Abstract: A multi-dimensional data prediction method and system for a discrete manufacturing workshop. The method comprises the following steps: obtaining a raw data set; using a DBSCAN algorithm to perform clustering on the raw data set, so as to obtain a plurality of data clusters, and establishing corresponding labels for the data clusters; searching for association relationships between the labels, so as to constitute data knowledge; deleting redundant data from all the data knowledge, so as to form a knowledge network; obtaining raw data which is cleaned in step S1 and corresponds to labels included in the data knowledge; initializing the weight of a BP network structure, so as to obtain an initial model; obtaining a final prediction model; and acquiring raw data of discrete manufacturing to be processed, and inputting same into the prediction model, and the prediction model outputting a prediction result.

Abstract: Disclosed in the present invention are a multimodal industrial data fusion method and system for discrete manufacturing. The method comprises: collecting discrete manufacturing industrial multimodal data in real time, performing feature extraction to obtain feature data, and inputting the feature data into a differentiable computer network to obtain a data fusion result, wherein a differentiable computer is further used for accomplishing a prediction objective on the basis of the data fusion result, and the differentiable computer network comprises a data fusion module and a memory system, the data fusion module fusing the feature data in an agent, and the memory system being used for storing and reading/writing re-fused data in the agent; and inputting the data in the memory system into an evaluation system to calculate a reward value, guiding the agent in data fusion on the basis of the reward value, and updating the memory system.

Abstract: An industrial data hybrid model construction method and system for discrete manufacturing. The method comprises: firstly, collecting discrete manufacturing industrial data in real time, and performing feature extraction to obtain a feature vector; then, separately inputting feature data into a first model and a second model to obtain a first output and a second output; and performing weighted summation on the first output and the second output to obtain an industrial data hybrid model. The first model is used for obtaining a fitting curve of the feature data in a discrete space, and the second model is used for using a decision tree as a weak learner to perform ensemble learning on the feature data. Regarding the characteristic of service scenarios in the discrete manufacturing industry being complex and variable, the flexibility of intelligent data inference is improved.

Abstract: Disclosed is an intelligent interactive decision-making method for a discrete manufacturing system. The method includes the following steps: step 1, establishing a production scheduling optimization model and strategy for discrete manufacturing for an actual application scene; step 2, training the scheduling strategy with existing production data on the basis of a deep reinforcement learning algorithm, and storing a state having a high reward in a training process in a memory; step 3, updating the state according to prior knowledge in the memory; step 4, inputting the updated state into a deep reinforcement learning network, obtaining a corresponding reward, and updating the memory according to the reward; and step 5, repeating step 4 until model parameters converge, and saving and putting the model into an actual production scene.

Abstract: This application relates to the field of image processing technologies and image scaling techniques. An image scaling method includes obtaining scaling coefficients through a fixed-point operation based on sizes of a source image and a destination image and a displacement value. Then, for each to-be-processed pixel point in the destination image, determining coordinates of a source pixel point in the source image corresponding to the to-be-processed pixel point. A pixel value of the to-be-processed pixel point is obtained through a fixed-point operation based on a pixel value of the source pixel point, a fixed-point interpolation coefficient, and a displacement value. Then the destination image is generated. The fixed-point operation is used in the whole process of image scaling, thereby avoiding a floating-point operation, reducing an operation amount, and improving operation efficiency.

Abstract: The present invention discloses a method for constructing an intelligent computation engine of an artificial intelligence cross-platform model based on knowledge self-evolution. The method comprises: determining source and target moments; dividing a discrete manufacturing system data set; initializing a dynamic discrete manufacturing system model; preprocessing data and constructing a task pool; constructing a meta learning framework; migrating a trained neural network to new tasks; iterating until convergence and storing model parameters; and testing in a new environment. This invention shortens the convergence time of model parameters, significantly benefiting the training of dynamic discrete manufacturing models subject to temporal disturbances in actual production.

Abstract: Disclosed is an intelligent interactive decision-making method for a discrete manufacturing system. The method includes the following steps: step 1, establishing a production scheduling optimization model and strategy for discrete manufacturing for an actual application scene; step 2, training the scheduling strategy with existing production data on the basis of a deep reinforcement learning algorithm, and storing a state having a high reward in a training process in a memory; step 3, updating the state according to prior knowledge in the memory; step 4, inputting the updated state into a deep reinforcement learning network, obtaining a corresponding reward, and updating the memory according to the reward; and step 5, repeating step 4 until model parameters converge, and saving and putting the model into an actual production scene.

Abstract: Disclosed are an emotional evolution method and terminal for a virtual avatar in educational metaverse.

Abstract: Disclosed are an emotional evolution method and terminal for a virtual avatar in educational metaverse.

Abstract: Disclosed is a characterization method based on deep reinforcement learning for discrete manufacturing industry data. The method includes: collecting discrete manufacturing industry data, and creating a spatio-temporal database; dividing the discrete manufacturing industry data into a discrete feature and a continuous feature, creating a data coupling coding network, converting a coding vector in the coding network into a characterization vector, and creating a data characterization model; quantitatively characterizing discrimination of a data category by means of cluster evaluation indexes; and using weights of cluster evaluation indexes of different dimensions as dynamic rewards, creating a deep reinforcement learning model, and updating a neural network parameter of deep reinforcement learning through characterization of an interactive relation between a model and a discrete manufacturing decision-making analysis system.

