Abstract: Methods and systems for automating user interactions include annotating chat logs to identify user intent in question-answer pairs. A classifier is trained, using the annotated chat log, to identify user intent in automated conversations. Chat flows are formed, using the annotated chat logs, that provide responses to user statements based on identified user intent. An automated conversation is conducted with a user, using the chat flows and the classifier, to provide automated responses to user statements.

Abstract: A vehicle occupant comfort system, comprises a processor that stores computer executable components stored in memory. A plurality of sensors sense ambient conditions associated with exterior and interior conditions of a vehicle. A context component infers or determines context of an occupant of the vehicle. A comfort model component implicitly and explicitly trained on occupant comfort related data analyzes information from the plurality of sensors and context component. A comfort controller adjusts environmental conditions of a passenger compartment of the vehicle based at least in part on output of the comfort model component.

Abstract: A vehicle occupant comfort system, comprises a processor that stores computer executable components stored in memory. A plurality of sensors sense ambient conditions associated with exterior and interior conditions of a vehicle. A context component infers or determines context of an occupant of the vehicle. A comfort model component implicitly and explicitly trained on occupant comfort related data analyzes information from the plurality of sensors and context component. A comfort controller adjusts environmental conditions of a passenger compartment of the vehicle based at least in part on output of the comfort model component.

Abstract: A computer-implemented method for health monitoring using artificial intelligence based on sensor data includes collecting sensor data from one or more wearable devices affixable to a user, each wearable device including one or more sensors, predicting a risk of premonitory symptoms based on the sensor data by using a neural network model, and transmitting an alert to one or more entities associated with the user based on the predicted risk.

Abstract: An alkali-metal vapor cell atomic clock system, including a first atomic vapor cell and a second atomic vapor cell. A digital signal processor outputs a first time sequence to control a first laser signal, and the digital signal processor outputs a second time sequence to control a second laser signal. Thereby, the first atomic vapor cell and the second atomic vapor cell can alternately lock a crystal oscillator. A Dick effect is reduced by alternately locking the crystal oscillator, which enables the alkali-metal vapor cell atomic clock system to have more stable frequency output. Because the crystal oscillator has low costs, the alkali-metal vapor cell atomic clock system has advantages of low costs and high stability.

Abstract: A system is provided for facilitating medical conversation. The system includes a user interface, having a Natural Language Processing (NLP) system and an Automatic Speech Recognition (ASR) system, for processing user utterances to extract symptoms, attribute types and attribute values from a user. The system further includes a memory for storing program code. The system also includes a processor for running the program code to transform the symptoms, the attribute types, and the attribute values into a graph and extract relative entities and relationships of the relative entities from the graph. The processor further runs the program code to calculate an Inquiry Efficiency Index (IEI) of each candidate inquiry path based on the relative entities and the relationships of the relative entities. The processor additionally runs the program code to calculate a recommended inquiry path from among the candidate inquiry paths based on the IEI of each candidate inquiry path.

Abstract: The present disclosure provides a method, computer system and computer program product facilitating generation of a conversation content. A computer-implemented method comprises: obtaining, by a device operatively coupled to one or more processors, history conversation data of an user; determining, by the device, a professional level of the user based on the history conversation data; and generating, by the device, a conversation content for the user based on the professional level of the user.

Abstract: A computer-implemented method is provided for processing a set D of conversation logs. The method includes learning, by a processor device, a set R of entity relation mining rules from a set K of known entity utterances uttered by known entities. The method further includes automatically recommending, by the processor device, extended utterances of the known entities from unrecognized ones of the known entities based on the set R.

Abstract: A cognitive conversation system that generates effective diagnostic questions is provided. The cognitive conversation system receives a set of currently known symptoms (or currently available answers to diagnostic questions) of a reported problem or fault. The system identifies (i) a set of possible root causes of the reported problem based on the currently known symptoms and (ii) probabilities for the set of possible root causes by using a bipartite graph data structure that links possible symptoms with possible root causes. Upon determining that at least one possible root cause has a probability that is higher than a threshold, the system presents an explanation or solution associated with the at least one possible root cause. Upon determining that none of the possible root causes in the set of possible root causes has a probability higher than the threshold, the system presents a question based on information entropy that is computed based on probabilities of the identified possible root causes.

