32 results about "User orientation" patented technology

The present invention relates to a computer-implemented method and system for generating a video editing project using artificial intelligence (AI) and machine learning (ML) techniques. The method includes processing a collection of video clips to generate text-based metadata, receiving selection criteria to identify relevant video clips, and generating a natural language prompt based on the selection criteria. The prompt, comprising instructions and context, is provided to a large language model (LLM), which processes the input and outputs data for constructing a video project data model. The project data model includes timing data for salient snippets within the selected video clips. A dynamic and interactive web-based user interface is rendered to visually represent the project data model, offering a timeline view and editing tools for refining the video project. This system streamlines the video editing process by integrating AI-driven content analysis with user-directed editing, resulting in a tailored video project that aligns with user-defined thematic elements.

The invention relates to the technical field of wireless communication perception, in particular to a user perception method based on a multi-layer intelligent omnidirectional metasurface, and proposes to realize accurate perception of reflection and refraction user orientations by utilizing heterogeneous characteristics of propagation paths on two sides of a multi-layer intelligent omnidirectional metasurface structure. Based on the architecture, a user reflection and refraction type judgment algorithm based on uplink pilot frequency information is provided, and the user reflection and refraction types are determined based on the heterogeneous characteristics of user channels on the two sides of the multi-layer intelligent omni-directional metasurface and based on least square optimization problem solving and target function size comparison. The propagation path angle estimation algorithm specifically comprises the following steps: firstly, based on uplink pilot frequency information, designing a channel estimation algorithm comprising alternating optimization, constant-rank manifold optimization, convex relaxation and other methods to estimate and obtain a channel matrix by utilizing channel constant-rank and angular domain sparse characteristics; and finally, based on a user type determination result, obtaining user angle information based on each channel matrix by using an orthogonal matching pursuit algorithm.

Systems and methods are provided herein for displaying control elements for devices based on user inputs and / or past user interactions. This may be accomplished by a system detecting a first input (e.g., voice query) and then calculating a field of view of a user when the first input was detected. The system may use both a first attribute associated with the first input and the field of view of the user to identify a first device of a plurality of devices. The system may then identify an action corresponding to the first device and the first attribute. A display element related to the action is retrieved and then displayed for the user. The system may then cause the first device to perform the action upon a user selection of the display element.

The invention discloses an intelligent exhibit guide system and method integrating multi-dimensional space perception and user intention judgment, and belongs to the technical field of indoor positioning and navigation. The method comprises the following steps: acquiring real-time state information of a user; according to the user coordinates, preliminarily screening the plurality of exhibits in a preset candidate radius to obtain a candidate exhibit set; for any candidate exhibit, executing physical visibility constraint verification based on a preset visual range polygon corresponding to the candidate exhibit, so as to update the candidate exhibit set; calculating a comprehensive matching score of each candidate exhibit in the candidate exhibit set based on the user orientation, the user coordinate and the exhibit center coordinate corresponding to the candidate exhibit; and determining a unique target exhibit according to the comprehensive matching score, and pushing guide information associated with the target exhibit. According to the method and the device, the problems of false triggering, confusion of affiliations of adjacent exhibits and dislocation explanation under abnormal positioning caused by only depending on distance judgment in the prior art are solved.

Systems and methods for providing autonomous user-directed insights and recommendations are provided herein. For example, a system includes a non-transitory computer-readable medium and a processor communicatively coupled to the non-transitory computer-readable medium. The processor is configured to execute processor-executable instructions to determine, by an insight engine, first usage tracking information associated with a first client device and generate, by the insight engine, a user-directed insight based on the first usage tracking information associated with the first client device. The user-directed insight includes a natural language insight. The processor is also configured to execute processor-executable instructions to generate, by a recommendation engine, recommendations based on the user-directed insight and the first usage tracking information, where each of the recommendations includes a recommendation response and one of a recommendation for a dashboard profile corresponding to the user-directed insight or a recommendation for creating a dashboard corresponding to the user-directed insight.

Brewing module (1a) for preparing a brewed drink from a portion capsule, comprising: a first brewing module part and a second brewing module part, wherein said brewing module (1a) comprises a single bar lever (11) operatively connected at least with said second brewing module part, which single bar lever (11) can be brought manually from a first operating position, in which the second brewing module part is in a first brewing module part position, into a second operating element position, in which the second brewing module part is in a second brewing module part position, and back, and wherein the single bar lever (11) comprises a user directed terminal portion (63), in or on which a user interface (14) for initiating beverage preparation is located.

