阅读说明：本技术 穴位判别模型的构建方法、穴位判别方法和判别系统 (Construction method of acupoint discrimination model, acupoint discrimination method and discrimination system ) 是由 高园 吴海涛 温川飙 高原 孙涛 罗悦 陈菊 宋海贝 姚光远 冯杰 于 2019-08-29 设计创作，主要内容包括：本发明公开了一种穴位判别模型的构建方法、穴位判别方法和判别系统,穴位判别模型的构建方法包括采集多个人体穴位及其附近皮肤的电位信号,经消噪处理和信号特征量提取处理后,与多个个体因素编码值构成多维信息数据库,将信息数据库的数据进行神经网络训练,得到穴位判别模型。穴位判别方法包括采集测试者穴位及其附近皮肤电位信号,以及确定测试者个体因素的取值,将电位信号经过消噪处理和信号特征量提取处理,得到信号特征量,个体因素的取值经过编码得到编码值,将信号特征量和编码值输入穴位判别模型,得到穴位判别结果。本发明考虑了个体化因素对穴位电位信号的影响,结合神经网络技术对穴位进行判别,提高了穴位定位的准确度。(The invention discloses a construction method of an acupuncture point discrimination model, an acupuncture point discrimination method and a discrimination system. The acupoint discrimination method comprises the steps of collecting potential signals of the acupoints and skin nearby the acupoints of a tester, determining values of individual factors of the tester, subjecting the potential signals to denoising processing and signal characteristic quantity extraction processing to obtain signal characteristic quantities, encoding the values of the individual factors to obtain encoding values, and inputting the signal characteristic quantities and the encoding values into an acupoint discrimination model to obtain an acupoint discrimination result. The invention considers the influence of individuation factors on the acupoint potential signals, and combines the neural network technology to distinguish the acupoints, thereby improving the accuracy of acupoint positioning.)

1. A construction method of an acupoint discrimination model is characterized by comprising the following construction steps:

s1: collecting potential signals spontaneously generated by a plurality of sample human body acupuncture points and skins nearby the acupuncture points;

s2: denoising the potential signal;

s3: decomposing and reconstructing the potential signal after denoising processing, dividing the potential signal into a plurality of sub-signal components, and calculating the correlation dimension of the sub-signal components to obtain signal characteristic quantity;

s4: respectively coding a plurality of individualized factors influencing the human body acupuncture point potential signals to obtain a coding value corresponding to each individualized factor;

s5: constructing a multi-dimensional information database of the electrical characteristics of the acupuncture points by using the signal characteristic quantities and the coding values which are obtained by a plurality of samples correspondingly;

s6: dividing the data in the multi-dimensional information database of the electrical characteristics of the acupuncture points in the step S5 into two groups according to a certain proportion: a learning group and a detection group; introducing RBF neural networks into the learning group data, performing classified learning, performing iterative training on the RBF neural networks, continuously improving the correction weight, and obtaining an acupuncture point discrimination model; and the detection group data is used for detecting the acupuncture point discrimination model to obtain the judgment accuracy.

2. The method for constructing an acupoint discrimination model according to claim 1, wherein the step S4 is performed at any time before the step S5.

3. The method for constructing an acupoint discrimination model according to claim 1, wherein in step S1, the time for acquiring the potential signal is greater than or equal to 1 minute.

4. The method for constructing an acupoint discrimination model according to claim 1, wherein the denoising processing in step S2 is performed by a wavelet transform method.

5. The method for constructing an acupoint discrimination model according to claim 1, wherein in step S3, the potential signals after denoising processing are decomposed and reconstructed by a wavelet packet analysis method, and/or the correlation dimension of the sub-signal components is calculated by a G-P algorithm.

6. The method for constructing an acupoint discrimination model according to any one of claims 1 to 5, wherein the individualization factors include physical constitution factors, BMI factors, and acupoint sensitization factors in step S4.

7. An acupuncture point discrimination method is characterized by comprising the following steps:

the method comprises the following steps: constructing an acupoint discrimination model according to the construction method of any one of claims 1 to 6;

step two: collecting potential signals spontaneously generated by human acupuncture points and skin nearby of a tester, and determining the value of individualized factors of the tester;

step three: denoising the potential signal by adopting a wavelet transform method;

step four: decomposing and reconstructing the electric potential signal subjected to the noise elimination processing by adopting a wavelet packet analysis method, dividing the electric potential signal into a plurality of sub-signal components, and calculating the correlation dimension of the sub-signal components to obtain the signal characteristic quantity of a tester;

step five: coding the value of the individualized factor of the tester to obtain the coded value of the tester;

step six: and inputting the obtained signal characteristic quantity and the coding value of the tester into the acupoint discrimination model to obtain an acupoint discrimination result.

8. The point discriminating method according to claim 7, wherein the first step can be performed at any time before the sixth step.

9. The method for identifying acupuncture points according to claim 7, wherein the fifth step can be performed at any time after the second step and before the sixth step.

10. A point discrimination system, comprising at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of acupoint discrimination as claimed in any one of claims 7 to 9.

Technical Field

The invention relates to human body acupoint discrimination, in particular to a construction method of an acupoint discrimination model, an acupoint discrimination method and a discrimination system.

