321 results about "Distance threshold" patented technology

The invention provides an industrial visual anomaly recognition method, system and device based on multi-modal feedback and a medium, and belongs to the technical field of industrial visual detection.The method comprises the steps that a production line video stream is collected in real time, an ROI is automatically segmented, a picture sequence is generated, features of a set dimension are extracted, and the features of the set dimension are extracted; comparing a preset dynamic distance threshold with a feature library, and preliminarily identifying an abnormal image; a cue word of a detection requirement is constructed, the cue word and abnormal related information are input into the multi-modal large model, and a determined abnormal image is output; using the determined abnormal image to construct a data set to train a target detection model, and adjusting the learning rate in the training process; and inputting pictures captured in an industrial scene into the deep learning model, the multi-modal large model and the target detection model in sequence to obtain a recognition result, feeding back the recognition result to a user for confirmation, adding the recognition result to the data set, and optimizing training of the target detection model. According to the invention, accurate identification of abnormal images in industrial production is realized, and the identification efficiency is high.

The invention relates to the technical field of safety monitoring, and particularly discloses an operation safety distance management method based on laser radar point cloud data, and the method comprises the steps: generating a dangerous point cloud set based on an initial three-dimensional point cloud model of a complete field environment; performing coordinate transformation on the point cloud data currently collected by the three-dimensional laser radar equipment based on the rigid body transformation matrix to obtain current point cloud data; registering the current point cloud data with the initial three-dimensional point cloud model and identifying all independent dynamic targets; determining a danger approaching trend of each independent dynamic target based on the motion prediction trajectory of each independent dynamic target; determining a dynamic safety distance threshold value of each dangerous dynamic target based on the danger approaching trend and the response delay of each independent dynamic target and the additional safety distance of the corresponding dangerous source area; triggering a corresponding alarm mechanism based on the dynamic safety distance threshold and the distance between the point cloud set of each independent dynamic target and the dangerous point cloud set; and the overall safety of a working site is improved.

A method, computer program product, and computing system for processing a dataset of query-answer pairs. Synthetic variations of queries are generated and each of the synthetic variations of queries are mapped to a corresponding answer from the dataset. An embedding dataset is generated by transforming the synthetic variations into synthetic query embeddings and the queries into query embeddings. A first set of embeddings is defined for storage in a semantic cache and a second set of embeddings are defined and are not stored in the semantic cache. A separate distance threshold is assigned to each embedding of the first set of embeddings and a pairwise distance between each query and the synthetic variations is determined. Distance thresholds for respective pairwise distances between a query and synthetic variations of the query are generated. Subsequent queries are processed using the semantic cache and the distance thresholds.

A wireless transmit receive unit (WTRU) is configured to receive configuration information for reporting Global Navigation Satellite System (GNSS) assistance information (AI). The configuration information comprises a reporting trigger threshold that is at least one of a distance threshold or a time offset threshold. The WTRU determines that the reporting trigger threshold is exceeded and reports GNSS AI. The GNSS AI comprises at least one of a GNSS validity duration or a GNSS acquisition time. The GNSS validity duration comprises an indication of a time duration associated with a validity of a GNSS acquisition, an indication of a time duration associated with expiration of the GNSS acquisition, or a WTRU location associated with the GNSS acquisition. The GNSS acquisition time comprises a time to acquire a GNSS position.

Aspects of the present disclosure are directed to triggering object transitions between near-field and far-field regions in an artificial reality environment. For example, the near-field region can be within arm's length for the user, while the far-field region can be greater than arm's length from the user. Objects can be displayed within these regions such that the user can interact with the objects in the artificial reality environment. A field manager can cause a displayed object to transition from the near-field region to the far-field region and / or from the far-field region to the near-field region. The field manager can compare sensed user movements to one or more trigger criteria (e.g., distance threshold(s), velocity threshold(s), etc.) to trigger transition of an object between field regions.

