334 results about "Visually impaired" patented technology

The invention provides a parallel attention convergence high-precision map construction method for assisting visually impaired people. The method comprises the following steps: firstly, collecting multi-view and multi-scale data of a traffic environment through multi-camera or multi-sensor equipment; a multi-scale feature fusion network EDS is utilized to integrate data features of different view angles, and semantic understanding of a complex scene is enhanced; then, accurate spatial position attention features are generated through a parallel attention aggregation module PAAM, and the feature aggregation effect and semantic segmentation performance are improved in combination with multi-scale context information; then optimizing multi-scale features by using a multi-resolution feature aggregation module MRFA to ensure the spatial consistency and real-time performance of the high-precision semantic map; and finally, applying the generated semantic map to a real-time navigation system for visually impaired people. According to the method, the semantic understanding and real-time map construction capabilities in a complex traffic environment are remarkably improved, and safe and accurate navigation assistance is provided for travel of visually impaired people.

The invention discloses a voice broadcasting method and device for visually impaired passengers and a storage medium, and relates to the technical field of vehicle-mounted voice broadcasting. The scheme comprises the steps of obtaining environment data of an environment where a target vehicle is located; and generating voice broadcast information according to the environment data by using a large language model so as to introduce the environment of the target vehicle to visually impaired passengers taking the target vehicle. Therefore, the environment data is integrated into the voice broadcast information, so that the visually impaired passenger can know the riding environment based on the voice broadcast content, the visual information gap is filled, the travel control feeling is effectively improved, the unstable emotion caused by information loss is relieved, and the riding experience of the visually impaired passenger is remarkably improved.

The invention provides a multi-mode integrated auxiliary system and method for a special demand group, and the system comprises a basic function subsystem which is used for collecting basic information, transmitting the basic information to an embedded processing unit, and providing an auxiliary service for the special demand group according to the related content from the embedded processing unit; the embedded processing unit is used for driving each module in the basic function subsystem, transmitting the received basic information to the cloud server and downloading related contents from the cloud server to the basic function subsystem; the cloud server is provided with a two-way sign language translation subsystem, a visual impairment navigation subsystem and a text-voice two-way conversion subsystem, and is used for carrying out two-way sign language translation, visual impairment navigation and text-voice two-way conversion on the basis of the basic information and sending generated related contents to the embedded processing unit or the user side; and the user side is used for visually displaying the related content.

The invention belongs to the technical field of braille input, and particularly relates to a braille input system, device and method, the input system comprises a braille input module, a braille display module, a communication module, a voice broadcast module, an algorithm processing unit and a core control unit, and the device is a contact display assembly and comprises a reset spring, a coil, a driving needle and an iron core. A plurality of round holes for accommodating the contact display components are formed in the shell, the iron cores, the reset springs and the driving needles are sequentially arranged in the round holes from bottom to top, the coils are sleeved on the iron cores, and the driving needles extend out under the action of the traction springs to form Braille convex points. According to the Braille input method, through hardware architecture optimization and multi-algorithm fusion, a Braille input solution with low cost, high portability and high recognition rate is realized, meanwhile, triple interaction modes of voice broadcast, visual display and tactile feedback are integrated, and the information interaction efficiency of visually impaired groups is remarkably improved.

The invention discloses an information acquisition system and method suitable for visually impaired people. The system comprises a hardware layer, a driving layer, an operating system layer, a middleware layer and an application layer which are sequentially in communication connection through interfaces. The application layer comprises a voice interaction module, a large model integration module and a braille conversion module; the hardware layer is used for collecting a voice input instruction and outputting a braille character sequence and a voice output result; the voice interaction module is used for converting a voice input instruction into a text input instruction and converting a text output result into a voice output result; the large model integration module is used for analyzing the text input instruction and generating a text output result; and the braille conversion module is used for converting the text output result into a braille character sequence, so that a hardware layer outputs the braille character sequence based on a timestamp alignment technology. Therefore, based on powerful semantic understanding and information retrieval of the large model integration module, accurate information acquisition is realized, and a five-layer decoupling architecture is adopted, so that the convenience of later system maintenance is improved.

