Simulation training system and method for acupuncture and moxibustion needle applying manipulation

Abstract

The invention relates to the technical field of traditional Chinese medicine acupuncture and moxibustion models, in particular to a simulation training system and method for acupuncture and moxibustion needle applying techniques. The method comprises the following steps: firstly, according to posture difference influence indexes corresponding to nodes to be analyzed of every two pieces of historical needling action frame data, adjusting an initial difference measure to obtain a track difference measure; according to the moving distance change condition of the to-be-analyzed node in the historical needling action frame data, acquiring participation measurement of the to-be-analyzed node in the historical needling action frame data; according to the distance metric value, clustering all historical needling action frame data to obtain each needling manipulation category; and acquiring a simulation training model of the acupuncture and moxibustion acupuncture manipulation according to all the acupuncture manipulation categories. According to the method, the influence of posture difference on the needle applying techniques and the participation degree of different hand nodes in the needle applying process are fully considered, so that the types of the needle applying techniques are more accurately divided, and the accuracy of the simulation training model of the acupuncture needle applying techniques is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traditional Chinese medicine acupuncture models, and particularly to a simulation training system and method for acupuncture needle application techniques. Background Art

[0002] Acupuncture, as an important part of traditional Chinese medicine therapies, covers two major fields: acupuncture and moxibustion. Acupuncture is to insert a filiform needle into the patient's body at certain acupoints and use techniques such as twirling and lifting to treat diseases. In order to carry out individualized treatment according to the specific conditions of patients, it is required that acupuncturists master the operation skills of various acupuncture needle application techniques. Trainees can conduct simulation training of acupuncture needle application techniques through an acupuncture virtual simulation training teaching system to improve their acupuncture skills. To ensure the sufficiency and effectiveness of the simulation training, the key lies in having rich and finely classified historical needle application action frame data as support. The scientific classification of historical needle application action frame data is crucial for optimizing the simulation training model. By carefully distinguishing different categories of data, the training model can flexibly adjust training parameters and strategies according to the data characteristics, so as to accurately simulate the real acupuncture scene.

[0003] Considering that the action characteristics of different needle application techniques are different, when the prior art classifies historical needle application action frame data, it classifies according to the moving distance differences corresponding to each hand node in the historical needle application action frame data. When using the prior art for classification, the influence of the body posture differences of the needle application object on the needle application technique and the different participation degrees of different hand nodes during the needle application process are not fully considered, making it difficult to accurately classify the historical needle application action frame data, resulting in unreliable simulation training of acupuncture needle application techniques. Summary of the Invention

[0004] In order to solve the technical problem that it is difficult to accurately construct a simulation training model for acupuncture needle application techniques in the prior art, the purpose of the present invention is to provide a simulation training system and method for acupuncture needle application techniques, and the specific technical solutions adopted are as follows: A simulation training system for acupuncture needle application techniques, the system includes: A data acquisition module, configured to acquire the time series data of the moving distance corresponding to each hand node in each historical needle application action frame data; A distance metric module is configured to obtain the initial difference metric of the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data based on the difference between the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data corresponding to the moving distance time series data; obtain the body posture difference influence index corresponding to the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data according to the periodicity of the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data corresponding to the moving distance time series data; adjust the initial difference metric according to the body posture difference influence index corresponding to the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data to obtain the trajectory difference metric of the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data; obtain the participation metric of the nodes to be analyzed in the historical acupuncture needle insertion action frame data according to the change of the moving distance of the nodes to be analyzed in the historical acupuncture needle insertion action frame data; and comprehensively obtain the distance metric value of each pair of historical acupuncture needle insertion action frame data based on the trajectory difference metrics of all the hand nodes in each pair of historical acupuncture needle insertion action frame data and the participation metrics of the hand nodes in the historical acupuncture needle insertion action frame data. A simulation module is configured to cluster all the historical acupuncture needle insertion action frame data according to the distance metric values of each pair of the historical acupuncture needle insertion action frame data to obtain each acupuncture technique category; and obtain a simulation training model for acupuncture techniques based on all the acupuncture technique categories.

[0005] Further, the method for obtaining the initial difference metric includes: Taking the DTW distance between the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data corresponding to the moving distance time series data as the initial difference metric of the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data.

[0006] Further, the method for obtaining the body posture difference influence index includes: Obtaining the action feature value corresponding to the nodes to be analyzed in the historical acupuncture needle insertion action frame data according to the duration and amplitude of the periodic term of the nodes to be analyzed in the historical acupuncture needle insertion action frame data corresponding to the moving distance time series data; Obtaining the action amplitude difference index corresponding to the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data according to the absolute value of the difference between the action feature values corresponding to the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data; Obtaining the action process similarity index corresponding to the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data according to the correlation coefficient of the periodic term of the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data corresponding to the moving distance time series data; Obtaining the body posture difference influence index corresponding to the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data according to the action process similarity index and the action amplitude difference index corresponding to the nodes to be analyzed in each pair of historical acupuncture needle insertion action frame data.

