9results about How to "Reduce operational overhead" patented technology

This invention discloses a lidar depth completion method based on hierarchical minimum surface reconstruction, relating to the fields of computer vision and image processing technology. The method includes: performing depth value inversion and morphological dilation on a sparse depth map to obtain a scene dilated depth map and a full-resolution effective mask; then downsampling to obtain a coarse-scale scene dilated map and a coarse-scale mask; using an iterative convolution kernel of the Laplacian operator to obtain a coarse-scale filled map; upsampling the coarse-scale filled map to obtain an upsampled depth map, and then fusing it with the scene dilated depth map to obtain a fused depth map; locating all remaining holes in the fused depth map using connected component analysis, and calculating the mean depth of the effective pixels within the annular pixel band around each remaining hole; using this mean depth to fill the corresponding remaining holes to obtain a hole-free depth map; and after global Gaussian blurring, performing a depth value inversion operation to obtain a scene dense depth map, thereby achieving high-precision 3D reconstruction.

The application provides a list component state synchronization method, system, medium, equipment and program product, relates to the terminal application technical field, and includes the following steps: when a scrolling operation is listened to, an offset is obtained from a global state manager before a sub-item mark is visible and is added to a dynamic linkage pool; a component controller is registered to join the linkage pool to receive a broadcast; when the broadcast is received, a current driver pointer is added to the sub-item through the global state manager; and the scrolling is performed in combination with the offset and the driver pointer. The application can avoid the inconsistency problem of rendering and data binding timing when a virtual list is high-speed scrolled, accurately mark an event source through a driver pointer, block an event loop of multi-way linkage without a state lock, simplify state management and control, avoid deadlock, and comprehensively improve the use experience of the virtual list in a complex scene.

This invention belongs to the field of lithium-ion battery management and provides a lithium-ion battery management method and system based on a visual large language model. The method involves acquiring battery operation sampling data and running a pre-built battery physical model. Based on the battery operation sampling data and the battery physical model, state estimation is performed. Based on residual window statistics, instantaneous residual extreme values, and operating condition anchor points, it is determined whether a battery management event has been triggered. When an event is triggered, a multi-trajectory residual panel plot is generated, forming a structured numerical summary. A query vector is constructed based on the current event, and similar historical cases are recalled from a pre-built task-partitioned enhanced knowledge base. The residual panel plot, structured numerical summary, operating condition anchor points, and historical cases are used as multimodal inputs, and the visual large language model is used to determine the task route. The corresponding execution branch is then entered based on the task route. This invention ensures real-time state estimation and avoids large-model inference on every frame of high-frequency data.

The invention discloses a multi-spectrogram lightweight acoustic scene classification method and device for auditory auxiliary equipment, equipment and a storage medium. The method comprises the following steps: firstly, acquiring a hearing-aid front-end environment audio signal to be processed, converting the hearing-aid front-end environment audio signal into a Mel spectrum feature map, a constant Q transformation spectrum feature map and a first-order difference spectrum feature map, and then stacking the Mel spectrum feature map, the constant Q transformation spectrum feature map and the first-order difference spectrum feature map to form a multi-channel spectrum feature map containing complementary time-frequency information as model input; then differential shallow layer feature extraction is carried out through an asymmetric multi-stream module, and depth features are extracted on a low-power-consumption computing platform by using a lightweight backbone network with a ghost bottleneck module and coordinate attention as cores; a spectral morphology module, a frequency band attention module and a channel weight balance fusion module are introduced, and multi-dimensional enhancement and dynamic weighting are carried out on the depth features; and finally, outputting an audio scene classification result by the classifier. According to the method, the classification performance of complex acoustic scenes can be improved while the model parameter quantity and the operation power consumption can be remarkably reduced.