The invention discloses a real-time collaborative cross-scene visual assistance and environment perception system for visually impaired people based on head-mounted equipment. According to the invention, through fusion of a multi-mode perception technology and a neural feedback mechanism, all-around environmental cognition support is provided for visually impaired people. Key targets such as curbs, steps and traffic signals in a complex scene can be accurately recognized, and a safe navigation scheme is generated in real time in combination with a dynamic path planning and obstacle avoidance algorithm. Through personalized feedback modes such as voice and vibration, the system can adjust the interaction rhythm according to the behavior habit and cognitive state of the user, ensure efficient and natural information transmission, effectively reduce the cognitive load of the user, help the visually impaired people to travel autonomously in different environments, improve the independent living ability, and improve the user experience. Real-time response and calculation efficiency are balanced through a collaborative architecture, so that a high-performance auxiliary function is not limited by heavy hardware equipment any more. The universal design reduces the use threshold, and is helpful for more visually impaired people to enjoy the convenience brought by science and technology.

Exemplary embodiments of the present disclosure are directed towards system for enhancing presentation accessibility through real-time audio and text narration. The system comprises computing and / or communication device with display unit for showing presentation content and processor executing instructions from real-time audio and text narration engine. The engine includes presenter-side script and control module that enables presenter to initiate and control slide transitions. Utilizing natural language processing algorithms, the engine listens to presenter's speech to detect cues and markers, triggering dynamic responses for changing slides and delivering images, audio playback, and text descriptions in real-time. Features include intro-sound indicator, AI voice reading, and special audio effects. Server, communicatively coupled via network, includes receiver module for receiving presentation content and processing module for generating real-time narration. The adaptive real-time response module monitors presentation content, user interactions, and feedback, making real-time adjustments to enhance accessibility for users, including visually impaired members.

The invention belongs to the technical field of education, and discloses a Chinese shadow puppet visual impaired person teaching guidance system and enlightenment method based on big data, a multi-modal data acquisition module assists the visual impaired person to establish spatial cognition by means of a sensor and three-dimensional modeling; the personalized teaching scheme generation module analyzes and customizes a teaching path according to the data and guides thinking; the real-time feedback module is combined with multiple technologies to timely correct operation; the culture knowledge base module integrates resources and constructs a shared community; the dynamic evaluation module generates a multi-dimensional report, supports family-school cooperation, assists the visually impaired person in learning shadow puppet art in an all-around manner, and constructs a personalized learning portrait through multi-modal data acquisition and intelligent analysis by applying technologies such as a sensor and voice interaction; implementing a dynamic self-adaptive personalized teaching strategy, customizing a teaching scheme according to portraits, pushing targeted tasks and generating interaction questions; multi-dimensional dynamic evaluation and collaborative optimization are carried out, an evaluation system is constructed for comparative analysis, a visual report is generated, and all parties collaboratively adjust the plan.

The invention relates to the field of intelligent aided navigation, in particular to a heterogeneous multi-agent collaborative full-scene continuous service system based on semantic comprehension, which realizes seamless navigation experience of visually impaired people among different scenes such as outdoor road sections, public facility internal channels and narrow spaces through a task division and handover mechanism driven by semantic comprehension. The semantic understanding module is used for constructing a semantic topological space and identifying a scene type and a user intention; the task division decision module optimizes a multi-agent cooperation structure based on a spectrogram theory; the task handover control module predicts scene switching opportunity and achieves smooth transition between intelligent agents, the system integrates a seeing-eye dog service intelligent agent, an unmanned aerial vehicle service intelligent agent, an intelligent walking stick service intelligent agent, a wearable equipment service intelligent agent and an environment fixing facility intelligent agent, and the most suitable intelligent agent combination is automatically selected according to different scenes. And an omnibearing, continuous and intelligent navigation service is provided.

Systems, devices, and methods related to provisioning services to a user are provided. An example of a user device worn by a visually impaired user is configured to obtain an image of a current scene surrounding the user, identify an object in the image, detect a plurality of texts associated with the object, detect a plurality of visual features and semantic features related to the text, determine an identity of the object and one or more attributes of the object based at least in part on the visual features and the semantic features, select one or more texts for presentation from the plurality of texts, and present the selected texts in an audio form to the user to allow the user to perceive the identity and one or more attributes of the object.

