1654 results about "EyeTap" patented technology

Automatic generation of in-store product information and navigation guidance, using Augmented Reality (AR) and a Vision-and-Language Model (VLM) and multi-modal Artificial Intelligence (AI). An automated method includes: providing to the VLM images that are captured within a retailer venue by an electronic device that is a smartphone or an AR device or smart glasses; (b) automatically feeding into the VLM those images, or pre-sliced or pre-cropped image-portions of those images that were sliced or cropped using Machine Learning that performs object boundaries detection and not product recognition; (c) invoking the VLM to generate outputs of VLM analysis of content of those fed images or image-portions. The VLM outputs can be: VLM-based product recognition, VLM-based product-related information, VLM-generated virtual shopping assistance, VLM-generated in-store navigation guidance, or other VLM-generated outputs. Based on the VLM-generated outputs, the electronic device provides real-time information about products depicted in the images, VLM-generated shopping assistance, and VLM-generated in-store navigation guidance.

The invention provides a smart glasses AI voice interaction method, which comprises the following steps: simultaneously acquiring a user gesture image and a voice signal, acquiring a user historical interaction record, extracting key point coordinates and pointing direction information of the gesture image, acquiring hand distance information, generating a gesture motion path, simultaneously extracting frequency spectrum information and an intonation peak value of the voice signal, and generating a gesture motion path; forming a voice beat sequence; extracting a spatial semantic mode of the gesture and voice fusion data, and recognizing a core object of a user pointing instruction according to pointing coordinates of a gesture motion path and an intonation peak value of a voice beat sequence; after the core object pointing to the instruction is recognized, the user intention is determined in combination with the spatial semantic mode and the historical interaction record of the user; and the complete intention analysis result is output to the intelligent glasses display module to execute corresponding operation, and is fed back to the acquisition module to adjust the next capture parameters including the acquisition frequency and the recognition sensitivity, so that the response speed and the accuracy are improved.

A computer-implemented system and method for pupil-directed retinal projection in near-eye displays are disclosed. The computer-implemented system provides smart glasses with directed physical pixels that project light beams / signals directly onto a user's retina based on pupil position and size. The glasses comprise a frame, lenses with directed pixel layers, and sensors for tracking pupil movement. Each directed pixel may generate multiple virtual pixels by rapidly changing its emission angle. The glasses function as prescription lenses, virtual reality displays, and augmented reality devices without traditional optical systems. Additional features include depth sensors, cameras, and connectivity to peripheral devices. The glasses enable a seamless blend of virtual and real-world experiences, creating an immersive “Mixverse” environment. Various input methods, including gesture recognition and brain-computer interfaces, allow for intuitive control and interaction.

The invention relates to the technical field of augmented reality and industrial safety monitoring, in particular to an AR glasses dangerous state dynamic labeling method and system based on multi-source perception, and the method comprises the steps: synchronously collecting data such as a depth image and gas concentration through multi-source equipment such as a depth camera and a gas sensor; extracting rotation invariant point cloud features through an improved dangerous target detection model, and fusing multi-modal data to generate a dynamic danger level; based on VIO, realizing accurate spatial registration of annotation and a real scene, and generating a self-adaptive annotation style according to a danger level; and multi-device labeling pose synchronization is realized through an entropy weighting ICP algorithm, and labeling transparency and size are dynamically optimized in combination with a user fatigue value and environment illumination. According to the method, the comprehensiveness of danger identification and the accuracy of marking are improved, team collaborative operation is supported, the method is suitable for scenes such as electric power inspection and dangerous chemical transportation, and the operation safety and efficiency are guaranteed.

