Portable acupoint stimulator and human-computer interactive adult swallowing rehabilitation training system
Through the system of portable acupoint stimulator interacting with human-computer, multi-module collaborative training and blockchain data storage, the problems of a single project and complex structure of the existing swallowing training device are solved, and the efficient effect of all-round swallowing rehabilitation training is achieved.
Patent Information
- Application Number
- CN202211698544.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-12-28
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-12-28
AI Technical Summary
The existing swallowing training device can only be trained in a single project, with a complex structure, which is inconvenient for patients to train independently, and the training effect is not good.
Design a portable acupoint stimulator to interact with human-computer adult swallowing rehabilitation training system, including a central control module, image feature extraction module, acupoint positioning module, breathing training component, tongue muscle training component and rehabilitation training evaluation module, through face images Feature extraction, automatic acupoint positioning, multi-module collaborative training and blockchain data storage to achieve all-round swallowing rehabilitation training.
It has achieved all-round training for patients with swallowing dysphagia, which is convenient to operate, improves training efficiency and effect, and is suitable for promotion and application.
Smart Images

Figure CN116020094B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of integration of traditional Chinese medicine and swallowing rehabilitation training with computer technology, and in particular relates to a portable acupoint stimulator and a human-computer interactive adult swallowing rehabilitation training system. Background Art
[0002] At present, with the acceleration of social aging and urbanization, stroke diseases in my country are in an explosive growth trend, and swallowing dysfunction is the most common complication of acute stroke, with an incidence of 22% to 65%. It can cause complications such as malnutrition, dehydration, and aspiration pneumonia in stroke patients, increase their morbidity, mortality, and hospitalization costs, and seriously affect patients' psychology and disease prognosis. In order to restore the swallowing function of patients, some external devices or tools are needed to assist in swallowing training. Swallowing training can have a good training effect on the recovery of swallowing dysfunction after stroke. However, the existing swallowing training device can usually only perform single-item training, such as single tongue muscle training, breathing training, or lip muscle training, and its structure is also relatively complex, which is not convenient for patients to conduct autonomous training, resulting in poor training effect. Therefore, it is urgent to design a new portable acupoint stimulator and human-computer interactive adult swallowing rehabilitation training system.
[0003] Through the above analysis, the problems and defects of the existing technology are: the existing swallowing training device can only perform single-item training, and has a complex structure, which is not convenient for patients to train independently and has poor training effect. Summary of the invention
[0004] In view of the problems existing in the prior art, the present invention provides a portable acupoint stimulator and a human-computer interactive adult swallowing rehabilitation training system.
[0005] The present invention is implemented in this way: a portable acupoint stimulator and a human-computer interactive adult swallowing rehabilitation training system are provided with:
[0006] Central control module;
[0007] The central control module is linearly connected to the verification module and the intelligent processing module. The verification module is used to diagnose and verify the degree of swallowing disease of the patient; the intelligent processing module is used to perform intelligent control on the required acupoint stimulation degree according to the disease verified by the verification module;
[0008] The central control module is linearly connected to a face image acquisition module, and the face image acquisition module is used to acquire face image data of a subject to be trained through an image acquisition device;
[0009] The central control module is also connected to an acupoint positioning module, which is used to automatically locate the rehabilitation training acupoints of the rehabilitation training object according to the facial image features through the positioning device;
[0010] The central control module is also connected to a breathing training module for training the breathing of the rehabilitation training subject through a breathing training component;
[0011] The central control module is also connected to a tongue muscle training module for training the tongue muscles of the rehabilitation training subject through the tongue muscle training component;
[0012] The central control module is also connected to a rehabilitation training evaluation module, which is used to evaluate the rehabilitation training indicators of the rehabilitation training object according to the breathing training data and the tongue muscle training data through an evaluation program;
[0013] The central control module is also connected to a data transmission module for sending the acquired facial image data and image feature data of the subject to be trained to the central processor via a data transmission device.
