218 results about "Mimetic Muscles" patented technology

The invention discloses an intelligent multi-modal virtual digital human interaction system based on an AI language large model. The system comprises a high-authenticity face generation module; the high-authenticity face generation module uses an AdaAN network, based on adaptive feature fusion and voice driving and time sequence modeling of voice features, feature information related to voice is extracted, the extracted voice features are processed through a deep neural network, it is ensured that the voice and facial expressions are highly aligned in time and space, and the face recognition accuracy is improved. Collecting a bio-electricity signal, mapping the signal to facial muscle movement, generating a final facial expression, and interacting with a user; the system further comprises an intelligent interaction module, a training optimization and efficient generation module, an efficient integration module, a multi-modal data acquisition module, an AI large model core processing module, a digital human image generation and driving module, an interaction scene adaptation module and a feedback optimization module. The invention further discloses a multi-mode digital human interaction method which has wide application value.

The invention discloses a fatigue driving monitoring and early warning method based on multi-dimensional feature fusion, and relates to the field of intelligent traffic and safe driving, and the method comprises the steps: carrying out the feature extraction of a collected face image of a vehicle driver through a feature extraction model based on a convolutional neural network, and obtaining a face key point; then calculating the eye closing rate, the mouth opening rate, the head posture data and the facial muscle data to finally obtain multi-dimensional features, and fusing the multi-dimensional features by using a multi-layer perceptron to obtain fused facial features; and then, a fatigue state detection model obtained based on recurrent neural network training is utilized to detect the facial feature time sequence at a plurality of continuous sampling moments so as to detect whether a fatigue driving state occurs and trigger alarm feedback. According to the method, the fatigue state of the driver can be identified and judged more accurately through combination of multi-dimensional data fusion and a time sequence analysis algorithm, and the monitoring and early warning accuracy and reliability are improved. And the system can keep high robustness even in an illumination change or complex driving environment.

The invention provides a virtual human design and application platform, method and device based on artificial intelligence, and relates to the technical field of virtual digital humans. The method comprises the steps of performing local anonymization on multi-modal input data on user equipment, encoding generated anonymized multi-modal features to obtain a multi-modal feature vector, and inputting the multi-modal feature vector into an emotion calculation model to obtain a user emotion intensity quantized value; inputting the multi-modal feature vector into a context sensing model, and generating a user intention vector after context correction in combination with a knowledge graph; generating an updated personality parameter matrix according to the user emotion intensity quantized value and the user intention vector; and outputting voice waveform data, facial muscle motion parameters and skeleton joint coordinate data based on the personality parameter matrix, and driving the virtual digital human three-dimensional model to perform real-time rendering. According to the scheme, the naturalness, emotional resonance and long-term user retention rate of virtual digital human interaction can be improved, and user privacy data security is protected.

The invention provides a digital human generation method based on a multi-modal large model. The method comprises the following steps: constructing a digital human basic model; generating a structured training set; generating a question and answer model supporting multi-channel interaction; semantic answers of the user questions are output, text emotional tendencies of the semantic answers are extracted, and emotional intensity parameters are output; generating facial muscle movement track data, and performing real-time rendering on the digital human basic model according to the facial muscle movement track data to output a digital human three-dimensional image with emotion expression. According to the embodiment of the invention, cross-modal alignment is carried out on text, image and audio data, and a multi-modal large model containing visual, voice and knowledge models is optimized by using a joint training method, so that more natural and smoother multi-channel interaction experience is realized; in addition, by introducing an emotion recognition model and a face interaction model, the emotion tendency contained in the semantic answer can be captured and reflected more accurately, so that a digital human three-dimensional image with real emotion expression is output.

The invention relates to the technical field of pain assessment, in particular to a paediatric pain assessment system which comprises a muscle group rhythm recognition module, a behavior linkage screening module, a periodic fluctuation extraction module, a behavior physiological difference module and a pain grading judgment module. According to the method, a linkage offset identification path is constructed through an angle relation between facial muscle groups and a starting time sequence, multi-muscle cooperative imbalance performance is identified, a region-level dynamic behavior judgment basis is formed, and a behavior cooperative judgment mechanism is established by utilizing response overlapping conditions of multiple behavior characteristics in the same time period; path signals which do not form effective cooperation are eliminated, the effectiveness of behavior characteristics is enhanced, a continuous trend structure of peak time in rhythm change is introduced, a periodic response sudden change monitoring channel is constructed, the recognition sensitivity of a short-time fluctuation concentration section is improved, and a response mismatch section is extracted based on a trigger time dislocation state between behavior and physiological response, so that the recognition sensitivity of the short-time fluctuation concentration section is improved. And a pain judgment key point is positioned in the time sequence overlapping region.