[0007] Further, the method for obtaining the action feature value includes: For the periodic term of the moving distance time series data corresponding to the node to be analyzed in any historical acupuncture needle insertion action frame data, calculate the product of the duration and amplitude of the periodic term to obtain the action feature value corresponding to the node to be analyzed in the historical acupuncture needle insertion action frame data.

[0008] Further, the method for obtaining the body posture difference influence index includes: Calculate the product of the action process similarity index and the action amplitude difference index to obtain the body posture difference influence index corresponding to the nodes to be analyzed in every two historical acupuncture needle insertion action frame data.

[0009] Further, the method for obtaining the participation measure includes: According to the correlation situation between the node to be analyzed and the moving distance time series data corresponding to all hand nodes in the historical acupuncture needle insertion action frame data, obtain the first participation coefficient of the node to be analyzed in the historical acupuncture needle insertion action frame data; Calculate the mean value of all the moving distances corresponding to the node to be analyzed in the historical acupuncture needle insertion action frame data to obtain the second participation coefficient of the node to be analyzed in the historical acupuncture needle insertion action frame data; Calculate the product of the first participation coefficient and the second participation coefficient and perform normalization processing to obtain the participation measure of the node to be analyzed in the historical acupuncture needle insertion action frame data.

[0010] Further, the method for obtaining the first participation coefficient includes: For any historical acupuncture needle insertion action frame data, calculate the absolute value of the Pearson correlation coefficient of the moving distance time series data corresponding to the node to be analyzed and the hand nodes to obtain the correlation coefficient between the node to be analyzed and the hand nodes; Calculate the mean value of the correlation coefficients between the node to be analyzed and all hand nodes to obtain the first participation coefficient of the node to be analyzed in the historical acupuncture needle insertion action frame data.

[0011] Further, the method for obtaining the distance metric value includes: Calculate the absolute value of the difference between the participation measures of the hand nodes in two historical acupuncture needle insertion action frame data to obtain the participation difference measure of the hand nodes in the two historical acupuncture needle insertion action frame data; Calculate the mean value of the participation measures of the hand nodes in two historical acupuncture needle insertion action frame data to obtain the overall participation index of the hand nodes in the two historical acupuncture needle insertion action frame data; Calculate the product of the participation difference measure, the overall participation index and the trajectory difference measure of the hand nodes in two historical acupuncture needle insertion action frame data to obtain the local difference degree of the hand nodes in the two historical acupuncture needle insertion action frame data; Calculate the sum of the local difference degrees of all hand nodes of two historical acupuncture needle insertion action frame data to obtain the distance metric value of each pair of historical acupuncture needle insertion action frame data.

[0012] Further, the method for obtaining the acupuncture needle insertion technique category includes: Using the K-Means clustering algorithm, cluster all the historical acupuncture needle insertion action frame data according to the distance metric value of each pair of the historical acupuncture needle insertion action frame data to obtain each acupuncture needle insertion technique category.

[0013] A simulation training method for acupuncture needle insertion techniques, and the method uses the simulation training system for acupuncture needle insertion techniques as described above for quality inspection.

[0014] The present invention has the following beneficial effects: In order to accurately classify the historical acupuncture needle insertion action frame data, it is necessary to construct a distance metric value to accurately reflect the difference in acupuncture needle insertion techniques between two historical acupuncture needle insertion action frame data. First, construct an initial difference metric to reflect the difference in the moving distance of the nodes to be analyzed in two historical acupuncture needle insertion action frame data; the body posture difference influence index reflects the influence of the patient's body posture difference on the nodes to be analyzed in the acupuncture needle insertion technique. Adjust the initial difference metric according to the body posture difference influence index to obtain a trajectory difference metric. The trajectory difference metric comprehensively considers the influence of the moving distance difference and the body posture difference, and can more accurately reflect the difference in the acupuncture needle insertion technique corresponding to the nodes to be analyzed. Considering that the participation degrees of different hand nodes in the acupuncture needle insertion process are different, the higher the participation degree of the node, the greater the influence on the acupuncture needle insertion technique. Combine the trajectory difference metrics of all hand nodes of each pair of historical acupuncture needle insertion action frame data and the participation metrics of the nodes to calculate the distance metric value between them. The distance metric value fully considers the influence of the body posture difference of the acupuncture target on the acupuncture needle insertion technique and the participation degree of different hand nodes in the acupuncture needle insertion process, and can more accurately reflect the actual difference situation of the acupuncture needle insertion technique. Divide the historical acupuncture needle insertion action frame data more accurately into each acupuncture needle insertion technique category through the distance metric value, thereby improving the accuracy of the simulation training model for acupuncture needle insertion techniques. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a system block diagram of a simulation training system for acupuncture needle insertion techniques provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, a simulation training system and method for acupuncture needle insertion techniques according to the present invention, including its specific implementation manners, structures, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following specifically describes the specific solutions of a simulation training system and method for acupuncture needle insertion techniques provided by the present invention in conjunction with the accompanying drawings.