Abstract: The present invention discloses a kind of xylanase mutant and its preparation method and application, which relates to the technical field of genomic engineering and genetic engineering. Such mutant includes one or more mutants obtained by taking xylanase HwXy110A as female parent to conduct saturation mutagenesis to the site of Gly363. Specifically, relates to obtaining 19 mutants through site-directed mutagenesis, and then conducting yeast expression to them, after that, obtaining two mutants with significantly improved specific activity and thermal stability through screening of thermal stability and catalytic activity; the present invention can significantly improve the thermal stability and catalytic efficiency of xylanase through modifying the site of Gly363, and is of important guiding significance for improving the thermal stability and the catalytic efficiency of the 10th family of xylanases and other glycoside hydrolases as well as lays the foundation for its application in industrial production.

Abstract: The present invention discloses a kind of xylanase mutant and its preparation method and application, which relates to the technical field of genomic engineering and genetic engineering. Such mutant includes one or more mutants obtained by taking xylanase HwXyl10A as female parent to conduct saturation mutagenesis to the site of Gly363. Specifically, relates to obtaining 19 mutants through site-directed mutagenesis, and then conducting yeast expression to them, after that, obtaining two mutants with significantly improved specific activity and thermal stability through screening of thermal stability and catalytic activity; the present invention can significantly improve the thermal stability and catalytic efficiency of xylanase through modifying the site of Gly363, and is of important guiding significance for improving the thermal stability and the catalytic efficiency of the 10th family of xylanases and other glycoside hydrolases as well as lays the foundation for its application in industrial production.

Abstract: Code and data versioning allow developers to work on code and data without affecting production code and data and without affecting the development activities of other developers. Code and data being worked on by a developer are associated with a task. The system automatically determines the dataset to use for a given development task from among a production dataset, a latest dataset, or a temporary dataset associated with the development task so that development code does not have to be modified to read from a specific dataset.

Abstract: Code and data versioning allows developers to work on code and data without affecting production code and data and without affecting the development activities of other developers. Code and data being worked on by a developer are associated with a task. The system automatically determines the dataset to use for a given development task from among a production dataset, a latest dataset, or a temporary dataset associated with the development task so that development code does not have to be modified to read from a specific dataset.

Abstract: A semipermeable element for the penetration of 3D printing curing inhibitors. The semipermeable element has a pore density of 107-1011/cm2, and/or the pore diameter of 0.01 ?m-5 ?m. A usage of a semipermeable element, and manufacturing method thereof as well as a 3D printing apparatus. The semipermeable element has good permeability to the curing inhibitor, and simply introducing air can achieve the thickness of inhibited curing layer as required by the continuous manufacturing of the three-dimensional objects.

Abstract: A 3D printing apparatus with a radiation source, a workbench, and a liquid tank, wherein a workbench for supporting a three-dimensional object being constructed, and a liquid tank for containing a polymerizable liquid for constructing a three-dimensional object. The apparatus also includes a cover plate which is located in the liquid tank or on the top of the liquid tank; the radiation source irradiates from above the cover plate. The cover plate is an element transparent to the radiation source; and the lower surface of the cover plate is a covering surface which remains in contact with the polymerizable liquid during the printing process.

Abstract: A semipermeable element for the penetration of 3D printing curing inhibitors. The semipermeable element has a pore density of 107-1011/cm2, and/or the pore diameter of 0.01 ?m-5 ?m. A usage of a semipermeable element, and manufacturing method thereof as well as a 3D printing apparatus. The semipermeable element has good permeability to the curing inhibitor, and simply introducing air can achieve the thickness of inhibited curing layer as required by the continuous manufacturing of the three-dimensional objects.

Abstract: A 3D printing apparatus with a radiation source, a workbench, and a liquid tank, wherein a workbench for supporting a three-dimensional object being constructed, and a liquid tank for containing a polymerizable liquid for constructing a three-dimensional object. The apparatus also includes a cover plate which is located in the liquid tank or on the top of the liquid tank; the radiation source irradiates from above the cover plate. The cover plate is an element transparent to the radiation source; and the lower surface of the cover plate is a covering surface which remains in contact with the polymerizable liquid during the printing process.

Abstract: The invention discloses an artificial pairing and breeding method of Platysternon megacephalum. The method comprises the selection of species sources, domestication before pairing, setting of a breeding pond, artificial pairing, collection and hatching of turtle eggs. The method fully considers the ecological and biological characteristics of the Platysternon megacephalum, including the behavior, feeding habit, habitat, and breeding ecology. The main problems in artificial pairing and captive breeding of the Platysternon megacephalum can be effectively solved, including the breeding turtle selection, pairing, pairing stage selection, sex ratio, density, artificial food, setting of the reproduction and hatching environments, the occurrence of disabilities and fatal events during the pairing and mating process is significantly reduced; the egg laying rate of female turtles and the hatching rate of turtle eggs are both significantly improved.