The embodiment of the invention discloses vehicle-mounted braille equipment, a control method and a vehicle. The vehicle-mounted braille equipment comprises a shell, a braille display module and a control module. The braille display module is located on the shell, and the control module is located in the shell. The braille display module is electrically connected with the control module, and the control module is used for controlling the braille display module to display braille. The control module is in signal connection with a vehicle cabin controller of the vehicle so that the vehicle cabin controller can conduct information interaction with the vehicle-mounted braille alphabet device. The vehicle-mounted braille equipment is in signal connection with the vehicle cabin controller of the vehicle, so that information interaction between the vehicle-mounted braille equipment and the vehicle cabin controller can be realized, a user with visual impairment can obtain vehicle information more accurately, some functions of the vehicle can be operated, and the user experience is improved. The riding experience of a user with visual impairment can be effectively improved, and the humanized design of the vehicle is improved.

The invention discloses an ophthalmology AI intelligent ward control system and method based on voice interaction. The system comprises an anti-noise voice acquisition unit, a multi-modal identity verification unit, a specialized semantic analysis unit, a medical rule engine unit, a safety protection unit, a multi-modal feedback unit and a dynamic optimization unit. Medical equipment noise is filtered out through a microphone array and an adaptive beam forming technology, and an instruction is analyzed in combination with a dialect recognition engine; executing triple identity verification, and performing forced superposition authentication on the cognitive impairment patient; calling an ophthalmology knowledge base to identify the risk keyword and generate a structured instruction; dynamically regulating and controlling the environment according to the eye disease type, and intercepting violation settlement according to a medical insurance rule; precise equipment voice control is forbidden, and when an emergency keyword is triggered, an OCT image is pushed preferentially and is directly connected with a physician; a big-character highlight interface and tactile pulse feedback are provided for the visually impaired patient, and data are synchronized to the HIS system in real time; and the dynamic optimization unit continuously updates the knowledge base and the medical insurance model. According to the invention, the instruction identification precision, the medical safety and the service suitability of the ophthalmology ward are obviously improved.

The invention provides an anti-counterfeiting traceability system and method based on a Braille dot matrix code, and the method comprises the steps: associating the multi-dimensional information of a whole life cycle of a product with the Braille dot matrix code through constructing a Braille dot matrix code generation rule of a fusion encryption algorithm and an error correction mechanism; storing the associated braille dot matrix code and product information to a block chain node to form a non-tampering traceability data chain; during verification, braille dot matrix codes are analyzed through visual scanning or tactile recognition, product information is extracted and subjected to consistency verification with hash values stored in the block chain, and tactile feedback interaction is provided for visually impaired users; and finally, anti-counterfeiting verification and full-process traceability of the product are realized, the use requirements of common users and visually impaired users are considered, and the problems that the existing anti-counterfeiting technology is easy to copy, the traceability data are unreliable and the traceability data are not friendly to visually impaired groups are solved.

A method includes receiving, for presentation to a user of a user device, image data representing an image. The method also includes generating, using a textual story generative model, based on the image data, a textual story for the image, and generating, based on the textual story for the image, textual story audio data representing the textual story for the image. The method further includes providing, for audible output from the user device, the textual story audio data.

The invention relates to the technical field of blind guiding sticks, in particular to an intelligent blind guiding stick based on an ultrasonic sensor, which comprises a stick body, an anti-slip handle and an anti-slip mat, the upper end of the stick body is fixedly connected with the anti-slip handle, and the outer side of the lower end of the stick body is sleeved with the detachable anti-slip mat; the crutch further comprises a vibration feedback device and an ultrasonic sensor, the vibration feedback device is arranged in the anti-skid handle, a solar cell panel and light-emitting strips which are symmetrically distributed up and down are installed in a concave position of the outer side of the crutch body, and a standby rechargeable battery, a GPS positioning module and a voice prompt module are sequentially installed on the outer surface of the crutch body from top to bottom. The upper end of the stick body is fixedly connected with an ultrasonic sensor; the intelligent blind guiding stick accurately measures the distance and the position of a front obstacle, an effective vibration feedback and voice prompt mode enables a user to know surrounding environment information in time, more comprehensive travel help is provided for visually impaired people, the endurance requirement of the user is guaranteed through the solar technology and a standby battery, and the intelligent blind guiding stick is suitable for popularization and application. And the portable and long-distance requirements are met.

