Intelligent acupoint recognition projection method suitable for multiple poses and controller

Abstract

The invention discloses an intelligent acupoint recognition projection method suitable for multiple poses and a controller, which are applied to the field of acupoint recognition, and the method comprises the steps: obtaining health data of a user and a user image collected by a camera; determining a user posture according to the user image, wherein the user posture is used for representing the position and direction of the posture of the user in the three-dimensional space; determining a personalized health model of the user according to the health data and the pose of the user; determining an acupuncture point position list related to the health condition of the user according to the personalized health model; sending the acupuncture point position list to the terminal; and in response to the selection of the terminal for the target acupuncture point, projecting the acupuncture point mark of the target acupuncture point on the user body through the projector. The method has the advantages that the position of the acupuncture point projection is automatically adjusted and determined according to the actual posture of the user, it is ensured that the acupuncture points can be accurately recognized and positioned in different postures, the recommended acupuncture points are determined in combination with the health data of the user, and therefore the effect of personalized massage and acupuncture service is achieved.

Description

Technical Field

[0001] The present application relates to the field of acupoint recognition, and in particular to an acupoint intelligent recognition projection method and controller suitable for multiple postures. Background Art

[0002] In the field of human health, massage and acupuncture are common treatment methods. However, due to the differences in the human body, different people may have different needs and preferences. Therefore, in order to provide personalized massage and acupuncture services, acupoint recognition is required for the human body in different postures.

[0003] The intelligent acupoint recognition method is a method that uses artificial intelligence technology to identify and locate acupoints on the human body. This method uses cameras, sensors and other equipment to detect and analyze the posture information of the human body, determine the posture information of the human body in different postures, and compare and match this information with the standard human body model to determine the best massage or acupuncture position.

[0004] However, this method still has certain limitations. When users need to perform acupuncture and massage, they need guidance from doctors or experienced people, and cannot complete acupuncture and massage by themselves. Summary of the invention

[0005] The present application provides a method and device for intelligent acupoint recognition and projection suitable for multiple postures, which is used to automatically adjust and determine the position of acupoint projection according to the user's actual posture, ensure that acupoints can be accurately identified and located in different postures, and determine recommended acupoints in combination with the user's health data, thereby realizing personalized massage and acupuncture services.

[0006] In the first aspect, the present application provides an acupoint intelligent recognition and projection method suitable for multiple postures, which is applied to an AI controller in a system, and the system also includes a camera and a projector. The method includes: obtaining the user's health data and the user image captured by the camera; determining the user's posture based on the user image, and the user posture is used to represent the position and direction of the user's posture in three-dimensional space; determining the user's personalized health model based on the health data and the user posture; determining a list of acupoint locations related to the user's health status based on the personalized health model; sending the acupoint location list to a terminal; in response to the terminal's selection of a target acupoint, projecting the acupoint mark of the target acupoint onto the user through a projector.

[0007] In the above embodiment, the user's health data and the user image captured by the camera are obtained, and the user posture, that is, the position and direction of the user's posture in three-dimensional space, is determined based on the user image. Then, the user's personalized health model is determined based on the health data and the user's posture, and then the list of acupoint locations related to the user's health status is determined. Finally, the acupoint markings of the target acupoints are projected onto the user through a projector. According to the user's actual posture, the position of the acupoint projection is automatically adjusted and determined to ensure that the acupoints can be accurately identified and located in different postures, and the recommended acupoints are determined in combination with the user's health data, thereby realizing personalized massage and acupuncture services.

[0008] In combination with some embodiments of the first aspect, in some embodiments, determining a user posture based on a user image specifically includes: determining a user bounding box based on the user image, the user bounding box is used to represent the user position detected in the user image; detecting user key points in the user bounding box to obtain user key point coordinates, the user key points include specific body parts of the user; determining a user posture based on the user key point coordinates, the user posture is used to represent the position and direction of the user's posture in three-dimensional space.

[0009] In the above embodiment, by determining the user boundary box and detecting the user key points, the user's body position and key points are accurately captured, thereby accurately determining the user's posture.

[0010] In combination with some embodiments of the first aspect, in some embodiments, a personalized health model of a user is determined based on health data and user posture, specifically including: calculating the similarity between the user posture and the corresponding preset user postures in several preset user models; determining the preset user model corresponding to the preset user posture whose similarity exceeds a set threshold as the target user model; and associating the health data with the target user model to obtain a personalized health model.