[0014] Furthermore, the portable acupoint stimulator and human-computer interactive adult swallowing rehabilitation training system further includes:
[0015] A data transmission module, connected to the central control module, is used to send the acquired facial image data and image feature data of the subject to be trained to the central processing unit through the data transmission device;
[0016] A central control module, connected to the data transmission module, the human-computer interaction module, the reminder module, the training record module, the data storage module, and the update display module, and used for coordinating and controlling the normal operation of the portable acupoint stimulator and each module of the human-computer interactive adult swallowing rehabilitation training system through a central processor;
[0017] A human-computer interaction module is connected to the central control module and is used for interactive operation between the subject to be trained and the adult swallowing rehabilitation training system through a human-computer interaction device;
[0018] A reminder module, connected to the central control module, for reminding the rehabilitation training subject of wrong training actions through an audio-visual reminder device according to human interaction information;
[0019] A training recording module, connected to the central control module, is used to record the swallowing rehabilitation training process data of the rehabilitation training subject through a training recording program;
[0020] A data storage module is connected to the central control module and is used to store the acquired facial image data, image feature data, rehabilitation training acupoints, breathing training data, tongue muscle training data, human-computer interaction information, reminder information and rehabilitation training evaluation results of the subject to be trained through a storage device;
[0021] The update display module is connected to the central control module and is used to update and display the real-time data of the facial image data, image feature data, rehabilitation training acupoints, breathing training data, tongue muscle training data, human-computer interaction information, reminder information and evaluation results of the rehabilitation training of the object to be trained through the display.
[0022] Furthermore, the feature extraction of the acquired facial image of the subject to be trained by the image feature extraction module using a feature extraction program includes:
[0023] (1) constructing a face image feature extraction model based on a deep convolutional neural network, and performing convolution calculations on the image feature extraction model based on the deep convolutional neural network layer by layer to obtain an image feature vector;
[0024] (2) transmitting the image feature vector to a central processing module, which calculates similarity between the image feature vector and a predetermined number of sub-center vectors corresponding to the face image category to obtain a preliminary diagnosis of the disease;
[0025] (3) transmitting the preliminary diagnosis to the verification module and the intelligent processing module, and the verification module compares the preliminary diagnosis with the facial image category with the maximum similarity value to verify the preliminary diagnosis;
[0026] (4) The verified disease information is transmitted to the intelligent processing module, and the intelligent processing module calculates the loss value based on the similarity of the facial image category; determines whether to continue training or end training according to the loss value; if the training is to continue, the optimizer is used to optimize the image feature extraction model based on the deep convolutional neural network, and the new image feature extraction model is used to perform secondary extraction of image features; if the training is to end, the image feature vector extracted for the first time is output.
[0027] Furthermore, before performing convolution calculation layer by layer using the image feature extraction model based on the deep convolutional neural network, the method further includes:
[0028] The face image to be input into the image feature extraction model is preprocessed by background removal and alignment, and the face image obtained after the preprocessing is input into the image feature extraction model.
[0029] Furthermore, the automatic positioning of the rehabilitation training acupoints of the rehabilitation training subject by the acupoint positioning module using the positioning device according to the facial image features includes:
[0030] (1) acquiring a first acupuncture point overlapping with the facial image feature according to the facial image feature, and calculating the same body size of the human body in the input facial image based on the bone measurement method according to the facial image;
[0031] (2) obtaining a second acupuncture point according to the facial image features and the same size of the human body in the facial image, and inputting the facial image features into the training results of the neural network model to obtain a third acupuncture point;
[0032] (3) The training result of the neural network model is obtained based on the facial image features and the position of the third acupuncture point; the obtained facial acupuncture point position of the human face is saved to complete the positioning of the facial acupuncture point of the human face.
[0033] Furthermore, the breathing training component includes a handpiece and an air whistle mechanism, and the air whistle mechanism is installed on the handpiece; the tongue muscle training component includes a pressure control component and a suction nozzle, and the suction nozzle is detachably connected to one end of the pressure control component.
[0034] The tongue muscle training of the rehabilitation training object through the tongue muscle training component includes: training the patient to raise the root of the tongue to pronounce, to close the lips to pronounce, and to reduce the number of nasal sounds for patients with heavy nasal sounds.
[0035] Further, the rehabilitation training evaluation module uses an evaluation program to evaluate the rehabilitation training index of the rehabilitation training subject according to the breathing training data and the tongue muscle training data, including:
[0036] (1) Synchronously collect the electromyographic signals and movement information of rehabilitation training subjects during swallowing;
[0037] (2) obtaining a muscle strength evaluation index by analyzing the electromyographic signal, and obtaining a movement time, movement smoothness, and pronunciation evaluation index of the rehabilitation training subject by analyzing the movement information;
[0038] (3) The weights of the muscle strength evaluation index, movement time, movement smoothness and pronunciation evaluation index in the rehabilitation effect evaluation were analyzed using the hierarchical analysis method to obtain the swallowing rehabilitation training effect.