[0020] The embodiments of the present invention provide a simulation training system and method for acupuncture needle insertion techniques. Please refer to Figure 1 , which shows a system block diagram of a simulation training system for acupuncture needle insertion techniques provided by an embodiment of the present invention. The system includes: a data acquisition module 101, a distance measurement module 102, and a simulation module 103.

[0021] The data acquisition module 101 acquires the moving distance time series data corresponding to each type of hand node in each historical needle insertion action frame data.

[0022] To ensure the sufficiency of the simulation training, it is first necessary to acquire sufficient historical needle insertion action frame data as a support; to classify the historical needle insertion action frame data, it is necessary to extract the moving distance time series data corresponding to each type of hand node from the historical needle insertion action frame data.

[0023] Using a detection system, each historical needle insertion action frame data is acquired. Here, a brief description of the process of collecting a historical needle insertion action frame data is given: To ensure that the details and three-dimensional information of hand movements can be comprehensively captured, the system installs cameras in three mutually perpendicular directions, such as the positive direction, the side direction, and the upward direction. This multi-angle arrangement can effectively avoid the limitations of a single perspective and ensure the integrity and accuracy of hand movements. The cameras collect the acupuncture needle insertion process of the acupuncturist at a preset sampling frequency to obtain the original acupuncture needle insertion images at each sampling moment. Since the collected original acupuncture needle insertion images may be disturbed by noise, the system performs noise reduction operations on the original acupuncture needle insertion images to eliminate noise and external interference and ensure the accuracy of subsequent analysis. The image after noise reduction is called the acupuncture needle insertion action frame image. The system counts all the acupuncture needle insertion action frame images collected by the cameras during the acupuncture needle insertion process to form historical acupuncture needle insertion action frame data. In the present invention, each acupuncture needle insertion process of the acupuncturist reflects a complete acupuncture needle insertion technique process, and each historical acupuncture needle insertion action frame data represents a complete acupuncture needle insertion technique process.

[0024] Considering that MediaPipe is a deep learning-based framework, which is particularly suitable for gesture recognition and human pose analysis tasks. It can analyze each acupuncture needle insertion action frame image in real time, detect and track the key points of the hand and return the position information of these key points, and use the key points as hand nodes. Through the acupuncture needle insertion action frame images collected by the cameras in three different directions, the system can construct a three-dimensional coordinate system of the hand nodes. For each hand node in the acupuncture needle insertion action frame image, the system can obtain its spatial position in the three-dimensional space. For any historical acupuncture needle insertion action frame data, the system sequentially counts the spatial positions of the hand nodes in the three-dimensional space at each sampling moment to form the time-series data of the corresponding spatial positions of the hand nodes. For any hand node, the system calculates the Euclidean distance between its spatial position at each sampling moment and the corresponding spatial position at the previous sampling moment in the time series as the moving distance at that sampling moment. The system counts the moving distances at all sampling moments in chronological order to form the time-series data of the moving distances of the hand nodes. The time-series data of the moving distances reflects the movement changes of the hand nodes during the acupuncture needle insertion process.

[0025] It should be particularly noted that in the present invention, the same type of hand node refers to the key points at the same hand position. For example, in the historical acupuncture needle insertion action frame data A, the node number of the thumb tip hand node is 1; in the historical acupuncture needle insertion action frame data B, the node number of the thumb tip hand node is also 1; these two hand nodes belong to the same type of hand node, and they both represent the thumb tip. All the historical acupuncture needle insertion action frame data have the same types of hand nodes. Such a design ensures the unity and comparability of the data and provides a solid foundation for subsequent analysis and processing. For the convenience of calculation, all the index data involved in the operations in the embodiments of the present invention have undergone data preprocessing to eliminate the influence of dimensions. The specific means of eliminating the influence of dimensions are well-known technical means to those skilled in the art and will not be limited here.

[0026] A distance metric module 102 is configured to obtain an initial difference metric for the nodes to be analyzed in each two historical acupuncture needle insertion action frame data according to the difference situation of the time series data of the corresponding moving distances of the nodes to be analyzed in each two historical acupuncture needle insertion action frame data; obtain an influence index of body posture difference corresponding to the nodes to be analyzed in each two historical acupuncture needle insertion action frame data according to the periodic situation of the time series data of the corresponding moving distances of the nodes to be analyzed in each two historical acupuncture needle insertion action frame data; adjust the initial difference metric according to the influence index of body posture difference corresponding to the nodes to be analyzed in each two historical acupuncture needle insertion action frame data to obtain a trajectory difference metric for the nodes to be analyzed in each two historical acupuncture needle insertion action frame data; obtain a participation metric of the nodes to be analyzed in the historical acupuncture needle insertion action frame data according to the change situation of the moving distance of the nodes to be analyzed in the historical acupuncture needle insertion action frame data; and obtain a distance metric value for each two historical acupuncture needle insertion action frame data by integrating the trajectory difference metrics of all hand nodes in each two historical acupuncture needle insertion action frame data and the participation metrics of the hand nodes in the historical acupuncture needle insertion action frame data.

