201 results about "Location aware" patented technology

Approaches presented herein provide for identification of sound from a sound source relative to an array of microphones of a potentially unknown configuration using, in part, differences in the audio signals received by the microphones. In at least one embodiment, audio signals are captured using an array of microphones and audio features are extracted from those signals. The audio features can be processed using a first neural network to generate a feature vector representing a spatial location of an audio source with respect to the plurality of microphones, where the spatial location is inferred based on audio differences and independent of an availability of information indicating a physical configuration of the plurality of microphones. The feature vector can be provided to a task-specific model to perform at least one audio-related task based in part on the spatial location.

The invention discloses a handwritten mathematical formula recognition method based on attention coverage and position perception, which comprises the following steps: constructing a position perception module, and generating a character position map through weak supervised learning; a multi-scale attention coverage module is constructed, and attention calculation in a Transform decoding architecture is optimized; and fusing the feature map and the position sensing map, and inputting the fused feature map and the fused position sensing map into a Transform decoder to generate a LaTeX sequence. Character position information is explicitly extracted through the position sensing module, and the understanding of the model on a complex mathematical structure is enhanced; the attention drifting is reduced by a multi-scale attention coverage mechanism; the training cost is reduced and the model performance is improved by adopting a counting label weak supervised learning mode.

The invention relates to the technical field of artificial intelligence and the technical field of equipment fault prediction and detection, and discloses a fault prediction and detection method based on an intelligent model, and the method comprises the steps: obtaining and preprocessing the historical data of a sensor, and generating time series data; pre-training the time sequence data to generate a pre-training model; performing fine tuning on the pre-training model based on the attention mask of position perception to generate a fine-tuned model; acquiring current data of the sensor, and generating prediction data; and analyzing the deviation between the predicted data and the actual data, and triggering an alarm signal when the deviation exceeds a preset threshold value. According to the method, the time series data features are learned through pre-training, multi-segment prediction is performed in combination with an attention mechanism, and the accuracy of fault prediction is improved; the fine-tuned model adapts to different working conditions, and the generalization ability of the model is enhanced; alarm is triggered through deviation analysis, intelligent monitoring of the equipment state is achieved, and real-time performance and reliability are improved.

A system can receive an untrusted onboard announcement message from a remote computer. The system can, based on the untrusted onboard announcement message, initiate an onboarding service policy to verify a device location claims policy associated with the remote computer. The system can receive an indication of a remote access controller hardware component of the remote computer, wherein the indication is of verifying a network port authentication policy applicable to determine whether a port-based network access control protocol certificate hostname that is associated with the remote computer matches an entity attestation token attribute extensible authentication protocol-transport layer platform certificate hostname of the remote access controller hardware component to determine a network authentication status. The system can determine whether device onboard location is successful based on a device location verification policy status and the indication.

Systems and methods are provided for implementing a customizable and animatable popup card system. The popup card system includes animatable popup cards and popup card user interface (“UI”) elements, with location awareness functionality and scrolling awareness functionality. A user experience (“UX”) that is generated and displayed by the popup card system is adaptive to a multitude of scenarios and app (e.g., window) surfaces and is responsive to a variety of user inputs (including via mouse, keyboard, pen / stylus, touch, and voice). Transitioning between popup card states and / or between corresponding popup cards is smooth and seamless, and is anchored within the UI or app window, without need for users to navigate to another page or app to complete an action triggered by user input.

The invention belongs to the technical field of graph classification, discloses a graph classification method based on subgraph integration and position sensing, and relates to a graph classification method SIPA combining substructure embedding and node position sensing. The SIPA firstly extracts sub-graphs through two different strategies so as to capture multi-sample sub-structures in the graphs, the structural features of the sub-structures are coded by adopting a graph convolutional network, and information of different sub-graphs is effectively fused through an attention mechanism. Then, anchor nodes are introduced to calculate relative position information of nodes, and the information is embedded into node representation to better capture global position features. And finally, a graph information bottleneck mechanism is used for optimizing node representation and removing redundant information irrelevant to a classification task. The method not only effectively learns the local structure information, but also enhances the perception capability of the relative position information of the nodes. Experimental results show that SIPA is superior to an existing baseline model in five data sets, and the superiority of SIPA in a graph classification task is verified.

