39 results about "Computer resources" patented technology

A routing circuit for an integrated circuit is configured to access a set of resources organized according to a topology having multiple dimensions. The routing receives a request for a particular resource in the set of resources, the request including an address that includes a first set of bits and a second set of bits, the topology having a first dimension with n routing options (where n is not a power of two) and a second dimension with m routing options. The routing circuit determines a first routing choice and a second routing choice for the first dimension and the second dimension by performing respective modulo-n and div-n operations on a value formed by the address including the first set of bits and the second set of bits. The routing circuit then activates one or more selection signals according to the first routing choice and the second routing choice, the one or more selection signals usable to cause the particular resource to be selected in response to the request.

The application provides an AI intelligent calculation platform reasoning resource scheduling method and system, relates to the technical field of computer resource management and task scheduling, and obtains task load information of a to-be-reasoned task, memory allocation records of an AI intelligent calculation platform in a preset time window, and a retransmission event timing sequence of a bus data link layer; obtains the discrete entropy of each computing node through a Shannon entropy formula according to the memory allocation records; counts the retransmission times of the retransmission event timing sequence in a sliding time window to generate a communication congestion index of each computing node; determines a weight coefficient according to the task load information, constructs a weighted bipartite graph, and determines a matching edge set that satisfies the most matching edges and the smallest sum of edge weights in the weighted bipartite graph by using a Hungarian algorithm, so as to be used for resource scheduling of the to-be-reasoned task. The problem of throughput decline caused by serious memory fragmentation and communication interference in the large model concurrent reasoning scene is solved.

A system includes a memory storing data associated with fuel dispensing operations and a processor operably coupled with the memory. The processor determines that a fuel dispensing operation is anomalous based at least in part on performance of the fuel dispensing operation by determining a measured volume per unit time parameter associated with fuel dispensed from a fuel dispensing terminal and comparing the measured volume per unit time parameter with a threshold volume per unit time parameter. The processor determines that the measured volume per unit time parameter is less than the threshold volume per unit time parameter, wherein the measured volume per unit time parameter being less than the threshold volume per unit time parameter indicates that the fuel dispensing terminal is manipulated to dispense fuel at a flow rate lower than an expected flow rate. In response to determining that the fuel dispensing operation is anomalous, the system deploys computer resources configured to determine a subsequent anomalous fuel dispensing operation before completion of the subsequent anomalous fuel dispensing operation.

The application discloses a kind of variable scale performance prediction methods of fuel cell system combined with neural network, construct the proton exchange membrane fuel cell model combined with neural network algorithm, realize the variable scale performance prediction of proton exchange membrane fuel cell system, and the proton exchange membrane fuel cell model includes air supply module, hydrogen supply module, water-thermal management module, battery stack module and neural network fitting module;Actual output power of fuel cell system is calculated;After all module combination connection, it is constituted into a variable scale numerical simulation model of proton exchange membrane fuel cell system combined with neural network algorithm.The application combines the advantages of neural network and mathematical modeling, uses limited amount of data resources, computer resources and time cost, completes high-precision simulation modeling of proton exchange membrane fuel cell, to provide guidance for the application of proton exchange membrane fuel cell in aviation field.

No method has been proposed to convert a computationally universal resource state into a quantum universal resource state, and thus it has been necessary to construct the respective resource states individually. According to a method of the present disclosure, a computationally universal resource state, once constructed, can be used to newly construct a quantum universal resource state. Also, the method of the present disclosure is applicable to any computationally universal resource state allowing for the execution of H and CCZ gates, and thus also has the versatility of also being applicable to as-yet undiscovered computationally universal resource states.

