37 results about "Instance selection" patented technology

A system or method for selecting an instance family for deploying a target application. The system accesses a configuration that specifies a target application, relevant performance metrics, and various instance families that are candidates for deployment. For each instance family, the target application is temporarily deployed during a specified test period, and the performance metrics are recorded and stored. These metrics are then analyzed to generate rankings corresponding to the instance families. Based on these rankings, a recommendation is generated for an instance family for the application deployment based on ranking metrics.

The invention provides a micro-service chain-level load balancing method based on deep reinforcement learning. The method comprises the following steps: establishing a response time-energy consumption model in a chain-level load balancing scene; determining a multi-objective optimization problem of chain-level load balancing; establishing a multi-target Markov decision model in an instance selection process in load balancing; constructing a chain-level load balancing model through a deep reinforcement learning method; training the chain-level load balancing model until rewards converge; and inputting load data into the trained model to obtain a balancing result. According to the method, load fluctuation is sensed in real time through the chain-level load balancing model, a proper load balancing strategy is adaptively selected, collaborative optimization of global response time and energy consumption of the micro-service chain is realized, and load balancing optimization requirements of high real-time performance and high request heterogeneity are met.

The embodiment of the invention provides a website data processing method and device, equipment and a storage medium, and the method comprises the steps: obtaining website instance data which comprises a plurality of website instances; the initialized particle swarm is evolved through a competitive particle swarm algorithm and website instance data, and particles in the particle swarm represent an instance selection scheme of the website instance data; and according to the evolved particle swarm, instance selection is carried out in the website instance data to obtain a target instance subset, and the target instance subset is used for classification model training of phishing websites. Therefore, the instance selection scheme in the website instance data is optimized through the competitive particle swarm algorithm, and the instance subset used for classification model training of the phishing website is selected from the website instance data according to the optimized instance selection scheme, so that the quality of training data of the classification model is improved; the accuracy of phishing website detection based on the classification model is improved.

The present invention discloses a recommendation method based on multi-view feature selection. In view of the differences in feature selection for given feature fields in different data in the recommendation system, and the problem of bias towards main features in the process of adaptively selecting features for each data instance, the present invention proposes multi-view feature selection to effectively select rich feature information for each instance. Specifically, the present invention adopts a multi-view network composed of multiple sub-networks, so that each sub-network learns data features of different feature patterns, reduces the deviation from the dominant pattern, and promotes the balance of the feature selection process. In addition, an effective importance scoring modeling strategy is adopted to perform strategy modeling independently for each field, so that there is no dependency between features, and ultimately effectively improves the efficiency of feature selection in recommendation.

The invention discloses a large model test set evaluation method based on a project reaction theory, which belongs to the technical field of large language models, and comprises the following steps: (1) data preparation; (2) embedding and obtaining questions; (3) reference instance selection; (4) obtaining a model test result; (5) constructing a network structure; (6) model training; (7) Fisher information calculation is carried out; and (8) performing quality evaluation and parameter analysis on the test set. According to the method, the Fisher information, the difficulty parameter b, the distinction degree parameter a, the guess parameter c, the feasibility parameter d and other multi-dimensional indexes of each question are obtained, and the quality of each benchmark test is analyzed and evaluated based on the indexes, so that the quality of the benchmark test is analyzed more accurately and more comprehensively, and then the capacity of a large model and the quality of a test set are evaluated more accurately.

Novel tools and techniques are provided for implementing object-oriented infrastructure-as-code platform (“OOIACP”) and its functionalities. In various embodiments, when a request to process one or more lifecycle events is received, a computing system may perform: selecting and scaling across a plurality of OOIACP instances; and causing the selected plurality of OOIACP instances to process the one or more lifecycle events. In some cases, each OOIACP instance may include an infrastructure-as-code (“IAC”) command line that instantiates component infrastructure among a plurality of component infrastructure to process at least one lifecycle event among the one or more lifecycle events concurrently and independently of other OOIACP instances. In some instances, the first plurality of OOIACP instances may be located within an environment in which the plurality of component infrastructure is located.

