Simulated acupuncture point hitting practical training and evaluation system based on non-standard human body holographic digital model

Abstract

The invention relates to the technical field of traditional Chinese medicine equipment, in particular to a simulated acupuncture training and evaluation system based on a non-standard human body holographic digital model, which comprises a work station, a scanning module and a VR all-in-one machine, and is characterized in that training evaluation software is arranged in the work station and comprises a model scanning unit, a test unit and an AI scoring unit; the method can effectively solve the problems that an existing acupoint selection method is poor in flexibility, cannot perform acupoint selection operation on different human body acupoints, is high in cost and is low in intelligent degree and safety degree.

Description

Technical Field

[0001] The present invention relates to the technical field of traditional Chinese medicine equipment, and in particular to a simulated acupoint pressing training and evaluation system based on a non-standard human body holographic digital model. Background Art

[0002] In the theoretical system of traditional Chinese medicine, acupoints and meridians are of great significance. By stimulating specific acupoints on specific meridians, the physiological functions of the human body can be regulated and related diseases can be effectively treated. In order to more effectively serve the diagnosis of clinical diseases and minimize the side effects of diagnosis and treatment, practitioners in the field of traditional Chinese medicine need to have accurate acupoint positioning capabilities. However, in the real environment, human body shapes are different, and there are differentiated acupoint positioning standards. How to efficiently conduct acupoint positioning training in the teaching of traditional Chinese medicine-related colleges and universities and the training of practitioners has become a problem that needs to be solved urgently. At present, there are mainly several solutions for acupoint positioning, such as VR acupoint selection, mutual acupoint tapping, and bronze man practice.

[0003] However, the existing acupuncture point positioning still has some shortcomings, specifically: the existing acupuncture point positioning method has poor flexibility, cannot perform acupuncture point positioning operations on different human acupuncture points, has high costs, and has low intelligence and safety levels.

[0004] Therefore, a simulated acupoint training and evaluation system based on a non-standard human holographic digital model is needed to solve the problems raised in the above background technology. Summary of the invention

[0005] The purpose of the present invention is to provide a simulated acupoint pressing training and evaluation system based on a non-standard human holographic digital model to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The simulated acupoint training and evaluation system based on the non-standard human holographic digital model includes a workstation, a scanning module and a VR all-in-one machine. The workstation is internally provided with training and evaluation software, and the training and evaluation software includes a model scanning unit, a testing unit and an AI scoring unit.

[0008] As a preferred solution of the present invention, the scanning module, the VR all-in-one machine and the workstation are all connected via optical fiber cables.

[0009] As a preferred solution of the present invention, the scanning module is various 3D scanners, and multiple groups of the scanning modules and the VR all-in-one machine are provided.

[0010] As a preferred solution of the present invention, the specific analysis steps of the model scanning unit are: the scanning module performs model scanning of the human body through algorithms such as landmark point splicing, feature splicing, texture splicing, and human body sway optimization, and inputs the scanned data into the workstation; the model scanning unit in the workstation performs format conversion on the input scanned data, and converts the input data format into three formats: obj, mt l, and jpg; the model scanning unit uses the converted obj, mt l, and jpg files to jointly complete the platform side model import and construction; the model scanning unit removes the noise model and adjusts the model position to the center, and sets the default angle and position for acupuncture points; the model scanning unit classifies the model and labels it for subsequent practical training and selection.

[0011] As a preferred solution of the present invention, the specific analysis steps of the test unit are as follows: the test unit is based on "Acupoint Names and Positioning", and through built-in bone measurement, auxiliary lines, bisectors and other standard acupoint selection tools, full-view 3D operation and high-precision model features can achieve convenient acupoint positioning within the standard error. The test unit adopts an error design based on the three-dimensional coordinate method to support custom errors. The test unit has built-in acupoint association information data table and standard acupoint selection step table that do not require acupoint selection standards. The acupoint information table contains information such as acupoint name, meridian name, specific acupoint, acupoint level, acupoint location, acupoint location description, acupoint selection step description, etc. According to the database retrieval function, the acupoint card information is automatically filled after the acupoint name is selected.

