87 results about "Message aggregation" patented technology

The invention provides an RDMA (Remote Direct Memory Access) message aggregation processing method and a network card device, which belong to the technical field of data communication, and comprise the following steps: S1, an RDMA message analysis step which comprises the links of hardware-level message capture, BTH header analysis and message classification and metadata generation; s2, an RDMA (Remote Direct Memory Access) caching step, wherein the step comprises a message descriptor recording link and a caching strategy link; s3, an RDMA message aggregation step, wherein the step comprises a context table aggregation step, an aggregation process step, a new aggregation process step and an existing context aggregation process step; s4, a zero-copy aggregation step, wherein the step comprises the links of metadata transmission, DMA delay processing and host memory writing; in order to solve the problem that stateless aggregation processing is not tried to be carried out on RDMA messages when an existing network card processes the RDMA messages, a plurality of received RDMA messages are aggregated into a larger RDMA message, and the larger RDMA message is sent to a downstream module for processing, so that the number of messages processed by a rear-stage module is reduced, and the bandwidth of the network card for processing the RDMA messages is improved.

The invention provides a power load prediction method based on feature decoupling and time-space diagram modeling, and particularly relates to the technical field of power load prediction, and the method comprises the steps: preprocessing the historical data of a power load, obtaining a normalized multivariable load sequence, and decomposing the normalized multivariable load sequence into a trend term and a season term through a learnable convolution kernel decomposition algorithm; a dominant period is extracted from seasonal term spectrum analysis, and multi-scale down-sampling is carried out according to the dominant period to generate a multi-scale sequence. Based on a multi-scale sequence, an adaptive mixed hop message aggregation mechanism is adopted, cross-scale time dependence and inter-variable high-order association are dynamically fused, and aggregation features are obtained. And performing combined prediction on the trend term and the aggregation feature, and outputting a load prediction result after inverse normalization. According to the method, the technical problem that an existing graph neural network model is difficult to accurately model a time-space dependency relationship of dynamic change under multiple scales in power load prediction is solved, so that the power load prediction precision and the model generalization ability are remarkably improved.

A message processing method includes displaying a message aggregation interface corresponding to a session interface, where the message aggregation interface includes a plurality of messages classified and displayed based on a message type, and the plurality of messages are all messages in the session interface; receiving a first input of a user for at least one first message in the plurality of messages; in response to the first input, selecting the at least one first message; receiving a second input of the user; and in response to the second input, performing a target operation on the at least one first message, where the target operation corresponds to the second input.

The present invention discloses a method and related device for topology identification of an active distribution network based on multi-task graph learning, belonging to the technical field of power system monitoring, and the method comprises using a plurality of autoencoders to respectively complete the missing of different measurement features in the distribution network; representing the topology of the distribution network in the form of a graph, training the topology identifier using graph data, performing message aggregation from the target node to the source node according to the multi-head attention coefficient, and obtaining the feature matrix of the whole graph edge; inputting the feature of each line into a fully connected neural network layer, and mapping the feature into the judgment value of the state of each line, judging the disconnection state of the line, and realizing topology identification; using multi-task learning to jointly learn and optimize the missing of the complement measurement feature and the topology identification process, determining the target model, inputting the real-time measurement data into the target model, and outputting the topology identification result. The present invention can reduce the dimension, reconstruct the incomplete data, and accurately identify the topology structure of the distribution network under the condition of limited measurement data.

The invention belongs to the field of artificial intelligence, and discloses a social robot detection method and system based on multi-type social behavior heterogeneous graph modeling, and the method comprises the steps: inputting social user information, and constructing a metadata feature channel and a text feature channel; the method comprises the following steps: constructing a network topology structure by using social behaviors of social users, and forming a plurality of different types of HINs by adopting a graph neural network; fusing the obtained metadata and text features to form comprehensive user features; performing supervised contrast learning training by using the fused user features to obtain contrast loss; fusing network structure information in a social behavior scene into user features, and performing message aggregation and feature updating; and inputting the user feature vector into the classifier to complete the detection of the social robot account. According to the method, the problem of social robot detection in a multi-social behavior scene can be effectively solved, the detection performance is ensured, the robustness and adaptive capacity of the model are ensured, and subsequent detection tasks are facilitated.

