51 results about "Tongue surface" patented technology

The invention discloses an illness state tracking management system and method based on a lingual face diagnosis instrument, and belongs to the technical field of traditional Chinese medicine tongue diagnosis and modern information technology fusion. The system comprises a multi-modal data acquisition module, a data processing and analysis module and an augmented reality visualization module; according to the method, illness state tracking is achieved through the steps of multi-modal data acquisition, data preprocessing and feature fusion, personalized digital twinborn model establishment, augmented reality visualization presentation and the like, multi-dimensional data such as tongue picture macroscopic features and tongue surface microorganism distribution can be integrated, dynamic association between the data is revealed, the health state and the intervention effect are visually displayed, and the method is suitable for being popularized and applied. The method is suitable for the fields of traditional Chinese medicine health management and chronic disease monitoring.

The invention discloses a traditional Chinese medicine cardiovascular health assessment method based on tongue picture image recognition, and the method comprises the following steps: collecting original tongue picture image data, and carrying out the image preprocessing; collecting lingual surface spectrum original data, and executing spectrum preprocessing; extracting features of the standardized tongue picture image data, and generating tongue picture image feature vectors; extracting features of the standardized lingual surface spectral data, and generating lingual surface spectral feature vectors; constructing multi-modal hidden space representation of the tongue picture image feature vector and the tongue surface spectrum feature vector, and executing feature decoupling and feature fusion processing; establishing a mapping relation between the tongue picture-spectrum fusion implicit vector and a cardiovascular health index, and generating a cardiovascular risk prediction vector; and generating a cardiovascular health risk assessment result. According to the invention, tongue image and spectral analysis are fused, cardiovascular health assessment is realized, and the method has the advantages of high accuracy and high stability.

1. The name of the design product: tongue detector (shengshi-tiangong AI spectrum diagnosis platform). 2. The use of the design product: for tongue detection. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

1. The name of the design product: Tongue surface collector (Chinese medicine intelligence 1). 2. The use of the design product: For collecting images of tongue surface and face. 3. The design points of the design product: In shape. 4. The picture or photo that best indicates the design points: Perspective view.

This application relates to a device for detecting organ function and its control method, as well as a dietary management method and system, belonging to the technical field of medical device testing. The control method compares and analyzes changes in the microscopic features of the same area of ​​the tongue before and after eating, and calculates the corresponding metabolic index change rate, constructing a mapping relationship between the tongue's microscopic morphology and organ function, providing a basis for assessing internal physiological function through external characterization. Simultaneously, the dietary management method uses physiological responses before and after eating as real-time biofeedback signals to generate dynamically adjusted dietary management plans, forming a personalized health management closed loop of "monitoring-assessment-intervention-remonitoring," achieving precise adaptive adjustment of intervention strategies.

The invention provides a key-point-driven tongue picture generation method, device and equipment and a storage medium, and relates to the technical field of tongue picture analysis, and the method comprises the steps: obtaining a tongue picture image, and extracting tongue edge boundary key points and tongue surface region key points through a key point positioning unit for representing the geometric morphology and viscera partition of a tongue body; based on a semantic analysis unit, identifying and standardizing the input tongue picture pathological feature tag to generate a structured control condition; according to the key points and the semantic tags, a mask generation unit generates a multi-channel control mask graph in a programmed mode, and the multi-channel control mask graph is used for indicating local features and severity of tooth marks, cracks, yellow moss, white moss and the like; the image generation unit adopts a stream matching vector field learning framework, carries out collaborative reasoning through a trunk generation network and a control network, and combines an ODE solver to generate a tongue picture image conforming to mask space constraints in finite steps; and the feature fusion unit injects control features step by step by using a zero convolutional layer in a decoding stage to realize tongue picture reconstruction with consistent space.

The application relates to the technical field of image acquisition and processing devices, and discloses a projection device for tongue surface detection, a connecting rod is fixedly connected to a rotating frame, a shielding curtain is detachably connected to the connecting rod, the bottom of the shielding curtain abuts against the bottom of a dark box, the surface of the shielding curtain is provided with a carbon fiber layer, the top of the dark box is provided with an air hole, the air hole is located on the front side of the shielding curtain, and the dark box is connected with an air outlet cavity. The photos taken by the device have high consistency for people with different postures and body shapes, and the machine analysis is facilitated. In addition, under the isolation and guiding action of the shielding curtain, the flow direction of the gas is consistent, the old gas carrying bacteria is further isolated by the airflow itself, the shielding curtain has the functions of adsorption and isolation, the airflow is guided and bound, the spread of droplets in the dark box is avoided, and the adhesion of the droplets to the camera and the coaxial light source is reduced.