[0012] As a preferred solution of the present invention, the specific analysis steps of the AI ​​scoring unit are as follows: the AI ​​scoring unit constructs an acupoint card vector library, the user inputs the question into the workstation, the AI ​​scoring unit searches the vector library and the Internet through the user's question keywords, scores the results respectively, and gives priority to displaying high-scoring content matched by the vector library; the AI ​​scoring unit constructs an acupoint selection step vector library, and assumes the acupoint selection auxiliary role of the AI ​​assistant through the prompt word engineering, the AI ​​scoring unit is trained by importing the constructed question-and-answer training template, and finally matches the result of the vector library according to the user's question; the standard full score description and the description of the specified error are input into the workstation, and then the voice processing tool is connected, the AI ​​scoring unit compares the text converted from the user's voice with the standard answer, and gives a matching score; the AI ​​scoring unit captures the scores of each point of each practical training task of the student in turn according to the set scoring points, comprehensively generates the score changes of specific scoring points generated by multiple tasks, and produces the mastery of the knowledge points corresponding to the final scoring points.

[0013] As a preferred solution of the present invention, the obj file is used to represent a 3D geometric body, indicating the position, UV coordinates and normal of each vertex, and each polygon is defined as a face of a vertex list. Generally, vertices are stored in a counterclockwise direction, and there is no need to display the normals of life faces; mt l is used to describe human body features, and apply attributes such as texture and color to the 3D model constructed by the obj file, so that the model can correctly display the color, texture and reflection effect of the material when rendered; the jpg file associates the real image of human skin with the obj file, is used for texture mapping, increases details and realism, and is an effective supplement to the mt l file.

[0014] As a preferred solution of the present invention, the specific process of the error design method based on the three-dimensional coordinate method is: select the coordinates of the center point of the acupuncture point sphere set in the answer in space, recorded as [x, y, z], set two error interval thresholds m, n, q for the answer error, m<n<q, at this time there are 4 intervals, namely interval 1-{[x, y, z], [x+m, y+m, z+m]}, interval 2-{[x+m, y+m, z+m], [x+n, y+b, z+b]}, interval 3-{[x+n, y+n, z+n], [x+q, y+q, z+q]} and interval 4-{[x+q, y+q, z+q], [x+∞, y+∞, z+∞]}, and then set the score ratio of each interval range respectively. When the user submits the acupuncture point answer, the interval where the set acupuncture point coordinates [x1, y1, z1] are located is compared with the 4 intervals, and the corresponding score is obtained according to which interval the acupuncture point coordinates fall.

[0015] Compared with the prior art, the present invention has the following beneficial effects:

[0016] 1. In the present invention, by adopting 3D ultra-clear scanning technology, the surface characteristics of the human body are restored with high definition, and every detail of the human body, including skin texture, muscle lines, bone landmarks, etc., can be accurately captured, providing users with more accurate acupoint positioning services. The system covers real-life models of different body shapes, ages, genders, parts, and postures, including both standard human bodies and non-standard human bodies, and supports rapid entry of model library data. Users can conduct comprehensive acupoint selection training according to their needs. The models cover the conditions of most patients in clinical practice. Different body position models can be entered for the same part. During training, try to select appropriate postures according to different acupoints, close to clinical practice. At the same time, the bone measurement tool in the system supports customized starting and ending points and folding measurements, precise projection of each equally divided skin surface, auxiliary line & equally divided line tools fit the complex lines of the human body, accurately assist in measurement, and acupoint markings can customize the acupoint error range to achieve 3D three-dimensional acupoint markings.