The invention relates to the technical field of workpiece assembly, in particular to a digital twinning and augmented reality guided man-machine cooperation assembly method and system, and the method comprises the steps: collecting a multi-view image, mechanical arm sensing data and a first person image of AR glasses; fusing the data, generating scene assembly information, and constructing a digital twin model; configuring an operation standard, a standard assembly unit space state and a standard hand action template of each assembly process stage, judging a current assembly process stage, identifying an operation intention, predicting a next process in combination with the current assembly stage and the operation standard, and generating a man-machine instruction and simulation data; three-dimensional action guidance is displayed through AR glasses, a mechanical arm is driven to execute planning actions, and a digital twin interface feeds back the assembly state, precision data and prediction animation in real time. According to the method, man-machine standardized cooperation and high-precision assembly are achieved, pre-stored parameters are adaptive to multi-variety production, and the process consistency is improved through real-time feedback.

The invention relates to the technical field of brain-computer interfaces, in particular to a multi-mode AI glasses vision-electroencephalogram cooperative control method, device and equipment. The method comprises the following steps: constructing a multi-modal data acquisition framework for acquiring a visual scene image and an electroencephalogram signal, generating an alignment data stream to identify a target feature, and generating an attention map; time sequence features are extracted, and intention features are recognized; constructing a feature matrix, performing modal alignment on the feature matrix, performing feature fusion based on an alignment result of modal alignment, and generating a unified representation; performing time sequence segmentation, extracting associated features, constructing a state sequence based on the associated features, marking conversion nodes by using the state sequence, and generating a dynamic mode according to the conversion nodes; performing information analysis by using a dynamic mode, determining a modal weight, performing feature selection based on the modal weight, performing classification mapping on a feature selection result, and generating a control sequence; and generating an interaction instruction according to the control sequence, and completing vision-electroencephalogram cooperative control of the multi-modal AI glasses.

The invention discloses an image processing method and system for intelligent glasses, and relates to the technical field of image recognition. The method comprises the following steps: synchronizing and preprocessing data collected by heterogeneous sensors in the intelligent glasses; constructing a global space-time coordinate system; a high-risk area is determined through dynamic saliency analysis, a high-resolution detection ROI is generated, full-pixel analysis is performed on a focus area, and an obstacle list with 3D positions, categories and danger levels is output; and generating a personalized safety path through a safety corridor generation algorithm based on the 3D position of the obstacle, the motion model of the visually impaired person and the real-time position. Data collected by heterogeneous sensors in the intelligent glasses are synchronized, a global space-time coordinate system is constructed, path planning is performed after obstacles are identified, high-frequency IMU angular velocity data and a self-adaptive optical flow correction network are fused, the image reverse compensation precision in a dynamic scene is improved, and navigation safety in a complex scene is guaranteed.

An AI-powered augmented reality (AR) system for optimizing product placement and customer loyalty. The system includes: • a user interaction data collection unit configured to monitor consumer behavior in real time in any retail scenario (point-of-sale POS, online e-commerce and shopping areas within a public virtual technology space), with the unit analyzing consumer movement patterns, engagement metrics, eye-tracking and purchase intent; • an intelligent spatial mapping module to build a contextual understanding of high-traffic zones, underutilized areas and high-quality product placements using heatmap analysis, other spatial computer algorithms and the live movement of consumers; • A model-based product placement recommender based on machine learning, which uses one or more DL-based predictive models trained by importing current sales data, historical text interaction data, and consumer preference data to suggest optimal product placement so that customers see the advertisement and are likely to click through it to ensure a conversion. • a customer-centric, real-time AR visualization interface configured to allow customers to experience digitally enhanced product presentations directly via mobile AR applications, smart glasses, or in-store digital kiosks, enabling customers to preview product placements, rotate and resize objects, and visualize interactive advertising content before purchasing; • a customized advertising and sales promotion engine configured to generate augmented reality-based marketing content and provide users with tailored promotions and interactive ads based at least in part on an analysis of consumer sentiment by the system, as well as information on location data or consumer interaction history, wherein the customized advertising and sales promotion engine personalizes the configuration instructions for advertising and sales promotion to encourage consumer interaction and achieve higher sales revenues; • A secure, cloud-based data processing and analytics unit that uses an automated engagement model to link online and in-store sales information with established activity models for product placement decisions. The unit leverages AI-powered consumer insights to continuously recommend product placement changes based on a variety of programmatic retail trends; • a privacy-friendly AI module based on federated learning and on-device AI processing, providing consumer behavior analytics while complying with global data protection regulations and preventing the use of open data; • a processing framework characterized by a low-power mode suitable for AR rendering and AI calculations, and implemented via dynamic voltage scaling and energy management techniques for seamless and sustainable operation; The system according to claim 1, wherein the user interaction data capture unit further comprises an eye-tracking and sentiment analysis sub-module, wherein the sub-module detects facial expressions, emotional reactions, and attention levels of consumers in real time to determine the effectiveness of product placements and advertising strategies.