[0039] Furthermore, the pronunciation evaluation index includes: initial consonant evaluation, final consonant evaluation and tone evaluation;
[0040] The initial consonants are used to evaluate the coordinated movement of the lips, teeth and tongue. The finals are used to evaluate the coordinated movement and resonance of the lips, teeth and tongue. The tones are used to evaluate the control of the airflow.
[0041] Furthermore, the verification module performs verification based on blockchain data storage, mainly including the following steps:
[0042] Step S1: Explain the physical symptoms to the doctor and accept the collection rehabilitation training. The patient blockchain data packaging module stores the data of the individual's current muscle strength evaluation index, exercise time, movement smoothness and pronunciation evaluation index;
[0043] Step S2: The digital signature verification module packages the patient's symptom treatment data into blocks and stores them in the blockchain service network, and performs digital signature verification to prevent data tampering and improve the security of data storage;
[0044] Step S3: The patient blockchain extraction module extracts the blocks in the blockchain service network and decompresses the block storage data;
[0045] Step S4: With the blockchain node established by the individual as the center, different rights are granted for medical condition communication.
[0046] Furthermore, the occlusal condition monitoring method based on the vision and speech fusion technology of the intelligent processing module includes the following steps:
[0047] (1) Continuously obtain facial images and tongue muscle training sound information of the monitored person and make real-time judgments on the movement and vocal tics of the monitored person;
[0048] (2) based on the real-time judgment results of the facial image of the monitored person and the tongue muscle twitching in the above steps, the obtained twitching information is saved in a database;
[0049] (3) Based on the relevant diagnosis of the monitored person’s condition stored in the blockchain data, the diagnostic basis and results will be promptly fed back to relevant personnel and continuously monitored.
[0050] Another object of the present invention is to provide a computer program product stored on a computer-readable medium, including a computer-readable program, which, when executed on an electronic device, provides a user input interface to apply the portable acupoint stimulator to the human-computer interactive adult swallowing rehabilitation training system.
[0051] Another object of the present invention is to provide a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to apply the portable acupoint stimulator to a human-computer interactive adult swallowing rehabilitation training system.
[0052] Another object of the present invention is to provide an information data processing terminal, which is used to implement the portable acupoint stimulator and the human-computer interactive adult swallowing rehabilitation training system.
[0053] In combination with the above technical solutions and the technical problems solved, please analyze the advantages and positive effects of the technical solutions to be protected by the present invention from the following aspects:
[0054] First, in view of the technical problems existing in the above-mentioned prior art and the difficulty of solving the problems, the technical solutions to be protected by the present invention and the results and data during the research and development process are closely combined to analyze in detail and deeply how the technical solutions of the present invention solve the technical problems, and some creative technical effects brought about after solving the problems. The specific description is as follows:
[0055] The portable acupoint stimulator and human-computer interactive adult swallowing rehabilitation training system provided by the present invention extracts facial image features through an image feature extraction module, and can automatically locate training acupoints according to the image features, thereby saving time and reducing workload for medical workers; a breathing training component is used to train the breathing of the rehabilitation training object, and a tongue muscle training component is used to train the tongue muscle of the rehabilitation training object, so that breathing training can be performed while tongue muscle training is achieved, the system is easy to use, improves the training treatment effect, is beneficial to patient recovery, and is suitable for popularization and application.
[0056] Second, considering the technical solution as a whole or from the perspective of the product, the technical effects and advantages of the technical solution to be protected by the present invention are described in detail as follows:
[0057] The portable acupoint stimulator and the human-computer interactive adult swallowing rehabilitation training system provided by the present invention can realize all-round training for patients with swallowing disorders, and has the characteristics of easy operation and improved efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] Figure 1 It is a schematic diagram of information interaction between a portable acupoint stimulator and a human-computer interactive adult swallowing rehabilitation training system provided by an embodiment of the present invention;
[0059] Figure 2 It is a flow chart of a method for extracting features from a facial image of a subject to be trained for rehabilitation using a feature extraction program through an image feature extraction module provided by an embodiment of the present invention;
[0060] Figure 3 It is a flow chart of a method for evaluating rehabilitation training indicators of a rehabilitation training subject according to breathing training and tongue muscle training data by using an evaluation program through a rehabilitation training evaluation module provided by an embodiment of the present invention;
[0061] Figure 4 It is a flow chart of verification performed by a verification module based on blockchain data storage provided by an embodiment of the present invention;
[0062] Figure 5 It is a flow chart of an occlusal condition monitoring method based on vision and speech fusion technology by an intelligent processing module provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0063] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0064] 1. Explanatory Examples In order to enable those skilled in the art to fully understand how to implement the present invention, this section provides an illustrative example that expands and describes the technical solution of the claims.