[0017] 2. In the present invention, by supporting VR expansion, the pointer follows the acupoint status in real time, and the user can use the mouse to realize all-round and multi-angle rotation and displacement of the model, and can perform customized scaling of the body surface. When using the desktop VR acupoint method, a three-dimensional control pen is used with 3D tracking glasses, which can realize touching, dragging, and fixing by raising the hand. The content of the stereoscopic view can be automatically adjusted, and it can be zoomed in and out at will through 3D interaction to explore each training detail. At the same time, it is designed based on the national standard and the Asia-Pacific standard of the World Health Organization, through the deep coupling of software and hardware, the progressive granular steps from model acquisition to acupoint training, the centralized management of training examinations, and the accurate user ability portrait, it realizes the integration of learning, practicing, testing, evaluating, and competing.

[0018] 3. In the present invention, through the characteristics of multimodal input based on large models, rich Internet resources and local vector libraries, it can serve the acupoint selection training process and also act on theoretical learning. At the same time, it can accurately perform individualized data analysis and customize the optimal practical training route. At the same time, it is equipped with professional-level theoretical teaching materials / theoretical PPT courseware, project-based practical training teaching materials / practical training instructions / operation manuals / practical training PPT resources, adopts point-line-surface evaluation, and can expand the resource library and question bank at any time to explore a new model of digital teaching of Chinese medicine acupoint selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the overall hardware structure of the present invention;

[0020] Figure 2 It is a schematic diagram of the system block structure of the present invention;

[0021] Figure 3 It is a schematic diagram of the operation flow of the system of the present invention;

[0022] Figure 4 It is a schematic diagram of the system architecture of the present invention;

[0023] Figure 5 This is a schematic diagram of the model import processing flow of the present invention;

[0024] Figure 6 It is a schematic diagram of the standard acupoint selection steps of the present invention.

[0025] In the figure: 1. Workstation; 2. Scanning module; 3. VR all-in-one machine; 4. Training and evaluation software; 5. Model scanning unit; 6. Testing unit; 7. AI scoring unit. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] To facilitate understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are given. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0028] It should be noted that when an element is referred to as being "fixed on" another element, it may be directly on the other element or there may also be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may also be a central element. The terms "vertical", "horizontal", "left", "right" and similar expressions used in this article are for illustrative purposes only.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0030] For examples, see Figure 1-6 , the present invention provides a technical solution:

[0031] The simulated acupoint training and evaluation system based on the non-standard human holographic digital model includes a workstation 1, a scanning module 2 and a VR all-in-one machine 3. The workstation 1 is internally provided with training and evaluation software 4, and the training and evaluation software 4 includes a model scanning unit 5, a testing unit 6 and an AI scoring unit 7.

[0032] Furthermore, the scanning module 2, the VR all-in-one machine 3 and the workstation 1 are all connected via optical fiber cables.

[0033] Furthermore, the scanning module 2 is a variety of 3D scanners, and the scanning module 2 and the VR all-in-one machine 3 are both provided with multiple groups.

[0034] Furthermore, the specific analysis steps of the model scanning unit 5 are: the scanning module 2 performs model scanning on the human body through algorithms such as landmark point splicing, feature splicing, texture splicing, and human body sway optimization, and inputs the scanning data into the workstation 1; the model scanning unit 5 in the workstation 1 performs format conversion on the input scanning data, and converts the input data format into three formats: obj, mtl, and jpg; the model scanning unit 5 uses the converted obj, mtl, and jpg files to complete the platform side model import and construction; the model scanning unit 5 removes the noise model and adjusts the model position to the center, and sets the default angle and position for acupuncture points; the model scanning unit 5 classifies the model and labels it for subsequent practical training and selection.

[0035] Furthermore, the specific analysis steps of test unit 6 are as follows: test unit 6 and "Acupoint Names and Positioning" are based on a variety of standard acupoint selection tools such as built-in bone measurement, auxiliary lines, and bisectors, and full-view 3D operation and high-precision model features can achieve convenient acupoint positioning within the standard error. Test unit 6 adopts an error design based on the three-dimensional coordinate method to support custom errors. Test unit 6 has built-in acupoint association information data table and standard acupoint selection step table that do not require acupoint selection standards. The acupoint information table contains information such as acupoint name, meridian name, specific acupoint, acupoint level, acupoint location, acupoint location description, acupoint selection step description, etc. According to the database retrieval function, the acupoint card information is automatically filled after selecting the acupoint name.