The invention discloses a method for relation extraction based on reinforcement learning. The relation extraction model based on reinforcement learning comprises an instance selector based on reinforcement learning and a relation classifier based on a PCNN model. The instance selector based on reinforcement learning obtains a selection result through a reinforcement learning process, and the selection result is a sentence that best expresses a package label in a package composed of sentences of the same entity pair. The selection result is input into the relation classifier, and sentences expressing the same relationship are identified according to the input sentences, and the instance selector is fed back. A strategy function is updated according to the feedback, and a better relation classifier is trained with the selected sentences to optimize the instance selection and relation classification process. Finally, the sentence that best represents the relation label is selected as the training data of the relation extraction model based on reinforcement learning. The invention reduces the influence of noise and coarse-grained problems of a remote supervision corpus on relation extraction, and improves the performance of relation extraction.

The invention discloses a single-stage full-sparse three-dimensional target detection method based on point cloud completion, and the method mainly comprises the steps: firstly, processing a point cloud through a sparse backbone network to extract the features of each point, and then inputting the features into an instance selection module to generate clustering instances; processing each clustering instance by an alignment-based point cloud completion module, and finally generating a complete point cloud; further, point features are input to a center point voting network, where each point predicts its perceived object center. The predicted center point and complemented point cloud features are fused at a feature level, and finally the generated features are sent to a detection head to obtain a 3D bounding box and a corresponding confidence score. The method is suitable for a single-stage full-sparse three-dimensional target detection network, and can improve the detection performance of a single-stage full-sparse three-dimensional target detector for severely shielded objects.

The invention discloses a to-be-assessed asset reference instance selection calculation method, system and device. The method comprises the steps of obtaining basic information of to-be-assessed assets; selecting a plurality of historical transaction assets of which the basic information is consistent with the to-be-evaluated assets from a pre-constructed asset transaction database, and taking the selected historical transaction assets as initial reference instances; calling an asset correction model to calculate a market correction coefficient, a land price correction coefficient, an area correction coefficient, a time correction coefficient and an assembly correction coefficient of each initial reference instance, and multiplying the correction coefficients to obtain a final correction coefficient; and selecting a plurality of initial reference instances of which the final correction coefficients are closest to a preset correction index as target reference instances for evaluating the assets to be evaluated. According to the method, the initial reference instance can be corrected from the aspects of market, land price, area, time, assembly and the like, so that the difference between each initial reference instance and the to-be-evaluated asset and the actual reference value of each initial reference instance are quantified, and the reasonability of a selection result and the reliability of an asset evaluation result are improved.

An embodiment of the present application provides an object extraction method and apparatus. The method includes: inputting a first picture including at least one object into a semantic segmentation feature network so that the semantic segmentation feature network outputs a first feature map. Processing the first feature map according to a semantic segmentation classification network to obtain a semantic segmentation result map, where the semantic segmentation result map includes a layer of an object mask map and a layer of a background mask map. Processing the first feature map and the layer of the object mask map according to an interest point generation network to obtain at least one interest point. Processing the first feature map and at least one interest point according to an interest point control network and an instance selection network to obtain a target mask map corresponding to each of the at least one interest point. Determining the positions of the respective objects in the first picture according to the target mask maps corresponding to the at least one interest point respectively to extract at least one object. This embodiment effectively ensures the effect and accuracy of the extracted rod-shaped object.

Reliability-based service chain instance selection in a 5G network includes evaluating, for a service chain provided in a 5G network, the service chain comprising a series of network functions with processing hand-offs and take-overs therebetween, reliability of each service chain instance of a plurality of available service chain instances of the service chain, obtaining a service request for processing in the 5G network, the service request to be serviced by the service chain, selecting a service chain instance of the plurality of available service chain instances to process the service request, the selecting being based on the evaluated reliabilities of the plurality of available service chain instances, and invoking processing of the selected service chain instance to process the service request.

The application discloses an edge delay perception microservice instance selection method based on graph reinforcement learning, belongs to the field of Internet of Things and edge computing, and comprises the following steps: first, edge computing environment state perception and graph structure feature extraction of an edge node instance deployment graph and a microservice request calling graph; second, microservice instance selection action decision generation based on graph features; third, edge computing environment interaction and classified experience sample recording; and fourth, edge microservice instance selection graph reinforcement learning model training and iterative optimization based on multiple groups of experiences, so that stable iterative optimization of the model is realized. The application realizes efficient selection of microservice instances in an Internet of Things edge computing environment, and takes into account request delay and instance load balancing.

