9 results about "Reliable computing" patented technology

The invention relates to a secure and trusted computing system based on real-time virtualization of an aneuhua OS (Operating System). The secure and trusted computing system comprises three program modules and a virtual machine manager, wherein the virtual machine manager provides a high-efficiency virtualization technology, adopts a Type1 type virtualization architecture, realizes a lightweight virtual machine manager at a bottom layer, and runs on a hardware platform; the trusted computing core is specially responsible for running an embedded operating system and is used for executing a secure and sensitive trusted computing task; the Linux core is used for operating user service processing and providing user experience and service support; the security isolation and monitoring module is used for realizing security isolation between the two trusted computing cores and the Linux core; the security authentication and authorization module is used for performing identity authentication and authorization on the user and the application program; the problems that real-time guarantee of tasks is difficult to realize and application requirements in the technical field cannot be met in a current system security extension technology are solved, and a secure and credible operation environment during multi-core heterogeneous hybrid deployment and credible computing is realized.

The application discloses a multi-modal graph fusion driven spatial transcriptome region identification method, and belongs to the field of biomedical informatics and computational biology. The method comprises the following steps: step 1, data acquisition; step 2, data processing; step 3, multi-modal adjacency matrix generation; step 4, differentiable multi-modal graph structure fusion; step 5, variational graph autoencoder training; and step 6, clustering. By constructing a spatial domain identification framework based on multi-modal graph fusion and variational autoencoder, the application significantly improves the accuracy, continuity and biological interpretability of spatial transcriptome clustering analysis, effectively solves the deficiencies of existing methods in multi-modal fusion, graph structure optimization and feature discriminability, and provides a more reliable computing tool for in-depth revealing of tissue spatial heterogeneity in the fields of brain science, tumor microenvironment analysis and other frontier biomedical researches.

This invention provides a method and apparatus for measuring computing power on an intelligent computing cloud platform based on GPU computing power consumption and inference token values. It relates to the fields of intelligent computing centers, smart computing centers, computing infrastructure, and smart computing cloud technologies, and includes the following steps: Step S1, collecting task data, GPU runtime data, and model and engine parameters during inference on the intelligent computing cloud platform; Step S2, extracting first feature information, second feature information, and third feature information from the task data, GPU runtime data, and model and engine parameters; Step S3, performing token fitting computing power calculation based on the first feature information, GPU model, and third feature information to obtain a first computing power consumption value; Step S4, performing GPU computing power consumption benchmark calculation based on the first, second, and third feature information to obtain a second computing power consumption value; Step S5, determining a reliable computing power consumption value based on the first and second computing power consumption values. This invention can significantly improve the accuracy of computing power measurement on intelligent computing center cloud platforms.

The application discloses a method and system for judging single-phase grounding fault of a power distribution network, and relates to the field of power distribution network fault judgment. The judgment system provided by the application adopts a starting algorithm for monitoring changes in fault component mutation variables in real time. After starting, the judgment system calculates relevant parameters of first-stage transient variables at the moment of fault and relevant parameters of second-stage steady-state variables after the fault is stabilized. After multi-criterion judgment and comprehensive fusion, reliable on-site judgment of single-phase grounding is realized. The method is simple and reliable, and has high calculation speed, thereby realizing on-site rapid judgment.

This application relates to the field of natural language processing technology, and more particularly to a method for solving mathematical problems using a small-parameter, large-language-model approach and its applications. The method involves a teacher model that structurally decomposes the mathematical problem, providing a reasoning path for the student model. Simultaneously, an external sandbox executor handles all numerical computation tasks, avoiding computational biases and reasoning errors that may arise from greedy decoding, thus achieving reliable computation for small-parameter models in solving mathematical problems. The aim is to address the problem of unreliable mathematical problem-solving caused by greedy decoding in long-term reasoning processes using small models. Without requiring model retraining, this method significantly improves the logical consistency, computational accuracy, and overall robustness of small-parameter models in mathematical reasoning tasks, making it suitable for applications such as mathematical problem solving, enhanced mathematical reasoning, and related intelligent problem-solving systems.

The invention discloses a drug target interaction multi-task prediction method based on multi-modal characteristics. According to the method, drug multi-dimensional structure features and drug target text semantic features are comprehensively utilized, and a multi-modal feature embedding framework is constructed. A multi-nuclear magnetic relation convolution layer is designed, a magnetic Laplacian matrix and a frequency domain graph filter are introduced, and a DTI multi-classification prediction model MFFGCN based on a graph convolution neural network is constructed. And a DTI natural language explanation text generation task is further proposed, a DTI natural language explanation text generation model EXDTI is utilized to formalize drug target interaction prediction into natural language explanation text generation, and readable mechanism description and relation explanation are generated. The method has excellent performance in DTI multi-task joint prediction, has good cold start adaptability, and provides an efficient and reliable calculation tool for new drug research and development and candidate screening.

The invention relates to the technical field of cross-domain resource scheduling, and particularly provides a cross-domain resource pool dynamic optimization and service rapid deployment method and device, comprising: (1) a first layer: a cross-domain resource pool dynamic optimization main process, Spring state machine drive; (2) a second layer: a computing power transaction trusted execution sub-process which is driven by a block chain and LiteFlow; (3) a third layer: a service containerization rapid deployment sub-process which is driven by K8s Java Client + LiteFlow; and (4) process instance management. Compared with the prior art, the real-time and high-reliability computing power service requirements can be met.

The application discloses a drug target interaction multi-task prediction method based on multi-modal features. The method comprehensively utilizes drug multi-dimensional structure features and drug target text semantic features to construct a multi-modal feature embedding framework. By designing a multi-core magnetic relationship convolution layer, introducing a magnetic Laplace matrix and a frequency domain graph filter, a DTI multi-classification prediction model MFFGCN based on a graph convolutional neural network is constructed. Furthermore, a DTI natural language explanation text generation task is proposed, and a DTI natural language explanation text generation model EXDTI is used to formalize the drug target interaction prediction into natural language explanation text generation, and readable mechanism explanation and relationship explanation are generated. The method performs excellently in the DTI multi-task joint prediction, has good cold start adaptability, and provides an efficient and reliable computing tool for new drug research and development and candidate screening.

The invention discloses a localized environment-based cross-department comprehensive supervision platform and a data processing method. The system architecture comprises an infrastructure layer, a data layer, a support layer, an application layer, a display layer and a security processing module. The infrastructure layer provides safe and reliable computing storage network resources by adopting a creative cloud and an e-government affair external network; the data layer stores and manages supervision data through a supervision basic library and a supervision thematic library; the support layer provides unified tool support and data support capabilities. According to the invention, a localized unified platform is constructed, the problems of cross-department data sharing and business collaboration are solved, interconnection and on-demand sharing, efficient collaboration and accurate differentiated supervision of supervision data are realized, the supervision efficiency and accuracy are improved, and the whole-process data security is guaranteed through multi-level security measures.