4 results about "Time dependency" patented technology

This invention discloses a rubidium atomic clock frequency adaptive prediction method and system based on LSTM network, belonging to the field of time and frequency technology. The invention includes the following steps: Step 1. Data acquisition; Step 2. Filtering and denoising preprocessing; Step 3. Normalization processing; Step 4. LSTM model training and deployment; Step 5. Frequency prediction; Step 6. Online model adaptation. This invention employs a Long Short-Term Memory (LSTM) network, a special type of recurrent neural network, which can effectively learn the complex time dependencies and noise patterns in rubidium atomic clock time and frequency data. The inherent gating mechanism of the LSTM model makes it adept at capturing long-term dependencies in time series, thus enabling high-precision prediction of short-term frequency fluctuations. Through an online fine-tuning mechanism, this invention allows the LSTM model to continuously adapt to the individual drift and aging characteristics of a single rubidium atomic clock, achieving precise optimization for each clock and model, significantly improving the practicality and long-term stability of the method.

Embodiments of the present application provide a transaction behavior identification method, device, equipment, storage medium and program product, relating to the fields of artificial intelligence and financial technology. The method comprises: acquiring time series data corresponding to a transaction behavior, the time series data comprising transaction feature vectors of a plurality of time steps; performing feature extraction on the transaction feature vectors through a self-attention mechanism to generate global features, the global features containing global dependency relationships; inputting the global features into a bidirectional time series modeling module to extract local time dependencies of the global features through forward and reverse sequence modeling to generate bidirectional hidden states; and performing classification processing on the bidirectional hidden states to obtain an abnormal probability of the transaction behavior being abnormal. The method of the present application significantly improves the identification capability of hidden abnormal transaction behaviors, solves the performance deficiency problem caused by single models in traditional methods, and achieves high-precision, low-false-alarm-rate abnormal transaction behavior detection effects.

The application discloses a fault root cause positioning method and system based on PLC log deep mining, which decomposes original PLC logs into continuous data streams and discrete event streams through a heterogeneous data shunting mechanism. A time series convolution network is used to capture the time series dynamic changes of high-frequency analog data, and a Transformer encoder is used to extract the semantic logical association of asynchronous discrete events, thereby avoiding the loss of time series accuracy and semantic confusion caused by forced time alignment. On this basis, a multi-level attention fusion mechanism is introduced to preserve the characteristics of each mode while realizing deep interaction and alignment of cross-modal features, and a unified feature representation containing rich space-time dependencies is constructed. The method effectively solves the technical problem of deep fusion of heterogeneous asynchronous data in industrial scenes, and realizes accurate positioning of fault root causes and visualization of fault propagation path.

An adaptive optimization system (100) for continuous integration / continuous delivery (CI / CD) that utilizes the dynamic generation of parallel build graphs and the resolution of runtime dependencies, comprising: a change detection module configured to continuously monitor one or more version control systems and automatically detect changes to the source code, configuration files, build scripts, or related artifacts in real time or near real time; a dependency analysis module that is functionally coupled with the change detection module, wherein the dependency analysis module is configured to identify and resolve both static and runtime dependencies between a variety of software components, services, and tasks by analyzing source code structures, metadata, execution environments, and configuration parameters; a dynamic graph generation module configured to create a directed acyclic execution graph for each pipeline instance based on identified dependencies, where the graph includes a variety of nodes representing executable tasks, including build, test, integration, validation, and deployment operations, and a variety of edges representing runtime-determined dependency relationships between the tasks; a scheduling engine configured to process the directed acyclic execution graph and dynamically determine an optimized execution plan by identifying independent and interdependent tasks, enabling fine-grained parallel execution of tasks by resolving dependency constraints at runtime, and distributing said tasks across available computational resources based on one or more parameters, including resource availability, execution priority, historical execution data, and predicted task duration; a distributed execution framework configured to execute scheduled tasks across one or more heterogeneous computing environments, including cloud-based systems, virtualized infrastructure, and local servers, wherein the distributed execution framework further provides dynamic load balancing, fault tolerance through automatic task retry and reassignment, and result caching to avoid redundant computations; a learning and optimization module configured to capture, store, and analyze historical pipeline execution data, including task execution times, resource utilization patterns, error events, and dependency resolution results, and further configured to apply machine learning or statistical modeling techniques to continuously refine pipeline planning decisions, improve prediction accuracy, and optimize subsequent pipeline executions; wherein the system (100) is further configured to perform incremental pipeline execution by selectively executing only those tasks affected by the detected changes and their dependent tasks, thereby reducing redundant processing steps, minimizing the overall execution time and improving computational efficiency; where the system (100) enables adaptive, scalable and efficient CI / CD pipeline orchestration through real-time dependency resolution and dynamic generation of parallel build graphs.