14 results about "Auditory sense" patented technology

The invention discloses a robot control method based on multi-modal perception and related equipment thereof, and belongs to the technical field of robots. According to the method, multi-modal sensing, hierarchical fusion processing, path planning and reinforcement learning decision collaborative mechanisms are introduced in the robot control process, so that the robot can realize more comprehensive and reliable environment cognition and autonomous control in a complex, dynamic and uncertain environment. Through carrying out synchronization and fusion processing on heterogeneous sensing information such as visual sense, auditory sense, tactile sense and force sense, richer environment information is obtained; through key feature extraction and evidence theory fusion, a relatively consistent environment state evaluation result can be formed when multi-source information has differences or conflicts. Planning a global optimal path through path planning in combination with environmental cost constraint, kinematics constraint and a risk assessment model; through continuous training and optimization of a motion control strategy, the control strategy can be adaptively updated according to operation data.

The invention relates to the field of man-machine interaction, in particular to a method for enhancing user space perception in augmented reality virtual pet interaction, which comprises the following steps executed in sequence: S1, constructing a space reference; s2, the multi-mode perception feedback stage comprises intelligent scheduling of auditory sense and tactile sense of the virtual pet; s3, the virtual pet behavior parameter control stage comprises the following steps: S31, taking the bearing plane as a motion constraint area of a virtual pet, performing reachability judgment on a target position, and when the target position exceeds the motion constraint area or falls into an unreachable area, executing the step S3; limiting the target position in the motion constraint area or projecting the target position to a nearest reachable point of a boundary; s32, when the walking speed, running speed, acceleration or single-frame displacement of the virtual pet reaches a preset upper limit, judging that the virtual pet is abnormal, and performing abnormality processing; intelligent scheduling is carried out in auditory sense and tactile sense, and the consistency of multi-mode feedback and visual sense in time sequence is ensured.

The invention discloses a tunnel traffic accident emergency escape unmanned aerial vehicle cooperative guidance system and method, and belongs to the technical field of tunnel safety emergency. The system comprises an unmanned aerial vehicle nest unit which is internally provided with an ejection mechanism and accommodates a plurality of foldable unmanned aerial vehicles, a guiding unmanned aerial vehicle which carries an SLAM navigator, a thermal imager, a projection lamp and an emergency material putting device, and a communication relay unmanned aerial vehicle which constructs a Mesh + optical communication redundant link. According to the control method, path planning is dynamically optimized based on a reinforcement learning algorithm, and visual sense-tactile sense-auditory sense multichannel guidance is realized in combination with UWB positioning and the adaptive projection lamp. According to the invention, the sensing precision of the complex environment is improved through multi-sensor fusion positioning, the communication delay is reduced through cooperation of the dual-frequency Mesh network and optical communication, the evacuation efficiency is improved through interaction of dynamic projection and the AR terminal, the problems of real-time positioning, communication coverage and accurate guidance in a tunnel fire scene are effectively solved, and the success rate of emergency rescue is remarkably improved.

The utility model relates to the technical field of generator air cooling systems, and provides a cross-core type columnar CT plugging device which comprises a threading pipe, a lock catch assembly and a plugging mechanism. By arranging the insulating plates and sleeving the two insulating plates on the outer side of the through core of the straight-through type columnar current transformer, holes are effectively blocked, the air leakage hidden danger of an air cooling system of a generator is eliminated, the cooling efficiency of the generator is improved, the service life of equipment is prolonged, and after the air leakage problem is eliminated, noise and vibration in a main open chamber of the generator can be remarkably reduced; damage to auditory sense of personnel is reduced, interference signal transmission is avoided, loosening and abrasion of electrical fastening parts are prevented, operation hidden dangers are reduced, meanwhile, sand grains entering the air cooling air chamber are reduced, and the surfaces of generator fan blades and stator windings are prevented from being impacted and damaged by the sand grains. The epoxy resin insulating plate has good insulating performance and mechanical strength, and the service life of the generator is prolonged. And meanwhile, the epoxy resin insulating plate is short in customization period and simple and convenient in process.

