Intelligent traditional Chinese medicine ear diagnosis auxiliary system

Abstract

The invention discloses an intelligent traditional Chinese medicine ear diagnosis auxiliary system, and the system comprises an in-ear data collection module which is used for collecting and preprocessing pathological image data, temperature ratio data and humidity ratio data in the ear of a patient; the pathological image data analysis module is used for performing matching analysis on the pathological image data to generate illness state diagnosis data; the temperature and humidity ratio data analysis module is used for performing integrated analysis on the temperature ratio data and the humidity ratio data to generate illness condition severity data; the accuracy analysis module is used for integrating and analyzing the illness state diagnosis data and the illness state severity data to generate accuracy data; and the illness state output module is used for outputting a diagnosis result and an error degree according to the illness state diagnosis data and the accuracy rate data. According to the invention, the authenticity and accuracy of diagnosis are improved, and misdiagnosis is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of traditional Chinese medicine diagnosis and treatment, and particularly to an intelligent traditional Chinese medicine ear diagnosis assistance system. Background Art

[0002] In the prior art with the publication number CN115083588A, a traditional Chinese medicine ear diagnosis instrument and its diagnosis system are proposed. In this prior art, a high-definition picture of the ear can be obtained through the ear diagnosis instrument body and automatically uploaded to the artificial intelligence module in the cloud. The artificial intelligence module uses image recognition technology and, according to the logic of traditional Chinese medicine ear diagnosis, obtains a preliminary diagnosis result. Then, the diagnosis result is confirmed online by traditional Chinese medicine ear diagnosis experts. Finally, medicine is prescribed online through the APP module and delivered to the home by express, enabling users to diagnose ear problems at home and avoiding the cumbersome and inconvenient process of going to the hospital.

[0003] Analyzing in combination with the prior art, it is found that the following problems still exist: 1. In the prior art, the ear diagnosis logic analyzed through image recognition technology does not explain the image data collected in detail, resulting in relatively low accuracy in the analysis input into the recognition model; 2. In the prior art, the situation of only detecting through image recognition cannot reflect the temperature and humidity conditions inside the ear canal in real time. When there is just a secretion phenomenon in the ear canal, real-time diagnosis cannot be performed through image analysis, and there is a delay in diagnosis. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to propose an intelligent traditional Chinese medicine ear diagnosis assistance system.

[0005] In order to achieve the above technical purpose, the technical solution adopted by the present invention is as follows: The present invention provides an intelligent traditional Chinese medicine ear diagnosis assistance system, including: An ear internal data acquisition module, which is used to collect pathological image data, temperature ratio data, and humidity ratio data of the patient's ear and perform preprocessing; A pathological image data analysis module, which is used to perform matching analysis on the pathological image data and generate disease diagnosis data; A temperature and humidity ratio data analysis module, which is used to perform integrated analysis on the temperature ratio data and humidity ratio data and generate disease severity data; An accuracy analysis module, which is used to perform integrated analysis on the disease diagnosis data and disease severity data and generate accuracy data; A disease output module, which is used to output a diagnosis result and an error degree according to the disease diagnosis data and accuracy data.

[0006] Further, the pathological image data includes auricle shape, auricle texture, earhole size, earhole color, and the condition of foreign objects in the earhole. The temperature ratio data is the ratio of the ear temperature to the indoor temperature, and the humidity ratio data is the ratio of the ear humidity to the indoor humidity.

[0007] Further, the pathological image data analysis module is processed using computer vision technology, and the construction of a machine learning model is required for the computer vision technology. The construction process of the machine learning model includes: Collect m groups of pathological image data, including normal and abnormal auricle shapes; Mark and annotate the m groups of pathological image data according to the corresponding diseases of the m groups of pathological image data, and classify them into normal or abnormal groups; Use the m groups of pathological image data as the input of the machine learning model, and the disease diagnosis data as the output of the machine learning model, with the prediction accuracy of the machine learning model as the training goal; Train the machine learning model. When the prediction accuracy of the machine learning model reaches the prediction accuracy threshold Z, stop training and generate the trained machine learning model Zn.

[0008] Further, the pathological image data analysis module compares the pathological image data through the machine learning model Zn, and matches through the auricle shape, auricle texture, earhole size, earhole color, and the condition of foreign objects in the earhole to generate disease diagnosis data.