The invention relates to a method and a device for generating a video with a body and electronic equipment. The method comprises the following steps: analyzing a task instruction and initial environment observation data, generating a key operation step sequence and an associated object set thereof, and constructing a three-dimensional physical constraint graph; generating an initial action video sequence based on the coding condition; in response to single-frame action execution, calculating a spatial error index, and if the object contact distance deviation, the trajectory collision probability or the physical constraint violation value exceeds a preset threshold, triggering the space-time diffusion model to generate a correction frame based on the current physical constraint graph; in response to the completion of the key operation steps, verifying the semantic matching degree of the generated result and the task target, and if the key object attribute loss or the operation logic error is detected, regenerating the task operation step sequence and the physical constraint graph; and updating the object position, the distance threshold and the motion feasible region in the physical constraint graph, and inputting the space-time diffusion model. According to the method, the problems of physical consistency deficiency, error accumulation and semantic understanding splitting are solved.

The invention discloses a method for detecting gluing defects and a storage medium thereof, and relates to the technical field of gluing detection.The method comprises the following steps that S10, a line laser sensor scans a gluing workpiece to obtain a gluing workpiece point cloud, and scans an unglued standard workpiece to obtain a standard template workpiece point cloud; s20, fitting to obtain a reference plane of a workpiece point cloud of a gluing workpiece point cloud standard template, and intercepting a gluing to-be-detected area point cloud and a template to-be-detected area point cloud; s30, point cloud registration is carried out on the point cloud of the gluing to-be-detected area and the point cloud of the template to-be-detected area; s40, performing point distance threshold judgment on the point cloud of the to-be-detected gluing area after registration, and performing separation to obtain a pure colloid point cloud; and S50, judging that the point cloud of the pure colloid in the region is unqualified according to the fact that the cross section width and the cross section area of the point cloud of the pure colloid are smaller than a preset threshold value. According to the invention, the gluing defect can be detected more accurately, and the efficiency is high.

The present application relates to the field of information retrieval, and in particular relates to a data processing method, an electronic device, a readable storage medium, and a program product. In the method, when a query result of a query vector needs to be searched in a constructed graph index, neighbor nodes of at least some nodes among multiple nodes included in the graph index satisfy at least one of the following: the included angle between two vectors obtained by subtracting a node from any two neighbor nodes of the node is greater than or equal to a first angle threshold value, the distance between any two neighbor nodes of the node is greater than or equal to a first distance threshold value, and the number of neighbor nodes of the node within a preset space range is smaller than a first number. Thus, the neighbor nodes of the nodes in the constructed graph index are relatively dispersed in space, and the problem that a query result falls into a local optimum due to being unable to find nodes at a certain portion of space during a node-based neighbor node search process, because the nodes are densely distributed at a certain position, is avoided.

The invention provides a GIS buffer generation method and system based on fuzzy semantics and geographic constraints, and belongs to the technical field of geographic information systems.The method comprises the steps that fuzzy descriptors, membership values and geographic entity types are input into a pre-trained language-space mapping model, and basic distance parameters are obtained; querying a spatial database based on the geographic entity keywords, obtaining geometric features associated with the geographic entities, and calculating feature lengths corresponding to the geometric features; correcting the basic distance parameter based on the intention direction, the membership value, the geographic entity type and the feature length expressed by the fuzzy description word to obtain a geographic distance threshold; generating an initial two-dimensional buffer polygon based on the geographic distance threshold and the spatial geometric features of the geographic entity; and querying a digital elevation model to obtain topographic data based on the initial two-dimensional buffer region polygon, and generating a three-dimensional buffer region curved surface through a gradient sensitive interpolation algorithm. According to the invention, the accuracy of generating the GIS buffer area is improved.

The invention discloses a multi-unmanned aerial vehicle target tracking method based on cross-view collaboration, which is suitable for robust target monitoring in a dynamic scene. The method comprises the following steps: firstly, establishing a spatial mapping relation among visual angles of multiple unmanned aerial vehicles through feature point matching and projection transformation; after each unmanned aerial vehicle node independently executes deep learning-based target detection, converting a detection frame center point coordinate of an auxiliary view angle into a main view angle coordinate system, and calculating an Euclidean distance between the detection frame center point coordinate and a main view angle detection result; a main visual angle potential leak detection area is identified by setting a dynamic distance threshold value, and a local high-sensitivity re-detection module is triggered based on leak detection confidence; and finally, realizing space-time tracking of observation data by adopting a single-view target tracking algorithm. According to the invention, the problem of leak detection caused by single-view-angle shielding is effectively solved through a cooperative verification mechanism of a cross-view-angle detection frame center point space relationship, and the continuity and reliability of target tracking in an unmanned aerial vehicle view angle complex environment are remarkably improved while the real-time performance is ensured.