[0027] To accurately classify the historical acupuncture needle insertion action frame data, it is necessary to construct a distance metric value to accurately reflect the difference in acupuncture techniques between two historical acupuncture needle insertion action frame data. First, an initial difference metric is constructed to reflect the difference in the moving distances of the nodes to be analyzed in two historical acupuncture needle insertion action frame data; the influence index of body posture difference reflects the influence of the patient's body posture difference on the nodes to be analyzed in the acupuncture technique. The initial difference metric is adjusted according to the influence index of body posture difference to obtain a trajectory difference metric. The trajectory difference metric comprehensively considers the influence of the moving distance difference and the body posture difference and can more accurately reflect the difference in the acupuncture technique corresponding to the nodes to be analyzed. Considering that the participation degrees of different hand nodes in the acupuncture process are different, the higher the participation degree of a node, the greater the influence on the acupuncture technique. The distance metric value between each two historical acupuncture needle insertion action frame data is calculated by integrating the trajectory difference metrics of all hand nodes in each two historical acupuncture needle insertion action frame data and the participation metrics of the nodes. The distance metric value fully considers the influence of the body posture difference of the acupuncture object on the acupuncture technique and the participation degree of different hand nodes in the acupuncture process, and can more accurately reflect the actual difference situation of the acupuncture technique.

[0028] To analyze the difference in acupuncture techniques between two historical acupuncture needle insertion action frame data, first, the difference in the movement of the same hand position in two historical acupuncture needle insertion processes is analyzed locally. Any kind of hand node is used as the node to be analyzed. To analyze the difference in the position movement of the nodes to be analyzed in two historical acupuncture needle insertion action frame data, preferably, in an embodiment of the present invention, the method for obtaining the initial difference metric includes: The DTW distance of the time series data of the corresponding movement distances of the nodes to be analyzed in every two historical acupuncture needle application action frame data is used as the initial difference measure of the nodes to be analyzed in every two historical acupuncture needle application action frame data. It should be noted that the DTW distance is a well-known prior art to those skilled in the art and can be obtained through the DTW (Dynamic Time Warping) algorithm, which will not be elaborated here.

[0029] For the above steps, the historical acupuncture needle application action frame data reflects the data corresponding to the historical acupuncture needle application technique. Any one of the hand nodes is used as the node to be analyzed, and the DTW distance of the time series data of the corresponding movement distances of the nodes to be analyzed in every two historical acupuncture needle application action frame data is used as the initial difference measure of the nodes to be analyzed in every two historical acupuncture needle application action frame data. The larger the initial difference measure, the greater the difference in the movement distances of the nodes to be analyzed in the two historical acupuncture needle application action frame data, indicating a greater difference in the movement of the hand positions corresponding to the nodes to be analyzed in the two historical acupuncture needle application action frame data.

[0030] Considering that the acupuncture needle application technique is usually periodic, that is, there are multiple repetitions of the same action. For example, the lifting and thrusting method is a common acupuncture needle application technique, and by slightly lifting and inserting the needle handle and repeatedly performing the lifting and thrusting actions, the local or overall function can be improved. For the same acupuncture needle application technique, the body posture differences of different acupuncture needle application objects will cause changes in the acupuncture needle application technique. This kind of change is usually reflected in the periodic change of the movement amplitude of the hand nodes. For example, for obese patients, the needle needs to be inserted deeper, and if the twirling method is used, the action amplitude is also larger. The movement amplitude changes of different hand nodes during the acupuncture needle application process are different. Therefore, it is necessary to conduct a detailed analysis of the technique change based on the hand nodes in order to analyze the influence of the body posture differences of the acupuncture needle application objects corresponding to the two historical acupuncture needle application processes on the movement of the nodes to be analyzed. Preferably, in an embodiment of the present invention, the method for obtaining the body posture difference influence index includes: Obtain the action feature value corresponding to the node to be analyzed in the historical acupuncture needle application action frame data according to the duration and amplitude of the periodic term of the time series data of the corresponding movement distance of the node to be analyzed in the historical acupuncture needle application action frame data; Obtain the action amplitude difference index corresponding to the nodes to be analyzed in every two historical acupuncture needle application action frame data according to the absolute value of the difference between the action feature values corresponding to the nodes to be analyzed in every two historical acupuncture needle application action frame data; Obtain the action process similarity index corresponding to the nodes to be analyzed in every two historical acupuncture needle application action frame data according to the correlation coefficient of the periodic term of the time series data of the corresponding movement distance of the nodes to be analyzed in every two historical acupuncture needle application action frame data; According to the action process similarity index and the action amplitude difference index corresponding to the nodes to be analyzed in every two historical acupuncture action frame data, obtain the body posture difference influence index corresponding to the nodes to be analyzed in every two historical acupuncture action frame data. It should be noted that the method for obtaining the periodic term is a well-known prior art in the technical field of the present invention. The periodic term of the moving distance time series data corresponding to the nodes to be analyzed in the historical acupuncture action frame data can be obtained by using the STL (Seasonal-Trend Decomposition using LOESS) algorithm. The specific obtaining method will not be elaborated here; the method for obtaining the Pearson correlation coefficient is a well-known prior art to those skilled in the art and will not be elaborated here.