[0009] Further, the temperature and humidity ratio data analysis module includes: Set the temperature ratio threshold T1 and the humidity ratio threshold H1; Compare the temperature ratio data Tr with the temperature ratio threshold T1. If the temperature ratio data Tr is less than the temperature ratio threshold T1, generate a first normal label; if the temperature ratio data Tr is not less than the temperature ratio threshold T1, generate a first abnormal label; Compare the humidity ratio data Hr with the humidity ratio threshold H1. If the humidity ratio data Hr is less than the humidity ratio threshold H1, generate a second normal label; if the humidity ratio data Hr is not less than the humidity ratio threshold H1, generate a second abnormal label; Calculate the temperature-humidity ratio coefficient Jer based on the temperature ratio data Tr and the humidity ratio data Hr, and compare it with the preset threshold J1 and the preset threshold J2, where the preset threshold J1 is less than the preset threshold J2. If the temperature-humidity ratio coefficient Jer is less than the preset threshold J1, generate a low-degree abnormal label; if the temperature-humidity ratio coefficient Jer is not less than the preset threshold J1 and less than the preset threshold J2, generate a medium-degree abnormal label; if the temperature-humidity ratio coefficient Jer is not less than the preset threshold J2, generate a high-degree abnormal label; Integrate the generated first normal label, first abnormal label, second normal label, second abnormal label, low-degree abnormal label, medium-degree abnormal label, and high-degree abnormal label to generate severity data of the disease condition.

[0010] Furthermore, the calculation formula for the temperature-humidity ratio coefficient Jer is: Jer = (Jer > 0); where K is an error correction constant, e is the natural constant, which is used to enhance the sensitivity of the temperature ratio data Tr in pathological analysis; a is a humidity adjustment factor.

[0011] Furthermore, the severity data of the disease condition includes high-risk disease condition identification, medium-high-risk disease condition identification, medium-risk disease condition identification, and low-risk disease condition identification. The generation process includes: Classify the first abnormal label, second abnormal label, and high-degree abnormal label as high-risk labels; classify the medium-degree abnormal label as a medium-risk label; classify the first normal label, second normal label, and low-degree abnormal label as low-risk labels; Generate corresponding severity identifications of the disease condition according to the combination of high-risk, medium-risk, and low-risk labels. Specifically: if there are more than two high-risk labels at the same time, generate a high-risk disease condition identification; if there is one high-risk label, one medium-risk label, and one low-risk label at the same time or there is one high-risk label and two low-risk labels at the same time, generate a medium-high-risk disease condition identification; if there is one medium-risk label and two low-risk labels at the same time, generate a medium-risk disease condition identification; if there are three low-risk labels at the same time, generate a low-risk disease condition identification.

[0012] Furthermore, the accuracy data includes high-accuracy objects, suspicious objects, and abnormal objects. The generation process of the accuracy data includes: Construct a disease condition data matching model, and generate simulated disease condition data according to the disease condition diagnosis data. The simulated disease condition data includes high-risk simulated identification, medium-high-risk simulated identification, medium-risk simulated identification, and low-risk simulated identification; Classify the simulated disease condition data and the severity data of the disease condition to generate level identifications. Specifically: classify the high-risk simulated identification and the high-risk disease condition identification as first-level identifications, classify the medium-high-risk simulated identification and the medium-high-risk disease condition identification as second-level identifications, classify the medium-risk simulated identification and the medium-risk disease condition identification as third-level identifications, and classify the low-risk simulated identification and the low-risk disease condition identification as fourth-level identifications; Generate label data for high-accuracy objects, suspicious objects, or abnormal objects based on the difference in level identifiers. Specifically: If the level identifier between the simulated disease condition data and the disease severity data differs by more than two levels, generate label data for abnormal objects; if the level identifier between the simulated disease condition data and the disease severity data differs by only one level, generate label data for suspicious objects; if the simulated disease condition data and the disease severity data have the same level identifier, generate label data for high-accuracy objects.