The invention relates to the technical field of face verification, and discloses a face identity verification data processing method based on dynamic feature extraction, which comprises the following steps: acquiring a continuous face video frame sequence and calculating a full-pixel instantaneous velocity vector to generate an original dense optical flow field, selecting rigid region anchor points to calculate a rigid affine transformation matrix and construct a theoretical rigid motion field, performing differential stripping on the theoretical rigid motion field from the original dense optical flow field, and extracting a non-rigid micro-motion residual field; mapping the non-rigid micro-motion residual field to a facial muscle topological grid to generate a time sequence feature tensor, and calculating a geodesic line distance between a covariance matrix of the time sequence feature tensor and a reference dynamic feature in a Riemannian manifold space; when the geodesic distance is smaller than a threshold value, verification is passed, through a rigid-non-rigid orthogonal decomposition mechanism, the special viscoelastic micro-motion and cooperation law of biological soft tissue is captured by utilizing a residual field, and the high-simulation mask is effectively defended.

The invention discloses a facial action unit identification method based on CLIP and multi-mode mask prompt learning. The method comprises the following steps: 1, carrying out facial action unit identification on the basis of the CLIP and the multi-mode mask prompt learning; the method comprises the steps that 1, a multi-modal shared AU prompt (AU-prompt) and an attention mask are designed based on an AU prior position, the AU-prompt comprises a plurality of learnable tokens, the attention mask is designed according to prior positions of different AU facial muscle changes, and a specific AU attention mask is obtained; 2, in a multi-mode prompt learning process, introducing an attention mask of a specific AU into different layers of a CLIP model text and an image encoder for prompt learning, and learning local detail features of the AU and global association features among different AUs to obtain local features and global features; and step 3, fusing the local features and the global features, calculating loss with the text features, and finally realizing AU identification. According to the method, the facial action unit can be effectively recognized under the condition that the labeled data is limited.

The invention relates to the technical field of bionic expression robots, in particular to a facial muscle neural network intelligent bionic expression robot control system which comprises a supporting body, a power module, a control module, a muscle neural network and an expression generator. According to the facial muscle neural network intelligent bionic expression robot control system, grid conductors are connected with second sensors, a plurality of intersection points are formed among the grid conductors, each intersection point is distributed and connected with a driving unit, and the tail ends of the grid conductors are electrically connected with first output ports. The driving units generate driving force under the action of the control unit, the first sensor is used for sensing longitudinal force generated by the driving units, and the second sensor is used for sensing transverse force generated by the driving units, so that when the first output port outputs a power difference value through the grid conductor to act on the driving units, the power difference value acts on the driving units. And the power difference value of the adjacent driving units continuously changes, so that the deformation area generates continuous deformation quantity.

The invention discloses a voice-driven facial animation simulation method based on facial muscle linkage, and belongs to the field of artificial intelligence, and the method comprises the steps: S1, constructing a PPMF encoder; s2, constructing a decoder based on FDCP to decode FP features provided by the PPMF so as to obtain a facial animation; s3, training a 3D face animation framework DCPTalk driven by voice; s4, optimizing the model; and S5, quantitatively evaluating the model. According to the invention, a DCPTalk framework is provided, and the Mouth2Face is provided based on the linkage characteristic of the facial muscle group. Motion of the mouth has strong correlation with voice signals, and can be synthesized with sound track dynamics easily. In order to further enhance the details of the facial movement, the Refine Decoder is adopted to simulate the skin deformation of the surface layer to refine the facial animation. Inherent body characteristics and body characteristics related to facial muscle group movement are embedded into Mouth2Face, a personalized facial muscle control system is constructed, and meanwhile, an external driving signal is modulated by using a speaking style. Qualitative and quantitative experiments and user research show that the DCPTalk is superior to the most advanced method in the prior art.

