Abstract: Embodiments of the present disclosure relate to question answering. A computer-implemented method includes determining a plurality of intention candidates of a user from the user's question; determining a set of entities and attributes associated with the set of entities from the plurality of intention candidates; constructing a decision tree from the set of entities and the attributes associated with the set of entities, wherein each node of the decision tree is associated with a respective one of the attributes and represents a respective subset of the plurality of intention candidates, and wherein the respective subset of the plurality of intention candidates are split based on the entities associated with the respective one of the attributes; and generating a question corresponding to a node of the decision tree to determine the user's intention.

Abstract: The present disclosure relates to a method and apparatus for determining a status of a position on a shelf, a shelf and a non-transitory computer-readable storage medium. The method includes: acquiring current detection data of the shelf in a current detection period; determining first status information of respective positions from the current detection data, in response to determining that the current detection data satisfies a preset condition; in response to the current detection data indicating that a target position whose first status information indicates the first status exists, acquiring first status information of the target position from previous detection data in a previous detection period; and determining second status information of the target position based on the first status information of the target position in the current detection data and the previous detection data respectively, the second status information indicating a third status that an object is put back.

Abstract: A computer-implemented method for determining influence of applications on system performance includes collecting, by a processor, for several applications that are executing on a computing system, respective instrumentation data during multiple time-segments. The method further includes determining, for each of the applications, a performance value and a robustness value for each of the time-segments based on the respective instrumentation data. Further, using the performance value and robustness value for each time-segment, multiple health-waveforms are generated, where a health-waveform is generated for each respective application. The method further includes determining, by the processor, an influence-factor of a first application on a second application, the first application and the second application are executing on the computing system.

Abstract: Methods, apparatus, computer program products for two-phased medical diagnosis are provided. The computer-implemented method comprises, receiving, by one or more processors, data during a process of a medical diagnosis from a source of data information. The computer-implemented method also comprises extracting, by one or more processors, features from the received data. The computer-implemented method also comprises transferring, by one or more processors, the extracted features in form of feature vectors to a server via a network. The computer-implemented method further comprises obtaining, by one or more processors, a recommendation of medical diagnosis from the server, wherein the recommendation of medical diagnosis is based, at least in part, on labels determined for the feature vectors.

Abstract: An approach is provided for optimizing a feedback-type question answering process. A training set is constructed to detect missing information of a question. A natural language generation model is trained using the missing information. The natural language generation model is executed to generate a rhetorical question. A response to the rhetorical question is combined with the question to generate an input to a language processor. A new question is generated. The new question is applied to a document library. A final answer is generated.

Abstract: Aspects of the invention include determining an event associated with a computing system, the event occurring at a first time, obtaining system data associated with the computing system, determining a system state of the computing system at the first time based on the system data, determining, based on the system state, two or more system data clusters comprising clustered system data associated with the system state of the computing system, determining, via an interpolation algorithm, an interpolated data value for the first time based on the system data, and adjusting the interpolated data value based on a determination that the interpolate data value is outside the two or more system data clusters.

Abstract: A system, method, and computer program product for implementing cognitive natural language processing software framework optimization is provided. The method includes receiving instructions associated with an audible user input of a user. An AI input intention of the user is determined and key information is extracted from the audible user input. The key information is inputted into a generated database table and additional key information is retrieved from a dialog table. A supplementary database table comprising the additional key information is generated and the key information is spliced with the additional key information. A resulting spliced data structure is merged into a final database table and natural language is converted into a request code structure within an SQL structure and an interactive AI interface presenting results of the converting is generated. Operational functionality of an AI device is enabled for audibly presenting results of the conversion.

Abstract: A computer-implemented method, according to one embodiment, includes: receiving an image having characters that correspond to a language, and using a text recognition algorithm to determine a first language believed to correspond to the characters. A first confidence level associated with the first language is also computed, and a determination is made as to whether the first confidence level associated with the first language is outside a predetermined range. In response to determining that the first confidence level associated with the first language is not outside the predetermined range, the first language is output as the given language. The text recognition algorithm is trained using a simple shallow neural network and a generated mixed language corpus. The generated mixed language corpus is formed by: randomly sampling libraries having vocabulary and/or characters therein, and combining the randomly sampled vocabulary and/or characters to form the generated mixed language corpus.

Abstract: A method, system, and computer program product for dependency-based software upgrading. The method may include determining respective dependency degrees between a plurality of software products based on property information related to a plurality of upgraded versions of the plurality of software products, a target software product depending on the plurality of software products. The method may also include dividing the plurality of software products into a plurality of groups of software products based on the respective dependency degrees. The method may also include determining a plurality of test scores associated with the plurality of groups, each test score indicating a performance enhancement degree of the target software product achieved by installing upgraded versions of at least one software product comprised in one of the plurality of groups. The method may also include determining a target upgrade solution for the target software product based on the plurality of test scores.

Abstract: In order to perform a semantic search based on a graph database, sets of nodes are selected from a plurality of nodes in a graph database. A set of nodes semantically matches a keyword in a natural language query. At least one target node is identified in the sets of nodes. A path is selected from candidate paths based on similarities between the candidate paths and a plurality of paths in the graph database. A graph query for retrieving information from the graph database is generated based on the selected path and the query target.

