8results about How to "Lower confidence" patented technology

The invention discloses an aerocar mode conversion method, system and device and a storage medium, and the method comprises the steps: S1, obtaining image data, point cloud data and radar data of the surrounding environment of an aerocar, and carrying out the target detection; s2, fusing target detection results of the image data and the point cloud data; s3, performing confidence correction on the fusion result by using a target detection result of the radar data; and S4, according to the correction result, judging whether the surrounding environment meets the requirement of mode conversion or not, if the judgment result is that the surrounding environment is not shielded, sending out a mode conversion permission signal, and if the judgment result is that the surrounding environment is shielded, sending out a mode conversion forbidding signal. The detection accuracy of the surrounding environment is improved, and stable mode conversion of the hovercar is achieved.

This invention relates to the field of electronic clock technology, specifically disclosing a method and system for calibrating the timing accuracy of electronic clocks based on data fitting. The method includes: based on the timing characteristics of the electronic clock, performing temperature difference mapping on the extreme value offset of the jitter amplitude distribution set to solve for the sensorless temperature estimate; combining the nominal period of the real-time pulse segment sequence of the electronic clock, matching and calibrating the temperature estimate to establish a temperature-offset mapping table; performing temperature difference mapping again on the current pulse segment to obtain the real-time temperature estimate, and obtaining the interval reference offset based on the interval positioning of the mapping table; configuring a compensation step size for the jitter amplitude according to the reference offset, generating a dynamic compensation step size, and adjusting the phase of the accumulated count value to obtain the single-cycle refresh value; using this as a correction reference, performing timing calibration on subsequent pulses of the electronic clock, and outputting the final working signal of the electronic clock; this invention can improve the timing accuracy and temperature tracking response capability of electronic clocks under conditions without an external temperature sensor.

A dual-engine collaborative retrieval and bidirectional real-time interaction method and system. Step one: vector retrieval generates candidate set and expands locally in graph atlas; Step two: relationship path encoding attention fusion generates reconstructed query vector; Step three: vector semantics, graph structure and cross-engine cross joint confidence iteratively propagate along the graph to convergence; Step four: cross-engine neighborhood consistency index (CECI) detects semantic drift and structural noise, and false consensus detection calculates consensus reliability index (CRI) through embedded vector attribution decomposition to identify false consensus of two engines simultaneously overestimating the same entity and decouple calibration; Step five: dynamic adjustment of dual-engine collaboration mode in interview stage; Step six: full-duplex communication protocol (WebSocket) establishes retrieval-feedback closed loop; Step seven: graph-vector mutual calibration eliminates hub bias and popularity bias. Under 2156 queries, F1 rises from 82% to 95%.

The present application discloses an emotion recognition method, device, terminal equipment and computer-readable storage medium, the method comprising: extracting the face area of ​​each frame image as a training sample based on an input continuous frame video sequence; inputting the training sample into a three-dimensional convolutional neural network model to obtain a global feature map of each video frame sequence; dividing the global feature map into blocks, using the generated local feature map and the global feature map as feature blocks, extracting one-dimensional features of each feature block and inputting them into the three-dimensional convolutional neural network model, outputting an initial predicted emotion score, and determining an initial weight of each feature block, determining a corresponding target weight according to the initial weight of each feature block; using the target weight to weight the initial predicted emotion score to generate a target predicted emotion score. The present application combines a three-dimensional convolutional neural network and feature map blocks to enhance the confidence of the unobstructed part, improve the accuracy and efficiency of emotion recognition, and has a wider range of applications.

This application provides an AI-powered intelligent assessment method and system for environmental quality anomaly events. It identifies multiple environmental atomic events carrying spatiotemporal tags from multi-source environmental monitoring data; constructs an environmental causal knowledge graph using these environmental atomic events as nodes and the causal relationships between events as directed edges; calculates the credibility weight of each causal directed edge based on the spatiotemporal proximity and causal test values ​​between events; uses the anomaly event corresponding to the environmental quality anomaly event query command as the target node; and generates at least one candidate causal chain by backtracking from the environmental causal knowledge graph; selects the target causal chain based on the credibility weights between adjacent nodes in each candidate causal chain; and outputs the event explanation information corresponding to the target causal chain. By constructing an environmental causal knowledge graph that integrates spatiotemporal proximity constraints and statistical causal tests, this application can dynamically locate pollution sources and infer causal chains, thereby reducing causal misjudgments caused by spurious correlations and noise.

The embodiment of the present application provides an object positioning method, device, electronic device and storage medium, the method includes: determining a first detection area and a second detection area within a preset range around a vehicle; determining multiple vehicle-side position information based on a target detection algorithm; detecting the first detection area based on a target detection algorithm and a first obstacle confidence threshold, and detecting the second detection area based on a target detection algorithm and a second obstacle confidence threshold through a roadside device to obtain multiple roadside position information; matching multiple vehicle-side positions with multiple roadside position information to obtain multiple matching combinations; inputting the first matching position information and the second matching position information in the multiple matching combinations into a position prediction model, performing position prediction processing, and obtaining multiple target position information corresponding to multiple target objects. The object positioning method provided by the embodiment of the present disclosure can improve detection efficiency and reduce missed detection and false detection.

This invention discloses an acoustic imaging device and method for detecting pavement voids, belonging to the field of non-destructive testing technology for roads. The device includes an excitation module, an accelerometer, a multi-aperture reconfigurable microphone array module, a synchronous acquisition module, a sound field feature construction module, a multi-source fusion module, a geometric inversion module, and a coordinate registration and imaging output module. The excitation module applies a transient impact to the pavement under test. The accelerometer acquires the acceleration signal at the excitation point, and the multi-aperture reconfigurable microphone array module acquires multi-channel near-field sound pressure signals around the excitation point. The sound field feature construction module determines the impact initiation time and impact energy based on the acceleration signal at the excitation point, and performs time alignment, energy normalization, and feature extraction on the multi-channel near-field sound pressure signals. This invention improves the stability and quantitative characterization capability of pavement under-slab void detection, and is suitable for detecting under-slab voids in cement concrete pavements, composite pavements, and bridge deck paving.