[0011] In the above embodiment, based on the user's health data and posture information, the similarity between the user's posture and the corresponding preset user posture in the preset user model is calculated, and then the preset user model corresponding to the preset user posture whose similarity exceeds the set threshold is determined as the target user model. By associating the health data with the target user model, a personalized health model related to the user's posture and the user's health data is obtained, thereby realizing the identification and positioning of acupoints related to the user's posture and the user's health status.

[0012] In combination with some embodiments of the first aspect, in some embodiments, a list of acupoint locations related to the user's health status is determined based on a personalized health model, specifically including: predicting the user's health based on the personalized health model to obtain a health prediction result; determining the acupoints related to the user's health status based on the health prediction result; arranging the acupoints related to the user's health status in a preset order to obtain a list of acupoint locations.

[0013] In the above embodiment, the user's health is predicted according to the personalized health model to obtain the health prediction result, and the acupoints related to the user's health condition are determined according to the health prediction result. The relevant acupoints are arranged in a preset order to form an acupoint location list, so as to achieve targeted acupoint positioning of the user's health condition. This helps users to perform acupoint therapy more effectively, pay attention to acupoints related to their health condition, and improve treatment effects and personal health management levels.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of sending the acupoint location list to the terminal, the method also includes: in response to the terminal's shooting instruction for the user-specified location, sending the recommended acupoints at the user-specified location, location pictures of the recommended acupoints, and acupoint information of each recommended acupoint to the terminal, the acupoint information including the acupoint name, acupoint location, acupoint efficacy, and acupoint operation; in response to the terminal's selection of the recommended acupoints, displaying the acupoint information of the recommended acupoints on the terminal.

[0015] In the above embodiment, in response to the terminal's shooting instruction for the user's designated location, the location image and acupoint information of the recommended acupoint at the user's designated location are sent to the terminal. This helps the user to accurately find the recommended acupoints, understand the location and related information of the recommended acupoints, and correctly stimulate the acupoints. This interactive method improves the user's participation and the feasibility of acupoint therapy, thereby enhancing the effect of personalized health management.

[0016] In combination with some embodiments of the first aspect, in some embodiments, before the step of calculating the similarity between the user posture and the corresponding preset user postures in several preset user models, the method also includes: obtaining user three-dimensional data in different postures; determining a preset user posture model based on the user three-dimensional data in different postures; and associating the preset user posture model with the corresponding acupuncture point position to obtain the preset user model.

[0017] In the above embodiment, the user's three-dimensional data in different postures is obtained, and the preset user posture model is determined according to the user's three-dimensional data. The preset user model is obtained by associating with the acupoint position. It is convenient to match the user posture with the preset user posture model to obtain the preset user model, and associate it with the acupoint position to obtain the preset user model. In combination with some embodiments of the first aspect, in some embodiments, after the step of projecting the acupoint mark of the target acupoint onto the user through a projector in response to the terminal's selection of the target acupoint, the method also includes: determining the user posture change based on the user image; determining the acupoint position change based on the user posture change; and projecting the acupoint position change onto the user in real time through the projector.

[0018] In the above embodiment, the user's posture change is determined based on the user image, and the user's posture change is reflected in the acupoint position. The change of the acupoint position is projected on the user in real time through the projector, realizing real-time acupoint positioning and projection effect. In this way, the user can accurately understand his or her acupoint condition and massage effect, and improve the effect and experience of massage and acupuncture.

[0019] In a second aspect, an embodiment of the present application provides a controller, which includes: an acquisition module for acquiring a user's health data and a user image captured by a camera; a first determination module for determining a user's posture based on the user image, wherein the user posture is used to represent the position and direction of the user's posture in a three-dimensional space; a second determination module for determining a personalized health model of the user based on the health data and the user posture; a third determination module for determining a list of acupoint locations related to the user's health status based on the personalized health model; a sending module for sending the acupoint location list to a terminal; and a projection module for projecting the acupoint marking of the target acupoint onto the user through a projector in response to the terminal's selection of the target acupoint.

[0020] In a third aspect, an embodiment of the present application provides a controller, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the controller to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a fourth aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when the computer program product runs on a controller, enables the controller to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a controller, the controller executes the method described in the first aspect and any possible implementation method of the first aspect.

