AI artificial intelligence-based ear acupuncture point identification method and ear acupuncture point bean pressing management system

Abstract

The invention discloses an AI artificial intelligence-based ear acupuncture point recognition method and an auricular point bean pressing management system, and relates to the field of auricular point treatment, and the system comprises an image acquisition module, an image preprocessing module, a feature extraction module, an acupuncture point recognition module and a result output module; the feature extraction module comprises a data set construction module, a model training module, an algorithm optimization module and a system integration module; an auricular point bean pressing management system based on AI artificial intelligence is suitable for an auricular point recognition method based on AI artificial intelligence and comprises a patient information management module, an auricular point selection and management module and a treatment effect evaluation module. According to the AI artificial intelligence-based ear acupuncture point identification method and the auricular point pressing bean management system, through the ear acupuncture point identification method, a large amount of data is collected to construct an ear acupuncture point model, and through the auricular point pressing bean management system 2, the positions and the number of the auricular points to be treated are selected according to the illness state of a patient, so that errors during manual selection are avoided; and the treatment effect of the patient is not good.

Description

Technical Field

[0001] The present invention relates to auricular acupuncture point treatment technology, and in particular to an auricular acupuncture point recognition method and an auricular acupuncture point pressure bean management system based on AI artificial intelligence. Background Art

[0002] Ear points are acupuncture points distributed on the auricle. They are also called reaction points or stimulation points. When the internal organs or body of the human body are diseased, local reactions often occur in certain parts of the auricle, such as tenderness, nodules, discoloration, conductivity, etc. This phenomenon can be used as a reference for diagnosing diseases, or stimulating these reaction points (ear points) to prevent and treat diseases.

[0003] The ear is closely related to the internal organs and meridians. Each internal organ has a corresponding reaction area (ear acupoints) on the auricle. Stimulating the ear acupoints has a certain regulating effect on the corresponding internal organs. The main methods of stimulating the ear acupoints are: acupuncture, needle embedding, bloodletting, ear acupoint sticking, magnetic therapy, massage, etc. When a part of the human body is sick, it will react on certain parts of the auricle. These parts are the stimulation points of ear acupuncture treatment, collectively called ear acupoints.

[0004] Since the 1980s, China has strengthened the research and application of auricular acupuncture. The indications of auricular acupuncture treatment have been continuously expanded, from dozens to more than 100. Auricular acupuncture anesthesia occupies a considerable proportion in the field of acupuncture anesthesia in China. In 1982, China established the Auricular Acupuncture Collaboration Group, in 1987 established the National Auricular Acupuncture Research Association, and in 1992, issued the National Standard of the People's Republic of China "Names and Locations of Auricular Acupuncture Points".

[0005] According to the national standard GB / T13734-92, there are 91 ear acupoints. It was updated and revised in 2008. The current standard is "GB / T13734-2008 Names and Positions of Ear Acupoints". The distribution pattern of ear acupoints is that the acupoints corresponding to the cheek are on the earlobe; the acupoints corresponding to the upper limbs are around the ear; the acupoints corresponding to the trunk are on the body of the antihelix; the acupoints corresponding to the lower limbs are on the upper and lower feet of the antihelix; the acupoints corresponding to the abdominal cavity are on the cymba concha; the acupoints corresponding to the chest cavity are in the cavity of the concha; the acupoints corresponding to the digestive tract are around the foot of the helix, etc.

[0006] When existing AI-based ear acupoint recognition methods and ear acupoint pressure bean management systems are used, doctors mostly rely on their naked eyes and experience to identify different acupoints required for different diseases. However, the ears of different patients are different, and it is easy to make mistakes in identification, resulting in poor treatment effects. Summary of the invention

[0007] The purpose of the present invention is to provide an ear acupoint recognition method and an ear acupoint pressure bean management system based on AI artificial intelligence, so as to solve the above-mentioned shortcomings that the prior art mostly relies on the doctor's naked eyes and experience to identify different acupoints required for different diseases, while the ears of different patients are different, and it is easy to identify incorrectly, resulting in poor treatment effects.

[0008] In order to achieve the above-mentioned purpose, the present invention provides the following technical solutions: an ear acupoint recognition method and an ear acupoint pressure bean management system based on AI artificial intelligence, comprising:

[0009] Image acquisition module, image preprocessing module, feature extraction module, acupoint recognition module, result output module;

[0010] The feature extraction module includes: a data set construction module, a model training module, an algorithm optimization module, and a system integration module.