The invention belongs to the technical field of target detection, particularly relates to an infrared weak and small target detection method based on cross-domain feature migration, and provides a novel detection network which is SA-YOLO for short. Firstly, a position guidance enhancement module is designed under the inspiration of a multispectral feature migration idea, and infrared spectral feature response of a weak and small target is effectively enhanced through a triple structure of position perception attention, multi-scale significance fusion and position guidance filtering. Secondly, a spectrum-space sensing module is provided, and a progressive voidage and a double-branch attention mechanism are adopted, so that robustness modeling of multi-scale spatial features is realized. Then, a sensitivity stability loss function is innovatively proposed, and the problem of sudden drop of scale sensitivity of a weak and small target is relieved through dynamic penalty weight and composite normalization. And finally, an infrared small target data set named as ISUAV-D is also collected. Experimental results show that SA-YOLO shows significant advantages in a strong light interference environment and a tiny target detection scene.

A system and method for contextual three-dimensional messaging in augmented reality (AR) environments is disclosed. The system receives chat messages with specified real-world destinations and stores them associated with those locations. When a user wearing an AR device enters a destination location, the system detects their presence using techniques like GPS, Wi-Fi positioning, or computer vision. It then generates a 3D visual representation of the message and determines an appropriate spatial position within the physical environment based on environmental analysis and object detection. The 3D message is displayed at the determined position in the AR view. The system can analyze message content to identify topics and match them to detected real-world objects for contextual placement. Users can interact with displayed messages through gestures or voice commands to reply, forward, delete, or reposition messages. This enables immersive, location-aware messaging experiences that seamlessly blend digital content with the physical world.

Systems and methods of location-aware caller identification via machine learning techniques are disclosed. In one embodiment, an exemplary computer-implemented method may include: utilizing a trained call annotation machine learning model to determine one or both of an annotating condition and annotating location granularity, and associate one location of a user with one phone number of the user based at least on one or both of the annotating condition and the annotating location granularity; receiving second transactional information of one transaction associated with a first user; extracting second location information from the second transactional information of the one transaction; utilizing the trained call annotation machine learning model to automatically annotate one phone number record of one phone number of the first user, with the second location information at the annotating location granularity to form at least one user-specific location-specific annotated phone number record.

The invention provides an intelligent fault diagnosis and self-healing method and system for a low-voltage standardized cabinet, and belongs to the technical field of standardized cabinet fault diagnosis and self-healing control based on deep learning. The method comprises the following steps: firstly, by constructing a digital twin system and adopting a three-dimensional matrix type sensor layout, collecting data containing a limit fault working condition and fusing sensor position information, completing the construction of a fault diagnosis data set; then designing an intelligent fault diagnosis model to realize fault type judgment and position sensing; meanwhile, a fault self-healing reinforcement learning model is constructed, and a fault state feature representation network, a repair strategy network and reward strategy design are covered; and finally, constructing a reinforcement learning multi-stage action step execution strategy based on the model framework to gradually guide strategy iteration, and ensuring the safety and efficiency of fault self-healing operation so as to optimize the overall performance of the model. According to the invention, full-process automation from fault diagnosis to fault self-healing is realized, and the automation and intelligence degree of fault detection is greatly improved.

The invention provides a traffic flow prediction method and system for a dynamic association information fusion space-time network, and the method employs a time attention mechanism to adaptively adjust the association strength between different time points, and distributes a relative weight for each time point, so as to achieve the precise modeling of a time sequence dependence relation. And the space-time dynamic module captures directional information and position sensing features of the traffic flow by introducing a space-time feature enhancement mechanism so as to improve the expression ability of the traffic flow data and the extraction effect of the space-time features. Meanwhile, a gating attention unit is provided, the deep dynamic trend in the traffic sequence data is effectively mined, and a potential time sequence change mode is captured. By constructing a dynamic feature matrix, spatial correlation and node features are fused in real time, so that richer and more accurate spatial context information is provided. Associated information extracted by a dynamic feature matrix is introduced into a spatial graph convolutional network to deeply learn dynamic spatial topological structure features in a traffic network.