The application discloses an interpretable tongue diagnosis auxiliary diagnosis system based on knowledge graph fusion reasoning. The system obtains tongue diagnosis image data containing at least tongue surface image and sublingual plexus image, determines a plurality of preset tongue diagnosis regions and generates regional node features; constructs an image graph and updates the image graph by a first graph neural network to obtain image node features; constructs a traditional Chinese medicine knowledge graph containing tongue image, pathological factors, viscera, syndrome nodes and their relationships and updates the knowledge graph by a second graph neural network to obtain knowledge node features, projects and maps the image node features and the tongue image node features to the same embedding space, aligns the cross-modal modes according to a contrast learning loss to obtain cross-modal correlation; constructs a fusion graph based on the image graph, the knowledge graph and the cross-modal correlation and performs graph reasoning to output syndrome results and reasoning path information. Explicit connection of image regions and traditional Chinese medicine semantics and output of traceable paths reduce experience dependence and enhance interpretation and review.

The invention relates to the technical field of biomedical engineering, and provides a tongue body motion form reconstruction and neuromuscular lesion recognition method, which comprises the following steps: S1, acquiring a multi-modal original signal by using a flexible electrode array attached to a lingual surface, and recording a system timestamp; s2, performing targeted filtering, artifact removal and feature extraction processing on the multi-mode original signal; s3, reconstructing a local dynamic curved surface of the lingual surface by adopting a preset model, and inferring an overall position and posture sequence of the tongue body in combination with an IMU signal; s4, a joint optimization objective function is constructed, and a tongue body three-dimensional dynamic form sequence is obtained through iterative solution; s5, performing motion unit action potential MUAP decomposition and feature extraction on the surface electromyogram signal sEMG; and S6, constructing lesion feature vectors based on the multi-dimensional abnormal features, and analyzing and generating a tongue lesion risk map TDM through a machine learning model. The defects that real motion reconstruction, form inference and neuromuscular lesion positioning of the tongue cannot be achieved through an existing tongue detection technology are overcome.

The invention discloses a digital human generation system and method based on a language model, and relates to the technical field of artificial intelligence. A complete digital human pronunciation modeling path from voice signal acquisition, formant frequency extraction, deviation analysis and pronunciation stability evaluation to motion compensation control and three-dimensional animation fusion is realized. Compared with the existing mode of driving the digital human pattern only based on energy envelope or mouth shape classification, the method has the advantages that the multi-frame formant frequency of the user voice is extracted and processed, so that the digital human can generate dynamic lingual surface and tongue tip actions according to the sound channel change in the real pronunciation process of the user; therefore, the physical correspondence and linguistic consistency of the pronunciation actions of the digital human are improved. According to the method, the direct mapping between the pronunciation characteristics and the three-dimensional tongue actions is realized, and the authenticity of the pronunciation animation of the digital human and the guidance in a teaching scene are remarkably improved.

An ornamental design for a facial exercise device, as shown in the figures and description. The facial exercise device is used to strengthen, tighten, and tone the midface, lower face, orofacial region, and oropharynx (including the tongue and floor of the mouth muscles) for both aesthetic and rehabilitative therapeutic purposes. The facial exercise device comprises a trapezoidal tubular body having a primary isosceles trapezoidal shape. The trapezoidal tubular body defines a plurality of openings with equally spaced compressible and bendable body members centered around a central opening, positioned at predetermined locations for isometric and isotonic muscle resistance training for various facial and tongue movements. The facial exercise device can be positioned anywhere, including under the lower lip, under the upper lip, under both lips, on one or both cheeks, around the outer periphery of the mouth, and within the oral cavity (contacting the hard palate, tongue surface, and floor of the mouth). 1.1) Perspective view; 1.2) Front view; 1.3) Plan view; 1.4) Bottom view; 1.5) Right side view; 1.6) Left side view; 1.7) Rear view; 1.8) Cross section; 1.9) Reference view showing the state of use; 1.10) Reference view showing the state of use