The invention relates to the field of human-computer interaction, and discloses a human-computer interaction robot facial expression implementation control method, which comprises the following steps: dynamically capturing the face, sound and posture of a user in a human-computer interaction scene, and generating an initial emotion perception sequence; performing hierarchical cross mapping on the initial emotion perception sequence, and performing combinatorial analysis on facial expressions, voices and intonations and body movement features to form an emotion matching vector; based on the emotion matching vector, utilizing a priority regulation model to predict the emotion trend of the user at the next moment, and identifying an expression enhancement point and an emotion attenuation area; mapping the generated facial micro-expression adjusting instruction to a robot facial driving unit, and performing real-time correction and conflict resolution on an expression action sequence; and reversely fusing a user fixation point, facial muscle micro-motion and voice emotion which are acquired in real time into an emotion matching vector, and dynamically updating a perception weight and expression regulation and control parameters. The method has the advantage of improving the emotion matching degree of the robot expressions.

The invention discloses an interactive humanoid robot expression simulation method based on artificial intelligence, and relates to the technical field of expression simulation, and the method comprises the steps: collecting a brain wave signal of a user, carrying out the preprocessing, and generating a power spectrum density feature; inputting the power spectral density features into a pre-trained emotion classification model, and outputting an emotion category and an emotion intensity value of the user; performing emotional expression mapping on the emotional category and the emotional intensity value, and outputting a bionic muscle contraction instruction; performing facial adjustment on facial muscle fibers of the humanoid robot according to the bionic muscle contraction instruction, dynamically adjusting surface texture details of the humanoid robot, and generating a simulated micro expression; and capturing user face feedback data through camera shooting eyeballs, evaluating the acceptance degree of the user on the simulated micro-expression based on the user face feedback data, and outputting an expression optimization strategy. According to the method, through deformation matching and expression optimization double-closed-loop modeling driven by user feedback, biological simulation of micro-expressions of the humanoid robot is realized.

The utility model provides a facial paralysis rehabilitation training robot which comprises a head-mounted robot body, a power system and a traction system, and the power system and the traction system are both installed on the head-mounted robot body. The head-mounted robot body is provided with a guide panel, the traction system passes through the guide panel from the head-mounted robot body and extends to a face area, and / or the traction system does not pass through the guide panel from the head-mounted robot body and extends to the face area; and the power system drives the traction system to pull or relax target facial muscles of the patient. The traction system is driven by the power system to move, appropriate force and resistance are applied to facial muscles of a patient to promote movement and activity of the muscles, the activity range of the facial muscles can be increased, neuromuscular connection can be improved, recovery of facial expressions can be promoted, and appropriate force and resistance can be provided; therefore, the patient is helped to gradually recover the functions of facial muscles.

The invention belongs to the technical field of image restoration and computer vision, and particularly relates to a multi-mode face restoration and expression recognition system and method based on semantic guidance of a facial action unit. According to the system, multi-scale features are extracted through visual coding, and an AU activation probability is detected by using a graph neural network; the semantic conversion module converts the numerical probability into an interpretable biomechanical structured text; the multi-modal reasoning module fuses vision and text information, introduces the common sense reasoning ability of a multi-modal large language model, and improves the student network performance through knowledge distillation; and finally, the conditional generation module realizes image restoration by taking the semantic features as guidance. The facial action unit is used as a biomechanical medium, the multi-modal reasoning ability is converted into restoration constraint, the defects that in the prior art, restoration of physiology is distorted, recognition depends on image quality, and two tasks are isolated are overcome, collaborative enhancement of face restoration and expression recognition is achieved, and it is ensured that the restoration result is clear in vision and conforms to the physiological law of facial muscles.

The invention relates to the technical field of English pronunciation learning, and discloses an AI (artificial intelligence) English learning system capable of correcting pronunciation. The system comprises a multi-source voice acquisition layer, an acoustic feature analysis layer, a pronunciation quality evaluation layer, a correction decision generation layer and a biological feedback execution layer. The multi-source voice acquisition layer captures a multi-channel sound wave signal and a maxillofacial electromyographic signal in real time when a user pronounces, and generates an original pronunciation data stream; the acoustic feature analysis layer performs time-frequency domain conversion on original data, separates multi-scale acoustic features and constructs a three-dimensional feature tensor; the pronunciation quality evaluation layer compares the standard template library to output scores and phoneme offset vectors; the correction decision generation layer constructs a pronunciation error topological graph and generates a correction instruction set containing tongue position, airflow and vocal cord parameters; and the biological feedback execution layer synchronously monitors the physiological response and updates the weight of the template library. According to the system, accurate acquisition, analysis, evaluation, correction and dynamic optimization of pronunciation learning are realized, and the English pronunciation learning effect is improved.