[0031] Specifically, for the periodic term of the moving distance time series data corresponding to the nodes to be analyzed in any historical acupuncture action frame data, calculate the product of the duration and amplitude of the periodic term to obtain the action feature value corresponding to the nodes to be analyzed in the historical acupuncture action frame data; calculate the absolute value of the difference between the action feature values corresponding to the nodes to be analyzed in every two historical acupuncture action frame data to obtain the action amplitude difference index corresponding to the nodes to be analyzed in every two historical acupuncture action frame data; calculate the absolute value of the Pearson correlation coefficient of the periodic terms of the moving distance time series data corresponding to the nodes to be analyzed in every two historical acupuncture action frame data to obtain the action process similarity index corresponding to the nodes to be analyzed in every two historical acupuncture action frame data; calculate the product of the action process similarity index and the action amplitude difference index to obtain the body posture difference influence index corresponding to the nodes to be analyzed in every two historical acupuncture action frame data. In an embodiment of the present invention, the formula for the body posture difference influence index includes: In the formula, represents the body posture difference influence index corresponding to the nodes to be analyzed in the historical acupuncture action frame data and the historical acupuncture action frame data ; corresponding to the nodes to be analyzed; represents the action feature value corresponding to the nodes to be analyzed in the historical acupuncture action frame data ; corresponding to the nodes to be analyzed; represents the action feature value corresponding to the nodes to be analyzed in the historical acupuncture action frame data ; corresponding to the nodes to be analyzed; represents the Pearson correlation coefficient of the periodic terms of the moving distance time series data corresponding to the nodes to be analyzed in the historical acupuncture action frame data and the historical acupuncture action frame data ; corresponding to the nodes to be analyzed; represents the historical acupuncture action frame data and the historical acupuncture action frame data ; Corresponding action process similarity index; Represents the historical acupuncture needle insertion action frame data And the historical acupuncture needle insertion action frame data Nodes to be analyzed Corresponding action amplitude difference index; Represents the absolute value symbol.

[0032] For the above steps, extract the periodic term from the moving distance time series data corresponding to the nodes to be analyzed of the historical acupuncture needle insertion action frame data. The periodic term reflects the periodic change characteristics of the acupuncture technique. For any node to be analyzed of the historical acupuncture needle insertion action frame data, calculate the product of the duration and amplitude of its periodic term to obtain the action characteristic value of this node. The action characteristic value combines the period length and amplitude of the acupuncture technique, comprehensively reflecting the action amplitude; for every two nodes to be analyzed of the historical acupuncture needle insertion action frame data, calculate the absolute value of the difference between their corresponding action characteristic values to obtain the action amplitude difference index. The action amplitude difference index reflects the change of the action amplitude of the same node in different acupuncture processes, thereby reflecting the influence of body posture differences on the action amplitude. For every two nodes to be analyzed of the historical acupuncture needle insertion action frame data, calculate the absolute value of the Pearson correlation coefficient of the periodic terms of their corresponding moving distance time series data to obtain the action process similarity index. The action process similarity index reflects the similarity of the action patterns of two acupuncture needle insertion action frame data. The larger the value of the action process similarity index, the closer the two acupuncture needle insertion action frame data are in the action pattern and the more likely they represent the same acupuncture technique. Considering that the more similar the acupuncture patterns of two acupuncture processes are and the greater the action amplitude difference is, it represents that the influence of body posture differences on the acupuncture process is greater and the two acupuncture processes are more likely to represent the same acupuncture technique. Calculate the product of the action process similarity index and the action amplitude difference index to obtain the body posture difference influence index corresponding to every two nodes to be analyzed of the historical acupuncture needle insertion action frame data. The body posture difference influence index represents the influence degree of body posture differences on the acupuncture process.

[0033] In order to more accurately reflect the differences in the acupuncture techniques corresponding to the nodes to be analyzed, preferably, in an embodiment of the present invention, the method for obtaining the trajectory difference metric includes: Calculate the product of the negative correlation mapping result of the body posture difference influence index corresponding to every two nodes to be analyzed of the historical acupuncture needle insertion action frame data and the preset adjustment value to obtain the target adjustment value; calculate the product of the initial difference metric and the target adjustment value to obtain the trajectory difference metric of every two nodes to be analyzed of the historical acupuncture needle insertion action frame data. It should be noted that negative correlation mapping is a well-known technical means in the art. Negative correlation mapping can be in the form of inverse proportion or negative exponential power, which is not limited here. In an embodiment of the present invention, the preset adjustment value is 1.51, and the implementer can set it according to the implementation scenario.