The invention provides a health assessment analysis method, system and device based on tongue diagnosis. The method comprises the following steps: collecting a lingual surface picture of an evaluated person; performing tongue picture recognition on the tongue surface picture to obtain tongue picture characteristics of the tongue surface picture; calling a question of a physique corresponding to the tongue picture feature for an assessed person to answer; and judging the physique of the evaluated person according to the answer result and generating an evaluation report. The system comprises the front-end equipment adopting the method, the data processing cloud and the tongue picture feature classification cloud. A program for executing the method is stored in the device. According to the invention, the traditional Chinese medicine constitution evaluation result of the user can be conveniently and accurately obtained.

The application relates to the technical field of image processing, and discloses a tongue surface adaptive partitioning method, a tongue surface adaptive partitioning system and a medium. The method comprises the following steps: acquiring an original image containing a tongue body, performing tongue body segmentation on the original image to obtain a binary mask; extracting a tongue body contour and calculating a tongue body morphological parameter based on the binary mask; then calculating partitioning key point coordinates through a dynamic positioning formula according to the morphological parameter; then dividing the tongue surface into a plurality of sub-regions corresponding to viscera based on key point connecting lines; and finally fusing sub-region boundary information and the original image to generate and output a partitioning result image. The method provided by the application can adapt to individual tongue shape differences, significantly improves the partitioning accuracy, provides a standardized region division basis for tongue diagnosis objectification, and can be automatically implemented, the result is intuitive and easy to understand, and is convenient for clinical and scientific research application.

This application provides an image synchronous acquisition method, system, device, storage medium, and program product, relating to the field of medical image acquisition and processing. The method includes: synchronously acquiring an initial tongue image of a target object using a coaxial optical structure. The initial tongue image includes a tongue image and a facial image. The coaxial optical structure includes a first image acquisition device and a second image acquisition device, which are coaxially aligned to acquire initial tongue images of the same region of the target object. A real-time image processing unit is then used to process the initial tongue image in real time to obtain a target tongue image corresponding to the target object. This method, through the combination of a coaxial optical structure and a hardware processing unit, solves the problem of spatiotemporal inconsistency caused by segmented acquisition, achieving strict alignment of the acquired images in both time and space dimensions.

The invention relates to the technical field of tongue image diagnosis, in particular to a human body tongue image feature extraction and analysis method and system.According to the human body tongue image feature extraction and analysis method and system, a tongue surface main region boundary set is effectively extracted by counting the edge point change frequency and the curvature change rate, the limitation of high subjectivity in traditional tongue diagnosis is avoided, and the accuracy of human body tongue image feature extraction and analysis is improved. Therefore, standardized path reconstruction of the lingual surface area is realized, errors are remarkably reduced, analysis precision is improved, and the graph neural network is introduced to compare similar section contour difference values, so that structural feature extraction and detail judgment are enhanced, the adaptive capacity to different tongue picture structures in the analysis process is improved, and the analysis accuracy is improved. According to the method, the mapping accuracy of the tongue surface structure is optimized, the abnormal value of the color principal component is detected through the isolated forest model, efficient screening and accurate matching of tongue picture task labels are achieved, the large color difference and subtle influences in the tongue diagnosis process are effectively overcome, and the consistency and reliability of diagnosis results are ensured.

1. The name of the design product: Tongue skin detector (M64). 2. The use of the design product: For detecting tongue and skin health status. 3. The design points of the design product: In shape. 4. The picture or photo that best shows the design points: Perspective view 1. 5. Other circumstances that need to be explained: The B part and C part are transparent materials.

1. Name of the design product: tongue scraper. 2. Use of the design product: for cleaning the tongue surface. 3. Design points of the design product: in shape. 4. Picture or photo best indicating the design points: perspective view.