The invention provides an intelligent expression generation method and system based on a facial motion unit, and belongs to the technical field of intelligent generation, and the method comprises the steps: determining a unit data set of each facial motion unit of a corresponding individual based on a multi-modal facial sample; inputting the phoneme codes into an expression predictor to obtain a prediction data set of each facial motion unit; establishing a mapping relationship based on the unit data set of each facial movement unit according to different individuals in various expression states, and establishing a neutral relationship between each facial movement unit and the corresponding expression state in combination with a deviation set determined based on the prediction data set and the unit data set; establishing a facial motion unit expression model; and searching required motion features and parameter settings from the established facial motion unit expression model, and performing dynamic adjustment based on physical constraints of facial muscle motion and natural transition constraints of expression changes to generate expression animations for interaction. And a high-precision, high-reality and controllable expression generation effect is realized.

The utility model discloses a facial muscle auxiliary massage device which comprises a mounting plate, threaded grooves and limiting holes are formed in the periphery of the outer wall of the mounting plate in an annular array penetrating mode, the limiting holes are located on the outer sides of the threaded holes, and the facial muscle auxiliary massage device further comprises adjusting assemblies connected to the inner walls of the threaded holes in a threaded mode. A wearing assembly is fixedly connected to the outer wall of one side of the mounting plate, the adjusting assembly comprises a threaded rod screwed to the inner wall of the threaded hole, and a U-shaped handle is fixedly connected to the outer wall of one end of the threaded rod. When a patient feels that the L-shaped massage soft cushion excessively or slightly extrudes facial muscles, the threaded rod can be rotated, the position of the extrusion assembly can be adjusted forwards or sequentially when the threaded rod rotates, the position of the L-shaped massage soft cushion can be conveniently adjusted so that the L-shaped massage soft cushion can be comfortably attached to the face of a user, and the using effect is guaranteed.

The invention discloses a physical and psychological health evaluation method based on a facial micro-vibration image, and belongs to the technical field of artificial intelligence emotion calculation. The method comprises the following steps: acquiring a facial video, analyzing and measuring to obtain the frequency and amplitude of pixel points in facial muscles, further calculating various psychological and physiological indexes, and displaying a light ring of a facial contour through a video frame; results based on frequency and amplitude changes of pixel points in facial muscles can be visually seen; and respectively calculating different parameter models based on the obtained frequencies and amplitudes of the pixel points in the facial muscles so as to calculate each psychological index and each physiological index, namely 12 psychological indexes and 2 physiological indexes in total. According to the physical and psychological health evaluation method based on the facial micro-vibration image, psychological indexes and partial physiological indexes related to the emotion can be calculated through the vibration of facial muscles, and the accuracy of facial emotion recognition is improved by integrating multiple indexes.

The invention provides a depression degree assessment method based on space-time relevance of a facial region, belongs to the technical field of computer vision and medical diagnosis, and solves the problem that an existing depression identification method is not high in accuracy. The invention provides a deep learning model fused with a space-time attention mechanism. The method comprises the following steps: dividing a face image into a plurality of sub-regions, and independently calculating the importance of each sub-region; the space importance, the space context, the time context and the space similarity are dynamically fused through a space-time attention mechanism, and a face attention map is generated; based on the constructed recognition model, a time sequence feature fusion module is used for extracting dynamic expression change features, and precise assessment of the depression degree is achieved. Experiments show that the method obtains the identification performance of MAE 5.79 and MAE 5.76 on the AVEC 2013 data set and the AVEC 2014 data set respectively, and is superior to the prior art. According to the method, an efficient and objective solution is provided for automatic depression recognition by capturing a space-time correlation mode of facial muscles through fine grit.

The invention relates to the technical field of speech recognition and synthesis, and discloses a multi-mode speech conversion method and system based on user behaviors, and the method comprises the steps: carrying out the vibration separation of a bone conduction signal, obtaining a separation vibration signal, mapping the face muscle micro-current into a muscle deformation gradient, and analyzing the intention intensity of a user through implicit behavior data; mapping the muscle deformation gradient into a voice fundamental frequency of the user, linearly converting the separation vibration signal into a voice formant of the user, and performing noise injection on a non-voice active section based on intention intensity to obtain noise injection voice; constructing user behavior voice corresponding to the voice fundamental frequency, the voice formant and the noise injection voice through an orthogonal projection layer in a preset orthogonal regularization vocoder; and synthesizing the speech feature vector and the user behavior speech into bone conduction propagation speech through a bone conduction synthesis layer in an orthogonal regularization vocoder. According to the invention, the accuracy of the multi-mode voice conversion technology can be improved.