The invention relates to a visual transformer substation intelligent inspection system and method based on a multi-mode large language model, and belongs to the technical field of power system intelligence. The system obtains image, temperature, vibration and noise data of substation equipment in real time through a multi-modal data acquisition module, and performs preprocessing and fusion. A high-precision three-dimensional semantic model is constructed by using a three-dimensional dynamic modeling module, and the device attributes are automatically labeled by fusing LLM semantic understanding capability. A multi-modal large language model (LLM) engine is combined with cross-modal feature extraction, a dynamic knowledge base and a self-adaptive reasoning unit to realize accurate diagnosis of equipment faults. An augmented reality (AR) interaction module displays the real-time state of equipment through AR glasses and supports natural language interaction. The self-interpretation decision support module generates interpretable fault reports and maintenance suggestions, and the communication and feedback module is responsible for data uploading and remote alarm. According to the method, multi-dimensional perception, dynamic knowledge reasoning and self-adaptive decision support of the equipment state are realized, the intelligent level of substation inspection is remarkably improved, the inspection efficiency is improved by more than 40%, the omission ratio is reduced to less than 1%, and rapid diagnosis of more than 95% of novel faults is supported.

The invention discloses an AR glasses control system and method, and belongs to the field of artificial intelligence and AR glasses application, and the method comprises the steps: capturing a user face image, combining a voice assistant, collecting user voiceprint data, and carrying out the matching through a recurrent neural network; constructing a three-dimensional environment model, positioning and marking obstacles and interactive objects, and identifying objects in the environment; the method comprises the following steps of: tracking a gesture, acquiring a key point coordinate by adopting an OpenPose algorithm, identifying a predefined gesture by utilizing a support vector machine, and mapping the gesture into a specific operation instruction; analyzing the user intention based on natural language processing, and calling a corresponding function module according to an analysis result; acquiring a gazing direction of a user by using an eye movement tracking sensor, calculating a screen focus position through an algorithm, and dynamically highlighting options or displaying information according to a gazing point position; through multi-modal data fusion, gestures, voices and fixation point input are analyzed in a unified manner. By accurately understanding the intention of the user, the interaction precision of the AR glasses is improved, and the user experience is optimized.

The invention relates to a positioning method of large-space intelligent glasses, head display equipment and a storage medium, belongs to the technical field of meta-cosmic space calculation, and is suitable for a meta-cosmic positioning function that the head display equipment of players in a multi-user interaction large space can directly interact without learning or reasoning of a central server. A plurality of different texture pictures are arranged on the bottom surface or the ceiling of a large space, any camera on the intelligent glasses is used for collecting images, the texture pictures are recognized from the images collected by the camera T, picture information corresponding to the texture pictures is obtained, the world position of the camera T can be obtained through geometric calculation, and the texture pictures are displayed on the intelligent glasses. The method can be quickly realized on local head-mounted display equipment, so that the learning process of a server or the delay of image reasoning and position information returning and errors caused by a positioning sensor are avoided, and the problem of errors caused by long distance of a large-space site or shielded texture pictures is also avoided.

