An acupoint positioning method, device, equipment and medium

Abstract

The application discloses an acupoint positioning method and device, equipment and medium, and relates to the technical field of acupoint positioning. The method comprises the following steps: acquiring real-time electroencephalogram signals of a user and an image of a body surface to be positioned; inputting the real-time electroencephalogram signals and the image into an acupoint positioning model to obtain accurate acupoint position information in the image; and projecting the acupoint position information to the body surface to be positioned to perform acupoint positioning. Thus, by inputting the real-time electroencephalogram signals of the user and the image of the body surface to be positioned into the acupoint positioning model, the position information of the acupoints can be quickly and accurately obtained, and after the acupoint position information is projected to the body surface to be positioned, the acupoint positioning can be completed, so that the accuracy and efficiency of acupoint positioning are improved.

Description

Technical Field

[0001] This application relates to the field of acupoint location technology, and in particular to an acupoint location method, device, equipment and medium. Background Technology

[0002] Acupoints refer to specific points or areas along the meridians of the human body. Traditional Chinese medicine uses acupuncture, massage, and moxibustion to stimulate these acupoints to treat diseases, making accurate acupoint location extremely important. Specifically, acupoints can be located by utilizing their sensitization phenomena. As sites where the Qi of the internal organs and meridians is transported to the body surface, acupoints exhibit widespread sensitization, manifesting in various forms such as heat sensitivity, pain sensitivity, electrical sensitivity, and shape sensitivity.

[0003] There are two methods for acupoint location in related technologies. The first is based on the theory of human meridians, determining the absolute location of acupoints on the human body and their relative positions, thus mapping all locations onto the body for acupoint location. However, due to significant differences in body shape among individuals, it is impossible to accurately locate acupoints for every user, resulting in low accuracy. The second method involves applying electromagnetic stimulation to the user and testing the deviation between the user's actual electrophysiological data and theoretical electrophysiological data. If the actual electrophysiological data corresponding to a point on the user's body matches the theoretical electrophysiological data of the target acupoint, then that point is the target acupoint. However, since the theoretical electrophysiological data differs for different acupoints, the theoretical electrophysiological data needs to be adjusted in real time when locating different acupoints, making the operation extremely cumbersome and resulting in low efficiency in acupoint location.

[0004] Therefore, how to improve the accuracy and efficiency of acupoint location has become an urgent technical problem to be solved. Summary of the Invention

[0005] This application provides a method, device, equipment, and medium for locating acupoints, which can improve the accuracy and efficiency of acupoint location.

[0006] This application discloses the following technical solution:

[0007] Firstly, this application provides a method for locating acupoints, the method comprising:

[0008] Acquire the user's real-time EEG signals and images of the body surface to be located;

[0009] The real-time EEG signal and the image are input into the acupoint localization model to obtain the acupoint location information in the image;

[0010] The acupoint location information is projected onto the body surface to be located in order to perform acupoint localization.

[0011] Optionally, the method for constructing the acupoint location model includes:

[0012] Acquire a user image, the user image including the target acupoint;

[0013] Obtain the initial position of the target acupoint on the user image;

[0014] Obtain the electroencephalogram (EEG) signals of the initial position and surrounding points of the initial position;

[0015] Based on the electroencephalogram (EEG) signals, the initial location and the surrounding points of the initial location are classified into painful acupoint locations and non-painful acupoint locations.

[0016] A machine learning model is trained based on the user image, the location of the painful acupoint, and the location of the non-painful acupoint to construct an acupoint localization model.

[0017] Optionally, obtaining the initial position of the target acupoint on the user image includes:

[0018] Acquire a human body image marked with target acupoints, wherein the human body image is a two-dimensional image;

[0019] According to the circular detection algorithm, the two-dimensional coordinates of the target acupoint in the human body image are obtained;

[0020] Obtain the reference points in the user image and the human body image;

[0021] By aligning the reference point in the user image with the reference point in the human body image, the two-dimensional coordinates are affinely mapped onto the user image to obtain the initial position of the target acupoint on the user image.

[0022] Optionally, the method for determining the surrounding points of the initial position includes:

[0023] Draw a circle with the initial position as the center and the target distance as the radius, and determine the surrounding points of the initial position on the circle at every target angle.