The invention discloses a dynamic sign language dictionary self-adaptive updating method and system combined with reinforcement learning, and the method comprises the steps: recognizing an updating demand through monitoring the search failure data of a user in real time, constructing a vocabulary entry in combination with sign language linguistics rules and multimedia dynamic demonstration, and driving a reinforcement learning model to continuously optimize the vocabulary entry quality through user feedback. User behavior data are converted into reinforcement learning reward signals, a driving model dynamically adjusts semantic relevance and expression accuracy of entries, it can be ensured that new entries conform to a sign language grammar system through associated word network analysis, multimedia dynamic demonstration makes up for the defects of static expression of a traditional dictionary, and the dynamic demonstration efficiency is improved. According to the sign language dictionary updating method, user guidance and language normalization are integrated in the updating process, the problems that a traditional sign language dictionary is lagged in updating, user feedback is faulted and static presentation is limited are solved, continuous self-optimization of entry quality is achieved through reinforcement learning, and the problem that in the prior art, the updating rate and the updating effect are unbalanced in a sign language dictionary updating method is solved.

The invention discloses a three-dimensional indoor positioning method based on visual sense and 5G sensing fusion, and relates to the technical field of indoor positioning and space perception. The method comprises the following steps: modeling an indoor reflecting surface to obtain a virtual anchor point; a user azimuth vector detected, identified and tracked by a camera target is projected to a scene reflection surface to construct a candidate reflection path and identify a direct incidence path, and the candidate reflection path and the direct incidence path are mapped to a beam codebook of a base station, so that a beam search range is narrowed, and a higher angle resolution is obtained; the user terminal establishes a communication link through the reference signal, and the base station acquires channel state information; in the channel parameter processing stage, angle and time delay estimation is carried out on channel parameters; an estimation result is matched with a direct or virtual anchor point path, and pseudo paths which do not conform to scene constraints are eliminated, so that a direct path and an effective reflection path are distinguished; the position of the user is jointly solved by using multi-angle constraints formed by the direct path and the reflection path, and continuous estimation of the three-dimensional position of the user is realized by combining a filter.

A system for providing a gamified virtual construction lab, comprising a game model system generating a virtual game environment, an objectives system displaying one or more game objectives to a user in the virtual game environment, a user movement system receiving object selection data by a user of an object in the virtual environment, user movement data from one or more movement data sources, and object orientation data from one or more user orientation data sources, to determine whether the user movement data and the user orientation data results in a collision between the selected object and the virtual game environment and to generate collision data, and a scoring system receiving the collision data and the game objectives and generating score data in response.

An apparatus and method for tracking user orientation in a real-world space, wherein the user consumes, via an audio output device, data representing a spatial audio scene comprising one or more audio sources which are rendered at respective spatial positions with respect to a reference orientation in the real-world space. Responsive to a tracked change in user orientation from the reference orientation to a new orientation, the respective spatial positions of the audio sources are then modified so as to counter the change in user orientation from the reference orientation to the new orientation. This is followed by tracking a spatial position of the user in the real-world space with respect to a travel route, wherein the travel route comprises one or more portions which will cause one or more respective changes in user orientation from the reference orientation when the user travels along the portions. This is followed by updating the reference orientation based on the tracked spatial position of the user indicating that the user is travelling along one of said one or more portions, wherein the one or more audio sources are thereafter rendered at the respective spatial positions with respect to the updated reference orientation.

The present application discloses a user orientation method, apparatus, computer equipment and computer-readable storage medium, which relates to the field of big data technology. By defining a user environment identifier, some users who are not currently being oriented can be oriented according to their current environment, thereby improving orientation efficiency, making up for scenarios that cannot be reached by tags, expanding the scope of user orientation and avoiding omissions. The method includes: responding to a user orientation request, determining the user to be oriented, the orientation execution parameters, and obtaining the orientation expression based on the user environment identifier included in the orientation execution parameters; querying the address information of the user to be oriented, obtaining the variable replacement value in the orientation execution parameters; replacing the variable placeholder in the orientation expression with the address information and the variable replacement value, and executing the replaced orientation expression to obtain an execution result; when the execution result indicates that the address information verification is successful, determining that the orientation of the user to be oriented is successful, and outputting the execution result.