The invention discloses a proxy model auxiliary evolution method based on two-stage adaptive switching and Voronoi niche. The method comprises the steps of generating an initial sample by adopting optimal Latin hypercube sampling, obtaining a real fitness value through simulation, constructing an initial training data set, and setting an initial iteration counter k and an evaluation budget threshold value; training a proxy model based on the current data set, and executing evolutionary algorithm optimization by using the proxy model to obtain a current optimal individual; judging two stages according to an iteration counter k and a distance threshold value; the development execution stage comprises the following steps: evaluating the real fitness and updating a data set; the exploration execution stage comprises the steps of multi-modal approximate detection, Voronoi niche division, multi-modal collaborative search, real fitness evaluation and data set updating; judging a termination condition and outputting a result; according to the method, three core technologies of an adaptive stage switching mechanism, multi-modal approximate detection and Voronoi niche division and multi-extremum collaborative filling are creatively integrated, so that the defects of insufficient global exploration, low local development precision and poor convergence efficiency of a traditional method in a high-dimensional multi-modal expensive optimization problem are effectively overcome; and the solving efficiency and reliability of a complex and expensive optimization problem are remarkably improved.

The invention relates to the technical field of cloud computing and information security services, and particularly discloses a network security and data hosting integrated cloud service system and method, and the method comprises the steps: obtaining a multi-dimensional behavior data flow of a user, and generating a user feature vector; inputting the user feature vector into an incremental clustering algorithm, calculating the distance between the feature vector and a clustering center, performing user classification according to a distance threshold, and generating a user type tag; calculating a user reputation score based on the historical behavior statistical data of the category to which the user belongs; a sliding window algorithm is adopted to collect a data packet arrival time interval sequence, a jitter value in a window is calculated, a jitter value at the next moment is predicted, the number of packet loss in the window is counted, and a packet loss rate estimation value is calculated; and inputting the user type label, the reputation score, the jitter prediction value and the packet loss rate estimation value into a QoS decision engine. According to the invention, the problem of poor high-value user experience caused by unreasonable resource allocation is solved.

The invention relates to the technical field of intelligent blasting, and discloses an automatic blasthole arrangement method for a slow slope deep hole step and related equipment, and the method comprises the following steps: obtaining topographic data of a target step, and determining an initial blasthole layout for the target step according to the topographic data; determining whether a first included angle between the designed slope bottom line of the target step and the natural slope surface line is within a preset range or not; in response to the first included angle within the preset range, determining that the slope surface of the target step is a gentle slope surface; a main blast hole closest to the gentle slope in the initial blast hole layout is determined, a first intersection point of the main blast hole and a designed slope bottom line and a second intersection point of the natural slope surface line and the designed slope bottom line are determined, and the resistance line distance between the first intersection point and the second intersection point is calculated; whether the resistance line distance exceeds a preset distance threshold value or not is determined, and it is determined that a supplementary blast hole is additionally formed between the main blast hole and the natural slope line in response to the fact that the resistance line distance exceeds the preset distance threshold value. Therefore, it can be guaranteed that the blasting effect is better.

The invention relates to the technical field of path planning, and discloses a mechanical arm path planning method and system based on RRT *, and the method comprises the steps: sampling in a map space to obtain a sampling point, finding a node closest to the current sampling point from an expansion tree, determining the generation direction of a new node in combination with an artificial potential field method, and expanding to generate the new node; judging whether the new node collides with an obstacle or not, if not, adding the new node into the extension tree, and otherwise, re-sampling; constructing a father node according to whether collision occurs or not, performing rewiring, judging whether the distance between a new node and a target node in the extension tree is smaller than a preset distance threshold value or not and whether collision does not occur on a connection path between the two points or not, if yes, ending generation of the new node, and if not, performing resampling; and connecting the initial node, all the new nodes and the target node to obtain an initial planning path, removing redundant nodes in the initial planning path, and performing smoothing processing to obtain a final planning path. According to the invention, environment adaptability, efficiency and path quality can be improved.