[0065] The embodiment of the present invention provides a portable acupoint stimulator and a human-computer interactive adult swallowing rehabilitation training system comprising:
[0066] The central control module is linearly connected to the verification module and the intelligent processing module. The verification module is used to diagnose and verify the degree of swallowing disease of the patient; the intelligent processing module is used to perform intelligent control on the required acupoint stimulation degree according to the disease verified by the verification module;
[0067] The central control module is linearly connected to a face image acquisition module, and the face image acquisition module is used to acquire face image data of a subject to be trained through an image acquisition device;
[0068] The central control module is also connected to an acupoint positioning module, which is used to automatically locate the rehabilitation training acupoints of the rehabilitation training object according to the facial image features through the positioning device;
[0069] The central control module is also connected to a breathing training module for training the breathing of the rehabilitation training subject through a breathing training component;
[0070] The central control module is also connected to a tongue muscle training module for training the tongue muscles of the rehabilitation training subject through the tongue muscle training component;
[0071] The central control module is also connected to a rehabilitation training evaluation module, which is used to evaluate the rehabilitation training indicators of the rehabilitation training object according to the breathing training data and the tongue muscle training data through an evaluation program;
[0072] The central control module is also connected to a data transmission module for sending the acquired facial image data and image feature data of the subject to be trained to the central processor via a data transmission device.
[0073] The portable acupoint stimulator and human-computer interactive adult swallowing rehabilitation training system also includes:
[0074] A data transmission module, connected to the central control module, is used to send the acquired facial image data and image feature data of the subject to be trained to the central processing unit through the data transmission device;
[0075] A central control module, connected to the data transmission module, the human-computer interaction module, the reminder module, the training record module, the data storage module, and the update display module, and used for coordinating and controlling the normal operation of the portable acupoint stimulator and each module of the human-computer interactive adult swallowing rehabilitation training system through a central processor;
[0076] A human-computer interaction module is connected to the central control module and is used for interactive operation between the subject to be trained and the adult swallowing rehabilitation training system through a human-computer interaction device;
[0077] A reminder module, connected to the central control module, for reminding the rehabilitation training subject of wrong training actions through an audio-visual reminder device according to human interaction information;
[0078] A training recording module, connected to the central control module, is used to record the swallowing rehabilitation training process data of the rehabilitation training subject through a training recording program;
[0079] A data storage module is connected to the central control module and is used to store the acquired facial image data, image feature data, rehabilitation training acupoints, breathing training data, tongue muscle training data, human-computer interaction information, reminder information and rehabilitation training evaluation results of the subject to be trained through a storage device;
[0080] The update display module is connected to the central control module and is used to update and display the real-time data of the facial image data, image feature data, rehabilitation training acupoints, breathing training data, tongue muscle training data, human-computer interaction information, reminder information and evaluation results of the rehabilitation training of the object to be trained through the display.
[0081] The information interaction diagram of the portable acupoint stimulator and the human-computer interactive adult swallowing rehabilitation training system provided by the embodiment of the present invention is shown in FIG. Figure 1 shown.
[0082] like Figure 2 As shown, the method provided by the embodiment of the present invention of extracting features from the acquired face image of the subject to be trained by using the feature extraction program through the image feature extraction module includes:
[0083] S201: constructing a face image feature extraction model based on a deep convolutional neural network, and performing convolution calculation on the image feature extraction model based on the deep convolutional neural network layer by layer to obtain an image feature vector;
[0084] S202: transmitting the image feature vector to a central processing module, wherein the central processing module calculates similarity between the image feature vector and a predetermined number of sub-center vectors corresponding to the face image category to obtain a preliminary diagnosis of the disease;
[0085] S203: transmitting the preliminary diagnosis of the disease to the verification module and the intelligent processing module, and the verification module performs a face image category comparison on the obtained preliminary disease and obtains the maximum similarity, thereby verifying the preliminary disease;
[0086] S204: The verified disease information is transmitted to the intelligent processing module, and the intelligent processing module calculates the loss value based on the similarity of the face image category; determines whether to continue training or end training according to the loss value; if training is to continue, the optimizer is used to optimize the image feature extraction model based on the deep convolutional neural network, and the new image feature extraction model is used to perform secondary extraction of image features; if training is to end, the image feature vector extracted for the first time is output.