The invention discloses a child cerebral palsy cranial nerve injury assessment instrument and method based on big data, and relates to the field of child cerebral palsy brain, the child cerebral palsy cranial nerve injury assessment instrument comprises a first supporting plate fixed at the upper end of a mounting frame, and a placement assembly is fixed on the upper surface of the first supporting plate; the device further comprises a moving assembly fixed above the placing assembly and a collecting assembly arranged on one side of the placing assembly. The collecting assembly is pushed into the oral cavity of a patient through the moving assembly for tongue surface image collection, and the light supplementing module fixed to the surface of the collecting assembly simulates natural light, so that in the process that the collecting module collects the image in the oral cavity, the influence of the dark environment in the oral cavity on image collection is reduced; meanwhile, the tongue surface is fixed through the tongue depressor, movement and reflection of the tongue can be restrained, the tongue root can be further exposed, and completeness and clearness of the tongue root image are improved.

The invention discloses a shoe tongue, a preparation method thereof and a shoe. The shoe tongue comprises a shoe tongue body formed by sequentially laminating and compounding a shoe tongue inner layer, a middle layer and a shoe tongue surface layer, and the shoe tongue body is provided with a breathable area and a shaping area which are not adjacent to each other; wherein the ventilation area is provided with a plurality of through holes penetrating through the shoe tongue body, and a lining piece lined into the shoe tongue body is arranged in the shaping area. By arranging the breathable area and the shaping area, it is guaranteed that the shoe tongue is comfortable and breathable, and folding or deformation is avoided during use.

The application provides a tongue image recognition method and system based on three-dimensional face and tongue reconstruction technology, and relates to the technical field of image processing. The method comprises the following steps: inputting three-dimensional face point cloud data of a current user according to a multi-modal acquisition device; capturing a face action anchor point and recording and archiving, obtaining tongue point cloud data when the user moves; connecting the tongue point cloud data with an RGB-D array channel to construct a tongue simulation model; extracting tongue surface partition features, outputting a partition tongue surface feature set, and transmitting the feature set to a management end of an electronic diagnosis and treatment medical record corresponding to the user. The application solves the technical problem that static acquisition cannot effectively capture dynamic changes, leading to inaccurate tongue point cloud data and affecting the accuracy of tongue information. The three-dimensional face and tongue reconstruction technology ensures the accuracy of the point cloud data, thereby obtaining more comprehensive tongue information.

This utility model discloses an auxiliary traction device for gastroscopy, relating to the field of medical auxiliary instruments. It includes an anterior oral plate, one end of which is fixedly connected to a connecting strap, and the other end of which has an adhesive structure for fixing the end of the connecting strap. A tube-penetrating hole is formed through the middle of the anterior oral plate, and a U-shaped groove is formed on the lower side of the tube-penetrating hole. A supporting structure drives the outer side of a tongue depressor to rotate upwards, and under the action of leverage, the other end of the tongue depressor presses down on the tongue surface. The endoscope tube is then inserted into the esophagus through the tube-penetrating hole. After the lens of the endoscope tube is moved to the lesion site, a U-shaped sleeve is pressed down. During the downward rotation of the U-shaped sleeve, two linkage arms are squeezed closer together. At this time, two arc-shaped clamps hold the endoscope tube on both sides. During insertion, the clamping and fixing prevents the arms from being held up for a long time, facilitating subsequent stable operation by medical personnel and improving practicality.

The invention discloses a tumor patient tongue picture and syndrome type correlation analysis method based on deep learning, and relates to the technical field of traditional Chinese medicine intelligent diagnosis, and the method comprises the following steps: obtaining a tongue picture image and tongue type label data of a target object; matching convolution is carried out on the tongue picture image according to a preset tongue surface partition template, a partition mask is output, frequency domain reconstruction is carried out on the partition mask through local short-time Fourier transform, a region boundary diagram is generated, and a frequency domain reconstruction strategy is selected according to a denoising parameter set in the frequency domain reconstruction process. According to the scheme, frequency domain selective reconstruction is carried out by using the denoising parameter set in the process of generating the region boundary map, accurate reservation of fine texture and boundary information of the tongue surface is realized, and by carrying out wavelet decomposition on the tongue picture image and carrying out weighted calculation in combination with the region boundary map and the channel weight vector, selective enhancement is realized, and the local saliency map is generated. And the lingual surface region and the texture feature which contribute to syndrome type judgment are highlighted.