The present invention is a stretching apparatus enabling a user to independently stretch back, leg, and abdominal muscles without assistance. The device includes a rigid modular frame with a detachable base, a pivotable panel assembly with padded arms, and a motorized actuator. The actuator adjusts the angle of the panel under user control via a remote or integrated interface. The apparatus supports multiple user orientations and stretch types through reconfiguration of the panel and frame. Ergonomic padded supports enhance comfort, and the modular design allows for transport, storage, and adaptation across clinical, athletic, and home environments. Programmable features and locking mechanisms enable precision, safety, and repeatable stretching routines. The invention provides a versatile, self-operated system for rehabilitation, fitness, and flexibility training.

A data processing method and a control device are provided. The method of the present disclosure is directed to a loudspeaker system including a plurality of loudspeakers. By collecting locally measured distance information from respective loudspeakers and determining a real-time spatial layout of the loudspeaker system based on the distance information, automatic layout calibration of the loudspeaker system is achieved. Subsequently, according to the layout of the loudspeaker system, and in combination with an actual orientation of a user and spatial position-related data indicative of a position of a sound source in audio content to be played, corresponding data in the audio content is assigned to corresponding loudspeakers, thereby utilizing playback by the respective loudspeakers to collectively achieve spatial audio rendering, providing an immersive sound experience for the user. The method of the present disclosure does not require additional layout calibration processing, and thus can achieve real-time layout determination without user awareness and can automatically adjust audio playback of the loudspeakers according to changes in the real-time orientation of the user, thereby achieving user orientation-adaptive spatial audio rendering.

The present disclosure provides an audio generation method, device, electronic equipment and storage medium. The audio generation method can include: obtaining a to-be-processed audio signal; obtaining a plurality of track signals corresponding to a plurality of sound sources by performing track separation on the to-be-processed audio signal; determining user orientation information in a three-dimensional space, and generating three-dimensional space metadata corresponding to each track signal in the plurality of track signals; and generating a three-dimensional audio signal corresponding to the to-be-processed audio signal based on the user orientation information, the plurality of separated track signals, and the three-dimensional space metadata corresponding to each track signal. The present disclosure can generate a three-dimensional audio that is closer to a real three-dimensional audio, increase the immersion of the three-dimensional audio, and improve the user experience.

Systems and methods for an adaptable computing device, including a device configuration that is convertible between a flat, personal computing orientation and a polyhedron multi-user orientation, and related software for control of audio and video features. An example configuration includes: a segmented display screen to output a display from a plurality of segments repositionable between a first orientation and a second orientation for multiple users; a microphone array and camera array located among the plurality of segments; and processing circuitry to detect a usage mode based on an orientation of the segmented display screen, and modify the audio capture and the video capture based on the usage mode. For instance, the multi-user orientation separates the plurality of segments into respective display areas on outward-facing sides of the segmented display screen, when the adaptable computing device is in a polyhedron shape in the multi-user orientation.

A system for providing spatialized audio in a vehicle, including a vehicle orientation sensor outputting a vehicle orientation signal and being disposed on the vehicle and a controller configured to receive a user orientation signal output from a user orientation sensor being on a wearable that, during use, moves with a first user's head, wherein the controller is further configured to determine an orientation of the user's head relative to the vehicle based, at least, on a difference between the vehicle orientation signal and the user orientation signal, the controller being further configured to output to a first binaural device, according to the orientation of the user's head relative to the vehicle, a first spatial audio signal, such that the first binaural device produces a first spatial acoustic signal perceived by the user as originating from a first virtual source location within a cabin of the vehicle.

The present invention discloses a method and system for adaptively updating a dynamic sign language dictionary combined with reinforcement learning. The method identifies update needs by real-time monitoring of user search failure data, constructs entries by combining sign language linguistic rules with multimedia dynamic demonstration, and utilizes user feedback to drive a reinforcement learning model to continuously optimize entry quality. The method converts user behavior data into reinforcement learning reward signals, driving the model to dynamically adjust the semantic relevance and expression accuracy of the entries. The method can ensure that the new entries conform to the sign language grammar system through associative word network analysis. The multimedia dynamic demonstration makes up for the defects of static expression of traditional dictionaries, making the update process both user-oriented and linguistically standardized, avoiding the problems of delayed update, user feedback gaps, and static presentation limitations of traditional sign language dictionaries. The method achieves continuous self-optimization of entry quality through reinforcement learning, solving the problem of imbalance between update rate and update effect in sign language dictionary update methods in the prior art.