The invention belongs to the technical field of project management and intelligent supervision, and discloses a project cost accounting management method and system for project supervision, and the method comprises the steps: inputting a preprocessing data packet into an edge calculation node, carrying out the dynamic data cleaning through employing a noise filtering matrix algorithm, and outputting a structured data set with a quality label; on the basis of the structured data set with the quality label, scanning a construction part through augmented reality glasses, comparing actual coordinates with building information model design coordinates in real time, and when a deviation accumulated value exceeds an early warning threshold value, generating an acceptance evidence chain which cannot be tampered; and accumulating the incremental cost of the plurality of standardized visa file packages, carrying out time sequence analysis through a long-short term memory prediction model, and outputting a project cost analysis report with a risk level. The problem of loss of acceptance evidence chains in traditional cost accounting is solved, and the strong dependence of a conventional prediction model on data distribution is broken through.

The invention relates to the technical field of optical assembly detection, provides a confocal-based pixel-level definition judgment and 3D fusion reconstruction system and method, and aims to perform high-precision definition detection on each pixel of a lens by using a confocal detection module through a point-by-point scanning technology so as to ensure that tiny defects on the surface and in the lens are identified. And then, the defect identification module analyzes the detection result, determines the specific position and type of the defect, and generates a detailed defect report. And then, the 3D reconstruction module constructs a three-dimensional model of the lens according to the defect identification result, evaluates the influence of the defects on the imaging effect, and helps manufacturers to know the severity of the defects. And finally, a data analysis module organizes and analyzes all detection and reconstruction data to provide comprehensive production optimization suggestions and ensure the quality and stability of the optical assembly. Through close cooperation of the four modules, comprehensive and accurate detection and analysis of the optical assembly of the VR glasses can be realized.

Systems and methods for autofilling and autocorrecting an AI supported UI form text field via smart glasses are provided. The data autofillted and autocorrected may be identification data, including account numbers and user IDs. The smart glasses may work together with a conversation tracking application and a smart glasses UI. Methods may include prompting agents based on real-time conversational analysis with context clues and texts to assist and maintain customer eye contact. Methods may further include capturing segments of data within conversational analysis and storing the segments of data in memory on the smart glasses. Methods may further include updating smart glasses UI form text fields based on AI supported autocorrection from real-time conversation, by autofilling the segment of data in the smart glasses UI form text fields.

The invention relates to the technical field of computers, and discloses an interaction control method of intelligent glasses. The method comprises the following steps: synchronously acquiring multi-modal data such as eye movement, voice, gestures and head postures and environment and application context information; carrying out independent time sequence feature coding on each modal data; generating a modulation vector in combination with the context, and outputting probability distribution of user intentions through a cross-modal attention fusion network; and a unique execution instruction is determined through an instruction arbitration module based on rules and a state machine. The system comprises corresponding function modules. According to the method, the accuracy, robustness and naturalness of interaction are improved through multi-modal synchronous fusion and a context self-adaption mechanism.

The invention discloses a driving skill level classification method based on multi-dimensional data fusion. The method comprises the following steps: (1) acquiring behaviors, physiological data and environmental data of a driver in real time through a driving simulator, eye movement tracking glasses and a physiological sensor; and (2) processing and analyzing the multi-dimensional data by using a CNN-LSTM classifier (CNN-LSTM-attention) so as to evaluate the skill level of the driver. According to the method, control skills and cognitive skills are comprehensively evaluated, key parameters including steering, braking, eye movement frequency, concentration duration and the like are captured in real time by using a driving simulator, eye movement tracking glasses and a physiological sensor, and a CNN-LSTM-attention classifier is constructed. According to the method, the complexity of the scene is quantified, the classifier is trained according to different scenes, the accuracy is improved, and meanwhile, the reliability of driving ability evaluation is enhanced by using multi-dimensional data.

