Abstract: New question and answer (QA) pairs can be automatically discovered from a corpus of data such as online chats and conversations. Newly discovered QA pairs can augment QA database, which can be used by a computer processor or device, e.g., by a chatbot, an automated machine, and/or another. Existing QA knowledge can be used to learn the structures of QA knowledge distribution in conversations, and new QA knowledge can be automatically learned through the structure of learned QA knowledge distribution in conversations. The structure of learned QA knowledge distribution can be refined by adding more semantics based on labeled data.

Abstract: A line double-end steady-state quantity distance measuring method and system based on an amplitude-comparison principle. According to the method and system, voltage values and current values of both sides of a line before and after a fault are collected (102), a voltage variable quantity and a current variable quantity of both sides of the line are calculated (103), and after a voltage phasor value and a current phasor value are determined according to the voltage variable quantity and the current variable quantity (104), the position of a short-circuit point is determined by performing iterative calculation on the voltage of the short-circuit point. The method is simple in principle, and can accurately recognize a fault point, achieving precise distance measurement of lines.

Abstract: A computer-implemented authentication method, the method comprising: matching a brain pattern sequence with a predetermined password to allow access to a system, wherein the brain pattern sequence is calculated by analyzing a signal slope of a slope threshold of the brain activity to determine a timing and a duration of the brain activity.

Abstract: Techniques for topology based interoperability determination for an information technology (IT) infrastructure are described herein. An aspect includes receiving a replacement notification for an element of an IT infrastructure. A topology subgraph corresponding to the element is generated based on a topology graph of the IT infrastructure. A plurality of replacement candidates for the element is determined. A respective interoperability subgraph based on the topology subgraph is generated for each replacement candidate of the plurality of replacement candidates. A recommended replacement candidate is selected from the plurality of replacement candidates based on the generated interoperability subgraphs.

Abstract: In embodiments, a reusable and adaptive multi-task orchestration dialogue system orchestrates a set of single-task dialogue systems to provide multi-scenario dialogue processing. In embodiments, for each question propounded by a user, using a deep learning predictive model, a best single-task dialogue system is chosen out of the set. In embodiments, multi-task orchestration is done without the need to change, or even understand, the inner workings or mechanisms of the individual single-task dialogue systems in the set. Moreover, the multi-task orchestration is also unconcerned with what rules are set in each individual single-task dialogue system. In embodiments, prior to selection of the best single-task dialogue system to return the best answer, new intents and entities are discovered and used to update an existing dialogue path. In embodiments, additional data is continually collected, and used to retrain model so as to further improve performance.

Abstract: A shower system includes on one or more valves and a plurality of showerheads. The plurality of showerheads are electrically coupled to one another and configured to receive electrical signals from one another. The plurality of showerheads are fluidly coupled to the one or more valves and configured to receive water therefrom. The plurality of showerheads includes a sprayer, one or more sensors, and an integrated user interface. The sprayer is configured to dispense water provided by the one or more valves. The one or more sensors are configured to register motion gestures made by a user. The integrated user interface is configured to control operation of the sprayer. The one or more sensors generates an internal signal to the plurality of showerheads corresponding to the motion gesture. One of the plurality of showerheads is a master showerhead.

Abstract: The present application provides a control method and device for an air conditioning unit, the method including: obtaining a return air temperature, a condensation temperature, an evaporation temperature, compressor parameters, and fan parameters of the air conditioning unit; determining a preset evaporation temperature according to the return air temperature, the condonation temperature, the evaporation temperature, the compressor parameters, the fan parameters, a compressor power curve, and a fan power curve, wherein the sum of a compressor power and a fan power is minimized at the preset evaporation temperature; determining a preset compressor frequency and a preset fan frequency corresponding to the preset evaporation temperature according to the compressor power curve and the fan power curve; controlling a compressor according to the preset compressor frequency; and controlling a fan according to the preset fan frequency.

Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.

Abstract: A chatbot system receives utterances of a conversation. The chatbot system constructs a conversation knowledge graph comprising one or more dialogue segments that correspond to utterances of the conversation. The chatbot system identifies a dialogue segment in the conversation knowledge graph having a contextual uncertainty that is detected based on a context model. The chatbot system generates a clarifying question for the identified dialogue segment having the contextual uncertainty. The chatbot system receives a clarifying answer from a user interface of the computing device to the clarifying question. The chatbot system updates the context model and the conversation knowledge graph based on the clarifying question and the clarifying answer to resolve the contextual uncertainty of the identified dialogue segment.