[0024] Optionally, the EEG signals include resting EEG signals and pain EEG signals. The step of classifying the initial location and surrounding points into painful acupoint locations and non-painful acupoint locations based on the EEG signals includes:

[0025] The resting EEG signal and the pain EEG signal are respectively processed by frequency domain extraction to obtain resting EEG information and pain EEG information;

[0026] The location corresponding to a positive difference between the pain EEG information and the resting EEG information, or the location corresponding to the maximum difference between the pain EEG information and the resting EEG information, is taken as the location of the pain acupoint.

[0027] The locations other than the painful acupoints are designated as non-painful acupoints among the initial location and the surrounding points.

[0028] Optionally, the step of performing frequency domain extraction processing on the resting EEG signal and the pain EEG signal to obtain resting EEG information and pain EEG information includes:

[0029] The resting EEG signal and the pain EEG signal are preprocessed to obtain the processed resting EEG signal and the processed pain EEG signal, respectively. The preprocessing includes one or more of filtering, rereference processing and artifact removal processing.

[0030] The processed resting EEG signal and the processed pain EEG signal are subjected to frequency domain extraction processing to obtain resting EEG information and pain EEG information, respectively.

[0031] Secondly, this application provides an acupoint positioning device, which includes: an image acquisition module, a location acquisition module, and an acupoint positioning module;

[0032] The image acquisition module is used to acquire the user's real-time electroencephalogram (EEG) signals and images of the body surface to be located;

[0033] The location acquisition module is used to input the real-time EEG signal and the image into the acupoint positioning model to obtain the acupoint location information in the image;

[0034] The acupoint positioning module is used to project the acupoint location information onto the body surface to be positioned in order to perform acupoint positioning.

[0035] Optionally, the device for constructing the acupoint positioning model includes: a first positioning module, a second positioning module, a third positioning module, a fourth positioning module, and a fifth positioning module;

[0036] The first positioning module is used to acquire a user image, the user image including target acupoints;

[0037] The second positioning module is used to obtain the initial position of the target acupoint on the user image;

[0038] The third positioning module is used to acquire the electroencephalogram (EEG) signals of the initial position and the surrounding points of the initial position;

[0039] The fourth positioning module is used to classify the initial position and the surrounding points of the initial position into painful acupoints and non-painful acupoints based on the electroencephalogram (EEG) signal.

[0040] The fifth positioning module is used to train a machine learning model based on the user image, the location of the painful acupoint, and the location of the non-painful acupoint to construct an acupoint positioning model.

[0041] Optionally, the second positioning module includes: a first positioning submodule, a second positioning submodule, a third positioning submodule, and a fourth positioning submodule;

[0042] The first positioning submodule is used to acquire a human body image marked with target acupoints, wherein the human body image is a two-dimensional image;

[0043] The second positioning submodule is used to obtain the two-dimensional coordinates of the target acupoint in the human body image according to the circular detection algorithm;

[0044] The third positioning submodule is used to acquire reference points in the user image and the human body image;

[0045] The fourth positioning submodule is used to align the reference point in the user image with the reference point in the human body image, and then affine the two-dimensional coordinates onto the user image to obtain the initial position of the target acupoint on the user image.

[0046] Optionally, the device for determining the surrounding points of the initial position includes: a surrounding positioning module;

[0047] The peripheral positioning module is used to draw a circle with the initial position as the center and the target distance as the radius, and to determine the peripheral points of the initial position on the circle at every target angle.

[0048] Optionally, the EEG signals include resting EEG signals and pain EEG signals, and the fourth positioning module includes: a fifth positioning submodule, a sixth positioning submodule, and a seventh positioning submodule;

[0049] The fifth positioning submodule is used to perform frequency domain extraction processing on the resting EEG signal and the pain EEG signal respectively to obtain resting EEG information and pain EEG information.

[0050] The sixth positioning submodule is used to take the position corresponding to the positive difference between the pain EEG information and the resting EEG information, or the position corresponding to the maximum difference between the pain EEG information and the resting EEG information, as the pain acupoint position.

[0051] The seventh positioning submodule is used to designate the initial position and surrounding points, excluding the painful acupoints, as non-painful acupoints.