The invention relates to the technical field of bionic robots, and provides a bionic robot head system which comprises a multi-mode sensing unit, a dynamic expression generation unit, an environment analysis unit and a bionic execution unit. The multi-modal sensing unit is used for synchronously acquiring visual, auditory and physiological signals and tactile data, the dynamic expression generation unit is used for generating a non-preprogrammed facial muscle driving instruction in real time by taking the multi-modal sensing data as an input condition, and the bionic execution unit is used for responding to the driving instruction to realize micro-expression movement with 0.1 mm-level precision. Visual, auditory and physiological signals and tactile data are synchronously collected through the multi-modal sensing unit, data fusion is performed by applying a cross-modal attention mechanism, human emotion changes can be accurately captured, and high-fidelity dynamic expression presentation is realized through cooperative operation of the dynamic expression generation unit and the bionic execution unit, so that the dynamic expression presentation efficiency is improved. Compared with a traditional robot, the robot is stiff and single in expression.

The invention provides a smokeless intelligent accurate control method for prevention and control of juvenile myopia. The smokeless intelligent accurate control method comprises the steps of eye movement and facial muscle multi-mode acquisition and noise filtering, dynamic graph convolutional network and spatial-temporal feature fusion analysis, blink and head movement prediction and intelligent moxibustion path adjustment. By constructing a resting state eye movement behavior mode library, coupling face and head dynamic data, utilizing multi-mode feature fusion and AI hierarchical control, accurately recognizing blinking and head disturbance, and generating an avoidance track and a dynamic moxibustion therapy power regulation strategy in advance, the method can effectively avoid periorbital sensitive areas, keep the temperature in the moxibustion therapy process constant, and improve the moxibustion therapy effect. The response speed and path stability are improved, and moxibustion safety and continuity are guaranteed.

The invention provides an informatization wound ticket giving system based on facial recognition, and relates to the technical field of identity verification. The system comprises a physiological status monitoring module, a permission adjustment control module, an identity adaptability matching module, a gait behavior verification module and a terminal data linkage module. By analyzing eyeball movement, blinking frequency, pupil change and facial muscle activity and monitoring the physiological state of an individual, dynamic permission adjustment during identity verification is achieved, matching precision is optimized through micro-expression analysis, mismatching caused by emotion fluctuation is reduced, the adaptability of identity verification is enhanced through behavior data in gait analysis, high accuracy is maintained, and the identity verification efficiency is improved. The real-time performance of bill management and access control is improved through a data linkage mechanism among multiple devices, and the verification safety and the remote operation stability are enhanced in combination with multi-dimensional biological characteristics.

The invention discloses a Parkinson's disease patient video analysis and evaluation system based on artificial intelligence. The method comprises the following steps: collecting a multi-modal data set; extracting face key point data in the multi-modal data set by using a Mediappe face detection algorithm, and analyzing blink frequency, eyelid movement symmetry and face muscle tension change; extracting a hand joint motion track through an OpenPose model, and calculating tremor frequency, motion completion time and motion smoothness; detecting step length, step width, step speed and coordination of left and right limbs in the gait of the human body based on a YOLOv8 target detection algorithm; dynamically weighting the facial tremor features, the limb movement features and the gait dynamics features through a multi-head attention mechanism; and outputting the symptom evaluation index of the Parkinson's disease patient through the LSTM network. And the efficiency and accuracy of illness state assessment are improved.

The invention relates to a cranial nerve motor function evaluation system and method based on a terminal with a camera. The system comprises a camera used for collecting a high-definition video sequence of facial actions; the model is used for identifying positioning points of the face according to the high-definition video sequence acquired by the camera; the analysis and evaluation module is used for quantitatively evaluating the cranial nerve motor function state according to the change of the positioning points of the face acquired by the model; the analysis and evaluation module performs analysis and evaluation according to the change quantitative indexes of the positioning points of the face; the camera, the model and the analysis and evaluation module are all deployed at the terminal; and the model and the analysis and evaluation module are deployed in an operating system of the terminal. The evaluation system and method are deployed on a common terminal, and are used for collecting a video sequence of a user completing a standard evaluation action, automatically identifying the movement of a positioning point of a face, and outputting a quantitative score according to a medical standard so as to evaluate human face muscle movement and a cranial nerve function state.

