Abstract: Disclosed in the present invention is a differentiable method for mining constant rules. On the basis of defining constant operators and path operators according to a knowledge graph, a fusion attention mechanism is used to evaluate relations passed by rules by using attention values. Meanwhile, attentions are calculated by aggregating surrounding attributes and the corresponding attribute values for tail node of each hop respectively. Attentions of the attributes are used to enhance selection of relations in the rules to achieve link prediction. According to generated model parameters, high quality symbolic rules are output by parameter analysis and statistics. This method is particularly suitable for application scenarios with complex reasoning requirements that require high prediction accuracy, provide interpretations for predictions, and need to precipitate reasoning rules.

Abstract: The present disclosure relates to a junction box facilitating wiring. The junction box facilitating wiring comprises a box body, a first upper cover and a second upper cover, wherein the first upper cover and the second upper cover are both covered and connected to a top of the box body, and the second upper cover is rotatably connected to the first upper cover; a damping structure is provided at a rotatable joint between the first upper cover and the second upper cover, and the damping structure is configured to keep the second upper cover at a current position when no external force is applied. When wiring is needed, the user can flip open the second upper cover. After stopping the opening action, the damping structure enables the second upper cover to remain in its current position, allowing the user to perform the wiring operation.

Abstract: Described herein are an integrated circuit (IC) device mounting board, and an IC device, both of which having one or more multi-conductor vias. Also described herein are methods for fabricating an IC device mounting board having multi-conductor vias, and methods for operating IC devices having multi-conductor vias. The multi-conductor vias include separate conductive segments formed within a single via that allow any one of data signal, power and ground to be conducted on any one of the segments. Additionally, any one or more or even all of the conductive segments may be floating. The multi-conductor vias enables fewer vias to be utilized for a given number of contact pads, allowing for increased interconnect density.

Abstract: Disclosed in the present invention is a knowledge graph pre-training method based on structural context information, the method comprising: for a target triple, constructing an instance comprising context triples, and adopting a triple integration module to encode each of the context triples in the instance to obtain an integration vector; combining the integration vectors for all context triples in the instance into a context vector sequence, and adopting a structural information module to encode the context vector sequence to obtain a structural representation vector for the triple; adopting a general task module to calculate the structural representation vector for the triple, and obtaining a label prediction value for the triples, updating the structural representation vector for the triple based on cross-entropy loss of the label prediction value for the triple and a label truth value for the triple until the completion of the training, so as to obtain an optimized structural representation vector for th

Abstract: A method for treating polluted acidic wastewater from smelting with an activated pyrite concentrate includes: drying and grinding a pyrite concentrate, and washing twice to produce a washed pyrite concentrate powder; mixing the washed pyrite concentrate powder with a Na2S powder to produce a mixed powder, and adding purified water; allowing a reaction for 3.5 h to 4.5 h; filtering to produce an activated pyrite concentrate; subjecting the activated pyrite concentrate to aeration and standing, drying, and grinding to produce an activated pyrite concentrate powder; adding a lime slurry to the wastewater to adjust a pH; adding the activated pyrite concentrate powder, and allowing an ultrasonic treatment, continuous stirring is conducted; allowing a settlement to produce a first supernatant; adding a lime slurry to the first supernatant to adjust a pH; further allowing a settlement to produce a second supernatant; and separating the second supernatant.

Abstract: A method for treating polluted acidic wastewater from smelting with an activated pyrite concentrate includes: drying and grinding a pyrite concentrate, and washing twice to produce a washed pyrite concentrate powder; mixing the washed pyrite concentrate powder with a Na2S powder to produce a mixed powder, and adding purified water; allowing a reaction for 3.5 h to 4.5 h; filtering to produce an activated pyrite concentrate; subjecting the activated pyrite concentrate to aeration and standing, drying, and grinding to produce an activated pyrite concentrate powder; adding a lime slurry to the wastewater to adjust a pH; adding the activated pyrite concentrate powder, and allowing an ultrasonic treatment, continuous stirring is conducted; allowing a settlement to produce a first supernatant; adding a lime slurry to the first supernatant to adjust a pH; further allowing a settlement to produce a second supernatant; and separating the second supernatant.

Abstract: A zinc aluminium silicate nanoparticles/granular red mud (ZAS/GRM) composite material of Zn2+-modified industrial waste red mud and a preparation method and application thereof are disclosed, belonging to the technical field of adsorbent preparation. The industrial waste red mud is used as a raw material to prepare Zn2+-modified red mud for ZAS/GRM adsorbent.