[0023] It is understandable that the controllers provided in the second and third aspects, the computer program product provided in the fourth aspect, and the computer storage medium provided in the fifth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. First, the present invention obtains the user's health data and the user image captured by the camera, and determines the user's posture based on the user image, thereby accurately positioning the position and direction of the user's posture in three-dimensional space. Compared with traditional manual massage and acupuncture, the present invention can more accurately locate the user's body parts, thereby effectively identifying the acupoint location of each user, and automatically adjusting and determining the position of the acupoint projection according to the user's actual posture, ensuring that the acupoints can be accurately identified and located in different postures, and combining the user's health data to determine the recommended acupoints, thereby realizing personalized massage and acupuncture services.

[0025] 2. Secondly, the present invention uses the user's health data and user posture to determine the user's personalized health model. By calculating the similarity between the user posture and the preset user posture corresponding to the preset user model, the preset user model corresponding to the preset user posture whose similarity exceeds the set threshold is determined as the target user model. The target model is associated with the health model to obtain a personalized health model, thereby accurately predicting the user's health status and determining the acupoint location. Compared with conventional massage and acupuncture methods, the present invention can better meet the personalized needs of users and provide more targeted acupoint treatment.

[0026] 3. In addition, the present invention also projects the target acupuncture points on the user in real time through a projector, realizing real-time tracking and projection of the changes in the user's acupuncture point positions. This real-time projection function enables the user to intuitively feel the location and operation of the acupuncture points during massage and acupuncture, thereby improving the treatment effect and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a method for intelligent acupoint recognition and projection applicable to multiple postures in an embodiment of the present application; Figure 2 It is another flowchart diagram of the acupoint intelligent recognition projection method applicable to multiple postures in an embodiment of the present application; Figure 3 This is a schematic diagram of a functional module structure of a controller in an embodiment of the present application; Figure 4 It is a schematic diagram of a physical device structure of a controller in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0031] In modern life, more and more people are concerned about health and comfort. Massage and acupuncture are popular as traditional health care methods. However, traditional massage and acupuncture have the following problems: 1) The operator's technical level and experience have a great impact on the efficacy; 2) It may be difficult to accurately control the acupoints during the operation; 3) Users cannot get the same effect at home. Therefore, a multi-position intelligent acupoint recognition projection method is needed to solve these problems.

[0032] In current technology, sensor- or camera-based systems may be used to track the user's body posture and provide guidance on acupoint locations. However, these systems have some drawbacks. For example, sensor systems may require users to wear devices, limiting their freedom and comfort; camera systems may be limited by light and angles, resulting in reduced accuracy. In addition, related technologies cannot provide personalized health models and cannot provide accurate acupoint locations based on the user's health status.

[0033] By adopting the intelligent acupoint recognition and projection method applicable to multiple postures in the embodiment of the present application, users can enjoy accurate acupoint massage at home. For example, a user named Xiao Ming uses the system for acupoint massage at home. He first provides his health data, such as blood pressure, heart rate, etc. Then, he lies flat and is photographed by a camera. The controller determines Xiao Ming's user posture by analyzing the user image and health data, and generates his personalized health model. According to the personalized health model, the controller determines a list of acupoint locations related to Xiao Ming's health status and sends it to the terminal. Xiao Ming can select the target acupoint and project the target acupoint on his body through a projector to perform accurate acupoint massage.

[0034] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of the intelligent acupoint recognition and projection method applicable to multiple postures in an embodiment of the present application.

[0035] S101, obtaining health data of the user and an image of the user captured by a camera; The controller establishes a connection with the sensor or device, and obtains the user's health data through various sensors or devices, such as smart watches, smart bracelets or health monitoring devices. The controller establishes a connection with the camera, and the camera captures an image of the user lying down, and transmits it to the controller as the user image.

[0036] S102, determining a user posture according to the user image, where the user posture is used to represent the position and direction of the user's posture in a three-dimensional space; First, the controller preprocesses the user image to remove background noise. Then, the controller uses computer vision technology, such as human pose estimation algorithm, to detect key points of the human body on the preprocessed user image. Key points usually include key joints such as head, neck, shoulder, elbow, wrist, hip, knee and ankle. Based on the detected key points, the controller uses camera geometry and 3D reconstruction technology to map the user's posture from image space to 3D space. The user's posture is obtained by calculating the relative positions and angles between joints.