A near-to-eye display system (1) and AR glasses (3). The near-to-eye display system (1) comprises an optical waveguide module (10), an optical engine module (20) and a metalens assembly (22). A first in-coupling grating region (111) and a first out-coupling grating region (112) are formed in the optical waveguide module (10). The optical engine module (20) comprises a light source assembly (21), which is arranged opposite the first in-coupling grating region (111), and the metalens assembly (22), which is arranged between the light source assembly (21) and the optical waveguide module (10), wherein the light source assembly (21) is used for outputting image optical signals to the metalens assembly (22), the image optical signals comprising at least two types of optical signals of different attributes, and the attributes comprising at least one of a wavelength, an emission angle and an emission position. The metalens assembly (22) comprises a substrate (221) and a metasurface structure (222) on the substrate (221), wherein the metasurface structure (222) is configured to receive the image optical signals and diffract the optical signals to the first in-coupling grating region (111). The optical signals which have the same emission position have the same diffraction angle. Thus, the volume and weight of a lens of the optical engine module (20) are reduced, and the design requirements for high image quality and a large field of view are also met.

The invention discloses an AR glasses blogger live video anti-shake processing method and processing system, and the method specifically comprises the steps: carrying out the calculation based on an original video stream and equipment motion data, and generating a preliminary stable frame sequence; based on the preliminary stable frame sequence, marking a key semantic region as a strong stability demand region, and segmenting a foreground main body and a background region; performing fine stabilization on the strong stability demand area and the foreground main body by applying non-rigid transformation, performing stabilization on the background area by applying rigid transformation and retaining the depth of the scene, and obtaining a frame sequence after partition correction; predicting a future multi-frame equipment motion track based on the frame sequence after partition correction, the equipment motion data and the segmentation information of the foreground main body / background region; and calculating and executing prospective canvas motion compensation in advance based on the future multi-frame equipment motion trail and the segmentation information of the foreground main body / background region. According to the invention, efficient anti-shake processing of the live video of the AR glasses is realized, and the stability of the live picture and the user experience are effectively improved.

The invention discloses a remote cooperation method and device based on a polymorphic large model, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring a visual field video stream of a production field and voice data inquired by field personnel, wherein the visual field video stream is acquired by AR glasses worn by the field personnel in real time; analyzing the view video stream to obtain first record content; extracting character information in the voice data, and matching the character information with a pixel position of a target object to obtain second record content; and inputting the first record content and the second record content into a pre-trained polymorphic large model, generating multimedia summary response content, and feeding back the multimedia summary response content to a user terminal of the field personnel, and enabling the field personnel to perform field inspection according to the multimedia summary response content displayed by the user terminal. The remote cooperation efficiency can be improved.

The invention provides a multi-modal interaction and image processing method for AI glasses, electronic equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of an original image collected by the AI glasses in real time based on a space-time attention mechanism, and obtaining a preprocessed image; performing voice recognition and semantic analysis on a voice instruction input by a user through the AI glasses to obtain a text instruction; performing keyword matching on the text instruction and a preset image processing instruction template library, and determining a corresponding image processing strategy; if the image processing strategy is dynamic tracking, predicting the position of a target in the preprocessed image in the next frame by using a Kalman filtering algorithm, and searching and positioning the target around the predicted position by using a twin network; and the appearance features of the target are learned and updated in real time based on the twin network, stable tracking of the target is realized, and a tracking target image sequence is output. According to the method, the defects that the subsequent appearance position of the target cannot be predicted and the target cannot be stably tracked at present are overcome.

The invention relates to the technical field of AR, and discloses an AR glasses image calibration method, device and system and AR glasses, and the system comprises a camera, an optical waveguide sheet, a glasses support and a controller. The camera is arranged on the glasses bracket, is connected with the controller and is used for collecting images displayed on the optical waveguide sheet; the controller is used for acquiring standard images and controlling the left optical waveguide sheet and the right optical waveguide sheet of the AR glasses to display the standard images respectively; controlling a camera to respectively collect standard images displayed by left and right optical waveguide sheets of the AR glasses to obtain left and right collected images; respectively judging whether the two acquired images are consistent with a standard image or not; if at least one acquired image is inconsistent with the standard image, calculating the offset between the acquired image and the standard image; and adjusting the display content of the optical waveguide sheet corresponding to the acquired image by using the offset. According to the method and the device, the effects of timely finding out the display inconsistency of the binocular images of the AR glasses and timely adjusting the inconsistent display content are achieved.

