation with repeatedly run step sequences such that automatic preselection of the process variables is which are relevant to the diagnosis is performed such that misdiagnoses can advantageously and largely be avoided and the reliability of the diagnostic statement can be increased.

Abstract: Various systems and methods for counting people. For example, one method involves receiving input data at an analytics system that includes a neural network. The input data includes a representation of an environment, including representations of several people. The method also includes identifying the representations of the people in the representation of the environment. The method also includes updating an output value that indicates the number of people identified as being present in the environment.

Abstract: A system facilitates the selection of a restaurant which is suitable for a group having disparate taste preferences. Individual flavor profiles contain information pertaining to flavor preferences of individuals, and a group flavor profile is created based on the flavor profiles of individuals in a particular group. The group flavor profile is matched to one or more restaurant flavor profiles. An individual flavor profile includes numerical values associated with different flavor types, such as savory, sweet, sour, bitter and salty. An individual flavor profile is created by receiving an input indicative of a flavor type (such as a dish or food image) and determining the flavor type using a deep-learning neural network. The group flavor profile is created by averaging numerical values for respective flavor types from the individual flavor profiles of the group. A flavor profile can also include non-food preferences such as cost, traffic, distance, and weather.

Abstract: A neural network device may include an input unit suitable for applying input signals to corresponding first lines, a calculating unit including memory elements cross-connected between the first lines and second lines, wherein the memory elements have respective weight values and generate product signals of input signals of corresponding first lines from among the plurality of first lines and weights to output the product signals to corresponding second lines from among the second lines, a drop-connect control unit including switches connected between the plurality of first lines and the plurality of memory elements, and suitable for randomly dropping a connection of an input signal applied to a corresponding memory element from among the plurality of memory elements, and an output unit connected to the plurality of second lines, and suitable for selectively activating signals of the plurality of second lines to apply the activated signals to the input unit and performing an output for the activated signals w

Abstract: The generation of flexible sparse metrology sample plans includes receiving a full set of metrology signals from one or more wafers from a metrology tool, determining a set of wafer properties based on the full set of metrology signals and calculating a wafer property metric associated with the set of wafer properties, calculating one or more independent characterization metrics based on the full set of metrology signals, and generating a flexible sparse sample plan based on the set of wafer properties, the wafer property metric, and the one or more independent characterization metrics. The one or more independent characterization metrics of the one or more properties calculated with metrology signals from the flexible sparse sampling plan is within a selected threshold from one or more independent characterization metrics of the one or more properties calculated with the full set of metrology signals.

Abstract: A method of controlling an electrical power network in which a sudden event which may lead to loss or excess of generation or load. The electrical power network comprises plural controllers, each controller configured to control an apparatus connected to the power network at a different respective location in the electrical power network. The method comprises determining the occurrence of the sudden and receiving synchronised quantities in each of the controllers each of the quantities corresponding to one of frequency and angle at respective different locations in the electrical power network. The method further comprises generating a control output from each controllers in dependence on the received plural quantities, each control output controlling its respective apparatus, each controller generating the control output independent of operation of any other controller and on an ongoing basis in dependence on ongoing receipt of the plural quantities.

Abstract: A processor or integrated circuit includes a memory to store weight values for a plurality neuromorphic states and a circuitry coupled to the memory. The circuitry is to detect an incoming data signal for a pre-synaptic neuromorphic state and initiate a time window for the pre-synaptic neuromorphic state in response to detecting the incoming data signal. The circuitry is further to, responsive to detecting an end of the time window: retrieve, from the memory, a weight value for a post-synaptic neuromorphic state for which an outgoing data signal is generated during the time window, the post-synaptic neuromorphic state being a fan-out connection of the pre-synaptic neuromorphic state; perform a causal update to the weight value, according to a learning function, to generate an updated weight value; and store the updated weight value back to the memory.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using multi-task neural networks. One of the methods includes receiving a first network input and data identifying a first machine learning task to be performed on the first network input; selecting a path through the plurality of layers in a super neural network that is specific to the first machine learning task, the path specifying, for each of the layers, a proper subset of the modular neural networks in the layer that are designated as active when performing the first machine learning task; and causing the super neural network to process the first network input using (i) for each layer, the modular neural networks in the layer that are designated as active by the selected path and (ii) the set of one or more output layers corresponding to the identified first machine learning task.

Abstract: An artificial neural network and methods for performing computations on an artificial neural network include multiple neurons, including a layer of input neurons, one or more layers of hidden neurons, and a layer of output neurons. Arrays of weights are configured to accept voltage pulses from a first layer of neurons and to output current to a second layer of neurons during a feed forward operation. Each array of weights includes multiple resistive processing units having respective settable resistances.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a sequence to sequence model that is recurrent in depth while employing self-attention to combine information from different parts of sequences.