The invention relates to the technical field of artificial intelligence, and discloses a knowledge graph completion method and device for relieving sparsity, and the method comprises the steps: constructing an auxiliary triple; performing instruction fine tuning on the large language model by adopting the data of the original knowledge graph to obtain a discriminator; filtering the auxiliary triple by adopting a discriminator, and fusing the filtered triple with the original knowledge graph to obtain an enhanced knowledge graph; performing message aggregation on the enhanced knowledge graph to obtain a graph structure representation fused with neighbor information; and a dynamic suppression strategy is adopted to correct loss in a graph structure representation result fused with neighbor information, the performance of the model on a knowledge graph completion task is improved, and an adjusted knowledge graph is obtained. According to the knowledge graph completion method and device for relieving sparsity, entity information similar to a rare entity is effectively mined through construction of the similarity matrix and the auxiliary triad, so that the answering ability of a system to a rare entity problem is improved.

The invention discloses an identity-based signature method supporting multi-message aggregation. The identity-based signature method comprises the steps of system initialization and key generation, user signature key generation, message signature construction, single signature verification, signature aggregation and aggregation signature verification. Due to the fact that the linear homomorphic signature technology is adopted, the identity-based aggregation signature method is provided, and the technical problems of signature after aggregation, key size expansion and the like in the existing aggregation signature technology are solved. Through the method, a verifier can safely and efficiently merge a plurality of signatures into a signature with a compact size, efficient data source authentication can be realized while the data integrity is guaranteed, and the verification efficiency is remarkably improved. The method has the advantages of high security, low communication cost, small calculation overhead and the like, can be applied to the technical fields of large-scale data authentication, distributed system security, lightweight cryptographic protocols and the like, and is particularly suitable for mobile terminals or Internet of Things equipment scenes with limited calculation resources.

The invention belongs to artificial intelligence, and particularly relates to a graph neural network confrontation defense method based on attribute enhancement PPR and self-loop weight adjustment, which comprises the following steps: a node stops at a current node or walks to a neighbor node at a certain probability, and executes topology migration or attribute migration at a certain probability during walking, calculating similarity among nodes by considering topology and attribute characteristics of multi-hop high-order information; utilizing similarity scores to cut off nodes with insufficient similarity for reconstruction, endowing corresponding connecting edges with weight values based on the similarity scores among the nodes, and reconstructing an adjacent matrix; in the message aggregation process, the proportion of the node itself and the neighbor node thereof in the final message is dynamically adjusted based on the out-degree of the target node, so that the proportion of the neighbor node is large when the number of neighbors is large, and the proportion of the node itself is large when the number of neighbors is small; performing message propagation through the reconstructed adjacent matrix; through iterative message aggregation and propagation, training a robust graph neural network with confrontation and defense capabilities; according to the invention, the robustness of the graph neural network is improved.

The application relates to the technical field of artificial intelligence, and discloses a knowledge graph completion method and device for relieving sparsity, which comprises the following steps: constructing auxiliary triplets; using the data of an original knowledge graph to perform instruction fine-tuning on a large language model to obtain a discriminator; filtering the auxiliary triplets by using the discriminator, fusing the filtered triplets with the original knowledge graph, and obtaining an enhanced knowledge graph; performing message aggregation on the enhanced knowledge graph to obtain a graph structure representation of fused neighbor information; using a dynamic suppression strategy to correct the loss in the graph structure representation of fused neighbor information, improving the performance of the model on the knowledge graph completion task, and obtaining an adjusted knowledge graph. The knowledge graph completion method and device for relieving sparsity can effectively mine entity information similar to rare entities through the construction of a similarity matrix and auxiliary triplets, thereby improving the answering capability of the system for rare entity problems.

The invention relates to a building layout generation method and system based on a generative adversarial network. According to the method, original node features and adjacency relations of a building are collected, and a bubble graph topological structure is constructed to serve as a constraint basis; a message aggregation mechanism of the graph neural network is utilized, weight self-adaptive regulation and control are carried out in combination with the initial probability distribution of the nodes, and an initial dynamic layout graph is generated; for the soft constraint node probability distribution, probability reweighting processing is carried out based on a conflict detection result, and updated spatial constraints are formed; and finally, through multiple rounds of adversarial training of the adversarial generative network, realizing iterative optimization and correction of the dynamic layout diagram. Therefore, the adaptability, the coordination and the conflict resolution capability of the layout scheme are remarkably improved while the topological compliance of the building function space is ensured.

The present application discloses a message processing method and apparatus, a device, and a medium. After at least one interactive message is obtained, the at least one interactive message is added to a target message queue. Meanwhile, a processing moment corresponding to the at least one interactive message that is stored is determined. That is, a received interactive message is processed with a delay. At least one interactive message added from a first moment to a second moment is read from the target message queue, and the at least one interactive message is aggregated to obtain a first aggregated interactive message. When a first processing moment arrives, the first aggregated interactive message is processed. That is, a plurality of interactive messages are aggregated in chronological order by processing interactive messages with a delay, so that the aggregated interactive message can be processed, thereby reducing processing pressure and improving processing efficiency.