[0037] If real-time updating of the user pose is required, the controller can consume a continuous stream of images and repeat the above steps at each time step to obtain the latest user pose.

[0038] Optionally, in general, determining the user's posture based on the user image can be achieved by the following methods: A user bounding box is determined based on the user image, and the user bounding box is used to represent the user position detected in the user image; user key points are detected in the user bounding box to obtain the coordinates of the user key points, and the user key points include specific body parts of the user; a user posture is determined based on the coordinates of the user key points, and the user posture is used to represent the position and direction of the user's posture in three-dimensional space.

[0039] The controller uses computer vision technology, such as object detection or human detection algorithms, to process the user image to determine the user's position in the image and obtain a user bounding box. Then, within the user bounding box, the controller uses a human pose estimation algorithm to detect the user's key points. The user's key points include specific body parts of the user, such as the head, neck, shoulders, elbows, wrists, hips, knees, and ankles. The human pose estimation algorithm can be based on a deep learning model or other computer vision technology. Next, the controller extracts the coordinate information of the user's key points based on the user's key points to obtain the user's key point coordinates. The user's key point coordinates are used to represent the position of the user's body parts in the image. Finally, the controller maps the user's key point coordinates from the image space to the three-dimensional space through three-dimensional reconstruction technology to determine the user's posture.

[0040] S103, determining a personalized health model of the user according to the health data and the user's posture; The controller stores a user posture model library, which includes a large number of preset user posture models. The user posture model is a posture model of different postures or activities when the user lies down. The controller uses computer vision technology, such as posture estimation algorithm, to detect and estimate the user posture. Then, the user posture is compared with the preset user posture model and the matching degree is calculated. Based on the matching degree, the controller selects the preset user posture model with the highest matching degree with the user posture as the current user posture model.

[0041] The controller processes and models health data using statistical analysis, machine learning, or deep learning methods to obtain features and patterns related to the user's health problems. Health data includes body indicators (such as heart rate, blood pressure, blood oxygen saturation, etc.), exercise data (such as steps, exercise time, calories consumed, etc.), sleep data, diet records, etc.

[0042] The controller combines the current user posture model and health data to build a personalized health model for the user, and uses machine learning techniques such as decision trees, support vector machines, neural networks, etc. to fuse the current user posture model and health data. By training and tuning the model, the association between the user posture, health data, and health problems is modeled, and a personalized health model for the user is generated.

[0043] S104, determining a list of acupuncture point locations related to the user's health status according to the personalized health model; The controller uses the personalized health model to predict the user's health status. The user's personalized health model can output the user's health score, health level, or the probability of a specific health problem.

[0044] According to the prediction results of the personalized health model, the controller maps specific health problems to acupoint locations based on preset association rules, medical research or traditional Chinese medicine theory, and determines a list of acupoint locations related to the user's health status.

[0045] Optionally, in general, determining a list of acupoint locations related to the user's health status according to the personalized health model can be implemented in the following ways: The user's health is predicted according to the personalized health model to obtain a health prediction result; the acupoints related to the user's health status are determined according to the health prediction result; the acupoints related to the user's health status are arranged in a preset order to obtain an acupoint location list.

[0046] The controller uses the personalized health model to predict the user's health data. Based on the input health data, the personalized health model outputs a health prediction result. The health prediction result reflects the user's current health status or existing health problems.

[0047] The controller maps specific health prediction results to corresponding acupoint locations based on medical research, TCM theory or other relevant knowledge. The controller determines the acupoints related to the user's health status based on the health prediction results of the personalized health model. The controller matches the health prediction results with the preset health prediction acupoint table to find the corresponding acupoint location.

[0048] The controller arranges the acupoints related to the user's health status in a preset order to obtain an acupoint location list. The preset order rule may be to sort the acupoints according to their importance, treatment priority or other factors.

[0049] S105, sending the acupuncture point location list to the terminal; The controller sends the acupuncture point location list to the terminal by establishing a communication connection with the terminal.

[0050] S106 . In response to the terminal selecting the target acupuncture point, projecting the acupuncture point mark of the target acupuncture point onto the user through a projector.

[0051] In order to accurately project the target acupuncture point on the user's body, the controller obtains the coordinate information of the target acupuncture point on the user's body, and then transmits the coordinate information of the target acupuncture point to the projector. The projector projects the target acupuncture point on the user's body according to the obtained coordinates of the target acupuncture point.