Abstract: The present invention discloses fine-tuning method, device, and application classification model of knowledge representation decoupling, decoupling knowledge representation and classification model, storing them in the knowledge base, and performing matching aggregation based on retrieval during application, this limits the rote memorization of the learning model and improves its generalization ability. At the same time, KNN is used to retrieve adjacent instance phrases from the knowledge base as continuous neural examples, and neural examples are used to guide classification model training and correct classification model predictions, improving the ability of the classification model in small and zero sample scenarios, when the amount of data is sufficient, the knowledge base also has better and richer information, and the classification model performs very well in fully supervised scenarios.

Abstract: The present invention discloses an adaptive knowledge graph representation learning method for integrating a graph structure with text information, including: (1) sampling a neighbor triple of each of a head entity and a tail entity in a target triple; (2) calculating semantic representations of the target triple, and neighbor triples of its head and tail entities; (3) calculating structure representations of the head and tail entities of the target triple; (4) splicing the semantic representation of the target triple with the structure representations of its head and tail entities, inputting a spliced result into an adaptive classification layer, and calculating a classification result and a classification loss; and (5) optimizing the foregoing module based on an optimization algorithm of gradient descent, until a loss value converges, to obtain a final spliced result between the semantic representation of the target triple and the structure representations of its head and tail entities.

Abstract: The present invention is a generative event extraction method based on ontology guidance, including: (1) constructing an event ontology knowledge base; (2) designing an event trigger word extraction template and an event argument extraction template; mapping an input event text to a first input sequence, and mapping an input event text integrating an event ontology to a second input sequence; (3) designing a class label mapping function that maps multi-word labels to event types and/or role types; (4) extracting the event ontology corresponding to the input event from the event ontology knowledge base, and constructing the first input sequence and the second input sequence according to the event trigger word extraction template and the event argument extraction template; and (5) predicting, by the event extraction model, the event type and the role type according to the class label mapping function and a processing mechanism thereof, and outputting an event trigger word span and an event argument span.

Abstract: A zinc aluminium silicate nanoparticles/granular red mud (ZAS/GRM) composite material of Zn2+-modified industrial waste red mud and a preparation method and application thereof are disclosed, belonging to the technical field of adsorbent preparation. The industrial waste red mud is used as a raw material to prepare Zn2+-modified red mud for ZAS/GRM adsorbent.

Abstract: The present invention discloses a perceptual representation learning method for protein conformations based on a pre-trained language model, including: obtaining a protein made up of an amino acid sequence, building different data sets according to protein conformations, and defining a prompt for each type of protein conformation; building, based on a pre-trained language model, a representation learning module for fusing an embedding representation of each type of the prompt into an embedding representation of the protein, so as to obtain a protein embedding representation under a prompt identifier; building a task module for performing task prediction on a task corresponding to each type of protein conformation based on the protein embedding representation under the prompt identifier; building a loss function for each type of task based on a task prediction result and a tag, and updating model parameters of the representation learning module and the task module in combination with loss functions of all type

Abstract: Disclosed in the present invention is a knowledge graph pre-training method based on structural context information, the method comprising: for a target triple, constructing an instance comprising context triples, and adopting a triple integration module to encode each of the context triples in the instance to obtain an integration vector; combining the integration vectors for all context triples in the instance into a context vector sequence, and adopting a structural information module to encode the context vector sequence to obtain a structural representation vector for the triple; adopting a general task module to calculate the structural representation vector for the triple, and obtaining a label prediction value for the triples, updating the structural representation vector for the triple based on cross-entropy loss of the label prediction value for the triple and a label truth value for the triple until the completion of the training, so as to obtain an optimized structural representation vector for th

Abstract: Disclosed in the present invention is a differentiable method for mining constant rules. On the basis of defining constant operators and path operators according to a knowledge graph, a fusion attention mechanism is used to evaluate relations passed by rules by using attention values. Meanwhile, attentions are calculated by aggregating surrounding attributes and the corresponding attribute values for tail node of each hop respectively. Attentions of the attributes are used to enhance selection of relations in the rules to achieve link prediction. According to generated model parameters, high quality symbolic rules are output by parameter analysis and statistics. This method is particularly suitable for application scenarios with complex reasoning requirements that require high prediction accuracy, provide interpretations for predictions, and need to precipitate reasoning rules.