[0011] Furthermore, it also includes:

[0012] S1. Obtain clear images of the ear through the image acquisition module. These images will serve as the basis for subsequent image recognition and acupoint positioning;

[0013] S2, preprocessing the collected images through the image preprocessing module to improve the image quality and recognition effect;

[0014] S3, through the feature extraction module, using the deep learning algorithm, extracting features from the preprocessed image for subsequent acupoint identification;

[0015] S4. The ear model data collected from a large number of patients are created into a data set containing a large number of labeled ear acupoint images through the data set construction module 131. The deep learning model is trained by using the constructed data set through the model training module 132. During the training process, the parameters and structure of the model need to be continuously adjusted to improve the accuracy of recognition. The algorithm for identifying ear acupoints is optimized by using the algorithm optimization module 133 to further improve the accuracy of recognition. The trained model is integrated into relevant medical equipment or software by using the system integration module 134 to realize automatic recognition of ear acupoints.

[0016] S5, using the acupoint recognition module to perform acupoint recognition based on the extracted features and using the trained model;

[0017] S6. Through the result output module, the recognition result is output in the form of image or text, which is presented to the user or used for subsequent treatment and analysis.

[0018] An AI-based ear acupuncture bean pressure management system, which is applicable to the AI-based ear acupuncture point recognition method according to any one of claims 1 to 2, comprising:

[0019] Patient information management module, auricular acupoint selection and management module, treatment effect evaluation module.

[0020] Furthermore, it also includes:

[0021] S11. Record the patient's basic information and medical history through the patient information management module;

[0022] S12, through the ear acupoint selection and management module, according to the patient's specific condition and constitution and using the ear acupoint recognition method, select the corresponding ear acupoints, and further record the position, number and corresponding symptoms of the ear acupoints selected for each treatment;

[0023] S13. Through the treatment effect evaluation module, the changes in the patient's condition after each treatment are recorded, and the treatment plan is adjusted according to the treatment effect.

[0024] Compared with the prior art, the AI-based ear acupoint recognition method and ear acupoint pressure bean management system provided by the present invention collect a large amount of data to construct an ear acupoint model through the ear acupoint recognition method, and select the position and number of ear acupoints for treatment according to the patient's condition through the ear acupoint pressure bean management system 2, thereby avoiding errors in manual selection and resulting in poor treatment effects for patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0026] Figure 1 A flow chart of a method for identifying ear acupoints provided by an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of a feature extraction module provided by an embodiment of the present invention;

[0028] Figure 3 This is a flow chart of the ear acupoint pressure bean management system provided by an embodiment of the present invention.

[0029] Description of reference numerals:

[0030] 1. Ear acupoint recognition method; 11. Image acquisition module; 12. Image preprocessing module; 13. Feature extraction module; 131. Data set construction module; 132. Model training module; 133. Algorithm optimization module; 134. System integration module; 14. Acupoint recognition module; 15. Result output module; 2. Ear acupoint pressure bean management system; 21. Patient information management module; 22. Ear acupoint selection and management module; 23. Treatment effect evaluation module. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0032] Embodiment 1:

[0033] See also Figure 1 and Figure 2 , the ear acupoint recognition method based on AI artificial intelligence includes:

[0034] Image acquisition module 11, image preprocessing module 12, feature extraction module 13, acupoint recognition module 14, result output module 15;

[0035] The feature extraction module 13 includes: a data set construction module 131, a model training module 132, an algorithm optimization module 133, and a system integration module 134.

[0036] The specific implementation method is that the algorithm optimization module 133 can use advanced technologies such as attention mechanism to improve the model's attention to key acupoints; it can also combine traditional Chinese medicine theory to constrain the location and shape of acupoints to further improve the accuracy of recognition.

[0037] Also includes:

[0038] S1, obtaining clear images of the ear through the image acquisition module 11, which will serve as the basis for subsequent image recognition and acupoint positioning;

[0039] S2, preprocessing the collected image through the image preprocessing module 12 to improve the image quality and recognition effect;

[0040] S3, using a deep learning algorithm through a feature extraction module 13, extracting features from the preprocessed image for subsequent acupoint identification;

[0041] S4. The ear model data collected from a large number of patients are created into a data set containing a large number of labeled ear acupoint images through the data set construction module 131. The deep learning model is trained by using the constructed data set through the model training module 132. During the training process, the parameters and structure of the model need to be continuously adjusted to improve the accuracy of recognition. The algorithm for identifying ear acupoints is optimized by using the algorithm optimization module 133 to further improve the accuracy of recognition. The trained model is integrated into relevant medical equipment or software by using the system integration module 134 to realize automatic recognition of ear acupoints.