The invention relates to an address processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining a positioning address corresponding to a positioning coordinate; if the first text similarity value of the positioning address and the order address is smaller than a similarity threshold value, searching a plurality of candidate positions, wherein the distances between the candidate positions and the positioning coordinates are smaller than a first distance threshold value; obtaining a candidate address corresponding to each candidate position; according to the second text similarity value of each candidate address and the order address, determining a plurality of recommendation addresses in each candidate address, and displaying each recommendation address; and in response to the selection operation, determining a target address in each recommended address. By adopting the method, the auditing difficulty of authenticity verification through field evidence collection can be reduced, and the labor cost is saved.

The invention provides a point cloud data plane detection method and apparatus, an electronic device and a readable storage medium. The method comprises the steps of obtaining a to-be-merged plane pair in point cloud data; if the two planes in the plane pair are determined to have a significant adjacent relationship, judging whether the two planes are effectively separated by an adjacent straight line between the two planes or not, otherwise, judging whether the two planes can be combined or not according to the adjacent points of the two planes; if not, the two planes are combined, and otherwise, the distance between the two planes is calculated; if the distance is smaller than a preset distance threshold value, combining the two planes, otherwise, determining interference points between the two planes and judging whether the number of the interference points meets a preset condition or not; wherein the preset condition is that the ratio of the number of the interference points to the length of the adjacent straight line is smaller than a preset proportion or the number of the interference points is smaller than a preset point number threshold; and if not, combining the two planes, otherwise, not processing. The plane detection efficiency and accuracy can be improved, and the method is suitable for point cloud data with extremely narrow planes.

The invention provides a time-space prediction method and device for settlement along a railway. The prediction method comprises the following steps: identifying an unstable target region based on monitoring data obtained by monitoring a railway line; obtaining time sequence settlement data of each monitoring point in the unstable target area, and performing noise reduction processing by using the optimal noise reduction model to obtain the time sequence settlement data of each monitoring point after noise reduction processing; obtaining an adjacent matrix and a degree matrix based on a preset distance threshold and the distance between every two monitoring points in the unstable target area; and based on the time sequence settlement data, the adjacency matrix and the degree matrix of each monitoring point after noise reduction processing, utilizing a GCN-LSTM prediction model, and adopting a rolling prediction method to carry out advanced prediction on the time sequence settlement data of each monitoring point to obtain an advanced prediction set of each monitoring point. According to the method, the time sequence settlement data of the monitoring points are predicted in advance by constructing the GCN-LSTM prediction model with the space-time sequence coupling characteristics, and the method has the advantage of being high in prediction precision.

Disclosed are systems and techniques for proximity detection using a wearable sensing device. An example method can include obtaining sensing data based on one or more wireless signals, the sensing data comprising at least one of a proximity measurement and a distance measurement; determining, based on the sensing data, a spatial relationship between a device associated with a user and a source of the one or more wireless signals; determining whether the spatial relationship satisfies a proximity condition associated with a distance threshold; and based on a determination that the spatial relationship satisfies the proximity condition associated with the distance threshold, triggering a sensory alert via one or more output components.

The invention discloses a logistics electronic fence sampling point accurate analysis system based on big data, relates to the technical field of electric digital data processing, and aims to solve the technical problems that existing logistics sampling points are large in positioning error, low in data acquisition efficiency and difficult to realize dynamic accurate management and control. The setting module is used for setting electronic fence position information, a fence range and an electronic fence early warning rule; the sampling point data dynamic analysis and deviation degree calculation module is used for sampling electronic fences of each driver and each cargo; the data processing center is used for receiving, storing and transmitting data information among the modules; and a user terminal. According to the method, the dynamic iteration of the early warning rule is realized, the early warning time threshold and the distance threshold can be continuously optimized, the problem of insufficient sampling point analysis accuracy caused by a static rule is fundamentally solved, and the timeliness and adaptability of electronic fence early warning are improved.