The application discloses a mouth shape retrieval model optimization method, system and device based on time sequence context modeling, which is applied to the technical field of data processing. Multi-frame audio feature coding is completed through a time sequence window, one-dimensional convolution and weighted fusion, so that audio representation with time sequence consistency is generated. A retrieval preference model is constructed in combination with historical retrieval data, time sequence smoothing constraints and state transition rules are formed. A retrieval sorting model is built relying on a multi-objective optimization function, candidate screening is completed by comprehensively matching multi-dimensional matching items and superimposing various types of penalty constraints. Meanwhile, boundary adaptive weight regulation and time sequence stable reasoning strategies are added, and dynamic optimization is performed for pronunciation boundary, high-risk and low-confidence scenarios. The whole scheme runs in a frame-by-frame streaming mode, upgrades traditional single-frame optimal retrieval to time sequence context constraint optimal retrieval, effectively solves the mouth shape jitter problem, and improves the overall time sequence stability and output naturalness.

The present disclosure provides a blockchain-based Web3.0 access authentication method and a spatial information network system. A first satellite access node determines an access time interval. When the access time interval and the credit level of a mobile user both satisfy a preset fast access condition, the mobile user and the spatial information network system interact based on a historical session key. When the access time interval and / or the credit level of the mobile user does not satisfy the preset fast access condition, the first satellite access node and the mobile user perform two-way trust verification. When the mobile user and the first satellite access node both pass the trust verification, the client and the first consensus ground node obtain a session key. Thus, the access convenience of high-frequency compliant users is considered, and the invalid occupation of network computing power is reduced through differentiated verification strategies, achieving a balance between spatial information network security protection and access efficiency, and computing power optimization.

The application discloses a complex layout document image tamper detection method and system, and relates to the technical field of image processing and computer vision. Aiming at the multi-scale tamper detection problem of complex layout personnel file images, a credible layout analysis network is proposed. The network first extracts pixel gradient direction distribution features as multi-view inputs by using a differential operator through an image detail feature enhancement module; then, with the help of a twin encoder, multi-level features of visual layout and gradient distribution are extracted through a multi-scale attention mechanism; then, after passing through a multi-level dual-flow fusion module, heterogeneous modal features are deeply fused, and global context modeling decoding is completed in combination with a matrix decomposition mechanism; finally, a tamper detection head outputs a fine-grained multi-class mask, realizes joint optimization of layout element recognition and tamper state discrimination, and improves the accuracy and robustness of detection with the mutual constraint of the two. The application significantly improves the multi-scale tamper detection precision, and simultaneously has excellent layout analysis performance and running efficiency.

The application discloses a plunger pump wear fault detection method based on pressure-temperature layered triggering and physical prior mask self-attention, and belongs to the technical field of hydraulic system state monitoring and fault diagnosis. The method comprises the following steps: collecting vibration, pressure and temperature multi-source signals, and setting a default low power consumption of a main controller; realizing layered early warning and deep diagnosis awakening based on four dynamic characteristics of pressure and temperature and an abnormal proportion of a sliding window; performing synchronous compression wavelet transform on the vibration signal and performing temperature-pressure analytical linear real-time correction, block encoding and vibration Token sequence generation; generating an additive physical mask guided self-attention calculation based on a fault frequency band prior, and extracting wear sensitive features; comparing with a working condition grouping fault feature library to determine the fault type and grade. The application runs through the whole chain of signal correction, feature fusion and diagnosis decision with physical knowledge, and under the lightweight design of a model parameter quantity less than 500k, realizes a variable working condition diagnosis accuracy of 94.2% and an early wear false negative rate of 3.5%.

This invention discloses a noise-resistant biomedical signal processing method, system, storage medium, and program product based on latent topological evolution. The invention acquires one-dimensional time-series biomedical signals and static auxiliary features, which are then fused and dimensionality-reduced using a dual-stream encoder to generate a global latent feature vector located in the Lie algebra tangent space. Geometric random perturbations are injected into the tangent space through an evolutionary dynamics system to generate an effective evolutionary velocity vector. A three-dimensional topological state orthogonal matrix is ​​generated using a single-step deterministic analytical mapping that avoids numerical orthogonalization iteration. The physiological signal state prediction results are output after classification and decoding, and control signals are generated. This invention avoids numerical iterative calculations through analytical mapping, significantly reducing computational load while maintaining accuracy. It is suitable for real-time edge monitoring and high-concurrency cloud processing scenarios, and can effectively eliminate sensor displacement artifact interference.