9 results about "Historical model" patented technology

Media plan generation systems and methods for TV advertising are disclosed. Embodiments of these systems and methods are adapted to generate a media plan comprising a core plan and a test plan. The core plan may be produced based on historical models regarding historical performance of an entity's media while the test plan may be produced based on a predictive model of media performance.

This invention discloses an intelligent layout system for the installation of exterior wall composite panels, relating to the field of intelligent construction technology. It collects building facade information to generate a structured digital twin model of the building site; matches the site model with historical construction digital twin models based on feature fingerprint similarity, extracting an initial intelligent layout model from the graph neural network architecture of the matching cases; analyzes the differences between the site model and the historical models and encodes them as adjustment instructions for the model input graph structure; performs transfer learning on the initial model, focusing on optimizing the difference areas, to obtain an optimized intelligent layout model; acquires site environmental data, combines it with a built-in physical and process knowledge base, drives the optimized model to generate multiple candidate schemes and perform construction feasibility simulations, outputting multi-dimensional construction scores for each scheme; compares the multi-dimensional construction scores and outputs the optimal layout scheme, solving the problems of traditional layout methods being unable to handle complex structures, ignoring environmental factors, and lacking reusable experience.

Technologies are described herein for classifying personalized interactions at an application. A method can include receiving and storing user inputs associated with interactions between users of the application, building historical models based on the user inputs to classify the interactions, wherein building a historical model for a particular user comprises aggregating particular user inputs associated with a set of previous interactions between a particular user and other users, in association with a pending interaction for the particular user and during the pending transaction associating a current user input with the historical model for the particular user and based on analyzing the historical model for the particular user, determining that the pending interaction satisfies a condition, and interrupting the pending interaction based on determining that the pending interaction satisfies the condition.

This specification discloses a model training method, a task execution time prediction method, and an apparatus, specifically including: filtering similar historical model training tasks based on historical resource usage data of historical model training tasks; inputting the historical resource usage data of historical model training tasks and similar historical model training tasks into a prediction model to determine the resource usage characteristic data corresponding to the historical model training tasks, thereby determining the predicted execution time corresponding to the historical model training tasks; training based on the predicted execution time and the execution time of historical tasks; and determining the predicted execution time of the target model training task based on the resource usage data of the target model training task. The method in this specification has higher prediction efficiency and greater accuracy. This effectively improves the utilization rate of training resources during subsequent resource allocation, avoiding resource waste and idleness, and greatly improving the overall training efficiency of the training process.

The invention relates to the technical field of industrial equipment state monitoring and data processing, and discloses a multi-parameter fusion triggered steam turbine generator unit vibration data recording method, which comprises the following steps: automatically judging whether a unit operates in a working condition steady state or transient state mode according to a macroscopic parameter fluctuation ratio; in the steady-state mode, monitoring is performed by comparing the structural difference between the real-time reference correlation matrix and the dynamic reference correlation matrix; in the transient mode, monitoring is carried out by matching the morphological difference between the real-time parameter track and the standardized template, and data recording is triggered when any monitored difference value exceeds the limit. Therefore, the method can automatically adapt to baseline drift generated by normal aging of the unit so as to avoid false alarm, and at the same time, for multi-parameter cooperative relationship disintegration caused by early failure, high sensitivity is shown so as to avoid missing alarm.

Technologies are described herein for classifying personalized interactions at an application. A method can include receiving and storing user inputs associated with interactions between users of the application, building historical models based on the user inputs to classify the interactions, wherein building a historical model for a particular user comprises aggregating particular user inputs associated with a set of previous interactions between a particular user and other users, in association with a pending interaction for the particular user and during the pending transaction associating a current user input with the historical model for the particular user and based on analyzing the historical model for the particular user, determining that the pending interaction satisfies a condition, and interrupting the pending interaction based on determining that the pending interaction satisfies the condition.

This invention discloses a federated image classification system and method based on historical state backtracking and probabilistic sampling grouping, comprising: an aggregation server communicating with multiple image acquisition terminals; the aggregation server maintaining a first-in-first-out model buffer for each terminal; each terminal uploading behavioral feature vectors; the server calculating the similarity between vectors, sampling dynamic thresholds from a Beta distribution probability, and constructing collaborative groups for each terminal based on the comparison results; the server using the current model parameters of a terminal as an anchor point, selecting the historical model version with the smallest Euclidean distance from the anchor point in the buffers of each member terminal within its collaborative group, and weighting and aggregating them to generate personalized model parameters which are then distributed to the terminals for classifying the acquired images. This invention achieves flexible collaborative grouping through probabilistic sampling, breaking through the bottleneck of hard clustering collaboration, and suppresses overfitting and model drift through historical state backtracking, thereby improving the personalized performance and convergence stability of the image classification model.

The application provides a federated learning method and system based on double-end safety protection, and belongs to the technical field of federated learning. Local data of each client is input into a main task for local training after being screened by a data filter, and a screening result is saved to generate a local data description. Each client uploads a local model and the local data description to a server. When the server has sufficient historical model information of the clients, a model filter is run to review the quality of the local model by using the processed local model set and the local data description of each client. The server will guide the federated training and aggregation process according to the review result of the quality of the local model of the client. The application performs offline automatic review on the local data set at the client side, reviews the collected local model at the server side, comprehensively protects the safety of the data and the model without violating the privacy protection principle of federated learning, and improves the robustness and credibility of federated learning.

The application discloses a cross-tool model conversion method based on a SysML model specification, and comprises the following steps: in step S210, a unified model expression specification suitable for different tools is determined according to a SysML specification of an OMG standard and model expression manners of different SysML modeling tools; in step S220, an input SysML model established by a specific tool is parsed and converted into a format defined by the unified model expression specification; and in step S230, a model represented by the unified model expression specification is parsed and converted into a SysML model under a specific modeling tool in conformity with output requirements. The application enhances the cooperation of SysML models between cross tools and the reuse of historical model data under different tools, reduces the workload of manual model conversion, improves the correctness and quality of model conversion, and provides important technical support for the practical application of cross-organization and cross-tool MBSE.