[0042] S5, using the acupoint recognition module 14 to recognize acupoints based on the extracted features and using the trained model;

[0043] S6. The recognition result is output in the form of an image or text through the result output module 15, and is presented to the user or used for subsequent treatment and analysis.

[0044] Embodiment 2:

[0045] See also Figure 3 , an AI-based ear acupuncture bean pressure management system, which is applicable to the AI-based ear acupuncture point recognition method according to any one of claims 1-2, comprising:

[0046] Patient information management module 21, ear acupoint selection and management module 22, treatment effect evaluation module 23.

[0047] Also includes:

[0048] S11, recording the patient's basic information and medical history through the patient information management module 21;

[0049] S12, selecting corresponding ear acupoints according to the patient's specific condition and constitution and using the ear acupoint identification method 1 through the ear acupoint selection and management module 22, and further recording the position, number and corresponding symptoms of the ear acupoints selected for each treatment;

[0050] S13. The treatment effect evaluation module 23 records the changes in the patient's condition after each treatment, and adjusts the treatment plan according to the treatment effect.

[0051] The specific implementation method is as follows: cleaning the ears: use a sterilized cotton swab to gently wipe the inside and outside of the auricle to reduce the risk of infection; finding sensitive points: the ear acupoint identification method identifies sensitive points of the ears, which are usually the locations of the acupoints; sticking beans and fixing: stick the fenugreek seeds on the selected acupoints, fix them with adhesive tape, and ensure that the fenugreek seeds fit tightly to the acupoints; precautions: avoid applying on the affected area or inflamed area; ear acupoint pressure bean treatment is not suitable for people with severe organic diseases, inflammatory diseases, hemophilia, severe neurasthenia, ear inflammation, etc.; pregnant women and breastfeeding women should consult a professional doctor before use.

[0052] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. The ear acupoint recognition method based on AI artificial intelligence is characterized by: include: Image acquisition module (11), image preprocessing module (12), feature extraction module (13), acupoint recognition module (14), result output module (15); The feature extraction module (13) includes: a data set construction module (131), a model training module (132), an algorithm optimization module (133), and a system integration module (134).

2. The method for identifying ear acupoints based on AI artificial intelligence according to claim 1, characterized in that: Also includes: S1, obtaining clear images of the ear through the image acquisition module (11), which will serve as the basis for subsequent image recognition and acupoint positioning; S2, preprocessing the collected image through an image preprocessing module (12) to improve the image quality and recognition effect; S3, using a feature extraction module (13) and a deep learning algorithm to extract features from the preprocessed image for subsequent acupoint identification; S4. The ear model data collected from a large number of patients are created into a data set containing a large number of labeled ear acupoint images through the data set construction module 131. The deep learning model is trained by using the constructed data set through the model training module 132. During the training process, the parameters and structure of the model need to be continuously adjusted to improve the accuracy of recognition. The algorithm for identifying ear acupoints is optimized by using the algorithm optimization module 133 to further improve the accuracy of recognition. The trained model is integrated into relevant medical equipment or software by using the system integration module 134 to realize automatic recognition of ear acupoints. S5, using the acupoint recognition module (14), based on the extracted features, using the trained model to perform acupoint recognition; S6. The recognition result is output in the form of an image or text through the result output module (15) to be displayed to the user or used for subsequent treatment and analysis.

3. An AI-based ear acupuncture bean pressure management system, which is applicable to the AI-based ear acupuncture point recognition method according to any one of claims 1-2, characterized in that: include: Patient information management module (21), ear acupoint selection and management module (22), treatment effect evaluation module (23).

4. The AI-based ear acupuncture bean management system according to claim 1, characterized in that: Also includes: S11, recording the patient's basic information and medical history through the patient information management module (21); S12, selecting corresponding ear acupoints according to the patient's specific condition and constitution and using the ear acupoint identification method (1) through the ear acupoint selection and management module (22), and further recording the position and number of the ear acupoints selected for each treatment and the corresponding symptoms; S13. The treatment effect evaluation module (23) records the changes in the patient's condition after each treatment and adjusts the treatment plan according to the treatment effect.

Images