[0087] Before performing convolution calculation layer by layer using the image feature extraction model based on the deep convolutional neural network, the method further includes:
[0088] The face image to be input into the image feature extraction model is preprocessed by background removal and alignment, and the face image obtained after the preprocessing is input into the image feature extraction model.
[0089] The acupoint positioning module uses the positioning device to automatically locate the rehabilitation training acupoints of the rehabilitation training object according to the facial image features, including:
[0090] (1) acquiring a first acupuncture point overlapping with the facial image feature according to the facial image feature, and calculating the same body size of the human body in the input facial image based on the bone measurement method according to the facial image;
[0091] (2) obtaining a second acupuncture point according to the facial image features and the same size of the human body in the facial image, and inputting the facial image features into the training results of the neural network model to obtain a third acupuncture point;
[0092] (3) The training result of the neural network model is obtained based on the facial image features and the position of the third acupuncture point; the obtained facial acupuncture point position of the human face is saved to complete the positioning of the facial acupuncture point of the human face.
[0093] The breathing training component comprises a handpiece and an air whistle mechanism, wherein the air whistle mechanism is mounted on the handpiece; the tongue muscle training component comprises a pressure control component and a suction nozzle, wherein the suction nozzle is detachably connected to one end of the pressure control component.
[0094] The tongue muscle training of the rehabilitation training object through the tongue muscle training component includes: training the patient to raise the root of the tongue to pronounce, to close the lips to pronounce, and to reduce the number of nasal sounds for patients with heavy nasal sounds.
[0095] like Figure 3As shown, the embodiment of the present invention provides a rehabilitation training evaluation module that uses an evaluation program to evaluate the rehabilitation training indicators of the rehabilitation training object according to the breathing training data and the tongue muscle training data, including:
[0096] S301: synchronously collecting electromyographic signals and movement information of the rehabilitation training subject during swallowing;
[0097] S302: Obtaining a muscle strength evaluation index by analyzing the electromyographic signal, and obtaining a movement time, movement smoothness, and pronunciation evaluation index of the rehabilitation training subject by analyzing the movement information;
[0098] S303: Analyze the weights of the muscle strength evaluation index, movement time, movement smoothness and pronunciation evaluation index in the rehabilitation effect evaluation by using the hierarchical analysis method to obtain the swallowing rehabilitation training effect.
[0099] The pronunciation evaluation index includes: initial consonant evaluation, final consonant evaluation and tone evaluation;
[0100] The initial consonants are used to evaluate the coordinated movement of the lips, teeth and tongue. The finals are used to evaluate the coordinated movement and resonance of the lips, teeth and tongue. The tones are used to evaluate the control of the airflow.
[0101] like Figure 4 As shown, the verification module performs verification based on blockchain data storage, mainly including the following steps:
[0102] S401: Explain the physical symptoms to the doctor and accept the rehabilitation training. The patient blockchain data packaging module stores the data of the individual's current muscle strength evaluation index, exercise time, movement smoothness and pronunciation evaluation index;
[0103] S402: The digital signature verification module packages the patient's symptom treatment data into blocks and stores them in the blockchain service network, and performs digital signature verification to prevent data from being tampered with and improve the security of data storage;
[0104] S403: The patient blockchain extraction module extracts blocks from the blockchain service network and decompresses the block storage data;
[0105] S404: With the blockchain node established by individuals as the center, different rights are granted for medical condition communication.
[0106] like Figure 5 As shown, the occlusal condition monitoring method based on the vision and speech fusion technology of the intelligent processing module includes the following steps:
[0107] S501: continuously acquiring the facial image and tongue muscle training sound information of the monitored person and making a real-time judgment on the movement and vocal twitch of the monitored person;
[0108] S502: based on the real-time determination result of the facial image of the monitored person and the tongue muscle twitching in the above steps, the obtained twitching information is saved in a database;
[0109] S503: Based on the relevant diagnosis of the monitored person's condition stored in the blockchain data, the diagnosis basis and diagnosis results are fed back to relevant personnel in a timely manner and continuously monitored.