The invention discloses an intelligent blind guiding glasses system based on a multi-mode large language model. The intelligent blind guiding glasses system comprises an image acquisition module, a voice acquisition module, a large language model module, a bone conduction sound transmission module, a navigation path planning module, a central processor module and a wireless communication module, the image acquisition module is used for acquiring a three-dimensional image of a front scene and providing three-dimensional space information; the voice acquisition module is used for acquiring a voice instruction of a user; the big language model module is used for generating character answers and converting the character answers into voice according to the voice instruction of the user by utilizing a big language model; the bone conduction sound transmission module is used for receiving and playing the voice generated by the large language model module; the navigation path planning module is used for planning a navigation path according to the user position and the destination; the functions of navigation positioning, line guiding, voice prompting and the like are provided for the blind, the glasses are adopted as a carrier, carrying is convenient, voice awakening and other instructions are adopted to replace keys, operation is easy, and practicability is high.

The invention relates to an intelligent glasses control method and system based on multi-modal privacy protection, and the method comprises the steps: collecting multi-modal sensory data of a user, carrying out the preprocessing of the multi-modal sensory data, and generating sensory sharing data; analyzing the sensory shared data by using a multi-modal privacy feature extraction algorithm to generate a privacy feature vector; classifying and identifying the privacy feature vectors based on a multi-layer privacy judgment rule to obtain a judgment result; performing data processing based on processing logic in the multi-layer privacy decision rule to generate shared data after privacy protection processing; storing the shared data subjected to privacy protection processing to a cloud end, retrieving the corresponding shared data subjected to privacy protection processing from the cloud end according to the sharing demand information of the target equipment, and encrypting the shared data to generate encrypted shared data; and decrypting and reconstructing the encrypted shared data in the target equipment to generate shared display data. The method has the effect of improving the accuracy of identifying the privacy data of the intelligent glasses.

The invention discloses an improved gesture recognition method suitable for an operation environment and an operation tool transmission system. The method comprises the following implementation steps: capturing an image by using a first visual angle of AR glasses, projecting a material required by a current operation into the AR glasses for virtual imaging to assist the operation, transmitting the image to an ROS system through TCP / IP and RosConnected, preprocessing the image, performing gesture recognition by using a RegNetCA network, entering a judgment gate after a gesture recognition result is obtained, and completing the operation according to the judgment gate. The robot arm is guided to grab and transfer corresponding objects, d435i on the kinova robot arm is used for object recognition, Yolov8 is used for recognizing the objects and returning three-dimensional coordinates of the objects, coordinates of the objects under a camera coordinate system are converted into overall coordinates through coordinate conversion, and after the coordinates are obtained, the robot arm reaches a target point position to grab the objects and transfer the objects to a designated position. According to the invention, a complete non-contact object transmission system is formed, and the accuracy of gesture recognition is improved through a color-fused gesture recognition algorithm.

The invention discloses an intelligent interaction control method for AI glasses, and relates to the technical field of AI glasses, and the method comprises the following steps: synchronously collecting user input signals and environmental parameters through a multi-source sensor group built in the glasses, the sensor group at least comprising an IMU, a binocular camera, a microphone array and a physiological sensor; carrying out real-time fusion processing on the multi-modal input data by adopting a lightweight neural network to generate an interaction intention feature vector; based on real-time detection results of environmental noise intensity and illumination conditions, dynamically distributing weight coefficients of all interaction modes; generating a hierarchical response instruction according to the weight coefficient and a confidence threshold; and continuously optimizing the personalized interaction strategy of the user through a federal learning framework. According to the AI glasses intelligent interaction control method, through multi-modal weighted fusion, edge AI acceleration and federated learning optimization, the interaction success rate in a complex environment is improved to 93.6%; the end-to-end delay is controlled within 28ms; and a user-defined interaction strategy is supported.