[0013] Furthermore, the establishment process of the disease condition data matching model includes: Set up the disease condition data matching model, classify the disease severity through the simulated disease condition data, and mark each group of simulated disease condition data with the corresponding disease severity, namely high risk, medium-high risk, medium risk, or low risk; Merge the actual disease severity data and the simulated disease condition data into a dataset; Use the merged dataset to train the disease condition data matching model on the disease severity, and use the simulated disease condition data for verification, and calculate the accuracy rate of the disease condition data matching model on the simulated disease condition data; Evaluate the matching situation of the disease condition data matching model for different disease severities; According to the performance evaluation results, analyze whether the disease condition data matching model has the matching ability to correctly distinguish different disease severities.

[0014] Furthermore, the disease condition output module displays the diagnosis result and the error degree through an output panel, where the error degree is distinguished by colors.

[0015] Adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are as follows: 1. Through the integrated analysis of the temperature and humidity ratio data and the pathological image data, and by means of classification detection by the machine learning model and the disease condition data matching model, classify the disease condition detected in the image, and further improve the authenticity and accuracy of the diagnosis through the temperature and humidity ratio data, reducing the situation of misdiagnosis; 2. Through the two-way analysis of the temperature and humidity ratio data and the pathological image data, while determining the disease condition, achieve the accurate detection of the disease degree, thereby improving the accuracy of the dosage of the medicine and enhancing the early warning of the risk of minor diseases. Brief Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 It is a module architecture diagram of an intelligent traditional Chinese medicine ear diagnosis assistance system provided by an embodiment of the present invention. Specific embodiments

[0018] The following will further describe the present invention in detail in conjunction with the accompanying drawings and embodiments. It should be specifically pointed out that the following embodiments are only used to illustrate the present invention, but do not limit the scope of the present invention. Similarly, the following embodiments are only partial embodiments of the present invention rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0019] Please refer to Figure 1 , an intelligent traditional Chinese medicine ear diagnosis assistance system of the present invention includes: an ear internal data acquisition module, a pathological image data analysis module, a temperature and humidity ratio data analysis module, an accuracy analysis module, and a disease condition output module; The ear internal data acquisition module is used to collect pathological image data, temperature ratio data, and humidity ratio data in the patient's ear, and perform preprocessing; send the pathological image data to the pathological image data analysis module, and send the temperature ratio data and humidity ratio data to the temperature and humidity ratio data analysis module; In this embodiment, the pathological image data includes the auricle shape, auricle lines, earhole size, earhole color, and foreign object conditions in the earhole. The temperature ratio data is the ratio of the ear internal temperature to the indoor temperature, and the humidity ratio data is the ratio of the ear internal humidity to the indoor humidity.

[0020] It should be noted that: for the collection of pathological image data in the ear, an ear internal image detector can be used for data collection, specifically obtained by a camera and other image acquisition devices, while the temperature ratio data and humidity ratio data can be collected through the temperature sensor and humidity sensor of the inner ear monitoring instrument. Preliminary disease diagnosis is carried out by observing the auricle shape, auricle lines, earhole size, earhole color, and foreign object conditions in the earhole captured in the photos. The collection of temperature ratio data and humidity ratio data is to further confirm whether there is an error in the diagnosis result obtained from the pathological image data; The steps of the preprocessing are: Resize the images to the same square size for input into the model. Generally, the images are usually scaled to the same size, such as 224x224 pixels or 256x256 pixels; Apply image enhancement techniques for brightness adjustment, contrast enhancement, histogram equalization, sharpening, and denoising; Convert the images from the original RGB color space to grayscale images (single-channel) or other color spaces (such as HSV, Lab, etc.) to reduce the dimensionality of the data and alleviate the computational burden; According to the task requirements, crop the images to retain the specific regions to be detected and remove the irrelevant parts. For example, in the processing of ear pathological images, perhaps only the auricle and ear canal parts need to be retained.

[0021] By performing random transformations on the images, such as rotation, flipping, scaling, translation, etc., the diversity of the data can be increased, which helps the generalization ability of the model; Normalize the pixel values of the images and scale them to a specific range, usually [0,1] or [-1,1], to match the input requirements of the model; Convert the image data into a format acceptable to the model, usually the tensor format, including rearrangement of channels, conversion of data types, etc.