The invention discloses a noisy label cross-modal retrieval method based on neighborhood perception instance refining, which comprises the following steps of: performing feature extraction on input noisy cross-modal data, and mapping the data to a shared semantic space; constructing a cross-modal boundary keeping module, and enhancing the global discrimination capability of feature representation through global mechanism regularization; constructing a cross-modal neighborhood consensus module, generating a soft label based on the cross-modal neighborhood consensus module, dynamically dividing a data set, and performing a targeted optimization strategy on the data set; integrating the loss functions of all the modules to perform end-to-end joint optimization, and training to obtain a cross-modal retrieval model with high robustness to noise tags; and efficient cross-modal retrieval is realized. According to the method, the robust learning method, the instance selection method and the label calibration method are integrated together, so that maximum utilization and fine processing of all training data are realized, and the retrieval performance in a high-noise environment is remarkably improved.

The invention discloses a power distribution network fault rapid positioning method and system. The method comprises the steps of data acquisition, triple undersampling processing, secondary decomposition, dynamic similar distance matrix calculation and condensed hierarchical clustering. The invention belongs to the technical field of power distribution networks, and particularly relates to a power distribution network fault rapid positioning method and system.According to the scheme, triple undersampling processing is carried out on original data based on unmarked data injection, instance selection and neighborhood cleaning; a residual term is secondarily decomposed into an intrinsic mode function and a residual, so that data can be more finely disassembled, and more signal components and features are extracted; a dynamic similarity distance calculation method is adopted to more accurately describe the similarity between the two time sequences; the dynamic similarity distance matrix is adopted for hierarchical clustering, so that dynamic similarity information between data can be fully utilized; fault positioning is carried out based on double tags, and the positioning speed and accuracy are improved.

The invention relates to the field of unbalanced classification, and discloses a multi-expert instance selection-based unbalanced classification method, which comprises the following steps of: loading a data set and calculating a constraint threshold value; randomly initializing a population; performing instance subset search based on a non-dominated sorting genetic algorithm NSGA-II; environment selection and feasible individual division are carried out, and an integration strategy is selected according to the number of feasible individuals; integrating the feasible individuals to obtain an integrated classifier; the multi-expert objective function provided by the invention considers different class distributions at the same time, the constraint threshold ensures that the selected instance subset is superior to the original training set, a group of high-quality instance subsets can be evolved, and the overall classification performance is improved.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes identifying a procedural instance; selecting control settings for the procedural instance, comprising, for a particular one of the controllable elements: assigning the procedural instance to a cluster for the particular controllable element in accordance with current values of a set of clustering parameters for the particular controllable element; and selecting a setting for the particular controllable element for the procedural instances based on a causal model that is specific to the cluster; obtaining environment responses to the selected control settings that define a value of the performance metric for the procedural instance; and updating, for the particular controllable element, the causal model for the cluster for the controllable element to which the procedural instance was assigned based on the value of the performance metric.

The present invention discloses a system and method for orchestrating the execution of computing tasks. An orchestration engine can receive task requests from multiple process engines via a network. Compared with the orchestration engine, the process engines can correspond to respective remote edge or field devices. Each task request can indicate at least one task requirement for executing the corresponding computing task. Multiple computing instances with available computing resources can be selected from a set of computing instances. A predicted runtime can be generated for each of the computing tasks. In an example, based on the predicted runtime, task requirements, available computing resources, and associated network conditions, the orchestration engine determines a scheduling and allocation scheme. The scheduling and allocation scheme defines when to execute each of the multiple computing tasks and which of the multiple selected computing instances executes each of the multiple computing tasks. The selected computing instances execute the multiple computing tasks according to the scheduling and allocation scheme.