The application belongs to the technical field of computer, and provides a virtualization platform exception detection method based on hardware performance counter. The method comprises the following steps: 1) collecting hardware event count of the part occupied by the guest in the computer resource in the sample running process, and dumping the preprocessed data to the host; 2) reading the data stored in the host in step 1) to train the random forest classification model, calculating the feature importance of different hardware events according to the feature importance, analyzing and comparing the importance of each event feature on the decision of the random forest classification model to perform feature screening, 3) performing data collection of step 1) again according to the hardware events screened in step 2), training the final random forest classification model, and obtaining the virtualization platform exception detection model in the process. 4) The virtualization platform exception detection model is used to detect whether the target program will produce abnormal influence in the running in the virtualization platform, so as to judge that the program is a malicious program.

The application relates to the field of message exchange, and discloses a message identification transmission method, equipment and a storage medium. The method comprises the following steps: an upper computer control system reads a target protocol corresponding hardware characteristic value, generates a characteristic database according to the target protocol corresponding hardware characteristic value; an ACL rule is generated based on the characteristic database; port data is read, the port data is mapped to the ACL rule, a mapped ACL rule is generated, and the mapped ACL rule is sent to a hardware exchange system; the hardware exchange system receives the mapped ACL rule; when an input message of a port is listened to, the input message is subjected to identification matching processing according to the mapped ACL rule, and a matched message is obtained; and the upper computer control system distributes the matched message to a corresponding target port according to a preset information distribution algorithm. In the embodiment of the application, programmable message identification filtering and uploading are realized at the hardware end, upper computer resources are released, and the overall performance and stability of the equipment are improved.

This paper presents a method for real-time self-optimization in database management systems (DBMS). The adaptive on-the-fly sampling technique described in this paper estimates database content statistics, which a machine learning (ML) model can use to predict configuration settings that save computing resources such as execution time and storage space. In an embodiment, the computer repeatedly samples the database content until a dynamic convergence criterion is met. In each iteration of a series of sampling iterations, a subset of rows from the database table is sampled, and the estimate of the database table's content statistics is adjusted based on the sampled subset of rows. Upon detection of dynamic convergence, the machine learning (ML) model immediately or ultimately predicts optimal values ​​for the configuration settings used for the DBMS based on the content statistics estimate.

The present application relates to the field of satellite navigation technology, and discloses a kind of unmanned plane satellite navigation anti-deception detection method based on control response, and the turning maneuver flight of unmanned plane is controlled by remote control instruction, whether the change of satellite navigation positioning track angle and unmanned plane body heading angle in the process of maneuver flight is consistent is detected, and then whether satellite navigation positioning data is judged to be deceived.The present application can realize effective detection and identification on whether satellite navigation positioning data is deceived interference by using existing navigation equipment and computer resources on unmanned plane, without increasing high-precision inertial navigation or other autonomous navigation equipment, which reduces system configuration requirements and cost.The present application method is available throughout the process in the process of unmanned plane air cruising, not only can be applied to detecting and finding that satellite navigation positioning data is deceived interference when unmanned plane flies into satellite navigation interference area, but also can be applied to detecting and confirming that satellite navigation positioning data restores normal and is not deceived interference when unmanned plane flies out of satellite navigation interference area, with strong engineering applicability.

Methods and systems are presented for providing a data storage optimization system. The data storage optimization system determines a data storage schema for storing data in one or more data storages. The data storage optimization system then monitors computer resources usage efficiency associated with accessing the data stored in the one or more data storages. When it is detected that the computer resources usage efficiency is below a threshold, the data storage optimization system determines modification recommendations for modifying the data storage schema. The data storage optimization system causes an implementation of the modification recommendations, and monitors the improvements to the computer resources usage efficiency.

To provide a content video playback program, a content video playback device, a content video playback method, a content video data generation program, and a content video data generation device capable of playing back a video of a suspended matter in the atmosphere such as a cloud, fog, a halo, a thermal, a gas, or the like at high quality with few computer resources, a video playback processing section that plays back compressed video data generates video data at high reproducibility by only performing a simple arithmetic processing of moving raster cell image data by a raster vector and performing an interpolation operation processing of luminance.