Abstract: A voltage-programmed display system allows measurement of effects on pixels in a panel that includes both active pixels and reference pixels coupled to a supply line and a programming line. The reference pixels are controlled so that they are not subject to substantial changes due to aging and operating conditions over time. A readout circuit is coupled to the active pixels and the reference pixels for reading at least one of current, voltage or charge from the pixels when they are supplied with known input signals. The readout circuit is subject to changes due to aging and operating conditions over time, but the readout values from the reference pixels are used to adjust the readout values from the active pixels to compensate for the unwanted effects.

Abstract: In one embodiment, a first path computation element (PCE) receives a request from a gateway for service chain functions (SFs) to be applied to a traffic flow, wherein a first subset of the SFs is located in a first zone. The first PCE identifies a boundary node located at a border between the first zone and a second zone where a second subset of the SFs are located. The first PCE sends a response to the gateway indicating a path within the first zone between the gateway and the boundary node to apply the first subset of SFs to the flow. The first PCE provides information regarding the flow and the boundary node to a second PCE that uses the information to configure the boundary node to route the flow in the second zone to apply the second subset of SFs to the flow.

Abstract: A method and device for detecting pyrethroid pesticide residues in crops. Reaction membrane is arranged on a bottom plate and provided with a check-up line and a quality control line; a first mounting block and a second mounting block are arranged on the bottom plate; a first slide is arranged in the first mounting block, a second slide is arranged in the second mounting block; a sample pad and a bonding pad are arranged in the first slide; a water absorption pad is arranged in the second slide; a liquid inlet provided with a pipe is formed in the first mounting block, a pressing hole provided with a press block is formed in the second mounting block; protrusions are respectively formed on the pipe and the press block; sliding grooves are formed in the liquid inlet and the pressing hole; and first springs are arranged between the protrusions and the sliding grooves.

Abstract: Embodiments may relate to identifying, by a baseband processor, an amount of data in a data radio bearer (DRB) buffer of the baseband processor. Embodiments further relate to determining, by the baseband processor based on an indication from an application processor of the electronic device, an amount of data in at least one buffer of the application processor. Embodiments further relate to generating, by the baseband processor based at least in part on the amount of data in the DRB buffer and the amount of data in the at least one buffer of the application processor, a buffer status report (BSR). Other embodiments may be described or claimed.

Abstract: A method, system and computer program product for speech recognition using multiple languages includes receiving, by one or more processors, an input from a user, the input includes a sentence in a first language. The one or more processors translate the sentence to a plurality of languages different than the first language, and create vectors associated with the plurality of languages, each vector includes a representation of the sentence in each of the plurality of languages. The one or more processors calculate eigenvectors for each vector associated with a language in the plurality of languages, and based on the calculated eigenvectors, a score is assigned to each of the plurality of languages according to a relevance for determining a meaning of the sentence.

Abstract: An electrical connector includes: an insulator; a terminal secured in the insulator and having a front mating portion, a tail portion, and an intermediate portion; an outer conductor receiving the insulator; and a rear metallic plate secured to the outer conductor, wherein the terminal intermediate portion includes a vertical part having a protrusion exposing rearwardly to air and spaced a predetermined distance from the rear metallic plate.

Abstract: Control logic in a memory device executes a first operation comprising a first set of programming pulses and a first set of program verify operations on a first portion of a first subset of memory cells to be programmed to identify a first start voltage level. A second set of programming pulses including at least one programming pulse having the first start voltage level is caused to be applied to program a second portion of the first subset of memory cells. A second operation including a third set of programming pulses and a second set of program verify operations are executed on a first portion of the second subset of memory cells to identify a second start voltage level.

Abstract: The embodiments of the present disclosure disclose a computer-implemented method, computer system and a computer program product for detecting and predicting an abnormal log event. In the method, a current event cluster from a plurality of event clusters for a log line in a log file is determined. The plurality of event clusters include at least one abnormal event cluster. Then, a time of event transition from the current event cluster to at least one abnormal event cluster is predicted.

Abstract: A method, computer system, and a computer program product for optical character recognition training are provided. A text image and plain text labels for the text image may be received. The text image may include words. The plain text labels may include machine-encoded text corresponding to the words. Semantic feature vectors for the words, respectively, may be generated based on the plain text label. The text image, the plain text labels, and the semantic feature vectors may be input together into a machine learning model to train the machine learning model for optical character recognition. The plain text labels and the semantic feature vectors may be constraints for the training.

Abstract: Techniques are provided for mapping natural language to code segments. In one embodiment, the techniques involve receiving a document and software code, wherein the document comprises a natural language description of a use of the code, generating, via a vectorization process performed on the document, at least one vector or word embedding, generating, via a natural language processing technique performed on the at least one vector or word embedding, a first label set, generating, via a machine learning analysis of the software code, a second label set, determining, based on a comparison of the first label set and the second label set, a match confidence between the document and the software code, wherein the match confidence indicates a measure of similarity between the first label set and the second label set, and upon determining that the match confidence exceeds a predefined threshold, mapping the document to the software code.