The invention provides a cloud mobile phone instance selection method and device based on load balancing, equipment and a medium, and relates to the technical field of computers. The method comprises the following steps: collecting network state data and user position information; dynamic coefficients of a plurality of candidate cloud mobile phone instances are generated based on the network state data through a pre-trained long and short-term memory network model; based on the dynamic coefficient, the network state data and the user position information, generating a dynamic weight load model corresponding to each candidate cloud mobile phone instance; respectively calculating weight scores of the plurality of candidate cloud mobile phone instances through a dynamic weight load model; and determining an optimal cloud mobile phone instance based on the weight score. According to the embodiment, the influence of the network state data of each candidate cloud mobile phone instance on the load balancing can be dynamically evaluated in real time based on the load balancing, so that the advantages and disadvantages of the candidate cloud mobile phone instances can be more comprehensively, efficiently and accurately evaluated, and the resource allocation in the cloud environment is optimized.

The invention belongs to the technical field of wireless communication, discloses a satellite communication network optimization method and system based on MEC, and aims to meet the time delay requirement of quality of service (QoS) and improve the service performance of the satellite communication network through joint optimization of task scheduling, access control, service instance selection and bandwidth allocation. And the long-term average weighted sum of the task failure rate and the equipment economic cost is minimized. According to the method, the mobile edge computing technology is utilized, the performance and reliability of a communication network are improved, the problems of wireless resource shortage and insufficient computing resources of a user side are solved, and energy consumption and time delay in the computing unloading process of equipment are reduced. Aiming at task dynamics, network condition volatility and complexity of an optimization problem in a satellite ground integrated system, the problem is converted into a deep reinforcement learning (DRL) problem, a joint optimization algorithm based on a multi-agent depth deterministic policy gradient (MADDPG) is provided, and the task failure rate and the economic cost are effectively reduced.

Process knowledge creation, development, and management techniques allow for and enable the creation of a universal process definition (UPD) of an industrial process, the automatic conversion or transformation of the UPD into different site-specific process definitions, and the implementation of the site-specific process definitions at different manufacturing, production, and / or automation sites. Typically, the UPD is site- and equipment-agnostic, and the transformation may generate and provide a set of site-specific process definition implementation files or routines to configure and / or govern the behavior of various site-specific execution systems, e.g., as site-specific operational instances of the UPD. The techniques may utilize feedback and information generated by site-specific operational instances to generate learned knowledge and update the UPD accordingly so that subsequent instantiations of the UPD may incorporate (and reap the benefits of) the learned knowledge. The techniques may automatically select a most suitable site for a particular instantiation of the UPD.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes identifying a procedural instance; selecting control settings for the procedural instance, comprising, for a particular one of the controllable elements: assigning the procedural instance to a cluster for the particular controllable element in accordance with current values of a set of clustering parameters for the particular controllable element; and selecting a setting for the particular controllable element for the procedural instances based on a causal model that is specific to the cluster; obtaining environment responses to the selected control settings that define a value of the performance metric for the procedural instance; and updating, for the particular controllable element, the causal model for the cluster for the controllable element to which the procedural instance was assigned based on the value of the performance metric.

The invention discloses a low-illumination target detection method based on class consistency screening and generative completion. The method comprises the steps of 1, performing feature extraction on a low-illumination input image, and outputting classification, positioning and centrality results; 2, class consistency screening is executed according to the instance-level basic features, and high-quality representative instance samples are obtained; step 3, constructing a category orthogonal space by using the instance sample and a vision-language model to form enhanced category-level semantic features; 4, generating corresponding phantom features based on the memory bank, and providing the phantom features and the instance samples to the step 5 for use; 5, multi-layer domain alignment is executed at the image level, the instance level and the category level, and unified optimization is completed; and 6, performing open set rejection judgment on the low-confidence and low-affinity targets in a reasoning stage, and outputting a final detection result. According to the method, three key problems of high-quality instance selection, cross-domain category discrimination enhancement and missing category completion are cooperatively solved on the premise of not depending on target domain labeling and not increasing the overhead of a reasoning stage.