Techniques for determining sound field directions are provided. In some embodiments, a method for determining sound field directions involves receiving orientation data and acceleration data based on sensor data obtained from sensors disposed in a headset or earbuds worn by a user, wherein the orientation data is in a quaternion format. The method may further involve determining a center direction for a user orientation based at least in part on the orientation data. The method may further involve selecting a center direction for a sound field based at least in part on the center direction for the user orientation. The method may further involve re-centering a reference frame used to render audio content to be played back using the headset or earbuds in accordance with the selected center direction for the sound field, wherein the re-centering is performed in the quaternion domain.

Systems and methods for providing autonomous user-directed insights and recommendations are provided herein. For example, a system includes a non-transitory computer-readable medium and a processor communicatively coupled to the non-transitory computer-readable medium. The processor is configured to execute processor-executable instructions to determine, by an insight engine, first usage tracking information associated with a first client device and generate, by the insight engine, a user-directed insight based on the first usage tracking information associated with the first client device. The user-directed insight includes a natural language insight. The processor is also configured to execute processor-executable instructions to generate, by a recommendation engine, recommendations based on the user-directed insight and the first usage tracking information, where each of the recommendations includes a recommendation response and one of a recommendation for a dashboard profile corresponding to the user-directed insight or a recommendation for creating a dashboard corresponding to the user-directed insight.

The invention provides an advertisement data management system. An advertisement data management system platform is constructed through a basic configuration module, a report module, a bottoming and putting module, a material submission module, a strategy module, a label module and an A / B experiment module. The problems that an existing advertisement data management system is scattered in data, difficult to integrate, single in advertisement putting strategy, lack of flexibility, inaccurate in advertisement putting user orientation, low in creative management efficiency, incomplete in advertisement putting effect evaluation, insufficient in advertisement putting test support and the like are solved, efficient management of advertisement data is achieved, and meanwhile the advertisement putting effect is improved. And the use experience of the user is also improved.

A data processing method and a control device are provided. The method of the present disclosure is directed to a loudspeaker system including a plurality of loudspeakers. By collecting locally measured distance information from respective loudspeakers and determining a real-time spatial layout of the loudspeaker system based on the distance information, automatic layout calibration of the loudspeaker system is achieved. Subsequently, according to the layout of the loudspeaker system, and in combination with an actual orientation of a user and spatial position-related data indicative of a position of a sound source in audio content to be played, corresponding data in the audio content is assigned to corresponding loudspeakers, thereby utilizing playback by the respective loudspeakers to collectively achieve spatial audio rendering, providing an immersive sound experience for the user. The method of the present disclosure does not require additional layout calibration processing, and thus can achieve real-time layout determination without user awareness and can automatically adjust audio playback of the loudspeakers according to changes in the real-time orientation of the user, thereby achieving user orientation-adaptive spatial audio rendering.

The invention relates to the technical field of intelligent security and protection, and particularly discloses a data analysis method and system based on a user orientation data path, and the method comprises the steps: collecting the position data and motion data of each person in a target region in real time; performing spatio-temporal clustering on the position data and the motion data, generating a personnel track fragment, and calculating a personnel state value; when the personnel state value exceeds a preset first threshold value, marking that there is a risk personnel, and according to the floor information of the risk personnel, starting a steerable monitoring device of a corresponding floor or a cross-floor, and entering an evidence obtaining mode; performing secondary analysis on the action information captured by the monitoring equipment, and performing Bayesian fusion on the action information and the personnel state value to obtain a final risk score; and when the final risk score exceeds a preset second threshold value, generating a multi-level alarm signal, and synchronously pushing the multi-level alarm signal to a security terminal or a building automation system. According to the invention, more timely, more comprehensive and more accurate safety early warning can be carried out on the target area.

The invention provides a data-driven central air conditioner cooling station energy efficiency optimization control method and system, and the method comprises the steps: data collection, data introduction, model construction, model training, intelligent control strategy making, and implementation and continuous optimization. According to the data-driven central air conditioner cooling station energy efficiency optimization control method and system, real-time complaint and evaluation of the user to the air conditioner system are analyzed, the user satisfaction degree is quantified, the user satisfaction degree is associated to the specific building area, a user-oriented optimization target is provided for a control strategy, the temperature set value is automatically adjusted when the negative emotion rises, and the energy efficiency of the central air conditioner cooling station is improved. And the concentration of fungi in a key area of the cold station is monitored in real time, equipment corrosion or air quality problems caused by excessive microorganisms are prevented, meanwhile, microorganism data and operation parameters are subjected to space-time alignment, potential correlation between the microorganism data and energy efficiency is excavated, and the system can comprehensively evaluate the operation state of the cold station.