[0052] Optionally, the fifth positioning submodule includes: a preprocessing module and a frequency domain extraction module;

[0053] The preprocessing module is used to preprocess the resting EEG signal and the pain EEG signal respectively to obtain the processed resting EEG signal and the processed pain EEG signal. The preprocessing includes one or more of filtering, rereference processing and artifact removal processing.

[0054] The frequency domain extraction module is used to perform frequency domain extraction processing on the processed resting EEG signal and the processed pain EEG signal respectively to obtain resting EEG information and pain EEG information.

[0055] Thirdly, this application provides an acupoint positioning device, including: a memory and a processor;

[0056] The memory is used to store programs;

[0057] The processor is used to implement the steps of the above-described acupoint location method when executing the computer program.

[0058] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described acupoint location method.

[0059] Compared with the prior art, this application has the following beneficial effects:

[0060] This application provides a method, apparatus, device, and medium for acupoint localization. The method includes: acquiring a user's real-time electroencephalogram (EEG) signal and an image of the body surface to be localized; inputting the real-time EEG signal and image into an acupoint localization model to obtain precise acupoint location information in the image; and projecting the acupoint location information onto the body surface to be localized to perform acupoint localization. Therefore, by inputting the user's real-time EEG signal and an image of the body surface to be localized into the acupoint localization model, the location information of acupoints can be obtained quickly and accurately. Projecting the acupoint location information onto the body surface to be localized completes the acupoint localization, thereby improving the accuracy and efficiency of acupoint localization. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 A flowchart illustrating an acupoint location method provided in this application embodiment;

[0063] Figure 2A schematic diagram of a human body image marked with acupoints provided for an embodiment of this application;

[0064] Figure 3 A schematic diagram illustrating a signal acquisition location provided in an embodiment of this application;

[0065] Figure 4 A schematic diagram illustrating the acquisition of electroencephalogram (EEG) signals, provided as an embodiment of this application;

[0066] Figure 5 A topographic map of pain differences provided in an embodiment of this application;

[0067] Figure 6 This is a schematic diagram of an acupoint positioning device provided in an embodiment of this application;

[0068] Figure 7 A schematic diagram of a computer-readable medium provided for an embodiment of this application;

[0069] Figure 8 This is a schematic diagram of the hardware structure of a server provided in an embodiment of this application. Detailed Implementation

[0070] As described above, sensitization can manifest in various forms, such as heat sensitivity, pain sensitivity, electrical sensitivity, and shape sensitivity, and acupoint sensitization can be used to locate acupoints.

[0071] Traditional acupoint location methods mostly rely on the experience of traditional Chinese medicine practitioners or the subjective pain sensations of the test subjects. Currently, there are two main types of acupoint location methods based on modern technology:

[0072] The first method is based on the theory of meridians in the human body, which determines the absolute location of acupoints on the body and the relative positions between acupoints, thus mapping all locations onto the body for acupoint location. However, due to significant differences in body shape between individuals, it is impossible to accurately locate acupoints for every user, resulting in a low accuracy rate for acupoint location.

[0073] The second method involves applying electromagnetic stimulation to the user and testing the deviation between the user's actual electrophysiological data and theoretical electrophysiological data. If the actual electrophysiological data corresponding to a certain point on the user's body matches the theoretical electrophysiological data of the target acupoint, then that point is the target acupoint. However, since the theoretical electrophysiological data differs for different acupoints, it is necessary to adjust the theoretical electrophysiological data in real time when locating different acupoints, making the operation extremely cumbersome and resulting in low efficiency in acupoint location.

[0074] In view of this, this application discloses a method, apparatus, device, and medium for acupoint localization. The method includes: acquiring a user's real-time electroencephalogram (EEG) signal and an image of the body surface to be localized; inputting the real-time EEG signal and image into an acupoint localization model to obtain precise acupoint location information in the image; and projecting the acupoint location information onto the body surface to be localized to perform acupoint localization. Thus, by inputting the user's real-time EEG signal and an image of the body surface to be localized into the acupoint localization model, the location information of acupoints can be obtained quickly and accurately. After projecting the acupoint location information onto the body surface, acupoint localization can be completed, thereby improving the accuracy and efficiency of acupoint localization.

[0075] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0076] See Figure 1 The figure is a flowchart of an acupoint location method provided in an embodiment of this application, the method including:

[0077] S101: Acquire user image.