The invention provides an open vocabulary space-time action detection method and device based on visual language pre-training, and relates to the technical field of space-time action detection. The method comprises the following steps: acquiring video data to be detected, and inputting the video data to a local branch to obtain human-related region features; the local branch comprises a human-centered and category-independent pipe detector and a position sensing region analyzer; inputting the video data into the global branch to obtain global video features; the global branch comprises a visual language pre-training model of a video level; and fusing the regional features related to the person and the global video features, and calculating the similarity between the fused video regional features and the text features to obtain a classification result of behavior categories. A wide range of experiments on a UCF-JHMDB data set show that the performance of the method is superior to that of an existing method. A feasible solution is provided for solving the problem of insufficient open recognition capability, and a new direction and thought are provided for further research on space-time action detection.

The invention relates to a position sensing method and device, computer equipment, a readable storage medium and a program product. The method is applied to a receiver, and comprises the following steps: processing a received receiving signal to obtain a direct link signal corresponding to a signal source; determining a reflected link signal from the received signal based on a serial interference cancellation strategy and the direct link signal; performing sensing parameter estimation on the reflection link signal to obtain position sensing data; and determining coordinate information of the target device based on the position sensing data. By adopting the method, the position sensing accuracy of the reflection and scattering equipment can be improved.

A computing system may include an image access engine configured to access a panoramic point cloud image of a physical environment. The computing system may also include an environment location-aware text engine configured to transform the panoramic point cloud image into an alternate representation that reduces distortion in the panoramic point cloud image and perform an optical character recognition (OCR) process on the alternate representation to determine text in the panoramic point cloud image. The environment location-aware text engine may further be configured to construct text labels to track the text determined in the panoramic point cloud image and support text searches for the physical environment through the text labels.

In various examples, a technique for managing map data stored in a location-aware system includes determining a corresponding set of attributes for each of a plurality of map data units stored in a memory within the location-aware system. For each map data unit included in the plurality of map data units, the technique computes a priority score for the map data unit based on the set of attributes corresponding to the map data unit. The technique also includes determining, based on the plurality of priority scores for the plurality of map data units, one or more map data units to be evicted from the memory. The technique further includes causing at least a portion of the one or more map data units to be deleted from the memory in response to receiving one or more new map data units for storage in the memory.

Systems and methods for location aware access are provided. A location aware access system comprises a card reader and at least one controller. The card reader obtains access credential from a card, generates a corresponding time stamp, ascertains location coordinates representative of a geolocation of the card reader when the access credentials were received, and provides the access credentials, the time stamp, and the location coordinates to the controller. The controller is configured to receive the access credentials, the time stamp, and the location coordinates corresponding to the geolocation of the card from the card reader. Further, the controller is configured to perform authentication of the card based on the access credentials, the time stamp, and the location coordinates corresponding to the geo location of the card, and trigger an unlocking mechanism corresponding to the card reader upon successful authentication of the card.

Techniques for instantiating objects in a simulated environment based on log data are disclosed herein. Some of the techniques may include receiving log data representing an environment in which a real-world vehicle was operating. Using the log data, a simulated environment for testing a simulated vehicle may be generated. The simulated environment may represent the environment in which the real-world vehicle was operating. The techniques may further include determining a location of the simulated vehicle as it traverses the simulated environment. Based at least in part on the log data, a prior location of the real-world vehicle in the environment closest to the location of the simulated vehicle in the simulated environment may be determined. In this way, the simulated environment may be updated to include a simulated object representing an object in the environment that was perceived by the vehicle from the prior location.

A system and method for artificial intelligence enhanced mobile energy and data and network control, planning and optimization. The present invention relates to a system and method for optimizing energy and data and network use in mobile platforms, such as facilities, vehicles, tools, and devices. The system leverages AI, data analytics, and context-aware techniques to collect, process, and analyze data from various sources, including sensors, weather data, and spatial and temporal data with locality aware computing, transport, storage and networking across assets that may be owned or operated by multiple stakeholders. By considering a variety of factors, the system generates optimized recommendations for data storage, compute, transmission, device settings, fleet management, and physical and virtual route planning and logic locality planning. The invention offers benefits, including improved energy efficiency, enhanced data and network management, increased operational efficiency, and cost savings.