[0034] For the above steps, a negative correlation mapping is used to convert the body posture difference influence index into a value negatively correlated with the initial difference metric. The larger the body posture difference influence index, the greater the influence of the body posture difference on the acupuncture needle insertion technique. At this time, the weight of the initial difference metric should be reduced to avoid the excessive influence of the body posture difference on the trajectory difference metric. The preset adjustment value is used to adjust the amplitude of the negative correlation mapping result. The implementer can adjust this value according to the actual application scenario to optimize the calculation effect of the trajectory difference metric. The trajectory difference metric combines the initial difference metric and the body posture difference influence index, and can more accurately reflect the difference in the trajectories of two acupuncture needle insertion action frame data. The smaller the trajectory difference metric, the more similar the trajectories of the two acupuncture needle insertion action frame data; the larger the trajectory difference metric, the greater the difference in the trajectories of the two acupuncture needle insertion action frame data, that is, the greater the difference in the acupuncture needle insertion techniques corresponding to the nodes to be analyzed.

[0035] To analyze the degree of participation of the hand nodes during the acupuncture needle insertion process, preferably, in an embodiment of the present invention, the method for obtaining the participation metric includes: Obtaining a first participation coefficient of the node to be analyzed in the historical acupuncture needle insertion action frame data according to the correlation between the node to be analyzed and the time series data of the moving distances corresponding to all hand nodes in the historical acupuncture needle insertion action frame data; Calculating the mean value of all the moving distances corresponding to the node to be analyzed in the historical acupuncture needle insertion action frame data to obtain a second participation coefficient of the node to be analyzed in the historical acupuncture needle insertion action frame data; Calculating the product of the first participation coefficient and the second participation coefficient and performing normalization processing to obtain the participation metric of the node to be analyzed in the historical acupuncture needle insertion action frame data. Among them, preferably, in an embodiment of the present invention, the method for obtaining the first participation coefficient includes: for any historical acupuncture needle insertion action frame data, calculating the absolute value of the Pearson correlation coefficient of the time series data of the moving distances corresponding to the node to be analyzed and the hand nodes to obtain the correlation coefficient between the node to be analyzed and the hand nodes; calculating the mean value of the correlation coefficients between the node to be analyzed and all hand nodes to obtain the first participation coefficient of the node to be analyzed in the historical acupuncture needle insertion action frame data. It should be noted that the normalization method used is: performing normalization using the norm normalization function to limit the numerical range between 0 and 1. Among them, normalization is a well-known technical means in the art, and the choice of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited here.

[0036] For the above steps, the first participation coefficient reflects the correlation in the motion pattern between the node to be analyzed and other hand nodes. The higher the correlation coefficient, the stronger the linkage between the node to be analyzed and other nodes, and the higher the degree of participation. The second participation coefficient reflects the motion amplitude of the node to be analyzed during the acupuncture needle insertion process. The larger the motion amplitude, the greater the influence of the node to be analyzed on the acupuncture manipulation. The participation metric combines the first participation coefficient and the second participation coefficient, and can accurately quantify the degree of participation of the node to be analyzed during the acupuncture needle insertion process. The higher the participation metric, the greater the influence of the node on the acupuncture manipulation.

[0037] To more accurately reflect the actual differences in the acupuncture manipulation, preferably, in an embodiment of the present invention, the method for obtaining the distance metric value includes: Calculating the absolute value of the difference in the participation metric of the hand nodes in two historical acupuncture action frame data in the historical acupuncture action frame data to obtain the participation difference metric of the hand nodes in the two historical acupuncture action frame data; Calculating the mean value of the participation metrics of the hand nodes in two historical acupuncture action frame data to obtain the participation overall index of the hand nodes in the two historical acupuncture action frame data; Calculating the product of the participation difference metric, the participation overall index, and the trajectory difference metric of the hand nodes in two historical acupuncture action frame data to obtain the local difference degree of the hand nodes in the two historical acupuncture action frame data; Calculating the cumulative sum of the local difference degrees of all hand nodes in two historical acupuncture action frame data to obtain the distance metric value for each two historical acupuncture action frame data.

[0038] For the above steps, for any two historical acupuncture action frame data, first focus on their hand nodes. Hand nodes play a crucial role in the acupuncture process because they are the main parts that perform the acupuncture actions.

[0039] Calculate the absolute value of the difference in the participation measures of each hand node in the two historical acupuncture needle insertion action frame data. The participation measure may refer to the activity level, position change, speed, or other relevant indicators of the hand node in a specific frame. By calculating the absolute value of the difference, the participation difference measure of the hand nodes in the two historical acupuncture needle insertion action frame data is obtained, which reflects the subtle differences in their acupuncture needle insertion actions. Next, calculate the mean of the participation measures of the hand nodes in the two historical acupuncture needle insertion action frame data to obtain the overall participation index. The overall participation index represents the average activity level or importance of the hand nodes in the overall acupuncture needle insertion action. With the participation difference measure, the overall participation index, and the trajectory difference measure that may have been calculated previously. Multiply these three measure values to obtain the local difference degree of the hand nodes in the two historical acupuncture needle insertion action frame data. This product comprehensively considers the differences, overall activity levels, and trajectory differences of the hand nodes in the acupuncture needle insertion action, thus providing a more comprehensive difference measure. Finally, calculate the sum of the local difference degrees of all hand nodes in the two historical acupuncture needle insertion action frame data to obtain the distance measure value between every two historical acupuncture needle insertion action frame data. This sum represents the overall difference degree between the two historical acupuncture needle insertion action frame data and is the basis for subsequent clustering analysis.