The invention relates to a message processing method and device, equipment, a storage medium and a vehicle. The method comprises the following steps: acquiring a message in response to network input or output; all the messages are stored in a first message aggregation queue based on the fact that the number of the messages in the preset time exceeds a first threshold value, and the first message aggregation queue is a standby virtual aggregation queue of the first operating system; judging whether the first message aggregation queue meets a preset first execution condition or not, and if yes, trapping all the messages in the first message aggregation queue to a second operating system; and receiving all external messages in a second message aggregation queue which is a standby virtual aggregation queue of a second operating system when the number of the internal and external messages exceeds a second threshold based on a preset time and when the second message aggregation queue meets a preset second execution condition, the processing time and resource overhead of the central processing unit are reduced, the message processing efficiency is improved, and optimization of the virtual machine network is realized.

The present invention discloses a graph embedding entity alignment method based on reinforcement learning enhancement. The present invention adopts the method of constructing heterogeneous subgraphs, and only performs message aggregation on the n-hop neighbors of the entity pairs to be aligned, which directly reduces the computing resource requirements. A graph embedding learning algorithm based on feature linear modulation is used, and the idea of ​​super network is introduced to complete the message transmission mechanism and node update mechanism with high computational complexity with a small number of parameters, so as to better utilize the interactive information between nodes. In addition, the present invention proposes a node selector enhanced by reinforcement learning, proposes and applies a reliability measurement method based on self-supervisory signals in the node selector, samples a certain number of reliable edges, filters problem edges while limiting the size of heterogeneous subgraphs, and ensures the reliability of edges participating in node updates. The present invention also implements a node sampling quantity update strategy based on reinforcement learning, dynamically optimizes the number of sampled nodes, and enhances the node selector.

The embodiment of the invention provides a message display method and device, electronic equipment and a computer program product, and relates to the technical field of computers. The method comprises the following steps: when a message receiving mode of a target group is in any mode, receiving a member attention operation aiming at the target group, and taking a selected group member as an attention group member; in response to a message update event of the concerned group members, determining a target update message set of the concerned group members, the target update message set comprising an update message subset corresponding to each concerned group member; and receiving a message viewing operation for the target update message set, and displaying the update message subset corresponding to the concerned group members. According to the invention, when the target group is in any message receiving mode, group member attention operation can be carried out; and after the user pays attention to the group members, the user can quickly check the update message aggregation content of all the concerned group members.

This invention discloses a rapid stress field calculation method based on a graph network proxy model. First, a simulation model is created and a training dataset is constructed. Then, mesh information is exported. A graph neural network method based on message aggregation, propagation, and updating is employed, introducing parameters such as unit centroid and volume as node features, and area as edge features to complete the graph construction. Compared with traditional proxy model creation methods, this method fully considers mesh information and improves calculation accuracy. By introducing global features and utilizing external environmental parameters or partial measurement point stress values, rapid and real-time calculation of the structural stress field can be achieved, reducing sensor deployment requirements and hardware costs. This method not only accurately predicts the stress distribution of the structure but also improves calculation efficiency.

A device may receive TU data associated with TUs, and may identify a problematic TU from the TU data. The device may extract TU messages from the TU data associated with the problematic TU, and may calculate a faulty event score, a faulty location score, a faulty battery score, a faulty alerts score, a faulty other score, and a heartbeat score based on the TU messages. The device may calculate a faulty TU score for the problematic TU based on the faulty event score, the faulty location score, the faulty battery score, the faulty alerts score, the faulty other score, and the heartbeat score, and may aggregate the TU messages into aggregated TU messages. The device may process the aggregated TU messages, with an LLM, to determine a problem with the problematic TU and an explanation of the problem, and may perform actions based on the problem and the explanation.

The application discloses a sequence recommendation method based on meta-path neighborhood target generalization. The method comprises the following steps: modeling items and their co-occurrence as an item-item graph according to the historical behavior sequence of a user, constructing an item-label graph according to the corresponding relationship between each item and a label, and constructing a meta-path for capturing different composite relationships between items or labels; encoding the historical interaction information of the user by using a heterogeneous graph, and constructing the relationship between items and items, items and labels, and adopting a message propagation mechanism and a message aggregation mechanism to fuse different types of nodes and their relationships; carrying out embedding learning training on the heterogeneous graph to obtain a trained sequence recommendation model, in the training, for each target prediction, generalizing potential item targets to assist in training, and inputting the vector representation of the item node into a conversion layer. The application can improve the accuracy of recommended items, and explore potential interest items of the user in addition to historical interaction behaviors.