[0036] Furthermore, the specific analysis steps of the AI ​​scoring unit 7 are as follows: the AI ​​scoring unit 7 constructs an acupoint card vector library, the user inputs the question into the workstation 1, the AI ​​scoring unit 7 searches the vector library and the Internet according to the user's question keywords, scores the results respectively, and gives priority to displaying the high-scoring content matched by the vector library; the AI ​​scoring unit 7 constructs an acupoint selection step vector library, and assumes the acupoint selection auxiliary role of the AI ​​assistant through the prompt word engineering, the AI ​​scoring unit 7 imports the training by constructing a question-and-answer training template, and finally matches the result of the vector library according to the user's question; the standard full score description and the description of the specified error are input into the workstation 1, and then the voice processing tool is connected, the AI ​​scoring unit 7 compares the text converted from the user's voice with the standard answer, and gives a matching score; the AI ​​scoring unit 7 captures the scores of each point of each practical training task of the students in turn according to the set scoring points, generates the score changes of specific scoring points based on multiple tasks, and produces the mastery of the knowledge points corresponding to the final scoring points.

[0037] Furthermore, the obj file is used to represent a 3D geometric body, indicating the position, UV coordinates and normals of each vertex, and each polygon is defined as a face of a vertex list. Generally, vertices are stored in a counterclockwise direction, and there is no need to display the normals of life faces; the mt l file is used to describe human body characteristics, and apply texture, color and other attributes to the 3D model constructed by the obj file, so that the model can correctly display the color, texture, reflection effect and other characteristics of the material when rendered; the jpg file associates the real image of human skin with the obj file, which is used for texture mapping to increase details and realism, and is an effective supplement to the mt l file.

[0038] Furthermore, the specific process of the error design method based on the three-dimensional coordinate method is as follows: select the coordinates of the center point of the acupuncture point sphere set in the answer in space, denoted as [x, y, z], set two error interval thresholds m, n, q for the answer error, m<n<q, and there are 4 intervals in total, namely interval 1-{[x, y, z], [x+m, y+m, z+m]}, interval 2-{[x+m, y+m, z+m], [x+n, y+b, z+b]}, interval 3-{[x+n, y+n, z+n], [x+q, y+q, z+q]} and interval 4-{[x+q, y+q, z+q], [x+∞, y+∞, z+∞]}, and then set the score ratio of each interval range respectively. When the user submits the acupuncture point answer, the interval where the set acupuncture point coordinates [x1, y1, z1] are located is compared with the 4 intervals, and the corresponding score is obtained according to which interval the acupuncture point coordinates fall.

[0039] The workflow of the present invention is as follows: when the simulated acupoint-pointing training and evaluation system based on the non-standard human holographic digital model designed by the present invention is in operation, the scanning module 2 performs model scanning on the human body through algorithms such as landmark splicing, feature splicing, texture splicing, and human body shaking optimization, and inputs the scanned data into the workstation 1. The model scanning unit 5 in the workstation 1 performs format conversion on the input scanned data, and converts the input data format into three formats: obj, mt l, and jpg. The obj file is used to represent a 3D geometric body, indicating the position, UV coordinates, and normals of each vertex. Each polygon is defined as a face of a vertex list. Generally, vertices are stored in a counterclockwise direction, and there is no need to display the normals of life faces. The mt l file is used to describe human body features, and attributes such as texture and color are applied to the 3D model constructed by the obj file, so that the model can correctly display the color, texture, and reflection effect of the material when rendering. The jpg file associates the real image of human skin with the obj file, which is used for texture mapping, increasing details and realism, and is an effective supplement to the mt l file. The model scanning unit 5 uses the converted obj, mt l, and jpg files. l and jpg files together complete the platform side model import and construction, the model scanning unit 5 removes the noise model and adjusts the model position to the center, and sets the default angle and position of the acupoints. The model scanning unit 5 classifies the model and labels it for subsequent practical training selection;