Approaches presented herein provide for identification of sound from a sound source relative to an array of microphones of a potentially unknown configuration using, in part, differences in the audio signals received by the microphones. In at least one embodiment, audio signals are captured using an array of microphones and audio features are extracted from those signals. The audio features can be processed using a first neural network to generate a feature vector representing a spatial location of an audio source with respect to the plurality of microphones, where the spatial location is inferred based on audio differences and independent of an availability of information indicating a physical configuration of the plurality of microphones. The feature vector can be provided to a task-specific model to perform at least one audio-related task based in part on the spatial location.

An improved computerized e-commerce system, optimized for smaller merchants such as florists who often provide seasonal perishable gifts that require local delivery, and who often desire to form cooperative networks with local merchants offering related gift services, as well as other related merchants such as other florists in more distant locations. The web server based system allows merchants to easily set up non-static (time variable) websites that automatically provide schedule driven promotions. New products can be quickly uploaded from smartphones, and sophisticated time and location aware algorithms can compute accurate delivery costs and make such costs transparent to customers. The system may also include backend software configured to assist in product production, inventory control, product cost optimization, and product delivery optimization, management, and tracking.

The invention discloses an automatic play window adjusting method, system and device based on browser position awareness and a medium, and belongs to the technical field of video play control, and the method comprises the steps that a message service is started in a player window, and a browser sends a message to the player window for setting the initial position and size of the player window; registering events in the player window, so that the player window can respond to the events, and the events comprise a browser window position and size change event and a mouse wheel sliding event; when a registered event occurs, the position and size of a player window are adaptively adjusted. According to the method and the device, the requirement of a user on efficient, stable and good-compatibility browser video playing experience can be met.

The invention discloses a multi-modal fusion sensing method and device for a vehicle position in a limited space and a medium, and the method comprises the steps: building a one-dimensional coordinate system OX in the limited space, and obtaining a set of all millimeter wave radar coverage areas; the method comprises the following steps: acquiring positioning data of UWB card readers on vehicles through the Ethernet, and calculating to obtain position information of k vehicles in a coordinate system OX to form a set A; acquiring vehicle data of the millimeter wave radar through a CAN bus, and calculating to obtain position information and speed information of n vehicles in a coordinate system OX to form a set B; performing fitting adjustment on the error of the vehicle position; dynamically diagnosing whether the millimeter wave radar is abnormal; and dynamically diagnosing whether UWB positioning is abnormal or not. According to the method, the millimeter wave radar with accurate local distance measurement is used, the position sensing result is dynamically fitted and corrected, and even if interference factors change after equipment installation, the vehicle position sensing effect can be improved; a multi-source sensing mode is adopted, diagnosis of the sensing technology state can be perfected, and abnormity or faults can be found in time.

Various embodiments employ multiple readers and tags in fixed locations in different geographical areas and / or along different storage units. This allows for more granular or precise location sensing. Particular embodiments employ multiple environment tags in various geographical locations and within multiple storage units. Using this new infrastructure setup, some embodiments can perform new functionality by predicting whether a target asset is in a particular geographical location, predict whether the asset is within a particular storage unit based on the proportion of readers mapped to that shelf which are actually reading the tag on the asset, and / or can predict where an asset's exact location in the located storage unit is based on comparing indications of signal strength values between each reader and tag in the storage unit with other indications of signal strength values between each reader and the tag that is attached to the asset.

The invention provides a remote sensing image ship target detection method based on a geographic information hybrid expert model. The method depends on a hybrid expert model and a Mask-RCNN network in deep learning, and is a visible light remote sensing image ship target deep learning detection method suitable for a multi-spatial resolution and complex geographical environment. In a Mask-RCNN feature extraction link, two expert groups are introduced, and two feature extraction expert groups guided by resolution and latitude and longitude geographic information respectively are constructed. In this way, detection of the ship target in the multi-resolution complex background visible light remote sensing image is achieved. The method not only has an accurate multi-scale target position sensing capability, but also can effectively eliminate ground feature interference in various geographic areas and complex background environments, and makes up for the deficiency of a current deep learning ship detection method in the aspect of multi-resolution complex background image research.