The application relates to the technical field of computer resource management, in particular to a server resource scheduling system for a high-density computing environment. The system acquires scheduling data of each dimension in real time, including task resource data; according to the difference between the actual value and the predicted value in the scheduling data of the dimension at the current time and the task resource data, the resource supply priority is acquired; according to the resource supply priority, the difference between the actual value and the predicted value of the preset specified historical task resource data of the same resource demand type of each task, the resource adjustment degree is acquired; based on the task resource data and the resource adjustment degree of each task at the current time, the server resources of the high-density computing environment at the current time are scheduled and processed. The application can accurately acquire the resource adjustment degree of each task at the current time, is beneficial to accurately adjusting the predicted resources of each task at the current time, and effectively improves the efficiency and stability of task execution.

A method and a system for interacting with one or more computer resource assets at a location. The system includes a processor, a storage, and an interface suite including a first interface configured to communicate with a user device and a second interface configured to interact with at least one computing resource asset at the location. The process is configured to receive a call, via the first interface, from the user device, the call being directed to a destination phone number, provide a conversational avatar by a machine learning platform based on the destination phone number, operate the conversational avatar by the machine learning platform to communicate with the user device and interact with a user of the user device using conversational language, generate by the machine learning platform a command to perform an operation or a function, and send, based on one or more words or sounds spoken during the interaction with the user, the command to a computing resource asset at the location to perform the operation or the function.

The application belongs to the technical field of computer resource scheduling, and provides a multi-level computer resource multi-target dynamic scheduling method and system under algorithm-network fusion, comprising: obtaining a task request of a user; based on the obtained task request, constructing a global resource-network state distribution view; according to the parameters of the task request and the global resource-network state distribution view, taking minimizing task completion delay, optimizing load balancing and minimizing energy consumption as the target, generating a task-to-computing resource node allocation scheme and a task data transmission path planning scheme through a multi-target optimization scheduling model; according to the generated allocation scheme and path planning scheme, distributing the task to the corresponding computing resource node, and monitoring the task execution state and resource load in real time; when it is detected that the load of the computing node or the network link exceeds the preset threshold, triggering a task migration mechanism to complete the multi-target dynamic scheduling of the multi-level computing resource under algorithm-network fusion.

The application discloses a server GPU computing power intelligent allocation method for large model training, and relates to the technical field of computer resource management. The method comprises the following steps: S1: determining the dependency relationship between each stage in the large model research and development workflow according to the large model research and development workflow defined by a directed acyclic graph, and obtaining a corresponding resource demand portrait matrix; S2: setting a dynamic priority resource reservation pool according to the resource demand portrait matrix, and generating a corresponding resource supply curve; S3: determining the short-term predicted demand corresponding to each task according to the actual resource consumption and the dynamic resource demand curve of each task on the critical path in the large model research and development workflow, comparing the short-term predicted demand with the resource supply curve, and dynamically adjusting the dynamic priority resource reservation pool. The application can adapt to the fluctuation and uncertainty of the training task operation, guarantee the progress of the critical path, and flexibly handle the excess resource demand.

A wafer measurement method and apparatus, an electronic device and a storage medium. The method comprises: acquiring a reference image obtained by scanning a reference wafer; on the basis of the reference image, acquiring positional information of reference dies in the reference wafer, so as to obtain a die distribution map; and, on the basis of the die distribution map, performing morphology measurement on dies to be measured in a wafer to be measured, so as to acquire morphology measurement data of the dies to be measured. The solution helps to improve the measurement efficiency of wafers, and reduce the occupation of computer resources by a large amount of measurement data.

The present application relates to the technical field of computer resource management, in particular to a device dynamic running state analysis method and system for multi-task scenarios, comprising: capturing fine-grained resource fluctuation data under multi-task concurrency through a hardware abstraction layer, and constructing a hardware resource monitoring matrix accordingly; inputting the hardware resource monitoring matrix into a preset dynamic weight distribution model to evaluate hardware real-time loss and performance redundancy, and generating a hardware health degree image; dynamically adjusting resource allocation parameters of the current environment according to the image, wherein the parameters include cache mapping strategies and memory bandwidth allocation ratios; determining whether the load data in the hardware resource monitoring matrix reaches a preset bottleneck threshold, and if so, triggering a cross-core resource live migration strategy based on the adjusted parameters to realize smooth migration of task flows among heterogeneous computing cores. The present application realizes hardware state perception and resource parameter closed-loop adjustment, effectively solves multi-task conflicts, and improves execution efficiency.