[0040] Test unit 6 is based on "Acupoint Names and Locations". Through built-in bone measurement, auxiliary lines, bisectors and other standard acupoint selection tools, full-view 3D operation and high-precision model features can achieve convenient acupoint selection and positioning within the standard error. Test unit 6 selects the coordinates of the center point of the acupoint sphere set in the answer in space, recorded as [x, y, z]. The answer error sets two error interval thresholds m, n, q, m<n<q. At this time, there are 4 intervals, namely interval 1-{[x, y, z], [x+m, y+m, z+m]}, interval 2-{[x+m, y+m, z+m], [x+n, y+b, z+b]}, interval 3-{[x+n, y+n, z+n], [x+q ,y+q,z+q]} and interval 4-{[x+q,y+q,z+q],[x+∞,y+∞,z+∞]}, and then set the score ratio of each interval range respectively. When the user submits the answer to acupuncture points, the interval where the acupuncture point coordinates [x1, y1, z1] are set according to the test unit 6 is compared with the four intervals, and the corresponding score is obtained in which interval. The test unit 6 has built-in acupuncture point association information data table and standard acupuncture point selection step table issued under different acupuncture point selection standards. The acupuncture point information table contains information such as acupuncture point name, meridian name, specific acupuncture point, acupuncture point level, acupuncture point location, acupuncture point location description, acupuncture point selection step description, etc. According to the database retrieval function, the acupuncture point card information is automatically filled after selecting the acupuncture point name;

[0041] The AI ​​scoring unit 7 constructs acupoint card vector library. The user inputs the question into the workstation 1. The AI ​​scoring unit 7 searches the vector library and the Internet based on the user's question keywords, scores the results respectively, and gives priority to displaying high-scoring content matched by the vector library; the AI ​​scoring unit 7 constructs acupoint selection step vector library, and assumes the acupoint selection auxiliary role of the AI ​​assistant through the prompt word engineering. The AI ​​scoring unit 7 is trained by importing the constructed question-and-answer training template, and finally matches the result of the vector library according to the user's question; the standard full score description and the description of the specified error are input into the workstation 1, and then the voice processing tool is connected. The AI ​​scoring unit 7 compares the text converted from the user's voice with the standard answer, and gives a matching score; the AI ​​scoring unit 7 captures the scores of each point of each practical training task of the students in turn according to the set score points, generates the score changes of specific score points based on multiple tasks, and produces the mastery of the knowledge points corresponding to the final score points.

[0042] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A simulated acupoint pressing training and evaluation system based on a non-standard human holographic digital model, comprising a workstation (1), a scanning module (2) and a VR all-in-one machine (3), characterized in that: The workstation (1) is internally provided with practical training and evaluation software (4), and the practical training and evaluation software (4) comprises a model scanning unit (5), a testing unit (6) and an AI scoring unit (7).

2. The simulated acupoint pressing training and evaluation system based on the non-standard human holographic digital model according to claim 1 is characterized in that: The scanning module (2), the VR all-in-one machine (3) and the workstation (1) are all connected via optical fiber cables.

3. The simulated acupoint pressing training and evaluation system based on the non-standard human holographic digital model according to claim 1 is characterized in that: The scanning module (2) is a variety of 3D scanners, and the scanning module (2) and the VR all-in-one machine (3) are both provided with multiple groups.

4. The simulated acupoint pressing training and evaluation system based on the non-standard human holographic digital model according to claim 1 is characterized in that: The specific analysis steps of the model scanning unit (5) are as follows: the scanning module (2) performs model scanning on the human body through algorithms such as landmark stitching, feature stitching, texture stitching, and human body sway optimization, and inputs the scanned data into the workstation (1); the model scanning unit (5) in the workstation (1) performs format conversion on the input scanned data, and converts the input data format into three formats: obj, mtl, and jpg; the model scanning unit (5) uses the converted obj, mtl, and jpg files to jointly complete the platform side model import and construction; the model scanning unit (5) removes the noise point model and adjusts the model position to the center, and sets the default angle and position of the acupoint; the model scanning unit (5) classifies the model and labels it for subsequent practical training selection.