The invention relates to the field of intelligent medical treatment, in particular to a cloud side-end collaborative diabetes intelligent medicine box management system and a compliance optimization method, and the system comprises a terminal sensing layer, an edge cognitive layer and a cloud intelligent layer. The terminal sensing layer acquires data through an environment self-adaptive multi-dimensional sensor module and has a temperature and humidity compensation function; the edge cognitive layer generates a medication time window adjustment instruction and a medication reminding strategy based on a multi-dimensional health state model, and is provided with an offline emergency system; the cloud intelligent layer is responsible for data encryption storage and analysis processing; the multi-mode man-machine interaction module sends prompts through visual sense, auditory sense and tactile sense according to the medication prompting strategy; according to the method, high-precision identification and dosage monitoring of the medicine are realized, the problem of false compliance is solved, and the medication effect is improved by dynamically optimizing the medication time window.

The invention discloses a material detection image defect enhancement method based on multi-light source complementation, and the method comprises the steps: collecting recognition parameters, carrying out the processing of a ternary mapping model, and outputting a noise feature prediction value and a multi-light source initial parameter; optimizing the initial parameters of the multiple light sources to obtain optimized parameters, then adjusting the multiple light sources, and collecting a noise-containing image of the to-be-detected material through a detection camera; inputting the noise feature predicted value, the optimization parameter and the noise-containing image into a preset conditional GAN anti-noise model with light source constraint, and generating a defect enhanced image; and when the parameter optimization criterion is not met, the optimization parameters are adjusted, the steps are repeated after a new noise-containing image is collected, a defect enhancement image is output until the parameter optimization criterion is met, and the defect enhancement image with obvious and accurate characteristics is generated by coordinating multi-light-source parameter adjustment and introducing a condition GAN. By introducing an artificial intelligence function library and computer visual and auditory sense to carry out model training reinforcement, the accuracy of subsequent defect identification can be greatly improved.

Provided is a driver assistance system or the like that makes it possible to assist a driver in taking a driving behavior more effectively by stimulating the auditory sense of the driver without executing complicated processing. A management server 20 repeatedly executes a behavior data acquisition process including acquiring behavior data of the driver based on a sound effect and a sound effect output control process including outputting the sound effect into the vehicle 1 while changing an output condition for outputting the sound effect into the vehicle 1. When the result of these processes satisfies a setting condition set in advance, the management server 20 executes an identification process including identifying the output condition corresponding to the result as an optimal output condition.

The present application provides an audio previewing method, an apparatus and a storage medium. The method plays, on a target audio file set interface, an audio preview clip of at least one audio file in a target audio file set in response to a previewing request of previewing the target audio file set without entering a target audio file set detailed interface, so that a user can quickly preview the target audio file set through auditory sense, and the user can preview the at least one audio file in the target audio file set at a time, which is simple in operation. In addition, embodiments of the present application further display, on the target audio file set interface, information of an audio file corresponding to the audio preview clip that is currently played during previewing, such as name and / or singer.

The invention discloses a multi-modal feedback-based anti-falling VR training system and method for the aged with osteoporosis, and relates to the technical field of VR virtual reality. The system comprises a safe VR training scene library, a multi-modal biomechanics and cognitive state real-time monitoring network, an immersive multi-modal real-time feedback mechanism and a self-adaptive difficulty adjustment module based on user performance. The safety type VR training scene library simulates daily falling risk scenes of old people, the multi-mode biomechanics and cognitive state real-time monitoring network collects and analyzes data such as motion balance of a user through hardware and software, and an immersive multi-mode real-time feedback mechanism guides the user to perform multi-aspect training from visual sense, auditory sense and tactile sense. According to the invention, customized training can be provided for the user in a safe environment, and the anti-tumble ability of the elderly can be improved while the training enthusiasm of the elderly user is improved, so that the risk that the elderly is injured due to tumble is reduced.