[0110] 2. Application Examples: In order to prove the creativity and technical value of the technical solution of the present invention, this section provides application examples of the technical solution of the claims on specific products or related technologies.
[0111] Another object of the present invention is to provide a computer program product stored on a computer-readable medium, including a computer-readable program, which, when executed on an electronic device, provides a user input interface to apply the portable acupoint stimulator to the human-computer interactive adult swallowing rehabilitation training system.
[0112] Another object of the present invention is to provide a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to apply the portable acupoint stimulator to a human-computer interactive adult swallowing rehabilitation training system.
[0113] Another object of the present invention is to provide an information data processing terminal, which is used to implement the portable acupoint stimulator and the human-computer interactive adult swallowing rehabilitation training system.
[0114] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.
[0115] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.
Claims
1. A portable acupoint stimulator and human-computer interactive adult swallowing rehabilitation training system, It is characterized in that The adult swallowing rehabilitation training system is provided with: Central control module; The central control module is linearly connected to the verification module and the intelligent processing module. The verification module is used to diagnose and verify the degree of swallowing disease of the subject to be rehabilitated; the intelligent processing module is used to perform intelligent control on the disease verified by the verification module and the required acupoint stimulation degree; The central control module is linearly connected to a face image acquisition module, and the face image acquisition module is used to acquire face image features of the subject to be trained through an image acquisition device; The central control module is also connected to an acupoint positioning module, which is used to automatically locate the rehabilitation training acupoints of the rehabilitation training object according to the facial image features through the positioning device; The central control module is also connected to a breathing training module, which is used to train the breathing of the rehabilitation training subject through a breathing training component; The central control module is also connected to a tongue muscle training module, which is used to train the tongue muscles of the rehabilitation training object through a tongue muscle training component; The central control module is also connected to a rehabilitation training evaluation module, which is used to evaluate the rehabilitation training indicators of the rehabilitation training object according to the breathing training data and the tongue muscle training data through an evaluation program; The central control module is also connected to a data transmission module, which is used to send the acquired facial image features and image feature data of the subject to be trained to the central processor through a data transmission device; The image feature extraction module uses a feature extraction program to extract features from the acquired face image of the subject to be trained, including: (1) constructing an image feature extraction model based on a deep convolutional neural network, and performing convolution calculation on the image feature extraction model based on the deep convolutional neural network layer by layer to obtain an image feature vector; (2) transmitting the image feature vector to a central processing module, which calculates the similarity between the image feature vector and a predetermined number of sub-center vectors corresponding to the facial image category to obtain a preliminary diagnosis of the disease; (3) transmitting the preliminary diagnosis of the disease to the verification module and the intelligent processing module, and verifying the preliminary diagnosis of the disease through the verification module and comparing the facial image categories with the maximum similarity; (4) transmitting the verified disease information to the intelligent processing module, and the intelligent processing module calculates the loss value based on the similarity of the face image category; determining whether to continue training or end training according to the loss value; if continuing training, using an optimizer to optimize the image feature extraction model based on the deep convolutional neural network, and using the new image feature extraction model to perform secondary extraction of image features; if ending training, outputting the image feature vector extracted for the first time; The breathing training component includes a handpiece and an air whistle mechanism, and the air whistle mechanism is installed on the handpiece; the tongue muscle training component includes a pressure control component and a suction nozzle, and the suction nozzle is detachably connected to one end of the pressure control component; The tongue muscle training of the rehabilitation training subject through the tongue muscle training component includes: training the rehabilitation training subject to raise the root of the tongue to pronounce, to close the lips to pronounce, and to reduce the number of times the rehabilitation training subject pronounces nasal sounds when the nasal sounds are too heavy.