5. The simulated acupoint pressing training and evaluation system based on the non-standard human holographic digital model according to claim 1 is characterized in that: The specific analysis steps of the test unit (6) are as follows: the test unit (6) is based on "Acupoint Names and Positioning", and through built-in bone measurement, auxiliary lines, bisectors and other standard acupoint selection tools, full-view 3D operation and high-precision model features can achieve convenient acupoint selection and positioning within the standard error. The test unit (6) adopts an error design based on the three-dimensional coordinate method to support customized errors. The test unit (6) has built-in acupoint association information data tables and standard acupoint selection step tables issued under different acupoint selection standards. The acupoint information table contains information such as acupoint name, meridian name, specific acupoint, acupoint level, acupoint location, acupoint location description, acupoint selection step description, etc. According to the database search function, the acupoint card information is automatically filled after the acupoint name is selected.

6. The simulated acupoint pressing training and evaluation system based on the non-standard human holographic digital model according to claim 1 is characterized in that: The specific analysis steps of the AI ​​scoring unit (7) are as follows: the AI ​​scoring unit (7) constructs an acupoint card vector library, the user inputs a question into the workstation (1), the AI ​​scoring unit (7) searches the vector library and the Internet through the user's question keywords, scores the results respectively, and gives priority to displaying high-scoring content matched by the vector library; the AI ​​scoring unit (7) constructs an acupoint selection step vector library, and assumes the acupoint selection auxiliary role of the AI ​​assistant through the prompt word engineering, the AI ​​scoring unit (7) is trained by constructing a question-and-answer training template and importing it, and finally matches the result of the vector library according to the user's question; the standard full score description and the description of the specified error are input into the workstation (1), and then the voice processing tool is connected, the AI ​​scoring unit (7) compares the text converted from the user's voice with the standard answer, and gives a matching score; the AI ​​scoring unit (7) sequentially captures the score of each point of each practical training task of the student according to the set score points, generates the score change of specific score points by integrating multiple tasks, and produces the mastery of the knowledge points corresponding to the final score points.

7. The simulated acupoint pressing training and evaluation system based on the non-standard human holographic digital model according to claim 4 is characterized in that: The obj file is used to represent a 3D geometric body, indicating the position, UV coordinates and normals of each vertex, and each polygon is defined as a face of a vertex list. Generally, vertices are stored in a counterclockwise direction, and there is no need to display the normals of life faces; the mtl file is used to describe human body features, and apply texture, color and other attributes to the 3D model constructed by the obj file, so that the model can correctly display the color, texture and reflection effects of the material when rendered; the jpg file associates the real image of human skin with the obj file, and is used for texture mapping to increase details and realism, and is an effective supplement to the mtl file.

8. The simulated acupoint pressing training and evaluation system based on the non-standard human holographic digital model according to claim 5 is characterized in that: The specific process of the error design method based on the three-dimensional coordinate method is as follows: select the coordinates of the center point of the acupuncture point sphere set in the answer in space, recorded as [x, y, z], set two error interval thresholds m, n, q for the answer error, m<n<q, at this time there are 4 intervals, namely interval 1-{[x, y, z], [x+m, y+m, z+m]}, interval 2-{[x+m, y+m, z+m], [x+n, y+b, z+b]}, interval 3-{[x+n, y+n, z+n], [x+q, y+q, z+q]} and interval 4-{[x+q, y+q, z+q], [x+∞, y+∞, z+∞]}, and then set the score ratio of each interval range respectively. When the user submits the acupuncture point answer, the interval where the set acupuncture point coordinates [x1, y1, z1] are located is compared with the 4 intervals, and the corresponding score is obtained according to which interval the acupuncture point coordinates fall.

Images