[0078] User images refer to images of the areas where users need to locate acupoints. For example, if a user wants to locate the Weicang and Geguan acupoints on their back, then the captured user image will be an image of the user's back.

[0079] In some specific implementations, user images can be captured using a binocular camera. A binocular camera utilizes bionic principles to obtain synchronously exposed user images through calibrated dual cameras. Compared to a regular monocular camera, using a binocular camera to capture user images can effectively obtain depth information for each pixel in the user image, helping to improve the accuracy of subsequent acupoint location.

[0080] It should be noted that the user images involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0081] S102: Align the user image with the human body image marked with the target acupoints to obtain the initial position of the target acupoints on the user image.

[0082] The initial position refers to the position after the target acupoint has been roughly located.

[0083] In some specific implementations, after acquiring the user's image, it is first necessary to obtain a 3D human body model marked with the target acupoints, and then obtain a 2D human body image marked with the target acupoints from it. See also... Figure 2 This figure is a schematic diagram of a human body image marked with acupoints, provided in an embodiment of this application. All acupoints on this human body image are marked based on the theory of human meridians. It can be understood that this human body image includes at least the target acupoints that the user needs to locate. For example, if the user wants to locate the Weicang and Geguan acupoints on the back, then the human body image must at least mark the Weicang and Geguan acupoints. It should be noted that this application does not limit the specific human body image and target acupoints.

[0084] Secondly, the coordinates of the target acupoint in the human body image are obtained through a circular detection algorithm. For example, the coordinates of the target acupoint can be two-dimensional coordinates (x, y), which represent the position of the target acupoint in the human body image.

[0085] Subsequently, the OpenPose algorithm can be used to identify reference points in user and human images. These reference points are points that can be accurately distinguished and quickly located, such as the right shoulder point, left shoulder point, and mid-hip point.

[0086] Finally, by aligning the reference points in the user image and the reference points in the human body image, the user image and the human body image are aligned, and the coordinates of the target acupoint in the human body image are affined onto the user image, thereby obtaining the initial position of the target acupoint on the user image.

[0087] S103: Acquire EEG signals from the initial location and its surrounding points.

[0088] Electroencephalogram (EEG) signals are the overall reflection of the electrophysiological activity of brain nerve tissue on the surface of the cerebral cortex. This application mainly studies resting EEG signals and pain EEG signals. Since the main response areas of pain EEG signals are located in the frontal, central, and parietal regions of the head, EEG signals from these regions can be collected. See also Figure 3 The figure is a schematic diagram of a signal acquisition location provided in an embodiment of this application. Electroencephalogram (EEG) signals can be acquired by placing electrodes at positions 1-8 in the figure and reference electrodes at positions A1 and A2 (earlobe positions).

[0089] See Figure 4This figure is a schematic diagram of acquiring electroencephalogram (EEG) signals according to an embodiment of this application. After obtaining the initial position of the target acupoint, the resting EEG signals of the initial position and its surrounding points can be acquired first. It can be understood that the surrounding points can be acquired by drawing a circle with the initial position as the center and a radius of 1 cm (i.e., the target distance), and taking one surrounding point every 45° (i.e., the target angle) on the circle, for a total of 8 surrounding points. Subsequently, by pressing on the initial position and its surrounding points, the pain EEG signals of the initial position and its surrounding points can be acquired.

[0090] It should be noted that moxibustion, acupuncture, or other treatments can also be applied to the initial location and surrounding points to obtain electroencephalogram (EEG) signals. This application does not limit the specific treatment methods.

[0091] S104: Preprocess and extract the frequency domain of the EEG signal to obtain EEG information.

[0092] After acquiring the EEG signals, one or more preprocessing operations are required, such as filtering, rereference, and artifact removal, to obtain the processed EEG signals. Subsequently, frequency domain extraction is performed on the processed EEG signals to obtain EEG information, which includes resting EEG information and pain EEG information.

[0093] In some specific implementations, bandpass filtering of 0.5-49 Hz (Hertz) can be applied to the resting EEG signal and the pain EEG signal respectively, and artifacts in the resting EEG signal and the pain EEG signal can be removed by independent component analysis algorithm to obtain a clean EEG signal, that is, the processed EEG signal.