[0040] The simulation module 103 is configured to cluster all the historical acupuncture needle insertion action frame data according to the distance measure value between every two historical acupuncture needle insertion action frame data to obtain each acupuncture technique category; and obtain the simulation training model of the acupuncture technique according to all the acupuncture technique categories.

[0041] The historical acupuncture needle insertion action frame data can be more accurately divided into each acupuncture technique category through the distance measure value, thereby improving the accuracy of the simulation training model of the acupuncture technique.

[0042] In order to be more accurately divided into each acupuncture technique category, preferably, in an embodiment of the present invention, the method for obtaining the acupuncture technique category includes: Using the K-Means clustering algorithm, cluster all the historical acupuncture needle insertion action frame data according to the distance measure value between every two historical acupuncture needle insertion action frame data to obtain each acupuncture technique category.

[0043] It should be noted that the K-Means clustering algorithm is a well-known technical means to those skilled in the art and will not be elaborated here. Only the brief process of using the K-Means clustering algorithm in an embodiment of the present invention to cluster all the historical acupuncture needle insertion action frame data according to the distance measure value between every two historical acupuncture needle insertion action frame data to obtain each acupuncture technique category is described: Considering that the larger the distance metric value between two historical acupuncture needle insertion action frame data is, the greater the difference in gesture actions is, the optimal k value is obtained by the elbow method. The distance metric values of every two historical acupuncture needle insertion action frame data are substituted into the clustering process to cluster all the historical acupuncture needle insertion action frame data in the historical database, and the clustering result is obtained, and each acupuncture needle insertion technique category is obtained. This makes the difference between the historical acupuncture needle insertion action frame data in different acupuncture needle insertion technique categories as large as possible, and the difference between the historical acupuncture needle insertion action frame data in the same acupuncture needle insertion technique category as small as possible. This makes the similarity of the acupuncture needle insertion behavior of the historical acupuncture needle insertion action frame data in each acupuncture needle insertion technique category as large as possible. In other embodiments of the present invention, the optimal k value of the K-Means clustering algorithm can be determined by other methods such as the silhouette coefficient method, which is not limited herein.

[0044] Further, based on the characteristics of each acupuncture needle insertion technique category, the system constructs a simulation training model for acupuncture needle insertion techniques; for example, for an acupuncture needle insertion technique category, the movement trajectories corresponding to all the historical acupuncture needle insertion action frame data are used as the standard action for simulation training of this acupuncture needle insertion technique category; the simulation training model can display the standard actions of each acupuncture needle insertion technique to the user through VR technology or other simulation means for the user to perform simulation training.

[0045] A simulation training method for acupuncture needle insertion techniques, and the method uses a simulation training system for acupuncture needle insertion techniques as described in any one of the above to perform quality inspection.

[0046] In summary, the embodiments of the present invention provide a simulation training system and method for acupuncture needle insertion techniques. First, according to the influence index of the body posture difference corresponding to the nodes to be analyzed in every two historical acupuncture needle insertion action frame data, the initial difference metric is adjusted to obtain the trajectory difference metric; according to the change situation of the moving distance of the nodes to be analyzed in the historical acupuncture needle insertion action frame data, the participation metric of the nodes to be analyzed in the historical acupuncture needle insertion action frame data is obtained; further, based on the distance metric values, all the historical acupuncture needle insertion action frame data are clustered to obtain each acupuncture needle insertion technique category; according to all the acupuncture needle insertion technique categories, a simulation training model for acupuncture needle insertion techniques is obtained. By fully considering the influence of body posture differences on acupuncture needle insertion techniques and the participation degree of different hand nodes in the acupuncture needle insertion process, the present invention more accurately divides each acupuncture needle insertion technique category and improves the accuracy of the simulation training model for acupuncture needle insertion techniques.

[0047] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0048] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A simulation training system for acupuncture needle manipulation, characterized in that: The system comprises: A data acquisition module is used to obtain the moving distance time series data corresponding to each hand node in each historical acupuncture action frame data; A distance measurement module is used to obtain an initial difference measurement of the nodes to be analyzed between each two historical acupuncture action frame data according to the difference of the moving distance time series data corresponding to the nodes to be analyzed between each two historical acupuncture action frame data; obtain a posture difference influence index corresponding to the nodes to be analyzed between each two historical acupuncture action frame data according to the period of the moving distance time series data corresponding to the nodes to be analyzed between each two historical acupuncture action frame data; adjust the initial difference measurement according to the posture difference influence index corresponding to the nodes to be analyzed between each two historical acupuncture action frame data, and obtain a trajectory difference measurement of the nodes to be analyzed between each two historical acupuncture action frame data; obtain a participation measurement of the node to be analyzed in the historical acupuncture action frame data according to the change of the moving distance of the node to be analyzed in the historical acupuncture action frame data; and obtain a distance measurement value of each two historical acupuncture action frame data by combining the trajectory difference measurement of all the hand nodes of each two historical acupuncture action frame data and the participation measurement of the hand nodes in the historical acupuncture action frame data; The simulation module is used to cluster all the historical acupuncture action frame data according to the distance measurement value between each two of the historical acupuncture action frame data to obtain each acupuncture technique category; based on all acupuncture technique categories, a simulation training model of acupuncture acupuncture techniques is obtained.