Abstract: Disclosed in the present invention is a generative event extraction method based on ontology guidance, including: (1) constructing an event ontology knowledge base; (2) designing an event trigger word extraction template and an event argument extraction template; mapping an input event text to a first input sequence, and mapping an input event text integrating an event ontology to a second input sequence; (3) designing a class label mapping function that maps multi-word labels to event types and/or role types; (4) extracting the event ontology corresponding to the input event from the event ontology knowledge base, and constructing the first input sequence and the second input sequence according to the event trigger word extraction template and the event argument extraction template; and (5) predicting, by the event extraction model, the event type and the role type according to the class label mapping function and a processing mechanism thereof, and outputting an event trigger word span and an event argument

Abstract: The present invention discloses a protein transformation method based on an amino acid knowledge graph and active learning, including: building an amino acid knowledge graph based on biochemical attributes of amino acids; enhancing protein data in combination with the amino acid knowledge graph to obtain enhanced protein data, and performing representation learning to obtain first enhanced protein representations; performing representation learning on the protein data or the protein data and the amino acid knowledge graph by using a pre-trained protein model to obtain second enhanced protein representations; synthesizing the first enhanced protein representations and the second enhanced protein representations to obtain enhanced protein representations; taking the enhanced protein representations as samples, and through active learning, screening out representative samples from the samples, manually annotating protein properties, and training a protein property prediction model by using the manually annotated

Abstract: The present invention discloses a perceptual representation learning method for protein conformations based on a pre-trained language model, including: obtaining a protein made up of an amino acid sequence, building different data sets according to protein conformations, and defining a prompt for each type of protein conformation; building, based on a pre-trained language model, a representation learning module for fusing an embedding representation of each type of the prompt into an embedding representation of the protein, so as to obtain a protein embedding representation under a prompt identifier; building a task module for performing task prediction on a task corresponding to each type of protein conformation based on the protein embedding representation under the prompt identifier; building a loss function for each type of task based on a task prediction result and a tag, and updating model parameters of the representation learning module and the task module in combination with loss functions of all type

Abstract: The present invention discloses an adaptive knowledge graph representation learning method for integrating a graph structure with text information, including: (1) sampling a neighbor triple of each of a head entity and a tail entity in a target triple; (2) calculating semantic representations of the target triple, and neighbor triples of its head and tail entities; (3) calculating structure representations of the head and tail entities of the target triple; (4) splicing the semantic representation of the target triple with the structure representations of its head and tail entities, inputting a spliced result into an adaptive classification layer, and calculating a classification result and a classification loss; and (5) optimizing the foregoing module based on an optimization algorithm of gradient descent, until a loss value converges, to obtain a final spliced result between the semantic representation of the target triple and the structure representations of its head and tail entities.

Abstract: The present invention is a molecular graph representation learning method based on contrastive learning, the method comprising: obtaining a molecular fingerprint representation of each molecule, and calculating a similarity between each two molecular fingerprints; collecting a full amount of chemical functional group information, and matching a corresponding functional group for each atom in the molecule; using a heterogeneous graph to model a molecular graph; using a RGCN in the structure-aware molecular encoder to encode the representation of each atom in the molecule and the representation of the functional group to which the atom belongs, and mapping the molecule to a feature space through an aggregation function to obtain a structure-aware feature representation; according to the fingerprint similarity between molecules, selecting positive and negative samples, and carrying out a comparative learning in the feature space; obtaining the structure-aware molecular encoder by using the contrastive learning m

Abstract: The present invention is a combined commodity mining method based on knowledge graph rule embedding, comprising: expressing rules, commodities, attributes, and attribute values as embeddings; splicing and inputting the embeddings of the rules and the embeddings of the attributes into a first neural network to obtain a importance scores of the attributes; splicing and inputting the rules and attributes into a second neural network to obtain the embeddings of the attribute values that the rules should take under the attributes; calculating a similarity between the value of two inputted commodities under the attribute and the embedding of the attribute value calculated by a model; after calculating scores of all attribute-attribute value pairs, summing up to obtain scores of these two commodities under this rule; then making the cross entropy loss with the real scores of these two commodities, and iteratively training based on an optimization algorithm having gradient descent; after the model is trained, parsing