[0022] The pathological image data analysis module is used to perform matching analysis on the pathological image data and generate disease diagnosis data; In this embodiment, the pathological image data analysis module is processed using computer vision technology, and the construction of a machine learning model is required for the computer vision technology. The construction process of the machine learning model includes: Collect m groups of pathological image data, including normal and abnormal auricle shapes; Mark and annotate the m groups of pathological image data according to the diseases corresponding to the m groups of pathological image data to indicate the auricle shape characteristics of each sample, and classify them into normal or abnormal groups; Use the m groups of pathological image data (whose influencing attribute values) as the input of the machine learning model, and the disease diagnosis data as the output of the machine learning model. Use the disease diagnosis data as the prediction target and the prediction accuracy rate of the machine learning model as the training target; Train the machine learning model, and preset the prediction accuracy threshold Z. When the prediction accuracy rate of the machine learning model reaches the prediction accuracy threshold Z, stop training. At this time, record the completed group as n; and mark the nth group of the trained machine learning model as Zn, that is, generate the trained machine learning model Zn, and send the trained machine learning model Zn to the pathological image data analysis module.

[0023] In this embodiment, the logic of the pathological image data analysis module for analyzing the pathological image data is: The pathological image data analysis module compares the pathological image data through the machine learning model Zn, matches the influencing attribute values such as the auricle shape, auricle texture, ear hole size, ear hole color and foreign body conditions in the ear hole, and generates disease diagnosis data.

[0024] It should be noted that the disease diagnosis data is specifically: The shape of the auricle can be observed to detect kidney deficiency, spleen deficiency and other internal organ problems. Kidney deficiency may cause changes in the shape of the auricle, such as loose auricle; spleen deficiency may cause the auricle to enlarge or deform; Changes in the lines on the auricle can reflect problems with the body's blood circulation or meridians; Ear hole size may be influenced by genetic factors, but it may also be related to external ear disease or pain; The color of your ear piercing may indicate circulation problems, such as anemia or poor circulation. Specific colors may be associated with ear infections or inflammation. Foreign objects in the ear canal: Foreign objects in the ear canal may cause ear pain, infection or other ear problems. The type and location of the foreign body may help determine the possible problem.

[0025] The pathological image data analysis module sends the disease diagnosis data to the disease output module and the accuracy analysis module; The temperature and humidity ratio data analysis module is used to integrate and analyze the temperature ratio data and the humidity ratio data to generate disease severity data; In this embodiment, the temperature and humidity ratio data analysis module includes: The temperature ratio data collected from the patient's ear is set as Tr, and the humidity ratio data collected from the patient's ear is set as Hr; the temperature ratio threshold T1 and the humidity ratio threshold H1 are set; The temperature ratio data Tr is compared and analyzed with the temperature ratio threshold value T1 to generate a first label. The first label includes a first normal label and a first abnormal label. The steps for generating the first label are: If the temperature ratio data Tr is less than the temperature ratio threshold T1, a first normal label is generated; if the temperature ratio data Tr is not less than the temperature ratio threshold T1, a first abnormal label is generated; The humidity ratio data Hr is compared and analyzed with the humidity ratio threshold H1 to generate a second label. The second label includes a second normal label and a second abnormal label. The steps of generating the second label are: If the humidity ratio data Hr is less than the temperature ratio threshold H1, a second normal label is generated; if the humidity ratio data Hr is not less than the temperature ratio threshold H1, a second abnormal label is generated; Calculate the temperature-humidity ratio coefficient Jer based on the temperature ratio data Tr and the humidity ratio data Hr. The calculation formula for the temperature-humidity ratio coefficient Jer is as follows: Jer = (Jer > 0); where K is an error correction constant, e is the natural constant, which is used to enhance the sensitivity of the temperature ratio data Tr in pathological analysis; a is the humidity adjustment factor.