2. The acupuncture needle manipulation simulation training system according to claim 1, characterized in that: The method for obtaining the initial difference metric includes: The DTW distance between the nodes to be analyzed between every two historical acupuncture action frame data and the moving distance time series data is used as the initial difference metric of the nodes to be analyzed between every two historical acupuncture action frame data.

3. The acupuncture needle manipulation simulation training system according to claim 1, characterized in that: The method for obtaining the body posture difference impact index includes: According to the duration and amplitude of the periodic item of the moving distance time series data corresponding to the node to be analyzed of the historical acupuncture action frame data, the action feature value corresponding to the node to be analyzed of the historical acupuncture action frame data is obtained; According to the absolute value of the difference between the action feature values ​​corresponding to the nodes to be analyzed of each two historical acupuncture action frame data, the action amplitude difference index corresponding to the nodes to be analyzed of each two historical acupuncture action frame data is obtained; According to the correlation coefficient of the periodic item of the moving distance time series data corresponding to the nodes to be analyzed of each two historical acupuncture action frame data, the action flow similarity index corresponding to the nodes to be analyzed of each two historical acupuncture action frame data is obtained; According to the action flow similarity index and the action amplitude difference index corresponding to the nodes to be analyzed of every two historical acupuncture action frame data, the posture difference influence index corresponding to the nodes to be analyzed of every two historical acupuncture action frame data is obtained.

4. The acupuncture needle manipulation simulation training system according to claim 3, characterized in that: The method for obtaining the action characteristic value includes: For any periodic item of the moving distance time series data corresponding to the node to be analyzed of the historical acupuncture action frame data, the product of the duration and amplitude of the periodic item is calculated to obtain the action feature value corresponding to the node to be analyzed of the historical acupuncture action frame data.

5. The acupuncture needle manipulation simulation training system according to claim 3, characterized in that: The method for obtaining the body posture difference impact index includes: The product of the action flow similarity index and the action amplitude difference index is calculated to obtain the posture difference influence index corresponding to each two nodes to be analyzed of the historical acupuncture action frame data.

6. The acupuncture needle manipulation simulation training system according to claim 1, characterized in that: The method for obtaining the participation metric includes: According to the correlation between the moving distance time series data corresponding to the node to be analyzed and all the hand nodes in the historical acupuncture action frame data, the first participation coefficient of the node to be analyzed in the historical acupuncture action frame data is obtained; Calculate the mean of all movement distances of the node to be analyzed in the historical acupuncture action frame data to obtain the second participation coefficient of the node to be analyzed in the historical acupuncture action frame data; The product of the first participation coefficient and the second participation coefficient is calculated and normalized to obtain the participation measure of the node to be analyzed in the historical acupuncture action frame data.

7. The acupuncture needle manipulation simulation training system according to claim 6, characterized in that: The method for obtaining the first participation coefficient includes: For any historical acupuncture action frame data, the absolute value of the Pearson correlation coefficient of the moving distance time series data corresponding to the node to be analyzed and the hand node is calculated to obtain the correlation coefficient between the node to be analyzed and the hand node; The mean value of the correlation coefficient between the node to be analyzed and all the hand nodes is calculated to obtain the first participation coefficient of the node to be analyzed in the historical acupuncture action frame data.

8. The acupuncture needle manipulation simulation training system according to claim 1, characterized in that: The distance measurement value acquisition method comprises: Calculate the absolute value of the difference between the participation measures of the hand nodes of the two historical acupuncture action frame data in the historical acupuncture action frame data to obtain the participation difference measure of the hand nodes of the two historical acupuncture action frame data; Calculate the mean of the participation metrics of the hand nodes of the two historical acupuncture action frame data to obtain the overall participation index of the hand nodes of the two historical acupuncture action frame data; Calculate the product of the participation difference measure, the overall participation index and the trajectory difference measure of the hand nodes of the two historical acupuncture action frame data to obtain the local difference degree of the hand nodes of the two historical acupuncture action frame data; The cumulative sum of the local difference degrees of all hand nodes of two historical acupuncture action frame data is calculated to obtain the distance measurement value of each two historical acupuncture action frame data.

9. The acupuncture needle manipulation simulation training system according to claim 1, characterized in that: The method for obtaining the acupuncture technique category includes: Using the K-Means clustering algorithm, all the historical acupuncture action frame data are clustered according to the distance measurement value between every two of the historical acupuncture action frame data to obtain various acupuncture technique categories.

10. A simulation training method for acupuncture needle manipulation, characterized in that: The method uses a simulation training system for acupuncture needle manipulation as described in any one of claims 1 to 9 to perform quality inspection.

Images