A multi-target tracking and monitoring method and system with high trajectory consistency, belonging to the field of computer vision, solves the problems of identity switching and trajectory fragmentation caused by long-term target occlusion and dense interaction in multi-target tracking, especially in UAV monitoring scenarios. The method includes the following steps: 1. Inputting a video sequence, performing target detection and feature acquisition for each frame; 2. Performing preliminary association through a basic tracker to obtain an initial trajectory; 3. Detecting the disappearance and appearance of abnormal trajectories using a position awareness submodule; 4. Storing abnormal trajectory features using a long-term memory submodule; 5. Performing secondary association using a multi-step cross-frame matching submodule; 6. Completing trajectory updates. This invention is applicable to UAV monitoring scenarios such as high-altitude inspection, low-altitude operations, and outdoor scene monitoring.

Embodiments for providing enhanced location-aware protection of latches in a computing environment are provided. One or more latches are combined in one or more of a plurality of bounding boxes on a two-dimensional circuit design layout based on one or more rules. A location-aware interleaving of error correction codes (“ECC”) and burst error correction codes may be selectively applied to one or more latches in those of the plurality of bounding boxes, where multiple bit errors are corrected.

The invention discloses a map identifier change detection method, device and equipment and a storage medium, relates to the technical field of map identifier detection, and discloses a map identifier change detection method comprising the following steps: obtaining a perception identifier according to sensor data, and obtaining a map identifier according to map information; according to the map identifier and the perception identifier, obtaining a geometric expression form of the map identifier and a geometric expression form of the perception identifier; calculating the position of the map identifier according to the geometric expression form of the map identifier, and calculating the position of the perceptual identifier according to the geometric expression form of the perceptual identifier; performing identifier matching according to the map identifier position, the perception identifier position, the geometric expression form of the map identifier and the geometric expression form of the perception identifier to obtain an identifier matching result; and carrying out map identifier change detection according to an identifier matching result. By integrating the perception data and the map data and using position matching and geometric expression form comparison, the real-time updating of the map identifier in the dynamic environment is realized.

Apparatuses and methods for golf alignment training include a device, attachable to a golf club, for measuring a golfer's alignment by a plurality of sensors, including a magnetometer. A location-aware device is used to select an intended target line. The plurality of sensors measure the golfer's actual alignment, including the face angle of the golf club at address of the ball, and the actual alignment is compared to the intended target line to provide feedback and suggested improvements.

Systems and methods of location-aware caller identification via machine learning techniques are disclosed. In one embodiment, an exemplary computer-implemented method may include: utilizing a trained call annotation machine learning model to determine one or both of an annotating condition and annotating location granularity, and associate one location of a user with one phone number of the user based at least on one or both of the annotating condition and the annotating location granularity; receiving second transactional information of one transaction associated with a first user; extracting second location information from the second transactional information of the one transaction; utilizing the trained call annotation machine learning model to automatically annotate one phone number record of one phone number of the first user, with the second location information at the annotating location granularity to form at least one user-specific location-specific annotated phone number record.

The embodiment of the application provides a kind of communication perception integration implementation method, position perception method, device and equipment;The method comprises: using first communication unit to generate probe signal, probe signal is respectively mapped to the multiple first perception symbols of first flexible frame, and probe signal is sent according to preset first frame structure, first flexible frame is a frame in first frame structure;Using second communication unit according to preset second frame structure, receive echo signal at each second perception symbol of second flexible frame, and send to perception processing unit, the structure of second frame structure is identical with first frame structure, the symbol ratio of first flexible frame and second flexible frame is different, echo signal is the signal after probe signal is reflected by target object;Using perception processing unit determines the relative position of communication device and target object.In the perception position, normal communication service is not affected, and communication function and position perception function can be completed in the same communication device.