Abstract: An example operation may include one or more of generating a three-dimensional (3D) model of an object via execution of a machine learning model on one or more images of the object, capturing a plurality of snapshots of the 3D model of the object at different angles to generate a plurality of snapshot images of the object, fusing a feature into each of the plurality of snapshots to generate a plurality of fused snapshots of the 3D model of the object, and storing the plurality of fused snapshots of the 3D model of the object in memory.

Abstract: Systems, methods and/or computer program products for automating evaluations of code deliveries for software projects. Automated evaluations are generated by selecting software projects and dividing a project into a plurality of code blocks by analyzing the code, build file and build log. Attributes of code blocks are extracted and correlations between code blocks are calculated. Dynamic distance between code blocks is calculated by the correlation and code delivery history, to create a Dynamic General Distance Map and Dynamic User Distance Map for the code blocks. Code delivery distance indicating the code delivery behavior is generated by the Dynamic User Distance Map while the delivery assessment criteria is generated to evaluate code delivery and assess levels of risk associated with delivery of the code. High-level risk indicates that a code delivery may not follow best practices and users are alerted to pay more attention to the code delivery during review.

Abstract: Analysis of edge closures of metal surface particles based on a graph structure.

Abstract: This invention relates to the technology of sterilizing medical ultrasonic probes, and discloses a portable ultraviolet sterilization case for ultrasonic probe, which includes a sterilization container for disinfecting and storing the ultrasonic probe, and a fixing clamp set configured to the interior of the sterilization container, wherein pairs of clamps trap the ultrasonic probe stably by an elastic structure. Hence the ultrasonic probe can be placed without colliding with the inner wall of the container.

Abstract: An example operation may include one or more of executing a machine learning model on training data, where the training data comprises a plurality of word strings, identifying words within the training data that are extracted by the machine learning model during the executing, determining a color for the machine learning model based on the identified words and a predefined mapping of words to colors, and rendering, via a user interface, a label associated with the machine learning model in the determined color for the machine learning model.

Abstract: An example operation may include one or more of generating a plurality of bounding boxes at a plurality of content areas in an image corresponding to a plurality of pieces of text within the image, converting the plurality of bounding boxes into a plurality of bounding box vectors based on attributes of the plurality of bounding boxes, training a machine learning model to transform a bounding box into a location in vector space based on the plurality of bounding box vectors, and storing the trained machine learning model in memory.

Abstract: Embodiments of the present invention provide an approach for compressing data, and more particularly, to large-scale text data encoding and compression using absolute overfitting on pre-trained language models. Large-scale data is parsed into sentences. A unique token is generated for each sentence to form a token list. A generative (or compression) model is trained from the tokens in the token list to produce the corresponding sentence of each token through absolute overfitting of a pre-trained language model. The compressed text data is stored as the token list and generative model, resulting in a storage space savings.

Abstract: A method and related system detail a split of an architecture of a monolithic application into an architecture of a micro service application. The method receives source code for the monolithic application, and maps the source code into a directed graph. The graph is split into subgraphs and optimized. The method further provides the detailing of the micro service application split, based on the subgraphs.

Abstract: What is disclosed are systems and methods for compensating for display OLED degradation. Correction factors k for OLED degradation of each sub-pixel is modelled and tracked based on grey level, temperature, and time, and used to correct image data provided to an OLED display.

Abstract: An approach is provided for improving a named entity recognition. Using a multi-label classification in a neural network, a sub-entity is identified in an original sentence. First and second labels are determined indicating first and second candidate types of the sub-entity. First and second replacement sentences are generated. The first replacement sentence replaces the sub-entity in the original sentence with a first sub-entity of the first candidate type. The second replacement sentence replaces the sub-entity in the original sentence with a second sub-entity of the second candidate type. First and second confidence scores for the first and second replacement sentences are determined. Based on the first confidence score exceeding the second confidence score by more than a threshold amount, the neural network is retrained by selecting the first instead of the second candidate type as the sub-entity type.

Abstract: A method, computer system, and a computer program product for data protection is provided. The present invention may include, generating an encoder network. The present invention may also include, encoding a training data using the generated encoder network, wherein the training data includes natural language data. The present invention may further include, training a deep learning model using the encoded training data.

Abstract: The present invention discloses a simulation method for three-dimensional full-space plasma response in EAST tokamak. In numerical simulation of plasma response in an EAST tokamak device, firstly, single frequency waves with different frequencies and amplitudes are selected according to experiment needs, to design waveforms of an external perturbation current field; then selected single frequency current field waveforms are respectively used as driving terms to solve magnetohydrodynamic equations containing an external driving current field to solve the distribution of the single frequency magnetic response signals in a three-dimensional full space; and finally, multiple groups of the single frequency magnetic response signals are superimposed and converted into a time domain space to obtain the three-dimensional full-space distribution of plasma magnetic response signals at any time.

Abstract: A system and method for field extraction including determining a key position of a key in an electronic file, isolating candidate key values based on a distance from the key position, selecting a key value from the candidate key values based on an output of a trained neural network, and extracting the key and the key value from the electronic file, regardless of a key-value structure.

Abstract: A system and method for table conversion including converting a table containing text in tabular form to an image, labeling each text area of the image with a bounding box, determining for each bounding box, a position information, a semantic information, and an image information, reconstructing the image into a graph form having a plurality of nodes, wherein each node represents the bounding box of the text areas of the image, inputting at least two nodes into a trained neural network to determine a relative relationship between the at least two nodes, building a knowledge graph using the relative relationship of the at least two nodes, and translating the knowledge graph into machine readable natural language.

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: A liner structure includes a liner main body and an insert located inside an opening of the liner main body. The liner main body is made of a polybutylene material. The liner structure has relatively good heat resistance within a temperature range corresponding to conventional liquid water, and can be used for containing hot water. Moreover, a feasible manufacturing method is provided. The method can overcome defects of material characteristics through process optimization, so that can implement manufacturing the liner structure.

Abstract: A method, computer program product, and computer system for generating and using a basic state layer. N task models are provided (N ? 2). Each task model was trained on a same pre-trained backbone model. Each task model includes M feature layers and a task layer (M ? 1). Each feature layer of each task model includes a parameter matrix that is different for the different models. An encoder-decoder model is trained. The encoder-decoder model includes sequentially: an input layer, an encoder, M hidden layers, a decoder, and an output layer. The encoder is a neural network that maps and compresses the parameter matrices in the input layer into the M hidden layers, which generates a basic state model. The decoder is a neural network that receives the basic state model as input and generates the output layer to be identical to the input layer.

Abstract: A 3D measuring equipment and a 3D measuring method are provided. The 3D measuring equipment includes a base, a fixture, a measuring device, and a controller. The fixture is disposed on the base for an object to be measured to be disposed thereon. The fixture has a plurality of rods. The heights of the rods are adjustable. The measuring device is installed on the base and is movable relative to the fixture. The controller is connected to the measuring device and the fixture and configured to perform the following. The heights of the rods are adjusted according to 3D model data of the object to be measured to support the object to be measured. The measuring device is driven to move relative to the fixture to measure the object to be measured.

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.

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.