The invention discloses a micro-expression recognition method and device based on AU guidance, and the method comprises the steps: carrying out the preprocessing of a micro-expression sample video, and obtaining a micro-expression sequence; generating a facial muscle movement text description for each micro-expression sample through an AU coding label of the public data set and a facial movement coding system; sending the processed micro-expression sequence into a visual encoder to obtain encoded visual motion features; sending the motion text description into a text encoder to obtain text motion features; by generating AU-guided fine-grained micro-expression facial muscle motion text description and utilizing CLIP comparison loss to perform cross-modal semantic alignment, perception and capture of a model on weak local micro-expression motion can be improved, remarkable space-time micro-expression motion features are learned, the motion features are effectively converted into emotional features, and the motion features are effectively converted into emotional features. And the Focal Loss classification loss is used to solve the problem of micro-expression data class imbalance, so that the recognition performance of the model is greatly improved.

The invention discloses an oral cavity baffle tongue lighting device, which belongs to the technical field of oral cavity equipment, and comprises a lower jaw frame, side arms and an upper jaw, a lower curved wall is fixedly embedded on the upper surface of the lower jaw frame, side grooves are distributed on two sides of the lower jaw frame, elastic pieces are assembled in the side grooves, one end of each side arm is fixedly connected with a side shaft, and the side shafts are rotatably inserted in the side grooves. The upper jaw frame is movably assembled at the top of the lower jaw frame, the purpose of auxiliary supporting on the upper jaw and the lower jaw of a patient in the treatment process can be achieved, the aching pain feeling of facial muscles of the patient is reduced, and the treatment effect of the patient is improved. Meanwhile, the flow speed of pump suction can be autonomously controlled through the occlusion action of the patient, the patient can conveniently and freely adjust the strength of pump suction, the step that treatment personnel manually suck dirty liquid is omitted, the illuminating lamp can be cooled through flowing of liquid, and discomfort of the patient caused by overheating of the lamp source is prevented.

To provide a mask inner made of a non-stretchable adhesive sheet which adheres to a facial skin, is expected to have an anti-fogging effect on glasses when wearing a sanitary mask, can also train facial muscles and can suppress inhalation of fine dust such as pollen.SOLUTION: A mask inner is made of a non-stretchable double-sided adhesive sheet 11 having a hood-like structure (hood part 1a) having a function of guiding exhaled breath downward and a breathing hole 1b.SELECTED DRAWING: Figure 10

The utility model discloses a face sagging prevention mask structure for facial paralysis after an auditory neuroma operation, and particularly relates to the field of medical care, the face sagging prevention mask structure comprises a mask, bandages are fixedly mounted on two sides of the mask, a binding buckle is arranged on one side of each of the two bandages, a pushing and pressing mechanism is arranged on the outer wall of the mask, and the pushing and pressing mechanism comprises fixed plates fixedly mounted on two sides of the mask. The two fixed plates are symmetrically arranged, a first rotating roller is fixedly installed on the outer walls of the two fixed plates, the first rotating roller is arranged in a vertical state, a position supporting plate is rotatably installed on the outer wall of the first rotating roller, and the position supporting plate and the outer wall of the mask are arranged in parallel; according to the utility model, the pushing and pressing mechanism is arranged, and structures capable of performing pressing and rolling massage are arranged on the two sides of the mask, so that a patient presses the face position by himself to perform pushing and pressing massage on the face, the facial muscles of the patient are relieved, and the situation that the face of the patient is tightened for a long time and consequently the face is stiff is avoided.

The article of this design is a waveform signal output unit to be connected to a facial beauty device (EMS: Electrical Muscle Stimulation) that stimulates muscles with a weak current and can train muscles mainly around the face, and is used by pressing and moving three spherical bodies against the skin of the face, etc. The three spherical bodies are provided at the tip of a wire as shown in the right side view, left side view, top view, and bottom view, respectively, and the central spherical body is provided on a straight wire, while the left and right spherical bodies are provided on a gently curved wire. In this way, the three spherical bodies can be simultaneously brought into contact with the contours of the nasolabial folds of a human face, and by training the muscles, it is expected that the effect of tightening the sagging skin can be expected, and also, the facial muscles that are usually difficult to train can be firmly trained by directly moving them with electrical stimulation.