The invention discloses a data input method and device for an intelligent POS with a silica gel keyboard, and the method comprises the steps: determining a key region and a touch window matrix of the silica gel keyboard on a display screen of the intelligent POS when the silica gel keyboard is detected at the outer side of the intelligent POS, adjusting a touch window on the display screen according to the touch window matrix, and waiting for the operation of a user, when a touch signal is received, coordinate information of a user touch position is obtained, whether user operation is in a key area of the silica gel keyboard on a display screen of the intelligent POS is judged according to the coordinate information, and if yes, a key value corresponding to the user touch position is determined according to a key matrix corresponding to each key of the silica gel keyboard stored internally and the coordinate information; and storing the key value in the storage area. According to the technical scheme, the application program in the intelligent POS does not need to be modified, and the method is suitable for common users, visually impaired users and outdoor special scenes and is safe and convenient to use.

The invention discloses an automatic injection pen which comprises a pen container shell with the open front end, a pre-filling syringe is arranged in the pen container shell, a medicine pushing rod and a locking mechanism are arranged in the pen container shell, and an unlocking structure is further connected to the pen container shell in a sliding mode. The pen container shell is further provided with a first elastic element which pushes the medicine pushing rod to collide with a piston of the pre-filled syringe after the locking mechanism is unlocked so as to make a first prompt sound and enable the pre-filled syringe to conduct injection. And a prompting piece is arranged between the medicine pushing rod and the pen container shell, wherein the prompting piece is locked when the medicine pushing rod is in the initial state, and the prompting piece is unlocked when the injection of the pre-filled syringe is finished after the medicine pushing rod advances by a second preset distance, so that the prompting piece collides with the pen container shell to give out a second prompting sound. The product can respectively generate clear and distinguishable sounds at two key nodes of injection starting and injection completion, so that a user can accurately judge the injection process without depending on vision, the product is suitable for visual impairment people or operation in an emergency scene, and the medication safety and psychological safety are improved.

The invention relates to the technical field of visual impaired people assistance, in particular to a self-adaptive perception prompting system and method for visual impaired people assistance, and the method comprises the following steps: obtaining environment data around a user; the target information is recognized and transmitted to the user through the wearable somatosensory feedback module in a skin stimulation mode, so that the user can perceive surrounding objects and directions thereof through skin stimulation, and then obstacle avoidance can be achieved. Furthermore, an active exploration self-adaptive auxiliary module is introduced, an action track of a user is collected and analyzed to be compared with an environment model, an omission area or space deviation in perception is recognized, and a reinforcing prompt is triggered, so that the user is guided to complete more comprehensive environment exploration and space construction. Limitations of a traditional blind guiding stick and a traditional blind guiding dog are avoided, and higher-precision space perception and navigation assistance can be obtained only by wearing the somatosensory feedback module.

Systems, devices, and methods related to provisioning services to a user are provided. An example of a user device worn by a visually impaired user is configured to obtain an image of a current scene surrounding the user, extract visual features of the image, determine a bounding box in the image based on the visual features, detect a vehicle within the bounding box, detect textual features associated with the vehicle in the bounding box, determine vehicle information of the vehicle based at least in part on the textual features, and present the vehicle information in an audio form to the user.

Systems, devices, and methods related to provisioning services to a user are provided. An example of a user device worn by a visually impaired user is configured to detect a current scene surrounding the user, obtain real-time user data and image data of the current scene, recognize objects in the current scene using the real-time image data, determine a point of interest (POI) associated with the user, select one or more objects relevant to the determined POI, identify one or more features associated with the identified objects, determine information about the identified objects and the identified features associated with each one of the selected objects, generate audio signals corresponding to the information, and output the audio signals through the user device to convey the information to the user and to allow the user to perceive the selected objects and the identified features associated with each selected object.

1. The name of the design product: blind recognition reminder. 2. The use of the design product: the design product is a blind stick detection device, which is used to detect obstacles and remind the visually impaired people when they go out. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective drawing.

The invention relates to an electronic watch with a sense of direction for visually impaired individuals which minimizes the transportation problem for visually impaired individuals and enables them to move as they wish without the need for anyone and which comprises the parts of watch case (1), battery (8), vibration motor (3), motherboard (7), processor, microphone (6) and solenoid coils (4).