[0094] Subsequently, frequency domain extraction is performed on the processed EEG signal based on one or more feature extraction methods, such as Fast Fourier Transform, Short-Time Fourier Transform, Wavelet Transform, and Hilbert Transform, to obtain EEG information.

[0095] S105: Based on resting EEG information and pain EEG information, classify the initial location and its surrounding points to obtain the locations of painful acupoints and non-painful acupoints.

[0096] See Figure 5 This figure is a topographic map of pain differences provided in an embodiment of this application. Within three frequency bands—delta (1–4 Hz), theta (4–8 Hz), and beta (13–30 Hz)—the position corresponding to the EEG information with the largest difference between pain and resting EEG information is selected as the pain acupoint location. All points in the initial position and its surrounding area, except for the pain acupoint location, are designated as non-pain acupoint locations.

[0097] S106: Train a machine learning model based on the locations of painful and non-painful acupoints to obtain an acupoint location model.

[0098] Based on the locations of painful and non-painful acupoints obtained in step S105, and the user image obtained in step S101, a support vector machine (SVM) model is trained to perform binary classification, resulting in an acupoint localization model. This model allows for the accurate acquisition of acupoint location information from the image.

[0099] Support Vector Machine (SVM) is a supervised learning model that performs well with small sample sizes. The basic idea of ​​SVM is to find the separating hyperplane that correctly partitions the training dataset and maximizes the geometric margin. Its main optimization parameters are the regularization coefficient C and the kernel function.

[0100] S107: By inputting the user's image to be located and the collected EEG signals into the acupoint location model, the acupoint location model outputs the acupoint location information in the image to be located.

[0101] At any time after the acupoint localization model is constructed, a target image of the user's body surface can be acquired. This target image is an image of the user's body surface to be located. By inputting this target image and the corresponding acquired EEG signals into the acupoint localization model constructed in step S106, the acupoint location information in the image can be obtained.

[0102] S108: Project the acupoint location information onto the user's body surface to perform acupoint positioning.

[0103] After obtaining the acupoint location information, the acupoint location can be projected onto the user's body surface to be located, thereby performing acupoint localization. It should be noted that the user's body surface is the same as the body surface in the user's localization image in step S107.

[0104] In summary, this application discloses an acupoint location method. After determining the coarse location of acupoints by combining the collected user images with the three-dimensional human body model, the method combines the pain sensitivity characteristics of acupoints with the recognition of pain intensity by EEG signals. The recognition of pain signals by EEG signals replaces the user's subjective evaluation of pain, and the precise location of acupoints is determined by utilizing the pain sensitivity characteristics of acupoints, thereby improving the accuracy and efficiency of acupoint location.

[0105] See Figure 6 The figure is a schematic diagram of an acupoint positioning device provided in an embodiment of this application. The acupoint positioning device 200 includes: an image acquisition module 201, a location acquisition module 202, and an acupoint positioning module 203.

[0106] Specifically, the image acquisition module 201 is used to acquire the user's real-time EEG signal and the image of the body surface to be located; the location acquisition module 202 is used to input the real-time EEG signal and the image into the acupoint location model to obtain the acupoint location information in the image; and the acupoint location module 203 is used to project the acupoint location information onto the body surface to be located in order to perform acupoint location.

[0107] In some specific implementations, the device for constructing the acupoint positioning model includes: a first positioning module, a second positioning module, a third positioning module, a fourth positioning module, and a fifth positioning module;

[0108] Specifically, the first positioning module is used to acquire user images, which include target acupoints; the second positioning module is used to acquire the initial position of the target acupoints on the user image; the third positioning module is used to acquire EEG signals of the initial position and surrounding points; the fourth positioning module is used to classify the initial position and surrounding points into painful acupoints and non-painful acupoints based on the EEG signals; and the fifth positioning module is used to train a machine learning model based on the user image, painful acupoints, and non-painful acupoints to construct an acupoint positioning model.

[0109] In some specific implementations, the second positioning module includes: a first positioning submodule, a second positioning submodule, a third positioning submodule, and a fourth positioning submodule;

[0110] Specifically, the first positioning submodule is used to acquire a human body image marked with the target acupoint, and the human body image is a two-dimensional image; the second positioning submodule is used to acquire the two-dimensional coordinates of the target acupoint in the human body image according to the circular detection algorithm; the third positioning submodule is used to acquire the reference points in the user image and the human body image; the fourth positioning submodule is used to affine the two-dimensional coordinates onto the user image by aligning the reference points in the user image and the reference points in the human body image, so as to obtain the initial position of the target acupoint on the user image.