The invention relates to the field of artificial intelligence education, and discloses a question generation method based on artificial intelligence and an intelligent system.The method is used for the intelligent system, interaction between the intelligent system and a user is achieved through questions.The method comprises the steps that S1, the front-end language gradient level of the user is obtained through the intelligent system; s2, extracting visual, dynamic and auditory questions from the original question gradient set based on the front-end language gradient level; s3, adjusting the question state in the original question gradient set according to the response of the user to the visual, dynamic and auditory questions; and S4, reproducing visual, dynamic and auditory questions through the intelligent system according to the rule of the forgetting curve. Existing AI language learning software has technical bottlenecks, for example, the feedback learning process of overseas users is relatively flat, and the language level is difficult to make significant progress in a short time; according to the method, comprehensive enhancement of vision, kinesthetic sense and auditory sense can be realized through visual, dynamic and auditory topics, so that the time required by a user for learning a new language is remarkably shortened.

We provide the system. [Solution] A means for receiving data acquired from multiple moving objects in real time and performing analysis to detect anomalies, Means for transmitting the analyzed anomaly data to a device for conveying it to the visual and auditory senses of the front-end user, A means for sharing detected anomaly patterns among intelligent devices mounted on multiple mobile vehicles and for autonomous learning, A system that includes this.

The invention discloses a digital sound watermark processing method and device based on echo hiding and electronic equipment, and relates to the technical field of digital watermarking. According to the core scheme of the digital sound watermark processing method based on echo hiding, a first audio signal is segmented through duration, then the energy of each segment is calculated, watermarks are embedded into the segments with high energy through an echo hiding method, and watermarks are not embedded into the segments with low energy. In this way, the shielding effect of human auditory sense is utilized, that is, the strong signal can cover the adjacent weak signal, so that the imperceptibility after the watermark is embedded is improved while the robustness of the watermark is ensured, that is, the relatively high audio subjective quality is kept. Meanwhile, an effective way is provided for controlling the embedding capacity of the watermark.

The utility model discloses a combined sound system, which comprises a first audio playing unit and a second audio playing unit, and sound waves emitted by the first audio playing unit are medium-high frequency sound waves processed by high-pass filtering; the sound waves emitted by the second audio playing unit are low-frequency sound waves after low-pass filtering processing. Through the design, an audio signal emitted by sound source equipment can be received by the two playing units and is accurately divided into two frequency bands by the two playing units, and the two frequency bands are respectively processed and played by the different playing units, so that the first audio playing unit is only used for replaying middle and high pitches; the second audio playing unit is only used for playing bass, and the first audio playing unit and the second audio playing unit are fused into a complete sound in auditory sense, so that an audience can obtain a complete audio signal, a three-dimensional surround sound effect can be realized, bass performance can be considered, and the audience is ensured to have relatively good sound playback experience.

The invention discloses a novel intelligent teaching device for a smart classroom, and the device comprises a first fixed plate, the upper end of the front surface of the first fixed plate is fixedly provided with an LED lamp strip, the lower end of the front surface of the first fixed plate is fixedly provided with a microphone, and the front of the first fixed plate is provided with a multimedia display screen. An electrical box is fixedly installed at the middle end of the back face of the first fixing plate, and an image recognition module, a microprocessor main control module, a word database module, a voice recognition module and a sentence processing verification module are sequentially and fixedly installed in an inner cavity of the electrical box from left to right. The physical operation that a student manually shakes the rotating shaft participates in learning, visual presentation of the letter balls, display of the word list, voice interaction of oral sentence making and color feedback of the LED lamp strip are combined, the touch sense, the visual sense and the hearing sense of the student are fully aroused, the interaction mechanism that physical operation and intelligent feedback are deeply fused is adopted, and the learning efficiency is improved. The interestingness of learning and the sense of participation of students are greatly enhanced.