Embodiments of the invention are directed to systems, methods, and computer program products for a secure distributed machine learning activity system using distributed ledger technology. The invention comprises an AI-ML model development de-centralized system that provides a secure mechanism which give secure provision to entities to develop AI-ML models in a distributed environment. The system allows the release of AI-ML model components, programs, binary files, and the like in distributed host system infrastructure in secure manner. Therefore, optimizing computer resources for various requirements, such as image processing or the like that may be performed on other secure mechanisms across the secure distributed network. In this way, distributing the AI-ML model across multiple devices across the secure distributed network.

This invention discloses a method for positive / negative identification in medical dialogues based on cue learning, relating to the field of medical dialogues. The method includes the following steps: designing a cue template based on the characteristics of cue learning and positive / negative identification in medical dialogues. The cue template includes the original input text x and a special token; copying the entity [Ent] mentioned in the original input text x that needs to be predicted into the cue text, adding conjunctions designed according to the task characteristics before and after the entity [Ent], and adding the identifier [MASK] as a special token to be predicted, thus completing the cue template design; designing a vocabulary and using the vocabulary and cue template to train a pre-trained language model to obtain a cue learning-based discriminative model. This invention solves the problems of existing discriminative methods failing to fully utilize the prior knowledge of the pre-trained language model, ignoring the independent relationship between context and entities, and consuming large amounts of computer resources.

Techniques regarding the management of computational resources based on clinical priority associated with one or more computing tasks are provided. For example, one or more embodiments described herein can regard a system comprising a memory that can store computer-executable components. The system can also comprise a processor, operably coupled to the memory, that executes the computer-executable components stored in the memory. The computer-executable components can include a prioritization component that can prioritize computer applications based on a clinical priority of tasks performed by the computer applications. The clinical priority can characterize a time sensitivity of the tasks. The computer-executable components can also include a resource pool component that can divide computational resources across a plurality of resource pools and can assign the computer applications to the plurality of resource pools based on the clinical priority.

This invention relates to an intelligent computing power scheduling method based on dynamic knowledge graphs, belonging to the field of computer resource scheduling technology. The method includes: constructing and updating in real-time a dynamic knowledge graph that integrates computing power resources, tasks, network, and environmental information; inputting the graph into a decision model based on graph neural networks and deep reinforcement learning, generating a scheduling strategy through graph representation learning and multi-objective optimization; executing the strategy and monitoring feedback to form a closed-loop optimization. This invention utilizes a dynamic knowledge graph as a unified digital twin of computing power, overcoming the shortcomings of traditional scheduling methods such as single resource modeling, lack of relational understanding, and delayed response. It achieves global perception, intelligent matching, and dynamic optimization of heterogeneous computing power resources, significantly improving resource utilization, scheduling efficiency, and decision interpretability.

The application discloses a robot control method and device based on escalator detection, which comprises the following steps: collecting a to-be-detected image in real time by using a camera configured by a robot, processing the to-be-detected image by using a Sobel operator, a preset binary algorithm and image morphological operation, determining a plurality of gradient connected regions in the to-be-detected image, generating a minimum circumscribed rectangle frame by calculating whether the area of each gradient connected region is greater than a set threshold, obtaining position information of the minimum circumscribed rectangle frame, and controlling the robot to perform corresponding operation according to the position information of the minimum circumscribed rectangle frame. By adopting the embodiment of the application, the position of the escalator can be directly positioned, data processing is reduced, computer resources are avoided from being wasted, the accuracy of detection is improved through various processing of the to-be-detected image.