[0111] In some specific implementations, the device for determining the surrounding points of the initial position includes: a surrounding positioning module;

[0112] Specifically, the peripheral positioning module is used to draw a circle with the initial position as the center and the target distance as the radius, and to determine the peripheral points of the initial position at each target angle on the circle.

[0113] In some specific implementations, the EEG signals include resting EEG signals and pain EEG signals. The fourth localization module includes: the fifth localization submodule, the sixth localization submodule, and the seventh localization submodule.

[0114] Specifically, the fifth positioning submodule is used to perform frequency domain extraction processing on the resting EEG signal and the pain EEG signal respectively to obtain resting EEG information and pain EEG information; the sixth positioning submodule is used to take the position corresponding to the positive difference between the pain EEG information and the resting EEG information, or the position corresponding to the maximum difference between the pain EEG information and the resting EEG information, as the pain acupoint position; the seventh positioning submodule is used to take the initial position and the surrounding points of the initial position, except for the pain acupoint position, as the non-pain acupoint position.

[0115] In some specific implementations, the fifth positioning submodule includes: a preprocessing module and a frequency domain extraction module;

[0116] Specifically, the preprocessing module is used to preprocess the resting EEG signal and the pain EEG signal respectively to obtain the processed resting EEG signal and the processed pain EEG signal. The preprocessing includes one or more of the following: filtering, rereference processing and artifact removal processing. The frequency domain extraction module is used to perform frequency domain extraction processing on the processed resting EEG signal and the processed pain EEG signal respectively to obtain resting EEG information and pain EEG information.

[0117] In summary, this application discloses an acupoint positioning device. After determining the coarse location of acupoints by combining the collected user images with a three-dimensional human body model, it combines the pain sensitivity characteristics of acupoints with the recognition of pain intensity by EEG signals. The recognition of pain signals by EEG signals replaces the user's subjective evaluation of pain, and the precise location of acupoints is determined by utilizing the pain sensitivity characteristics of acupoints, thereby improving the accuracy and efficiency of acupoint positioning.

[0118] See Figure 7 This figure is a schematic diagram of a computer-readable medium provided in an embodiment of this application. The computer-readable medium 300 stores a computer program 311, which, when executed by a processor, implements the above-described... Figure 1 The steps of the acupoint location method.

[0119] It should be noted that, in the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0120] It should be noted that the machine-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0121] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0122] See Figure 8 This figure is a schematic diagram of the hardware structure of a server provided in an embodiment of this application. The server 400 can vary considerably due to different configurations or performance, and may include one or more central processing units (CPUs) 422 (e.g., one or more processors) and memory 432, and one or more storage media 430 (e.g., one or more mass storage devices) for storing application programs 440 or data 444. The memory 432 and storage media 430 can be temporary or persistent storage. The program stored in the storage media 430 may include one or more modules (not shown in the figure), each module may include a series of instruction operations on the server. Furthermore, the CPU 422 may be configured to communicate with the storage media 430 and execute the series of instruction operations in the storage media 430 on the server 400.

[0123] Server 400 may also include one or more power supplies 426, one or more wired or wireless network interfaces 450, one or more input / output interfaces 458, and / or one or more operating systems 441, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0124] The steps performed by the acupoint location method in the above embodiments can be based on this. Figure 8 The server structure shown.

[0125] It should also be noted that, according to the embodiments of this application, the above... Figure 1 The process of acupoint location described in the flowchart can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing instructions for performing the above-described... Figure 1 The flowchart shows the program code for the method.