The present invention relates to a weakly supervised video anomaly detection method based on dynamically selecting comparison instances for learning, belonging to the field of video anomaly detection. The method first constructs an instance feature learning module based on contrastive learning to encourage the aggregation of normal instances while separating abnormal instances, thereby promoting the distinction between normal instances and abnormal instances; then, a dynamic instance selection module is constructed, which identifies the most likely normal instance candidates with the smallest feature quantity in abnormal videos; finally, a feature domain adaptation module is constructed to further enhance the separability between normal and abnormal instances through domain adaptation learning. The method of the present invention enables the model to learn the features of normal segments in abnormal videos, thereby more precisely distinguishing normal from abnormal; and the method of the present invention fully weakens the negative impact of scene similarity on the model through contrastive learning and domain adaptation learning, thereby improving the anomaly detection performance.

The application discloses a multi-tensor parallel instance selection method and device, equipment and a storage medium, which are corresponding solutions. In the solutions, stage sub-request selection is performed between inference instances with fixed tensor parallelism, and the tensor parallel configuration of the inference instance does not need to be dynamically changed for a single request. Moreover, candidate cost is calculated based on service pressure after placement and delay target occupation, so that the inference instance selection considers the delay target risk of the current stage sub-request and the service pressure of the allocated instance set. In addition, a stage-related state prediction model is adopted, and a unified candidate cost calculation method is adopted, so that the instance selection deviation caused by different evaluation logics in different inference stages can be reduced.

The disclosed embodiments provide a website data processing method, apparatus, device, and storage medium. The method comprises: obtaining website instance data, the website instance data including multiple website instances; evolving an initialized particle swarm using a competitive particle swarm algorithm and the website instance data, wherein the particles in the particle swarm represent an instance selection scheme for the website instance data; and performing instance selection in the website instance data based on the evolved particle swarm to obtain a target instance subset, which is used to train a classification model for phishing websites. Thus, the competitive particle swarm algorithm optimizes the instance selection scheme in the website instance data, and selects an instance subset from the website instance data according to the optimized instance selection scheme for training the classification model for phishing websites, thereby improving the quality of the training data for the classification model and the accuracy of phishing website detection based on the classification model.

According to a method, at a given instance of a cluster of instances of at least one service, at least one monitored instance is selected from the cluster of instances according to a selection criterion such that each instance of the cluster of instances is selected as a monitored instance by at least one other instance of the cluster of instances. The given instance is caused to detect an operational status of the at least one monitored instance. If the operational status indicates that one of the at least one monitored instance is failed, the operational status of the failed monitored instance is provided to a centralized controller for the cluster of instances. Through the solution, the detection of instance liveness can be executed by individual instances symmetrically in a distributed and self-management manner.

The invention discloses a face image detection method based on distributed optimization instance selection. The face image detection method is applied to a work and coordination node network. A work node carries out multi-objective evolutionary optimization with classification precision and compression rate as targets on a local sample; the coordination node aggregates the population by adopting direct splicing or based on a conflict instance strategy according to an iteration process and executes global evolution; variation parameters are adjusted by counting the instance frequency of the Pareto optimal solution set, and feedback information is generated to guide subsequent iteration of the working nodes; and finally, selecting an optimal SVM model for detection. Through a distributed coevolution and feedback mechanism, redundant samples can be effectively eliminated under the condition that data are not concentrated, and the recognition efficiency and classification accuracy of face detection are improved.

In a computing-aware traffic steering (CATS) network, such as those conforming to an IETF proposal, a service contact instance for a requested service is selected based on at least cache metrics associated with data cached at one or more egress nodes of the CATS network. In some embodiments, the selection is also based on compute and network metrics. In one implementation, the selection is based only on cache metrics unless that selection is too costly in terms of compute and / or network load. In that case, the selection is based on the compute and network metrics. In this way, cache metrics are prioritized over compute and network metrics as long as the cache-based selection is not too costly.

Techniques for configuring and creating a compute instance are disclosed. A system may receive a request to launch a compute instance where the compute instance defined by a configurable attribute, The request comprises one or more user-specified criteria for the configurable attribute without including a specific value for the configurable attribute. The system determines a set of candidate values for the configurable attribute. The system selects the specific value for the configurable attribute from the set of candidate values for the configurable attribute, based on the one or more user-specified criteria. The system stores the specific value in association with the configurable attribute; and launches the compute instance based on the system-selected specific value for the configurable attribute of the compute instance.