This invention relates to noise reduction methods, and more particularly to a lightweight multi-axis Transformer single-channel noise reduction method. It can fully extract the latent time-frequency features of speech signals. A multi-head dynamic local self-attention module is employed to efficiently extract local features. The proposed method has fewer network parameters and lower computational cost, while remaining competitive with state-of-the-art methods in terms of speech signal quality and intelligibility. It can fully extract the latent time-frequency features of speech signals, effectively reducing computer resource consumption. Hint blocks are used to help the model better learn frequency feature information.

The application provides a satellite visibility simulation method and device, wherein the satellite visibility simulation method comprises the following steps: generating a simulation time point set according to a preset simulation time length and a preset simulation step; grouping a to-be-simulated ground station and a to-be-simulated satellite based on a set grouping strategy, and constructing at least two simulation object groups, wherein the at least two simulation object groups perform visibility simulation in parallel, each simulation object group comprises at least one to-be-simulated ground station and at least one to-be-simulated satellite; selecting a target satellite and a target ground station from a target simulation object group, performing visibility simulation on the target satellite and the target ground station based on the simulation time point set, and determining a visibility simulation result of the target satellite for the target ground station. In this way, the grouping strategy can be customized, the to-be-simulated ground station and the to-be-simulated satellite are grouped, parallel processing is adopted, computer resources are maximally utilized, and the efficiency of the visibility simulation is greatly improved.

This application provides a method, apparatus, computer-readable storage medium, electronic device, and computer program product for controlling data transfer between memory locations, relating to the field of data processing technology. The method includes: determining the intersection of a j-th feature set and a (j+1)-th feature set to obtain high-frequency features, where the j-th feature set is the feature input into the model during the j-th time period of training the target model, and the (j+1)-th feature set is the feature input into the model during the (j+1)-th time period of training the target model; controlling the high-frequency features to be stored in a first memory location during both the j-th and (j+1)-th time periods; determining a first feature based on features other than the high-frequency features in the j-th feature set; controlling the transfer of the first feature from the first memory to a second memory location; and controlling the transfer of a second feature from the (j+1)-th feature set (excluding the high-frequency feature set) to the first memory location. This application embodiment can save bandwidth and facilitates the rational use of computer resources.

A method of authenticating a user device in providing access to a computer resource, the method includes identifying a device fingerprint record stored in an access log. The method includes produce, based on the device fingerprint record, a digital signature includes one or more session characteristics. The method includes determining, by a processing device from the digital signature, a root signature pattern associated with the one or more session characteristics. The method includes identifying an access request for a computer resource as an unauthorized access based on the device fingerprint record and the root signature pattern.

The application discloses a dynamic self-adaptive heterogeneous cluster resource scheduling method and device based on machine learning, equipment and storage medium, relates to the technical field of computer resource scheduling, and comprises the following steps: obtaining static hardware indexes of each node in a cluster, normalizing the static hardware indexes, and obtaining a node static image; performing aggregation processing based on the node static image to obtain a resource pool computing power score; extracting resource consumption characteristics of a job according to historical operation data to obtain a job image score; and determining a target resource pool of the job according to the resource pool computing power score and the job image score, so as to realize intelligent matching and scheduling between the job and the resource pool, and improve the matching precision of the job and the node computing power and the resource utilization efficiency in the heterogeneous cluster environment.

Embodiments herein describe a processor system that includes an integrated, adaptive accelerator. In one embodiment, the processor system includes multiple core complex chiplets that each contain one or processing cores for a host CPU. In addition the processor system includes an accelerator chiplet. The processor system can assign one or more of the core complex chiplets to the accelerator chiplet to form an IO device while the remaining core complex chiplets form the CPU for the host. In this manner, rather than the accelerator and the CPU having independent computer resources, the accelerator can be integrated into the processor system of the host so that hardware resources can be divided between the CPU and the accelerator depending on the needs of the particular application(s) executed by the host.