The utility model discloses a lingual surface and palm surface comprehensive diagnosis and treatment instrument which comprises a shell. An accommodating cavity is formed in the shell; the accommodating cavity is divided into a mounting cavity and a collecting cavity by an inner partition plate; the cross section of the inner partition plate is of an L-shaped structure, and the corner of the inner partition plate is in arc transition. The shape of the cross section of the arc-shaped guide rail is matched with that of the cross section of the inner partition plate, and the arc-shaped guide rail is mounted in the mounting cavity; the camera module is in sliding connection with the arc-shaped guide rail; the front end of the camera module passes through the strip-shaped camera window on the inner partition plate, and the tail end of the camera module is arranged between the inner partition plate and the arc-shaped guide rail; the neck support is arranged at the front end of the shell; a lingual surface collecting opening is formed above the neck collar, and a palm collecting opening is formed below the neck collar; the lingual surface collection port and the palm collection port are communicated with the collection cavity; according to the utility model, the camera module is driven to rotate through the right-angle guide rail with the arc-shaped corner, so that the camera module can be converted in the horizontal direction and the vertical direction; therefore, the diagnosis and treatment requirements of tongue diagnosis and hand diagnosis can be met at the same time.

The utility model provides a tongue-shaped straw for assisting in drinking water, which belongs to the technical field of intelligent drinking equipment and comprises a bionic tongue piece. Comprising a silica gel base body, a main runner pipe inserted into the tongue tip end of the silica gel base body, a cross flow deflector fixedly connected to the end face of the main runner pipe, a drainage groove formed in the upper surface of the silica gel base body, a flow dividing cavity formed in the lower layer of the silica gel base body and a plurality of flow dividing grooves formed in the bottom of an inner cavity of the flow dividing cavity. The micro-flow through holes are formed in the back surface of the silica gel base body and are communicated with the flow dividing grooves. Through the design of the bionic tongue piece and the double-channel shunting structure, the problems that a traditional suction tube is single in function and uncontrollable in liquid mixing are solved; a main flow channel and an auxiliary flow channel facilitate graded flow guiding, independent conveying of water and flavor liquid is achieved, and odor tainting is avoided; ergonomic adaptability: the gradient thickness (2-3mm) of the silica gel substrate and the nipple-imitating texture simulate the tongue surface touch sense, and fit the oral cavity shape, so that the comfort level is improved.

The invention discloses a tongue picture abnormal feature detection method and device, electronic equipment and a product, and relates to the technical field of target detection. The tongue picture abnormal feature detection method comprises the following steps: inputting a lingual surface panoramic image into a pre-trained first target detection model for tongue body region detection to obtain a tongue body region in the lingual surface panoramic image; cutting a tongue body area in the lingual surface panoramic image to obtain a cut image; performing linear interpolation amplification on the cut image, and inputting the cut image into a pre-trained second target detection model to perform abnormal feature detection to obtain an abnormal feature detection result; wherein the abnormal feature detection result comprises coordinates and confidence coefficients of the abnormal features, and the abnormal features comprise cracks and / or tooth marks. According to the tongue picture abnormal feature detection method and device, the electronic equipment and the product provided by the invention, interference of background noise on abnormal feature detection can be avoided, meanwhile, microscopic feature distortion is avoided, and the accuracy of tongue picture abnormal feature detection is improved.

The invention relates to the technical field of intelligent traditional Chinese medicine nursing, in particular to an AI-based traditional Chinese medicine nursing recommendation system. The AI-based traditional Chinese medicine nursing recommendation system comprises a tongue image feature extraction module, a tongue partition anomaly recognition module, a meridian mapping positioning module, a drug property tropism matching module and a nursing intervention recommendation module. According to the method, depth feature extraction and partition quantization are carried out on the tongue body image, visual information such as contours, textures and colors is converted into accurate numerical parameters, and an objective judgment reference is set according to statistical distribution of large-scale health samples, so that uncertainty and difference caused by traditional evaluation depending on subjective experience are overcome, and the accuracy of evaluation is improved. Standardized recognition of tongue picture abnormity is achieved, a calculation mode of spatial position contribution degree is introduced, the method can be automatically focused on the tongue body partition with the most remarkable pathological significance, then accurate mapping from the tongue surface abnormal partition to the body meridian path is constructed, local observation and an overall meridian system are closely associated, and the accuracy of the tongue picture abnormity recognition is improved. And the problem of generalization fuzziness of previous recommendation is solved.