Background

In traditional Chinese treatment, acupuncture points are generally considered to have certain specificity different from other non-acupuncture points, and corresponding diseases can be treated by acupuncture, massage, point pressing or moxibustion stimulation on the acupuncture points. In recent years, specific studies have been conducted on acupoints mainly from the aspects of tissue structure morphology, physical properties (electrical properties, electromagnetic properties, heat, sound, light), chemical properties, brain reaction, equilibrium of the acupoints with the same name on the left and right, and the like.

In the process of researching the essence of the channels, collaterals and acupuncture points, many scholars find that the acupuncture points have electrical characteristics and mainly research on resistance, volt-ampere characteristics, potential and current indexes of the acupuncture points, and a large amount of domestic research shows that skin low-resistance points or high-potential points mostly conform to the traditional acupuncture points, but in practice, the result of positioning the acupuncture points according to the electrical characteristics of the acupuncture points is low in accuracy.

Disclosure of Invention

The invention aims to overcome the defect that the accuracy of a positioning result is low when acupuncture point positioning is carried out by utilizing the electrical characteristics of acupuncture points in the prior art, and provides a construction method, an acupuncture point judgment method and a judgment system of an acupuncture point judgment model.

In order to achieve the above purpose, the invention provides the following technical scheme:

a construction method of an acupoint discrimination model comprises the following construction steps:

s1: collecting potential signals spontaneously generated by a plurality of sample human body acupuncture points and skins nearby the acupuncture points;

s2: denoising the potential signal;

s3: decomposing and reconstructing the potential signal after denoising processing, dividing the potential signal into a plurality of sub-signal components, and calculating the correlation dimension of the sub-signal components to obtain signal characteristic quantity;

s4: respectively coding a plurality of individualized factors influencing the human body acupuncture point potential signals to obtain a coding value corresponding to each individualized factor;

s5: constructing a multi-dimensional information database of the electrical characteristics of the acupuncture points by using the signal characteristic quantities and the coding values which are obtained by a plurality of samples correspondingly;

s6: dividing the data in the multi-dimensional information database of the electrical characteristics of the acupuncture points in the step S5 into two groups according to a certain proportion: a learning group and a detection group; introducing RBF neural networks into the learning group data, performing classified learning, performing iterative training on the RBF neural networks, continuously improving the correction weight, and obtaining an acupuncture point discrimination model; and the detection group data is used for detecting the acupuncture point discrimination model to obtain the judgment accuracy.

Preferably, the step S4 may be performed at any time before the step S5.

Preferably, in step S1, the acquisition time of the potential signal is greater than or equal to 1 minute. The invention combines the data acquisition form with the traditional Chinese medicine concept, the data acquisition is not limited to the acquisition and comparison of static points but relates to dynamic continuous acquisition, the acquisition time of each time is ensured to be 1 minute or more, and the acquired potential signals have the traditional Chinese medicine signal analysis basis.

Preferably, in step S2, the noise reduction processing is performed by a wavelet transform method.

Preferably, in step S3, the denoised potential signal is decomposed and reconstructed by a wavelet packet analysis method.

Preferably, in step S3, the correlation dimension of the sub-signal component is calculated by a G-P algorithm.

Preferably, in the step S4, the individualizing factors include a constitutional factor, a BMI factor, and an acupoint sensitizing factor.

The invention also discloses an acupuncture point distinguishing method, which comprises the following steps:

the method comprises the following steps: constructing an acupuncture point discrimination model according to the construction method;

step two: collecting potential signals spontaneously generated by human acupuncture points and skin nearby of a tester, and determining the value of individualized factors of the tester;

step three: denoising the potential signal by adopting a wavelet transform method;

step four: decomposing and reconstructing the potential signal subjected to the noise elimination processing by adopting a wavelet packet analysis method, dividing the potential signal into a plurality of sub-signal components, and calculating the correlation dimension of the sub-signal components to obtain the signal characteristic quantity of a tester;

step five: coding the value of the individualized factor of the tester to obtain the coded value of the tester;

step six: and inputting the obtained signal characteristic quantity and the coding value of the tester into the acupoint discrimination model to obtain an acupoint discrimination result.

Preferably, step one can be performed at any time before step six.

Preferably, the fifth step can be performed at any time after the second step and before the sixth step.

The invention also discloses an acupuncture point distinguishing system, which comprises at least one processor and a memory which is in communication connection with the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executable by the at least one processor to enable the at least one processor to perform the above acupuncture point determination method.

Compared with the prior art, the invention has the beneficial effects that:

the invention considers the influence of individuation factors on the acupoint potential signals, combines the individuation factors with the acupoint potential signals to construct an acupoint discrimination model, and the model has wide applicability in acupoint discrimination, avoids the influence of skin potential difference caused by individual difference, can realize more accurate acupoint discrimination and improves the accuracy of acupoint positioning.

The invention adopts modern signal processing means (anti-interference and signal characteristic extraction) and a neural network model to combine to judge the acupuncture points, can be applied to acupuncture clinic, replaces manual acupuncture point searching, and provides a new idea and method for objective acupuncture point positioning.

Description of the drawings:

fig. 1 is a block diagram of a method for constructing an acupoint discrimination model according to embodiment 1 of the present invention.

Fig. 2 is a block diagram of the method for identifying acupuncture points according to embodiment 2 of the present invention.

Detailed Description

The present invention will be described in further detail with reference to test examples and specific embodiments. It should be understood that the scope of the above-described subject matter is not limited to the following examples, and any techniques implemented based on the disclosure of the present invention are within the scope of the present invention.