The invention discloses a preparation and effect evaluation method of polluted tableware for dish-washing machine performance testing, which comprises the following steps: obtaining cooking rice pollutants, coating standard tableware with the cooking rice pollutants to obtain polluted tableware, drying the polluted tableware by adopting a drying oven drying method, loading the polluted tableware into a dish-washing machine, putting a detergent, operating different cleaning programs of the dish-washing machine, and after the cleaning programs are operated, scoring each polluted tableware and calculating the sensitivity of the standard polluted tableware to the cleaning programs by referring to a cleaning performance test method specified by the standard; according to the sensitivity of the standard polluted tableware to the washing program, the washing capacity difference of different washing programs of the dish-washing machine is judged. The method can promote the establishment of a Chinese washing performance test standard, and can improve the scientificity and user guidance quality of dish-washing machine program design.

Systems and methods for an adaptable computing device, including a device configuration that is convertible between a flat, personal computing orientation and a polyhedron multi-user orientation, and related software for control of audio and video features. An example configuration includes: a segmented display screen to output a display from a plurality of segments repositionable between a first orientation and a second orientation for multiple users; a microphone array and camera array located among the plurality of segments; and processing circuitry to detect a usage mode based on an orientation of the segmented display screen, and modify the audio capture and the video capture based on the usage mode. For instance, the multi-user orientation separates the plurality of segments into respective display areas on outward-facing sides of the segmented display screen, when the adaptable computing device is in a polyhedron shape in the multi-user orientation.

Systems and methods for providing autonomous user-directed insights and recommendations are provided herein. For example, a system includes a computer-readable medium and a processor communicatively coupled to the computer-readable medium. The processor is configured to execute processor-executable instructions to determine, by an insight engine, first usage tracking information associated with a first client device and generate, by the insight engine, a user-directed insight based on the first usage tracking information associated with the first client device. The user-directed insight includes a natural language insight. The processor is also configured to execute processor-executable instructions to generate, by a recommendation engine, recommendations based on the user-directed insight and the first usage tracking information, where each of the recommendations includes a recommendation response and one of a recommendation for a dashboard profile corresponding to the user-directed insight or a recommendation for creating a dashboard corresponding to the user-directed insight.

The present invention is a stretching apparatus enabling a user to independently stretch back, leg, and abdominal muscles without assistance. The device includes a rigid modular frame with a detachable base, a pivotable panel assembly with padded arms, and a motorized actuator. The actuator adjusts the angle of the panel under user control via a remote or integrated interface. The apparatus supports multiple user orientations and stretch types through reconfiguration of the panel and frame. Ergonomic padded supports enhance comfort, and the modular design allows for transport, storage, and adaptation across clinical, athletic, and home environments. Programmable features and locking mechanisms enable precision, safety, and repeatable stretching routines. The invention provides a versatile, self-operated system for rehabilitation, fitness, and flexibility training.

An apparatus configured to: obtain a user position value; obtain at least one input audio signal and associated metadata enabling a rendering of the at least one input audio signal; generate an intermediate format immersive audio signal based on the at least one input audio signal, the metadata, and the user position value, wherein the intermediate format immersive audio signal is configured to be rendered into a spatial audio output based, at least partially, on a user orientation value; and encode the intermediate format immersive audio signal.

The invention discloses a data sharing method for network courses, and relates to the technical field of data sharing of network courses. According to an existing network course data sharing method, efficient distribution of resources, real-time updating of the learning progress and cross-platform resource integration are achieved through the data sharing method; a current data sharing method has the problems that learning contents are not matched with user demands, course content complexity is not matched with user capabilities, and the utilization rate of learning resources is low. According to the method, through construction of the user guide graph and generation of the content preference portrait graph, accurate personalized recommendation is realized, and specific learning requirements of the user are met; through natural language processing, formula analysis and image recognition technologies, course content complexity is subjected to quantitative analysis, optimal distribution is performed in combination with user preferences, and the problem of insufficient content adaptability is solved; and through a complexity and preference matching technology, optimal or sub-optimal recommendation of existing courses is realized.