5results about How to "Reduce deployment" patented technology

The application belongs to the technical field of computing resource scheduling, and provides an edge device computing resource scheduling system and method based on artificial intelligence, aiming to solve the scheduling failure problem caused by the mismatch between edge device computing release prediction and real state, comprising: extracting AI predicted computing release time and real release time from historical scheduling failure data in the past period, calculating the deviation, and outputting the deviation distribution set through DBSCAN clustering with time stamp and deviation as features, analyzing the relevance of the deviation and the corresponding time stamp, constructing a time-computing deviation coupling model, comparing the current time range deviation output based on the model with the real deviation, calculating the compensation time to optimize the AI prediction when there is a scheduling risk, and generating a scheduling scheme in combination with the task demand and the real-time state of the device.

This invention relates to the field of vehicle collision detection technology, and specifically discloses a vehicle collision detection method and system based on an improved dual-stream convolutional network, comprising the following steps: Step S1: Real-time acquisition of an original video stream containing the target vehicle via an onboard camera; Step S2: Preprocessing the original video stream to extract spatial frame sequences and optical flow frame sequences; Step S3: Inputting the spatial frame sequences into the spatial flow branch of the improved dual-stream convolutional network. This vehicle collision detection method and system based on the improved dual-stream convolutional network achieves a significant improvement in detection accuracy and extremely low end-to-end processing latency, providing sufficient warning and response time for active safety systems. Its dual-stream parallel processing and adaptive feature fusion design effectively balance computational efficiency and feature integrity, enabling the system to maintain a low false alarm rate in complex driving scenarios and clearly distinguish between emergency braking and real collision risks.

This application discloses a method for correcting misjudgments in high-speed multi-type event detection based on LoRA, relating to the field of intelligent transportation technology. The method includes: acquiring real-time event information on the highway, identifying it using the YOLO algorithm, and outputting the original preliminary event detection results and environmental parameters; standardizing the preliminary detection results and extracting semantic and scene features of the event targets from the preliminary detection results to obtain standard preliminary detection results; performing secondary verification and misjudgment correction using a LoRA-optimized large model based on the standard preliminary detection results to obtain the event detection results; uploading the event detection results to the road segment central monitoring platform, and retaining misjudged, missed, and new scene samples for iterative optimization. This application aims to resolve the contradiction between the low reliability of event detection in complex highway environments and the inability to deploy high-precision large models at low cost and high efficiency under existing hardware conditions.

This application relates to the field of performance testing technology, providing a simulation testing method, apparatus, device, and storage medium. The method is applied to an electronic device and includes: receiving an interface call request sent by a test system, the interface call request being used to request a target service system to execute a target business function; processing the interface call request using a simulation system within the electronic device to generate simulation results, the business processing logic of the simulation system being consistent with the business processing logic of the target service system; and finally sending the simulation results to the test system. This method not only reuses the business processing logic of the target service system without relying on reverse engineering, thus effectively reducing development cycle and adaptation costs, but also effectively avoids the testing limitations caused by the closed nature of the target service system in related technologies, achieving full-process testing independent of the target service system.

This invention discloses an indoor data acquisition and positioning method, positioning system, and storage medium based on a neural network algorithm. It employs a multi-terminal collaborative architecture to achieve a closed-loop positioning process for small-scale indoor scenes. The system uploads indoor planar images via a front-end device and performs scale calibration to establish a mapping relationship between pixel coordinates and physical space. In acquisition mode, it acquires multi-source signals in real time and expands the effective sample. After back-end data processing and storage, the algorithm extracts signal features through a neural network, performs adaptive weight allocation and feature fusion, and trains to generate a fingerprint database model. In positioning mode, it performs signal matching and coordinate calculation based on this model, and finally, the positioning results are visualized and displayed on the front end. This invention requires no dedicated acquisition equipment or base station deployment, and has the advantages of high positioning accuracy, low deployment cost, convenient maintenance, and user-friendly operation, making it suitable for various small-scale indoor positioning needs.