2. The adult swallowing rehabilitation training system according to claim 1, It is characterized in that The adult swallowing rehabilitation training system also includes: A central control module, connected to the data transmission module, the human-computer interaction module, the reminder module, the training record module, the data storage module, and the update display module, and used to coordinate and control the normal operation of each module of the adult swallowing rehabilitation training system through a central processor; A human-computer interaction module is connected to the central control module and is used to perform interactive operations between the subject to be trained and the adult swallowing rehabilitation training system through a human-computer interaction device; A reminder module, connected to the central control module, for reminding the rehabilitation training subject of wrong training actions through an audio-visual reminder device according to human interaction information; A training recording module, connected to the central control module, is used to record the swallowing rehabilitation training process data of the rehabilitation training subject through a training recording program; A data storage module is connected to the central control module and is used to store the acquired facial image features, image feature data, rehabilitation training acupoints, breathing training data, tongue muscle training data, human-computer interaction information, reminder information and rehabilitation training evaluation results of the subject to be trained through a storage device; The update display module is connected to the central control module and is used to update and display the real-time data of the facial image features, image feature data, rehabilitation training acupoints, breathing training data, tongue muscle training data, human-computer interaction information, reminder information and evaluation results of the rehabilitation training of the subject through the display.
3. The adult swallowing rehabilitation training system according to claim 1, It is characterized in that Before performing convolution calculation layer by layer using the image feature extraction model based on the deep convolutional neural network, the method further includes: The face image to be input into the image feature extraction model is preprocessed by background removal and alignment, and the face image obtained after the preprocessing is input into the image feature extraction model.
4. The adult swallowing rehabilitation training system according to claim 1, It is characterized in that The acupoint positioning module uses the positioning device to automatically locate the rehabilitation training acupoints of the rehabilitation training object according to the facial image features, including: (1) acquiring a first acupuncture point overlapping with the facial image feature according to the facial image feature, and calculating the same body size of the human body in the input facial image based on the bone measurement method according to the facial image; (2) obtaining a second acupuncture point according to the facial image features and the same size of the human body in the facial image, and inputting the facial image features into the training results of the neural network model to obtain a third acupuncture point; (3) The training result of the neural network model is obtained based on the facial image features and the position of the third acupuncture point; the obtained facial acupuncture point position of the human face is saved to complete the positioning of the facial acupuncture point of the human face.
5. The adult swallowing rehabilitation training system according to claim 1, It is characterized in that The rehabilitation training evaluation module uses an evaluation program to evaluate the rehabilitation training indicators of the rehabilitation training object according to the breathing training data and the tongue muscle training data, including: (1) Synchronously collect the electromyographic signals and movement information of the subjects during the swallowing process; (2) obtaining a muscle strength evaluation index by analyzing the electromyographic signal, and obtaining a movement time, movement smoothness, and pronunciation evaluation index of the subject to be trained by analyzing the movement information; (3) The weights of the muscle strength evaluation index, movement time, movement smoothness and pronunciation evaluation index in the rehabilitation effect evaluation were analyzed using the hierarchical analysis method to obtain the swallowing rehabilitation training effect.
6. The adult swallowing rehabilitation training system according to claim 5, It is characterized in that The pronunciation evaluation index includes: initial consonant evaluation, final consonant evaluation and tone evaluation; The initial consonants are used to evaluate the coordinated movement of the lips, teeth and tongue. The finals are used to evaluate the coordinated movement and resonance of the lips, teeth and tongue. The tones are used to evaluate the control of the airflow.
7. The adult swallowing rehabilitation training system according to claim 1, It is characterized in that The verification module performs verification based on blockchain data storage, mainly including the following steps: Step S1: Explain the physical symptoms to the doctor and accept the collection rehabilitation training. The patient blockchain data packaging module stores the data of the individual's current muscle strength evaluation index, exercise time, movement smoothness and pronunciation evaluation index; Step S2: The digital signature verification module packages the patient's symptom treatment data into blocks and stores them in the blockchain service network, and performs digital signature verification to prevent data tampering and improve the security of data storage; Step S3: The patient blockchain extraction module extracts the blocks in the blockchain service network and decompresses the block storage data; Step S4: With the blockchain node established by the individual as the center, different rights are granted for medical condition communication.
8. The adult swallowing rehabilitation training system according to claim 1, It is characterized in that The occlusal condition monitoring method based on the vision and speech fusion technology of the intelligent processing module comprises the following steps: (1) Continuously obtain facial images and tongue muscle training sound information of the monitored person and make real-time judgments on the movement and vocal tics of the monitored person; (2) based on the real-time judgment results of the facial image of the monitored person and the tongue muscle twitching in the above steps, the obtained twitching information is saved in a database; (3) Based on the relevant diagnosis of the monitored person’s condition stored in the blockchain data, the diagnostic basis and results will be promptly fed back to relevant personnel and continuously monitored.