Abstract: A computer-implemented method is presented for enabling hierarchical conversational policy learning for sales strategy planning. The method includes enabling a user to have a conversation with a robot via a conversation platform, employing a plan database to store general plans used in the conversation, employing an industry database to store a plurality of candidate plans pertaining to sales promotions, and employing a plan and policy optimizer to allow the robot to select and output an optimal plan from the plurality of candidate plans, the optimal plan determined by hierarchical reinforcement learning via a first learner and a second learner, the first leaner selecting the optimal plan and the second learner selecting an optimal action.

Abstract: A method of setting up a cloud cluster is disclosed as providing at least one compute node with a baseboard management controller (BMC), the BMC of the compute node receiving secured information and using the secured information to establish communication with a cloud controller. Upon establishing the communication, the compute node then receives a cloud operating system (OS) image from the cloud controller via the BMC of the compute node. Finally, the cloud OS image is written to a host system in the compute node. A compute node is also disclosed.

Abstract: A clock circuit has a clock input terminal, a first clock output terminal, and a second clock output terminal. The clock circuit includes a pulse width adjustment module, a sampling module, a comparing module, and a differential signal converting module. A differential input terminal is electrically connected to a pulse width output terminal of the pulse width adjustment module. A positive differential signal output terminal and a negative differential signal output terminal are electrically connected to the first clock output terminal of the clock circuit and the second clock output terminal to output two clock signals with a phase difference of 180 degrees, respectively. A second input terminal of the sampling module is electrically connected to the second clock output terminal.

Abstract: A computer-implemented method is provided for medical conversation generation. The method includes receiving, by a processor device, clinical findings for a patient. The method further includes calculating, by the processor device based on the clinical findings, (i) a suspected disease and (ii) symptoms for inquiry with (iii) a symptom significance for each of the symptoms. The method also includes decomposing, by the processor device, the symptoms from a multi-dimensional abstraction. The method additionally includes selecting, by the processor device, an inquiry strategy based on the symptom significance calculated for each of the symptoms. The method further includes calculating, by the processor device based on a decomposition of the symptoms and the inquiry strategy, a combination benefit/cost and evaluating the combination benefit/cost to provide an optimized combination result.

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

Abstract: A vehicle occupant comfort system, comprises a processor that stores computer executable components stored in memory. A plurality of sensors sense ambient conditions associated with exterior and interior conditions of a vehicle. A context component infers or determines context of an occupant of the vehicle. A comfort model component implicitly and explicitly trained on occupant comfort related data analyzes information from the plurality of sensors and context component. A comfort controller adjusts environmental conditions of a passenger compartment of the vehicle based at least in part on output of the comfort model component.

Abstract: A method for recovering data on a failed storage device includes detecting that a first storage device has a failure, creating a simulated management module where the simulated management module linked with a second storage device, writing a replica of at least some of the data as stored in the first storage device to a second storage device, creating a permanent management module and deleting the simulated management module.

Abstract: Methods and systems for treating a disease include navigating a symptom-centric decision tree which accounts for probabilities for symptoms and diseases and emergency values for the symptoms and diseases, based on information provided by a user, to determine a disease. A treatment is provided to the user based on the determined disease.

Abstract: A clock circuit has a clock input terminal, a first clock output terminal, and a second clock output terminal. The clock circuit includes a pulse width adjustment module, a sampling module, a comparing module, and a differential signal converting module. A differential input terminal is electrically connected to a pulse width output terminal of the pulse width adjustment module. A positive differential signal output terminal and a negative differential signal output terminal are electrically connected to the first clock output terminal of the clock circuit and the second clock output terminal to output two clock signals with a phase difference of 180 degrees, respectively. A second input terminal of the sampling module is electrically connected to the second clock output terminal.

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.