[0026] And compare the temperature-humidity ratio coefficient Jer with the preset threshold J1 and the preset threshold J2. Among them, the preset threshold J1 is less than the preset threshold J2; substitute the temperature-humidity ratio coefficient Jer into the preset threshold J1 and the preset threshold J2 to generate an abnormality degree label. The abnormality degree label includes a low-degree abnormality label, a medium-degree abnormality label, and a high-degree abnormality label. The generation steps of the abnormality degree label are as follows: If the temperature-humidity ratio coefficient Jer is less than the preset threshold J1, generate a low-degree abnormality label. If the temperature-humidity ratio coefficient Jer is not less than the preset threshold J1 and less than the preset threshold J2, generate a medium-degree abnormality label. If the temperature-humidity ratio coefficient Jer is not less than the preset threshold J2, generate a high-degree abnormality label; Integrate the generated first normal label, first abnormal label, second normal label, second abnormal label, low-degree abnormality label, medium-degree abnormality label, and high-degree abnormality label to generate the disease severity data.

[0027] In this embodiment, the disease severity data includes a high-risk disease identifier, a medium-high-risk disease identifier, a medium-risk disease identifier, and a low-risk disease identifier. The generation process of the disease severity includes: Classify the first abnormal label, second abnormal label, and high-degree abnormality label as high-risk labels; classify the medium-degree abnormality label as a medium-risk label; classify the first normal label, second normal label, and low-degree abnormality label as low-risk labels; Generate the corresponding disease severity identifier according to the combination of high-risk, medium-risk, and low-risk labels. Specifically, if there are more than two high-risk labels at the same time, generate a high-risk disease identifier; if there is one high-risk label, one medium-risk label, and one low-risk label at the same time or there is one high-risk label and two low-risk labels at the same time, generate a medium-high-risk disease identifier; if there is one medium-risk label and two low-risk labels at the same time, generate a medium-risk disease identifier; if there are three low-risk labels at the same time, generate a low-risk disease identifier.

[0028] It should be noted that in the case of common ear canal diseases, the temperature of the auricle and ear canal increases, and at this time, secretions are produced, the humidity of the inner ear canal or the epidermal layer of the auricle increases. When the temperature and humidity of the auricle or ear canal increase, the temperature ratio data Tr and humidity ratio data Hr will also increase accordingly. The temperature-humidity ratio coefficient Jer, which is positively correlated with the temperature ratio data Tr and humidity ratio data Hr, will also increase simultaneously, and further determination will be made according to the degree of increase of the temperature-humidity ratio coefficient Jer; That is, when the temperature and humidity do not increase, the temperature-humidity ratio coefficient Jer is in a normal state; When only the temperature of the auricle and ear canal increases and the humidity does not increase or the humidity increases while the temperature does not increase, the growth degree of the temperature-humidity ratio coefficient Jer shows a slow upward state; When the temperature and humidity of the auricle and ear canal increase simultaneously, the growth degree of the temperature-humidity ratio coefficient Jer shows a rapid upward state, and thus the severity degree in the ear can be determined; The abnormal degree label is used to further analyze and determine the first label and the second label, so as to avoid the inaccuracy caused by detecting from simple temperature and humidity conditions.

[0029] The temperature and humidity ratio data analysis module sends the disease severity data to the accuracy analysis module; The accuracy analysis module is used to integrally analyze the disease diagnosis data and the disease severity data to generate accuracy data; In this embodiment, the accuracy data includes high-accuracy objects, suspicious objects and abnormal objects. The generation process of the accuracy data includes: Construct a disease data matching model, and generate simulated disease data according to the disease diagnosis data. The simulated disease data includes high-risk simulation identifiers, medium-high-risk simulation identifiers, medium-risk simulation identifiers and low-risk simulation identifiers; Classify the simulated disease data and the disease severity data to generate level identifiers. Specifically: classify the high-risk simulation identifier and the high-risk disease identifier as first-level identifiers, classify the medium-high-risk simulation identifier and the medium-high-risk disease identifier as second-level identifiers, classify the medium-risk simulation identifier and the medium-risk disease identifier as third-level identifiers, and classify the low-risk simulation identifier and the low-risk disease identifier as fourth-level identifiers; Generate label data of high-accuracy objects, suspicious objects or abnormal objects according to the difference of the level identifiers. Specifically: if the difference between the simulated disease data generated by simulation and the disease severity data is more than two levels, generate label data of abnormal objects; if the difference between the simulated disease data generated by simulation and the disease severity data is only one level, generate label data of suspicious objects; if the simulated disease data generated by simulation and the disease severity data are of the same level identifier, generate label data of high-accuracy objects.