1. Name of the product in this design: Braille Touch Trainer. 2. Purpose of this design: To assist visually impaired individuals in Braille touch training. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

To provide a game machine capable of increasing working efficiency in a manufacturing process of the game machine by a worker having a visual handicap.SOLUTION: In a Pachinko machine equipped with a game board having a flow-down area in which game balls can flow down, a recessed and projecting notation section 2111 indicated in a recessed and projecting shape is provided in a predetermined position of a middle flow path section 2102 provided in the game board as a flow path of game balls, character information by the recessed and projecting notation section 2111 is provided such that it can be touched by finger tips, the middle flow path section 2102 is mounted to a ball route unit 2100A provided in a predetermined position within the game board, and the recessed and projecting notation section 2111 cannot be visually recognized easily from the outside than when it is visually recognized directly when it is correctly mounted to the ball route unit 2100A, and the recessed and projecting notation section 2111 is visually recognized easily from the outside when it is mounted wrongly than when it is correctly mounted to the ball route unit 2100A.SELECTED DRAWING: Figure 160

The invention relates to the field of intelligent question and answer calculation, in particular to a visual impairment group vertical field multi-modal intelligent question and answer method based on a neural network, which comprises the following steps: S1, knowledge base preprocessing: standardizing a knowledge base, including performing information extraction, semantic understanding and multi-modal dialogue on texts in the knowledge base; s2, performing structured processing on the multi-mode vertical domain knowledge base; s3, generating detailed description information from the knowledge of the picture modality through an image-text big model; s4, forming a document by using the decomposed subject-predicate-object structure and the fixed complementary structure to replace the original characters, and identifying the document by using an ID (Identity); s5, collecting related attributes of the entities according to the query ID, and generating a candidate attribute list; and S6, according to the score, determining an attribute relationship closest to the question, and taking out an attribute value of the closest attribute relationship to complete answering. The method has the advantages that more accurate and personalized multimode vertical domain knowledge introduction question and answer service can be provided for visually impaired people to obtain information.

The embodiment of the invention provides a game control method and device, equipment, a readable storage medium and a program product, and relates to the field of maps and the like, and application scenes include but not limited to chess game scenes. The method comprises the following steps: displaying a target picture in a game through a terminal; in response to a detected touch operation for elements in the target picture, converting the touch operation into a corresponding vibration code based on a preset mapping relation table; corresponding vibration signals are generated based on the vibration codes, the terminal is controlled to conduct corresponding vibration based on the vibration signals, and the vibration signals are used for representing touch operation for the elements; in this way, through the vibration prompt in the chess game, the accuracy of the visually impaired user in controlling the chess game is improved.

1. The name of the design product: smart glasses. 2. The use of the design product: for the wearer to perceive multimedia information, and can be used for navigation by visually impaired people. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

This invention discloses a dynamic obstacle avoidance method for assistive visually impaired scenarios. First, a feature extraction module based on a hierarchical residual structure constructed within residual blocks is built, which expands the receptive field of deep features. Second, a spatial feature recovery module based on bilinear interpolation and transposed convolution upsampling is designed to make segmentation edges more accurate. Third, a discrete sampling strategy is used to extract obstacle category, distance, and contour information, and path planning is performed using a heuristic search algorithm considering safe distance constraints. Finally, priority rules and logical order rules for the obstacle avoidance warning system are assumed, and a decision is generated based on the planned path, effectively guiding blind users to avoid obstacles through auditory and tactile information. This invention solves the problem that single-stage instance segmentation algorithms struggle to simultaneously and accurately segment small target obstacles and background road surfaces, overcoming the difficulty of providing effective information for obstacle avoidance decisions in assistive visually impaired scenarios with instance segmentation results, enabling blind users to avoid obstacles more intelligently and autonomously.

1. Name of the product in this design: Braille dot display module. 2. Purpose of this design: Electromechanical assistive device for visually impaired individuals. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The present invention discloses an embedded music / Braille text conversion system capable of visually, audibly and tactilely synchronously presenting, which includes an acquisition module for acquiring musical scores in MusicXML format, a conversion module for converting the musical scores in MusicXML format into Braille musical scores consisting of Braille dots, and an output module for simultaneously outputting the Braille musical scores in three ways: visually, audibly and tactilely. The conversion system has a fast calculation speed and high accuracy, smoothly provides a new feasible means for Braille musical score information, and can realize the embedded function of visually, audibly and tactilely synchronously presenting Braille musical scores, with clear and accurate visual display, complete auditory reproduction, clear tactile sensation, and better presentation effect, which can further improve the efficiency of visually impaired people learning musical scores, and provide convenience for visually impaired people to acquire and touch-read a large amount of music materials.