58 results about "Message aggregation" patented technology

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.

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 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 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.

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.

Methods and systems for log message aggregation include determining a first similarity distance score for a first incoming message by comparing the first incoming message to one or more stored templates. It is determined that the first incoming message imperfectly matches a matched template of the one or more stored templates, based on the first similarity distance score. A token in the imperfectly matched template is replaced with a wildcard, to reduce the first similarity distance score.

Embodiments of the present application disclose an alarm processing method, device and equipment, wherein the method comprises: aggregating alarm messages meeting an association rule into at least one alarm group, wherein each alarm group comprises one main alarm and at least one sub-alarm, and the association rule is updated based on a rule change message; determining the alarm group meeting a trigger condition as a target alarm group, wherein the trigger condition comprises a main-sub trigger condition of the main alarm and the sub-alarm, a sub-sub trigger condition between the sub-alarms and a filtering condition, and the filtering condition is a logical relationship between the main-sub trigger condition and the sub-sub trigger condition; and outputting the target alarm group. In this way, the alarms matching the association rule are further screened according to the trigger condition, the accuracy of the association is improved, the accuracy of alarm positioning is effectively improved, and the number of invalid work orders is reduced.

In the various embodiments, systems and methods are disclosed for sending messages with validated representative links from entities to users on a network. In some embodiments, a message originator can interface with an A2P platform of a message aggregator server to upload a message template including message content and an Internet link. In some embodiments, the A2P platform can obtain a representative link corresponding to the Internet link from a representative link server. In some embodiments, the A2P platform can compile a message including the representative link and other information from the message template. In some embodiments, the A2P module can provide the compiled message to a messaging module of the message aggregator server. In some embodiments, the messaging module can communicate with the representative link server to validate the representative link and, if valid, transmit the compiled message to a messaging server of the network.

This invention discloses a method and apparatus for predicting interactive dynamic states based on mesh representation and atomic skill graphs, belonging to the field of robotics technology. It solves the problem of the disconnect between abstract action commands and underlying physical states in machine-object interactions. The method includes: extracting key interactive state nodes during the manipulation of a target object by an end effector; acquiring the environmental visual image, distributed time-of-flight (ToF), and ontological state information of the end effector at each state node; fusing visual and ToF information to reconstruct the topological mesh of the target object, and jointly constructing an atomic skill graph encompassing physical structure and contact features with the ontological state, as the model input; importing the model input into a graph neural network for latent space encoding and multi-round message aggregation and propagation, and outputting the dynamic state prediction result for the next moment through graph decoding. This invention achieves a unified mapping between abstract skills and physical states, improving the accuracy of interactive state prediction in the face of high-dimensional deformation and complex multi-point contact.

The invention discloses a message processing method and device, equipment and a storage medium, and belongs to the technical field of Internet of Things. The method is executed by a server device, and comprises: receiving a subscription request (301), the subscription request being used for subscribing a target resource in the server device; wherein the subscription request comprises batch indication information, and the batch indication information is used for indicating the server-side equipment to aggregate and send a plurality of notification messages corresponding to the target resource to the client-side equipment.

The invention discloses a protein function prediction method based on virtual atoms and distance hierarchical learning, and the method comprises the steps: carrying out the data preprocessing, initializing the virtual atoms, defining a relation set, enabling all atoms to pass through an embedded layer, obtaining an initial hidden state, sampling a uniform distribution as a weight probability coefficient of relation aggregation, according to the weight coefficients, K rounds of feature updating of the real atoms and the virtual atoms are conducted in sequence through a message aggregation network based on a relation set, the virtual atoms representing the protein serve as sphere centers to construct a plurality of concentric spheres with equal-distance threshold values, weighted summation pooling is conducted on the atoms in each concentric sphere, normalization is conducted, and protein representation is obtained, and inputting the protein representation into two layers of feed-forward networks and a softmax layer for classified output. According to the method, the non-covalent bond action in the protein is modeled, the perception of the network on the space structure is enhanced, and the accuracy of protein function prediction is effectively improved.

The embodiment of the specification provides a kind of iterative two-party privacy graph analysis method and device, method includes: the first party is based on the current sequence fragment of the tuple sequence of the first order obtained in last round, by and the second party are executed jointly for target permutation safe permutation agreement, obtain the current sequence fragment of the tuple sequence of the second order;Based on the current sequence fragment of the tuple sequence of the second order, and the second party is executed jointly from node to edge casual message propagation, obtain the first update fragment of the tuple sequence of the second order;Based on the first update fragment of the tuple sequence of the second order, by and the second party are executed jointly for target permutation inverse permutation safe permutation agreement, obtain the first update fragment of the tuple sequence of the first order;Based on the first update fragment of the tuple sequence of the first order, and the second party is executed jointly from edge to node casual message aggregation, obtain the second update fragment of the tuple sequence of the first order.

The invention discloses a message pushing method and device, equipment and a medium, and relates to the technical field of cloud computing. The method is applied to a cloud computing management platform and comprises the following steps: acquiring a state change message generated by platform service when a data state changes; if the state change message is a first priority message needing to be responded in real time, pushing the state change message to the client in real time; and if the state change message is a second priority message which can be processed in a delayed manner, judging whether a cached message exists in the current aggregation period, if not, taking the second priority message as a first message and pushing the first message to the client in real time, and if yes, caching the second priority message to pre-deployed message aggregation middleware, and after the current aggregation period expires, aggregating all the second priority messages cached in the message aggregation middleware into one aggregated message, and sending the aggregated message to the client. According to the technical scheme, the system load can be effectively reduced.

The invention relates to the technical field of artificial intelligence, in particular to a time sequence enhanced graph neural network false information detection method and system. The method comprises the following steps: acquiring social media information and propagation data thereof, and constructing a dynamic graph containing user nodes, post nodes and a propagation relationship with timestamps; extracting text and image content features of the information; a time sequence diagram network (TGN) is adopted as a core model, a propagation timestamp is coded through a multi-granularity time coding module, and a time sequence feature vector fusing periodicity, interval and discreteness is generated; in the message aggregation stage, a time granularity sensing gating mechanism is introduced, and node features, edge features and time sequence features are dynamically fused to calculate adaptive weights, so that a key time sequence mode in an information propagation path is captured; and finally, carrying out false information classification by utilizing the node representation after time sequence enhancement. According to the method, the defect that an existing detection model is insufficient in propagation dynamic time sequence characteristic modeling is overcome, and the false information detection accuracy and the early-stage discovery capability are remarkably improved.

The invention discloses a power operation personal risk dynamic model construction method, system and device, and a medium. The method comprises the following steps: constructing a power operation risk map structure through node initial features; inputting the electric power operation risk graph structure into a multi-hop graph convolutional network, respectively extracting information of each hop neighbor through a node layer, and generating multi-hop neighbor feature representation; predicting an acceptance field range of each target node through a meta-learner according to the multi-hop neighbor feature representation; according to the acceptance field range, generating fusion feature representation of the target node; and performing risk prediction on the fused feature representation, and outputting a power operation personal risk assessment result. According to the method, neighbor information of each hop is directly extracted through a node layer of the multi-hop graph convolutional network, multi-hop neighbor feature representation with non-overlapped information is generated, and the problem of excessive smoothness caused by aggregation of far-neighbor information through neighbor node serial transmission messages in a traditional graph neural network is avoided.