While at a first location, a user equipment (UE) connected to a core network via a non-terrestrial network (NTN) receives a distance threshold, before the UE enters a power saving mode, PSM. While in the PSM, the UE initiates the procedure for reporting a current UE location information when a current UE location has exceeded the distance threshold relative to the first location.

The invention provides a civil aviation airport obstacle real-time detection method and system based on a visual scheme, and belongs to the technical field of civil aviation airport safety monitoring, and the method comprises the steps: obtaining multi-source sensing data in real time, including distance data of a millimeter wave radar, and image contrast data and humidity data of a visible light camera unit; a radar weight coefficient Wr and an image weight coefficient Wi are calculated based on the humidity data, Wr is in positive correlation with the humidity value, and Wi is in negative correlation with the humidity value; fusing the distance data, the image contrast data and the weight coefficient to calculate a real-time visibility value, and limiting the visibility value within a preset effective range; switching a neural network quantization mode according to the visibility value; and when the visibility value is greater than a first preset distance threshold value, activating a low-precision quantization mode and executing channel pruning. The problems of poor meteorological adaptability and unbalanced resource precision are solved.

The invention discloses a ship pier anti-collision early warning method and system based on a laser radar, and relates to the field of ship collision early warning, and the method comprises the steps: judging the movement condition of a ship based on GPS data and imu data, and collecting the three-dimensional point cloud data in front of a ship driving route when detecting that the ship moves towards a collision object; converting the three-dimensional point cloud data from a radar coordinate system to a ned coordinate system, and filtering and segmenting the three-dimensional point cloud data after coordinate conversion to obtain a point cloud cluster of the collision object; based on the distance from each point in the point cloud cluster to the ship contour, a preset distance threshold value and a preset number threshold value, executing multi-level collision risk assessment so as to output an early warning signal of a corresponding level; according to the method, the three-dimensional point cloud data is filtered and segmented, noise point clouds are effectively eliminated, the point cloud cluster representing the collision object is accurately extracted, and refined and graded early warning of the collision risk is further realized through a multi-stage risk assessment mechanism.

The invention discloses an SCD file processing method and device based on a knowledge graph, terminal equipment and a storage medium, and belongs to the field of file verification. The method comprises the steps that an SCD file of a transformer substation system is acquired; based on a preset analysis mode, analyzing the SCD file to generate a virtual terminal table and a soft pressing plate list; calculating a similar distance value according to the virtual terminal table and the soft pressing plate list; judging whether the similar distance value is smaller than a distance threshold value or not; and if yes, performing information visualization on the SCD file based on a knowledge graph model. And if not, marking that the SCD file is abnormal. Therefore, by implementing the method and the device, the problem of low SCD file verification efficiency in the prior art can be solved.

The application discloses a vehicle abnormal gathering determination method and device, electronic equipment and storage medium, and relates to the technical field of Internet of Vehicles. The method comprises the following steps: acquiring a gathering radius, a first distance threshold, a second distance threshold, a quantity threshold and position data of a plurality of vehicles; determining a plurality of candidate position data from the plurality of position data; determining abnormal position data according to the vector distance between the plurality of candidate position data, wherein the vector distance between the abnormal position data is not less than the second distance threshold; acquiring selected position data in a region corresponding to each abnormal position data; and in response to the number of the selected position data being not less than the quantity threshold, determining vehicle abnormal gathering information, wherein the gathering position in the vehicle abnormal gathering information is the position indicated by the abnormal position data, and the gathering quantity is the total number of the selected position data. The method can obtain the vehicle abnormal gathering condition.

Disclosed are systems and techniques for proximity detection using a wearable sensing device. An example method can include obtaining sensing data based on one or more wireless signals, the sensing data comprising at least one of a proximity measurement and a distance measurement; determining, based on the sensing data, a spatial relationship between a device associated with a user and a source of the one or more wireless signals; determining whether the spatial relationship satisfies a proximity condition associated with a distance threshold; and based on a determination that the spatial relationship satisfies the proximity condition associated with the distance threshold, triggering a sensory alert via one or more output components.