According to the multi-part image acquisition system and method for traditional Chinese medicine inspection diagnosis, the medium, the program product and the terminal provided by the invention, full-automatic closed acquisition of three traditional Chinese medicine inspection diagnosis key parts, namely a human face, a lingual surface and a lingual floor, is realized. The environment light sensor and the color temperature sensor are integrated in the closed shooting cavity, a closed-loop feedback mechanism is constructed, the light source assembly is accurately regulated and controlled, and it is ensured that the color temperature is stabilized in a medical effective interval. According to the invention, a multi-mode in-place detection mechanism is provided, infrared proximity sensing and a light-weight tongue posture light detection model are fused, whether each part is subjected to compliance exposure or not is accurately judged, posture compliance guidance is carried out, and the visibility of key signs such as sublingual collaterals in the image is remarkably improved. Through a closed shooting cavity structure and a multi-mode in-place detection and closed-loop guide mechanism, multi-part high-quality image automatic acquisition without manual intervention from user guide, illumination adjustment and quality evaluation to automatic shooting is realized.

The utility model provides an adjustable bionic tongue sleeve type suction tube, which belongs to the technical field of suction tubes and comprises a bionic tongue sleeve. Comprising a silica gel base body, a plurality of main flow channels formed in the upper layer of the tongue face part of the silica gel base body, a main flow dividing groove formed in the silica gel base body and communicated with the confluence ends of the main flow channels, a flow dividing cavity formed in the lower layer of the tongue face part of the silica gel base body, and a plurality of auxiliary flow dividing grooves formed in the bottom of an inner cavity of the flow dividing cavity. The main channel and the auxiliary channel operate independently, the taste bud area is covered in a directional mode through the micro-flow through holes of the auxiliary channel, the main channel avoids the sensitive area, liquid mixing is effectively prevented, meanwhile, the drinking taste is improved through trace flavor liquid, and the drinking desire is stimulated; by means of the more than eight main flow channels distributed in the radial shape and the detachable channel plugs, a user can freely block part of the channels, the liquid flowing path and flow distribution are dynamically changed, and the comfort experience of the user can be improved.

The invention relates to the technical field of traditional Chinese medicine diagnosis and treatment, in particular to a tongue coating condition recognition system for traditional Chinese medicine diagnosis and treatment assistance, which comprises a data acquisition module for acquiring lingual visual data and corresponding diagnosis information at a plurality of medical nodes, performing structured processing matched with traditional Chinese medicine tongue diagnosis on the data, and acquiring a tongue coating condition recognition result; forming a data set containing tongue coat color, texture, distribution characteristics and tongue surface functional region division; the model building module is used for constructing a tongue coating recognition model by each medical node based on the data set, performing parameter initialization and feature expression training, and generating local recognition parameters; and the training framework construction module is used for establishing a federal cooperative training framework based on the parameter interaction protocol with the privacy protection capability under the condition of not transmitting the original data. According to the invention, the visual data of the lingual surface are collected at a plurality of medical nodes, so that the problem that the generalization ability of the model is insufficient due to the fact that a single-center centralized training mode is mostly adopted in traditional tongue coating recognition is solved.

The invention discloses a tongue picture texture analysis and phlegm-dampness constitution recognition method and device based on multispectral imaging and a storable medium, and belongs to the technical field of traditional Chinese medicine tongue diagnosis objectification and artificial intelligence application. In order to solve the problem of lack of objective and standardized quantitative analysis of tongue picture analysis at present, the device defines a tongue coating viscoelasticity index and a sublingual microcirculation response index by collecting a lingual surface multispectral image, tongue coating deformation recovery sequence data and sublingual speckle contrast sequence data; thick and greasy tongue coating, sticky and unsmooth tongue coating, phlegm-dampness blocking, qi and blood blocking and the like in traditional Chinese medicine are converted into quantitative indexes, classification and recognition are carried out on the phlegm-dampness constitution according to an AI recognition model, and results are output. According to the device, by fusing multispectral biological imaging and artificial intelligence analysis technologies, the conventional tongue diagnosis process depending on experience is objectively quantified, the physiological mechanism behind phlegm-dampness discrimination is disclosed, and the consistency and credibility of diagnosis results are improved.