The invention discloses a multi-channel electroencephalogram signal spatial filtering and feature enhancement method and device for intelligent glasses, and the method comprises the steps: taking a multi-channel electroencephalogram signal collected by the intelligent glasses as an original signal, generating a corresponding electrode mapping relation for analysis, determining a spatial structure and a filtering scale, and generating a filter group according to the filtering scale; performing component separation on the original signal according to the filter bank, obtaining component information and a corresponding signal source, and constructing an independent component sequence according to the signal source; spatial mapping is carried out on the independent component sequence, main components are determined, a weight matrix is constructed for spatial filtering, a spatial feature sequence is generated for spatial reconstruction, and enhanced features are generated; performing multi-scale decomposition on the filter bank and the enhanced features, acquiring multi-scale features to construct a feature combination, acquiring corresponding time-frequency features to perform spatial mapping, acquiring interference modes corresponding to the time-frequency features to perform feature enhancement, acquiring corresponding feature representations to perform spatial reconstruction, and acquiring spatial enhanced features.

Systems and methods are provided for orienting a surgical tool (or medical device) at a desired insertion angle and location within an environment using a smart headset for use in installing the medical device. In certain implementations, a method may include initiating a smart headset to be calibrated to the environment so that the position of the smart headset is known relative to the environment when the smart headset moves in the environment; receiving, by the smart headset from an electronic device, environmental data indicating the position of the surgical tool within the environment; receiving, by the smart headset from the electronic device, the desired insertion angle; generating, by the smart headset or otherwise, at least one graphical element for orienting the surgical tool at the desired insertion angle (such as a three-dimensional insertion angle) and location; and displaying the at least one graphical element superimposed within the environment.

The disclosure relates to augmented reality devices based on a curved waveguide. An augmented reality device is provided. The augmented reality device includes a projection system to project an undistorted image, an input optical compensator located on the path of light rays out-coupled from the projection system, a curved waveguide comprising an input diffractive optical element and an output diffractive optical element. The output diffractive optical element performs the function of an output optical compensator that converts the light beams of a distorted image at the output of the waveguide into parallel light beams to output an undistorted image. Augmented reality glasses comprising an augmented reality device are also proposed. There is provided the ability to project a virtual image without aberrations, distortions and doubling of the image.

The invention discloses an information search system based on a large language model, intelligent glasses and an information search method. The system comprises an intelligent glasses system and a model server, and a large language model is configured on the model server. The intelligent glasses system obtains a first voice containing a to-be-queried user question, obtains prompt information, converts the first voice into a first text, and sends the prompt information and the first text to the model server. And the model server determines characteristics of the user question according to the prompt information and the first text through a large language model (LLM), obtains a second text containing question reply according to the characteristics, and sends the second text to the intelligent glasses system. And the intelligent glasses system converts the second text into a second voice and plays the second voice. Real-time information search based on LLM is realized in the intelligent glasses system.

The invention discloses an application development method, an application development device and XR equipment, and relates to the technical field of augmented reality, and the method comprises the steps: receiving a preset XR scene component dragged by a user to an XR scene template through a visual editor; in response to a user request, calling an AIGC model to generate an XR content material, and inserting the XR content material into a specified position of a current XR scene; and receiving the configuration of the user on the interaction logic, converting the current XR scene and the interaction logic into an executable format of the target XR glasses through the adaptation layer, and outputting an application package adaptive to the target XR glasses. Visual development and AIGC automatic content generation are combined, so that the XR content creation threshold is reduced, the development efficiency is improved, and diversified application scenes are supported.