Aspects relate to mechanisms for an apparatus to aggregate latency tolerance reporting (LTR) messages from a plurality of endpoints to identify a minimum snoop latency and a minimum no-snoop latency across the plurality of endpoints. The minimum snoop latency and minimum no-snoop latency are provided to a processor configured for power management of the apparatus.

The invention provides an online and offline message processing method and system, equipment and a medium, and the method comprises the steps: obtaining a current time window, a current table index, a first online and offline message of the equipment and a first data table of a database; the time length of the current time window is larger than the time length of the previous time window when the first online and offline messages are stacked, and the number of the joint primary key elements in the current table index is smaller than or equal to the number of the joint primary key elements in the previous table index when the first online and offline messages are stacked; according to the current time window, performing first message aggregation on the first online and offline message to obtain first equipment aggregation data; and according to the current table index and the first equipment aggregation data, performing first storage updating on the first data table to obtain an equipment online and offline processing result. The method can effectively improve the consumption rate of the online and offline messages, inhibit the accumulation of the online and offline messages, and reduce the processing delay of the online and offline messages. The invention relates to the technical field of data processing.

Technologies for protocol execution include a command device to broadcast a protocol message to a plurality of computing devices and receive an aggregated status message from an aggregation system. The aggregated status message identifies a success or failure of execution of instructions corresponding with the protocol message by the plurality of computing devices such that each computing device of the plurality of computing devices that failed is uniquely identified and the success of remaining computing devices is aggregated into a single success identifier.

This disclosure provides a page processing method, apparatus, device, and storage medium, including: displaying a message aggregation page corresponding to a target account set, wherein the message aggregation page displays account information of at least one account in the target account set and messages published by at least one account, the messages including object information of at least one recommended object; and in response to a trigger operation targeting a target recommended object under the target account, displaying an object information page for the target recommended object. Embodiments of this disclosure support displaying account information of accounts in a target account set and messages published by those accounts containing object information of recommended objects on a message aggregation page. Therefore, embodiments of this disclosure facilitate users in obtaining object information of recommended objects in messages published by accounts in a target account set, enriching page-related interaction methods and improving the user's browsing experience.

This invention discloses a message processing method and related apparatus, relating to the field of message processing. When the current message cache is not full, the main thread receives live messages and submits them to a HandlerThread for asynchronous parsing to obtain different message types. Corresponding caching strategies are then applied, retrieving image cache data from the ImageSpan cache and text cache data from the plain text cache, assembling them into a complete live message, and inserting it into a RecycleView queue for message aggregation caching. The complete live message is then inserted into a scrolling control in the RecycleView list for display. Based on a preset scrolling strategy, the complete live message is directly scrolled and displayed using a SpannableString cache. This invention utilizes HandlerThread for asynchronous message processing, a three-layer caching mechanism to optimize performance, and strategy parsing to decouple rendering logic, ensuring the main thread maintains a high frame rate.

A method is disclosed. The method includes receiving, by a processing system, an enrollment message from a user device operated by a user via an authorizing entity computer. The enrollment message specifies one or more preferences associated with value portions associated with interactions conducted by the user. The method also includes receiving authorization request messages associated with a plurality of interactions conducted by the user, aggregating value portions associated with the authorization request messages to form an aggregate value; and processing a transfer of the aggregate value to one or more records associated with one or more receiving entities.

This invention relates to the field of dynamic response calculation for engineering structures, specifically disclosing a method for constructing a structural explosion response calculation model based on graph neural networks. The method includes: encoding and decoding the node and edge features of the graph structure; constructing a spatiotemporal graph processor consisting of multiple stacked spatiotemporal graph tiles, with spatial modeling of a physics-enhanced graph attention network and temporal modeling of gated recurrent units coupled within each tile; integrating physical information into the model in the form of soft or hard constraints; establishing a physics-driven message passing mechanism, including designing a physics-enhanced message function, a wave velocity-aware attention mechanism, and a physics-driven message aggregation and node update method; training the model using a multi-step Rollout training strategy, and validating the model through data accuracy evaluation and physical consistency checks. This invention integrates data-driven and physical mechanisms, solving the problems of time-consuming traditional numerical simulations, weak generalization of purely data-driven models, and insufficient physical consistency.