The invention provides a stacker-reclaimer anti-collision method and system based on multi-modal data fusion, and relates to the technical field of stacker-reclaimers, and the method comprises the steps: obtaining stacker-reclaimer parameters, radar point cloud data, image data and UWB distance data; aggregating the radar point cloud data to obtain point cloud features of each target cluster; inputting the image data into a target detection network, and outputting visual features of each target image; performing feature matching based on each point cloud feature and each visual feature to obtain the category, confidence, center point, radial speed and distance of each target; obtaining a UWB distance based on the category and the UWB distance data; obtaining a final distance and an updated confidence coefficient based on the distance and the UWB distance; and obtaining a dynamic safety distance threshold based on the parameters of the stacker-reclaimer, and obtaining the collision probability of each target based on each target parameter of the dynamic safety distance threshold. According to the method, the collision probability can be accurately obtained through multi-source data fusion and a safety distance dynamic adjustment mechanism.

This application provides an AI-based method for playing information on electronic class signs. Based on the course type, it adaptively searches for the corresponding anomaly detection distance threshold from a pre-set mapping table. It receives the pose features of multiple students wearing electronic school badges associated with the target class, transmitted within the previous first time period. The received pose features are clustered to obtain cluster center features. If the distance between any student's pose feature and the cluster center feature is greater than the anomaly detection distance threshold, a short video image containing the student is obtained. The course type and the student's short video image are input into a pre-trained model for determining abnormal classroom behavior. If abnormal behavior is detected, the electronic class sign in the classroom area displays the student's personal information and anomaly alerts.

The invention discloses a key agent discrimination method fusing future motion prediction information. The key agent discrimination method is characterized by comprising the following steps: selecting a true value of a key agent; constructing a self-vehicle multi-modal feature and an agent feature fused with future motion prediction information; and building a key agent selector model. The method can utilize the deep neural network model to adaptively learn and discriminate the key agent in a complex traffic environment, fully considers the possible interaction condition of a long time sequence in the future, breaks through the short-sight bottleneck of a traditional rule-based discrimination method, and improves the accuracy and rationality of an interaction determination result. According to the method, the key agent is judged by using the time window and the dynamically adjusted distance threshold value, a judgment method in a real driving process is highly simulated, and the causal reasoning capability of a key obstacle selector model is improved, so that powerful support is provided for subsequent trajectory planning.

The application relates to a control method and device of an ultrahigh pressure collision device, and relates to the technical field of energy saving and environmental protection.The method comprises the following steps: in response to a starting signal, spraying data is acquired; a distance threshold value, a predicted intersection surface and a reference recoil interval are determined according to the spraying data; a light spot image is collected based on the predicted intersection surface; a light spot position and a light spot distance are read from the light spot image; if the light spot distance is greater than the distance threshold value, a correction parameter is determined according to the light spot position; the angle of a spraying nozzle is adjusted based on the correction parameter; a preset spraying instruction is executed, a recoil force is collected, and the relationship between the recoil force and the reference recoil interval is judged; if the recoil force falls into the reference recoil interval, the angle adjustment is completed, and a collision heating operation is executed. The application has the effects of reducing production energy consumption cost and improving energy saving efficiency.

The present application relates to power industry safety domain boundary fitting technology, in particular to a kind of high-dimensional static security domain boundary fitting method of power system, considering system generator output constraint, node load value sampling is carried out, through power flow calculation, the sample in the security domain is filtered out, and initial sample set is formed.Boundary sample search algorithm is proposed, for each sample in initial sample set, find a sample in the security domain, a sample outside the security domain, and satisfy the distance between the two is less than the set distance threshold value.The data in the boundary sample set in the original power injection space is converted to new three-dimensional feature space by deep neural network model.Extract the boundary in feature space by the weighted tilt decision tree algorithm based on information gain ratio, and evaluate the boundary performance, select the optimal boundary.The method can realize the fitting of high-dimensional boundary of power system security domain, and reduce the error with actual boundary.