Abstract: Provided herein in some embodiments is an artificial intelligence (“AI”) engine configured to operate with multiple user interfaces to accommodate different types of users solving different types of problems with AI. The AI engine can include AI-engine modules including an architect module, an instructor module, and a learner module. An assembly code can be generated from a source code written in a pedagogical programming language. The architect module can be configured to propose a neural-network layout from the assembly code; the learner module can be configured to build the AI model from the neural-network layout; and the instructor module can be configured to train the AI model built by the learner module. The multiple user interfaces can include an integrated development environment, a web-browser interface, or a command-line interface configured to enable an author to define a mental model for the AI model to learn.

Abstract: The present invention relates to a method, system, and computer program product for determining storage device weight values to use to select one of the storage devices to use as a target storage to which data from a source storage is migrated. A determination is made, for each of the storage devices, of static parameter values for static parameters comprising attributes of the storage device and dynamic parameter values for dynamic parameters providing device health information determined by accessing the storage device to determine operational conditions at the storage device. Storage device weight values are determined as a function of the static parameter values and the dynamic parameter values of the device. The determined storage device weight values are used to select one of the storage devices as the target storage to which data from the source storage is migrated.

Abstract: A unified search system is described herein. The unified search system is configured to enable, in a control device (e.g., a remote control), a user to input a search query. The unified search system includes a plurality of content providing device interfaces configured to interface the control device with a plurality of content providing devices. Each content providing device interface is configured to receive the search query from the user input interface, format the search query according to a corresponding input device type, and provide the formatted search query to one or more corresponding content providing devices. Search results received from the content providing devices are displayed at a display of the control device and/or at another display (e.g., a television).

Abstract: A method in an analysis tool for dynamically analyzing client-side performance during the rendering of web content is provided. The method comprises automatically capturing data while a client application executes executable code written in a scripting language to render a web page wherein the data identifies components that are created, the execution time for creating each component, the execution start time for each component, and the components that are initially visible when the web page is rendered by the client application. The method further comprises analyzing the captured data as the data is captured to determine a plurality of factors that include the scripting language cycle duration, the identification of redundant code executions, and the prioritization and ordering of code module execution. The method further comprises generating a metric using the factors that characterizes the performance of the client application during web page rendering and displaying the metric.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.

Abstract: Search may be provided using a database storing a plurality of documents comprising a first set of documents and a second set of documents, a set of vetting values and a computer readable medium. In such a system, for each document in the second set of documents, the first set of documents comprises a document for which that document from the second set of documents is identified as a subsequent related document. Additionally, the set of vetting values may comprise, for each document from the second set of documents, a vetting value for the document from the first set of documents for which that document from the second set of documents is identified as the subsequent related document. Additionally, the medium may store instructions to respond to a query by determining, based on the set of vetting values, a search result set comprising documents from the first set of documents.

Abstract: The present invention relates to recurrent neural network. In particular, the present invention relates to how to implement and accelerate a recurrent neural network based on an embedded FPGA. Specifically, it proposes an overall design processing method of matrix decoding, matrix-vector multiplication, vector accumulation and activation function. In another aspect, the present invention proposes an overall hardware design to implement and accelerate the above process.

Abstract: Described is an object recognition system. Using an integral channel features (ICF) detector, the system extracts a candidate target region (having an associated original confidence score representing a candidate object) from an input image of a scene surrounding a platform. A modified confidence score is generated based on a location and height of detection of the candidate object. The candidate target regions are classified based on the modified confidence score using a trained convolutional neural network (CNN) classifier, resulting in classified objects. The classified objects are tracked using a multi-target tracker for final classification of each classified object as a target or non-target. If the classified object is a target, a device can be controlled based on the target.

Abstract: Systems and methods are provided for identifying pathological changes in follow up medical images. Reference image data is acquired. Follow up image data is acquired. A deformation field is generated for the reference image data and the follow up data using a machine-learned network trained to generate deformation fields describing healthy, anatomical deformation between input reference image data and input follow up image data. The reference image data and the follow up image data are aligned using the deformation field. The co-aligned reference image data and follow up image data are analyzed for changes due to pathological phenomena.

Abstract: A computer-implemented method, computer program product, and computer processing system are provided for generating inferences from a forest of predefined problem determination trees using a processor-based conversation platform. The method includes selecting a tree from among the forest of predefined problem determination trees, responsive to user utterances uttered during an inference generating session. The method further includes navigating the tree to allocate a relevant tree node to generate a problem diagnosis question or a problem resolution action by understanding the user utterances among common interaction patterns in problem diagnosis and problem resolution dialogs. The method also includes providing speech for uttering the problem diagnosis question or the problem resolution action to a user.