Abstract: Embodiments of the present invention relate to computer-implemented methods, systems, and computer program products for managing a conversational system. In one embodiment, a computer-implemented method comprises: obtaining, by a device operatively coupled to one or more processors, a first message sequence comprising messages involved in a conversation between a user and a conversation server; obtaining, by the device, a conversation graph indicating an association relationship between messages involved in a conversation; and in response to determining that the first message sequence is not matched in the conversation graph, updating, by the device, the conversation graph with a second message sequence, the second message sequence being generated based on a knowledge library including expert knowledge that is associated with a topic of the conversation.

Abstract: Embodiments of the invention are directed to computer-implemented methods of labeling unlabeled electronic information. In a non-limiting embodiment of the invention, the computer-implemented method includes receiving, using a processor system, an unlabeled error log (EL) having an EL format. A set of unlabeled EL keywords are extracted from the unlabeled EL. For each unlabeled EL keyword, the processor system uses the unlabeled EL keyword to extract an electronic document (ED) sentence from an ED based on a determination that the ED sentence is relevant to the unlabeled EL keyword. One or more ED keywords are extracted from the ED sentence. A deep neural network of the processor system is used to predict an ED sentence label for the ED sentence, an ED keyword label for the ED keyword, and an EL keyword label for the unlabeled EL keyword.

Abstract: Embodiments of the present disclosure relate to facilitating decision marking in a business process. In an embodiment, process execution data associated with execution of at least one instance of a business process are obtained. At least one first target attribute available at a first target point is determined based on the process execution data. The first target point is subsequent to a first decision point of a plurality of decision points in the business process, the at least one first target attribute has a contribution in deriving a first expected outcome at the first decision point, and the first target point is a first activity point or a first decision point. A suggestion is provided which suggests incorporating the at least one first target attribute in decision making at the first decision point executed in a further instance of the business process.

Abstract: Interpretation maps of convolutional neural networks having certifiable robustness using Rényi differential privacy are provided. In one aspect, a method for generating an interpretation map includes: adding generalized Gaussian noise to an image x to obtain T noisy images, wherein the generalized Gaussian noise constitutes perturbations to the image x; providing the T noisy images as input to a convolutional neural network; calculating T noisy interpretations of output from the convolutional neural network corresponding to the T noisy images; re-scaling the T noisy interpretations using a scoring vector ? to obtain T re-scaled noisy interpretations; and generating the interpretation map using the T re-scaled noisy interpretations, wherein the interpretation map is robust against the perturbations.

Abstract: Evaluation of a health condition includes obtaining a correlation between dietary habits and health issues of a plurality of reference users. The correlation is determined based on reference patterns. Each of the reference patterns indicates temporal characteristics of at least one dietary habit and at least one health issue of a reference user of the plurality of reference users. A target pattern of a target user is determined at least in part based on a profile for the target user. The target pattern at least indicates temporal characteristics of at least one dietary habit of the target user. An evaluation of a health condition of the target user is generated based on the target pattern and the correlation.

Abstract: Techniques for response generation are provided. One computer-implemented method comprises: receiving, by an electronic device operatively coupled to a processing unit, a query from a user. The computer-implemented method also comprises generating, by the electronic device, a dialog candidates set based on user context, wherein the user context comprises the query. The computer-implemented method can also comprise generating, by the electronic device, a response based on the dialog candidates set.

Abstract: Aspects of the present invention disclose a method for consolidating of a plurality of personal bills from diverse financial sources to reflect the payments, expenses, and balances without duplication. The method includes one or more processors parsing a plurality of bills of a user, the plurality of bills including bills with varying formats. The method further includes identifying a set of bills of the plurality of bills of the user, the set of bills including related bills based at least in part on a prebuilt rule. The method further includes determining a correlation of one or more items of respective bills of the set of bills of the user based at least in part on a machine learning algorithm. The method further includes generating a consolidated bill, from the set of bills of the user, based at least in part on the determined correlation of the one or more items.

Abstract: Techniques for topology based interoperability determination for an information technology (IT) infrastructure are described herein. An aspect includes receiving a replacement notification for an element of an IT infrastructure. A topology subgraph corresponding to the element is generated based on a topology graph of the IT infrastructure. A plurality of replacement candidates for the element is determined. A respective interoperability subgraph based on the topology subgraph is generated for each replacement candidate of the plurality of replacement candidates. A recommended replacement candidate is selected from the plurality of replacement candidates based on the generated interoperability subgraphs.

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 system and a method for recommending a protocol used for tissue processing are provided. The system includes: a basket, attached with an identification code, wherein the identification code is configured to identify a type of tissue contained in a cassette carried by the basket; and a tissue processor, configured to read the identification code to obtain the type of tissue, and to recommend a protocol according to the obtained type of tissue. With the system, it is possible to automatically recommend the protocol suitable for tissue processing, avoiding that a user selects a wrong protocol, and improving a quality of the tissue processing.

Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.