[0030] In this embodiment, the establishment process of the disease condition data matching model includes: Set up the disease condition data matching model, classify the disease severity through simulated disease condition data, and mark each group of simulated disease condition data with the corresponding disease severity, namely high risk, medium-high risk, medium risk or low risk; Combine the actual disease severity data with the simulated disease condition data into a data set; Use the combined data set to train the disease condition data matching model on the disease severity, and use the simulated disease condition data for verification, and calculate the accuracy rate of the disease condition data matching model on the simulated disease condition data; Evaluate the matching situation of the disease condition data matching model for different disease severities; According to the performance evaluation results, analyze whether the disease condition data matching model has the matching ability to correctly distinguish different disease severities.

[0031] The accuracy rate analysis module sends the accuracy rate data to the disease condition output module; The disease condition output module is used to output the diagnosis result and the error degree according to the disease diagnosis data and the accuracy rate data.

[0032] In this embodiment, the disease condition output module displays the diagnosis result and the error degree through an output panel, wherein the error degree is distinguished by colors, that is, different color images are used to indicate the accuracy rate degree.

[0033] The above are only some embodiments of the present invention, and thus do not limit the protection scope of the present invention. All equivalent device or equivalent process transformations made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are similarly included in the patent protection scope of the present invention.

Claims

1. An intelligent Chinese medicine ear diagnosis auxiliary system, characterized in that: include: The in-ear data acquisition module is used to collect pathological image data, temperature percentage data, and humidity percentage data of the patient's ear and perform preprocessing; Pathological image data analysis module, used to perform matching analysis on pathological image data and generate disease diagnosis data; The temperature and humidity ratio data analysis module is used to integrate and analyze the temperature ratio data and humidity ratio data to generate disease severity data; The accuracy analysis module is used to integrate and analyze disease diagnosis data and disease severity data to generate accuracy data; The condition output module is used to output the diagnosis results and error degree based on the condition diagnosis data and accuracy data.

2. The intelligent TCM ear diagnosis auxiliary system according to claim 1, characterized in that: The pathological image data includes the shape of the auricle, the lines of the auricle, the size of the ear canal, the color of the ear canal and the presence of foreign matter in the ear canal. The temperature ratio data is the ratio of the temperature inside the ear to the indoor temperature. The humidity ratio data is the ratio of the humidity inside the ear to the indoor humidity.

3. The intelligent TCM ear diagnosis auxiliary system according to claim 2, characterized in that: The pathological image data analysis module uses computer vision technology for processing. The computer vision technology requires the construction of a machine learning model. The construction process of the machine learning model includes: Collecting m sets of pathological image data, including normal and abnormal auricle shapes; Marking and annotating the m groups of pathological image data according to the disease conditions corresponding to the m groups of pathological image data, and classifying them into normal or abnormal groups; Take m groups of pathological image data as the input of the machine learning model, the disease diagnosis data as the output of the machine learning model, and the prediction accuracy of the machine learning model as the training target; The machine learning model is trained. When the prediction accuracy of the machine learning model reaches the prediction accuracy threshold Z, the training is stopped and a trained machine learning model Zn is generated.

4. The intelligent TCM ear diagnosis auxiliary system according to claim 3, characterized in that: The pathological image data analysis module compares the pathological image data through the machine learning model Zn, and matches the auricle shape, auricle lines, ear hole size, ear hole color with the foreign body situation in the ear hole to generate disease diagnosis data.

5. The intelligent TCM ear diagnosis auxiliary system according to claim 1, characterized in that: The temperature and humidity ratio data analysis module includes: Set the temperature ratio threshold T1 and humidity ratio threshold H1; Compare the temperature ratio data Tr with the temperature ratio threshold T1. If the temperature ratio data Tr is less than the temperature ratio threshold T1, generate a first normal label; if the temperature ratio data Tr is not less than the temperature ratio threshold T1, generate a first abnormal label; Compare the humidity ratio data Hr with the humidity ratio threshold H1. If the humidity ratio data Hr is less than the temperature ratio threshold H1, generate a second normal label; if the humidity ratio data Hr is not less than the temperature ratio threshold H1, generate a second abnormal label; The temperature-humidity ratio coefficient Jer is calculated based on the temperature ratio data Tr and the humidity ratio data Hr, and compared with the preset threshold value J1 and the preset threshold value J2, where the preset threshold value J1 is less than the preset threshold value J2; if the temperature-humidity ratio coefficient Jer is less than the preset threshold value J1, a low abnormality label is generated; if the temperature-humidity ratio coefficient Jer is not less than the preset threshold value J1 and is less than the preset threshold value J2, a moderate abnormality label is generated; if the temperature-humidity ratio coefficient Jer is not less than the preset threshold value J2, a high abnormality label is generated; The generated first normal label, first abnormal label, second normal label, second abnormal label, low abnormality label, moderate abnormality label and high abnormality label are integrated to generate disease severity data.