The application provides an RDMA message aggregation processing method and a network card device, and belongs to the technical field of data communication, and comprises the following steps: S1, an RDMA message analysis step, which comprises a hardware level message capture, a BTH header analysis, and a message classification and metadata generation link; S2, an RDMA cache step, which comprises a message descriptor record and a cache strategy link; S3, an RDMA message aggregation step, which comprises an aggregation context table, an aggregation flow, a newly created aggregation flow, and an existing context aggregation flow link; and S4, a zero-copy aggregation step, which comprises metadata transmission, DMA delay processing, and host memory writing links. In view of the fact that the existing network cards do not attempt to perform stateless aggregation processing on RDMA messages when processing the RDMA messages, the application aggregates multiple received RDMA messages into one larger RDMA message to send to a downstream module for processing, thereby reducing the number of messages processed by the downstream module and improving the bandwidth of the network card for processing the RDMA messages.

The application provides a single-cell RNA sequencing annotation method and device based on a dynamic hypergraph, relates to the technical field of bioinformatics, and comprises the following steps: obtaining a data set, extracting a low-dimensional embedding vector of each cell from a gene expression vector, and constructing a dynamic hypergraph with cells as nodes and gene pathways as hyperedges; extracting a pathway feature of each hyperedge from the dynamic hypergraph; calculating the importance weight of each cell in each hyperedge based on the low-dimensional embedding vector and the pathway feature of the hyperedge; inputting the dynamic hypergraph, the pathway feature and the importance weight into a preset hypergraph neural network for message aggregation and feature learning to generate a prediction label of a cell type; and training the hypergraph neural network through an optimization algorithm to obtain a trained cell annotation model. The application realizes more accurate and more biologically interpretable cell type and function annotation by introducing a hypergraph structure and a metabolic pathway activity dynamic modeling mechanism.

The invention belongs to the field of PCIe exchange chips, and relates to a PCIe message aggregation exchange method and device, and the device comprises a PCIe inlet port, an inlet aggregation module, a crossbar switch, an outlet deaggregation module, and a PCIe outlet port. The entrance aggregation module is used for screening and matching the plurality of received TLPs according to a preset aggregation condition, and judging whether an aggregation requirement is met or not; the crossbar switch is used for receiving the CTLP or the independent TLP sent by the inlet aggregation module, and forwarding the CTLP or the independent TLP to the corresponding outlet deaggregation module according to a destination port of a message; and the outlet deaggregation module is used for receiving the message forwarded by the crossbar switch and judging whether the message is a CTLP or an independent TLP. The bandwidth utilization rate is greatly improved, the transmission delay is remarkably reduced, the compatibility is excellent, the implementation cost is low, the reliability is high, and the universality is high.

The invention discloses a biomolecule relation modeling method based on semantic consistency hypergraph contrast learning, and aims to model a complex relation between biomolecules by effectively combining a local structure and global semantic information. According to the method, firstly, local representation of nodes is enriched by expanding a message aggregation mechanism guided by a subgraph, and global context information is combined to improve the modeling precision of the biomolecular relationship; secondly, performing hypergraph reconstruction by adopting a double-layer consistency mechanism, and maintaining the consistency of a local structure and semantics at a node level and a hyperedge level through semantics and structure constraints; besides, soft clustering is carried out by using a Gaussian mixture model (GMM) and a Bayesian information criterion (BIC) strategy, hyperedge selection is further optimized, and structural consistency in a reconstruction process is ensured. In order to ensure the consistency of local and global semantics, the method introduces a multi-granularity comparison target in a comparison learning framework, performs training at node, hyperedge and extended subgraph levels, feeds back high-level semantic information to low-level semantic information through a cross-layer feedback mechanism, stabilizes the model and enhances semantic alignment between representations. Experimental results show that the provided framework is excellent in performance in node classification and clustering tasks on multiple reference data sets, and compared with an existing method, local and global semantic relationships can be better captured and aligned, and the hypergraph learning effect is remarkably improved.

The application discloses a dynamic message aggregation and distribution method and system. The destination address of an original message in a received message is judged. If the destination address is local, the message is directly sent. If the destination address is not local, it is judged whether the message is repeated according to the message type and content. For the repeated message, message aggregation is performed. The message aggregation includes counting the message identifier of the repeated message and determining the forwarding server list of the aggregated message. The aggregated message is sent to the remote server closest to the local server in the server list. The aggregated message in the received message is dis-aggregated. The message with the local destination address is sent to the destination address. After the local address in the server list is deleted, the aggregated message is sent to other remote servers. Through accurate calculation of only receiving the forwarding server node set of the message, the forwarding of the group message to irrelevant servers is reduced, thereby greatly reducing the redundant network traffic and saving the valuable bandwidth resources.