[0126] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

[0127] While several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of this application. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0128] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for locating acupoints, characterized in that, The method includes: Acquire the user's real-time EEG signals and images of the body surface to be located; The real-time EEG signal and the image are input into the acupoint location model to obtain the acupoint location information in the image. The method for constructing the acupoint location model includes: acquiring a user image, which includes target acupoints; aligning a human image pre-calibrated with the target acupoints with the reference point of the user image to obtain the initial position of the target acupoints on the user image; using the initial position as the center, acquiring EEG signals of the initial position and surrounding points, the EEG signals including resting EEG signals in a resting state and pain EEG signals when stimulated; and then, for the initial position... The resting EEG signal and the pain EEG signal of the surrounding points of the initial position are respectively processed by frequency domain extraction to obtain the resting EEG information and pain EEG information of the initial position and the surrounding points of the initial position; based on the difference between the resting EEG information and the pain EEG information of the initial position and the surrounding points of the initial position, the initial position and the surrounding points of the initial position are classified into painful acupoint locations and non-painful acupoint locations; using the user image as input and the painful acupoint locations and non-painful acupoint locations as output labels, a machine learning model is trained to construct an acupoint localization model; The acupoint location information is projected onto the body surface to be located in order to perform acupoint localization.

2. The method according to claim 1, characterized in that, The step of obtaining the initial position of the target acupoint on the user image includes: Obtain a human body image pre-calibrated with the target acupoints, wherein the human body image is a two-dimensional image; According to the circular detection algorithm, the two-dimensional coordinates of the target acupoint in the human body image are obtained; Obtain the reference points in the user image and the human body image; By aligning the reference point in the user image with the reference point in the human body image, the two-dimensional coordinates are affinely mapped onto the user image to obtain the initial position of the target acupoint on the user image.

3. The method according to claim 1, characterized in that, The method for determining the surrounding points of the initial position includes: Draw a circle with the initial position as the center and the target distance as the radius, and determine the surrounding points of the initial position on the circle at every target angle.

4. The method according to claim 1, characterized in that, The method classifies the initial location and its surrounding points into painful acupoint locations and non-painful acupoint locations based on the differences between resting EEG information and pain EEG information of the initial location and its surrounding points, including: The locations corresponding to the positive difference between the pain EEG information and the resting EEG information at the initial location and the surrounding points of the initial location, or the locations corresponding to the maximum difference between the pain EEG information and the resting EEG information, are designated as pain acupoint locations. The locations other than the painful acupoints are designated as non-painful acupoints among the initial location and the surrounding points.

5. The method according to claim 1, characterized in that, The frequency domain extraction processing of the resting EEG signal and the pain EEG signal at the initial position and the surrounding points includes: The resting EEG signal and the pain EEG signal at the initial position and the surrounding points of the initial position are preprocessed to obtain the processed resting EEG signal and the processed pain EEG signal at the initial position and the surrounding points of the initial position. The preprocessing includes one or more of filtering, rereference processing and artifact removal processing. Frequency domain extraction processing is performed on the processed resting EEG signal and the processed pain EEG signal at the initial position and the surrounding points of the initial position.

6. An acupoint positioning device, characterized in that, The device includes: an image acquisition module, a location acquisition module, and an acupoint positioning module; The image acquisition module is used to acquire the user's real-time electroencephalogram (EEG) signals and images of the body surface to be located; The location acquisition module is used to input the real-time EEG signal and the image into the acupoint positioning model to obtain the acupoint location information in the image; the acupoint positioning model construction device includes: a first positioning module, a second positioning module, a third positioning module, a fourth positioning module, and a fifth positioning module; the first positioning module is used to acquire a user image, the user image including target acupoints; the second positioning module is used to acquire the initial position of the target acupoints on the user image by aligning a human image pre-calibrated with the reference point of the user image; the third positioning module is used to acquire EEG signals of the initial position and surrounding points with the initial position as the center, the EEG signals including resting state... The system analyzes the resting EEG signal and the pain EEG signal when stimulated. The fourth positioning module performs frequency domain extraction processing on the resting EEG signal and the pain EEG signal at the initial position and its surrounding points to obtain resting EEG information and pain EEG information at the initial position and its surrounding points. Based on the differences between the resting EEG information and the pain EEG information at the initial position and its surrounding points, the initial position and its surrounding points are classified into painful acupoint locations and non-painful acupoint locations. The fifth positioning module uses the user image as input and the painful acupoint locations and non-painful acupoint locations as output labels to train a machine learning model to construct an acupoint positioning model. The acupoint positioning module is used to project the acupoint location information onto the body surface to be positioned in order to perform acupoint positioning.

7. An acupoint positioning device, characterized in that, include: Memory and processor; The memory is used to store programs; The processor is configured to execute the program to implement the steps of the method as described in any one of claims 1 to 5.

8. A computer storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images