6. The intelligent TCM ear diagnosis auxiliary system according to claim 5, characterized in that: The calculation formula of the temperature-humidity ratio coefficient Jer is: You= (You>0); Among them, K is the error correction constant, e is the natural constant, which is used to enhance the sensitivity of temperature ratio data Tr in pathological analysis; a is the humidity adjustment factor.

7. The intelligent TCM ear diagnosis auxiliary system according to claim 5, characterized in that: The disease severity data includes a high-risk disease indicator, a medium-high-risk disease indicator, a medium-risk disease indicator, and a low-risk disease indicator. The generation process includes: Classify the first abnormal label, the second abnormal label, and the highly abnormal label as high-risk labels; classify the moderately abnormal label as a medium-risk label; and classify the first normal label, the second normal label, and the low-abnormal label as low-risk labels. The corresponding disease severity identification is generated according to the combination of high-risk, medium-risk and low-risk labels. Specifically: if there are two or more high-risk labels at the same time, a high-risk disease identification is generated; if there is one high-risk label, one medium-risk label and one low-risk label, or one high-risk label and two low-risk labels, a medium-high-risk disease identification is generated; if there is one medium-risk label and two low-risk labels, a medium-risk disease identification is generated; if there are three low-risk labels, a low-risk disease identification is generated.

8. The intelligent TCM ear diagnosis auxiliary system according to claim 7, characterized in that: The accuracy rate data includes high-precision objects, suspicious objects, and abnormal objects. The generation process of the accuracy rate data includes: Constructing a disease data matching model to generate simulated disease data based on disease diagnosis data, wherein the simulated disease data includes a high-risk simulated identifier, a medium-high-risk simulated identifier, a medium-risk simulated identifier, and a low-risk simulated identifier; Classifying the simulated condition data and the condition severity data to generate level identifications, specifically: classifying the high-risk simulation identification and the high-risk condition identification as a first-level identification, classifying the medium-high risk simulation identification and the medium-high risk condition identification as a second-level identification, classifying the medium-risk simulation identification and the medium-risk condition identification as a third-level identification, and classifying the low-risk simulation identification and the low-risk condition identification as a fourth-level identification; Generate label data for high-precision objects, suspicious objects or abnormal objects based on the difference in level identification. Specifically: if the level identification between the simulated medical condition data and the disease severity data differs by more than two levels, generate label data for abnormal objects; if the level identification between the simulated medical condition data and the disease severity data differs by only one level, generate label data for suspicious objects; if the simulated medical condition data and the disease severity data have the same level identification, generate label data for high-precision objects.

9. The intelligent TCM ear diagnosis auxiliary system according to claim 8, characterized in that: The process of establishing the disease condition data matching model includes: Set up a disease data matching model, classify the disease severity by simulating disease data, and mark each group of simulated disease data as the corresponding disease severity, i.e. high risk, medium-high risk, medium risk or low risk; Merge the actual disease severity data and simulated disease severity data into one dataset; Use the merged dataset to train the disease data matching model based on disease severity, and use simulated disease data for verification, and calculate the accuracy of the disease data matching model on the simulated disease data; Evaluate the matching performance of the disease data matching model for different disease severities; Based on the performance evaluation results, analyze whether the disease data matching model has the matching ability to correctly distinguish different disease severities.

10. The intelligent TCM ear diagnosis auxiliary system according to claim 1, characterized in that: The condition output module displays the diagnosis result and error degree through an output panel, wherein the error degree is distinguished by color.

Images