[0052] The following is a supplement to the scenario of this embodiment.

[0053] In addition to automatically adjusting and determining the position of acupoint projection according to the user's actual posture, ensuring that acupoints can be accurately identified and located in different postures, and combining the user's health data to determine recommended acupoints, thereby achieving personalized massage and acupuncture services, the controller can also monitor changes in user posture in real time, determine changes in acupoint position, and project acupoint position changes onto the user in real time.

[0054] After combining the above scenarios, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , which is another flow chart of the intelligent acupoint recognition and projection method applicable to multiple postures in an embodiment of the present application.

[0055] S201, obtaining three-dimensional data of the user in different positions and postures; The user's three-dimensional data in different postures is collected through preset sensors. The preset sensors include depth cameras (such as Microsoft Kinect), laser scanners or structured light sensors, etc., to capture the user's posture and body shape information. The controller obtains the user's three-dimensional data in different postures.

[0056] S202, determining a preset user posture model according to the three-dimensional data of the user in different postures; The controller stores a large number of preset user posture models in different postures, and different preset user posture models correspond to different three-dimensional data. The controller determines the preset user posture model that best matches the user three-dimensional data from the preset user posture models according to the user three-dimensional data in different postures.

[0057] For example, when the user lies flat with his legs slightly open and his hands pressed against the outside of his thighs, the user's three-dimensional data in this posture is obtained. This three-dimensional data is matched with the three-dimensional data of a large number of preset user posture models in different postures to determine a preset user posture model that best matches the user's three-dimensional data.

[0058] S203, associating the preset user posture model with the corresponding acupuncture point position to obtain a preset user model; In the preset user position model, the corresponding acupoint position is determined according to the relevant TCM acupoints. Since the preset user posture model is represented by three-dimensional data, the acupoint position corresponding to the preset user posture can also be represented by three-dimensional data. The preset user posture model is associated with the corresponding acupoint position to obtain the preset user model. The preset user model includes user posture and corresponding acupoint position information.

[0059] S204, calculating the similarity between the user posture and the corresponding preset user postures in a plurality of preset user models; Each preset user model corresponds to a preset user posture, and the controller calculates the similarity between the user posture and several preset user postures through a similarity measurement method, such as Euclidean distance, cosine similarity or correlation coefficient.

[0060] In the embodiment of the present application, the cosine similarity is used to calculate the similarity between the user posture and each preset user posture, and the user posture data and the preset user posture data are regarded as vectors, and the cosine similarity between them is calculated. The closer the similarity is to 1, the higher the similarity. The user posture data and the preset user posture data of each preset user model are measured for similarity to obtain a set of similarities.

[0061] S205, determining a preset user model corresponding to a preset user posture whose similarity exceeds a set threshold as a target user model; According to the similarity exceeding the set threshold, it is determined which preset user model is most similar to the user posture. The controller traverses all similarities and selects the preset user model whose similarity exceeds the set threshold as the target user model.

[0062] S206, associating the health data with the target user model to obtain a personalized health model; The controller determines which acupoints the user needs to massage to adjust and improve the body based on the health data and the corresponding functions of the acupoints. For example, if the user's health data indicates that the user often has headaches and has difficulty falling asleep, the corresponding acupoints may be Fengchi, Taichong and Taiyang; if the user's health data indicates that the user has irregular menstruation, menstrual dysmenorrhea and menopausal symptoms, the corresponding acupoint may be Sanyinjiao; if the user's health data indicates that the user has throat problems and often has dry mouth and thirst, the corresponding acupoint may be Renzhong... I will not list them all here.

[0063] The controller associates the health data with the target user model, determines the corresponding acupoint locations in the target user model, and obtains a personalized health model.

[0064] S207, in response to a shooting instruction of the terminal for the user-specified position, sending the recommended acupoints at the user-specified position, the position pictures of the recommended acupoints, and the acupoint information of each recommended acupoint to the terminal, wherein the acupoint information includes the acupoint name, acupoint location, acupoint efficacy, and acupoint operation; The terminal displays a picture of the user lying down, and the user can select any position as the user-specified position for shooting. The controller receives the shooting command sent by the terminal, and processes and analyzes the user image captured by the camera through image processing or computer vision technology to identify the acupuncture points in the user image and obtain the recommended acupuncture points at the user-specified position. The controller displays the recommended acupuncture points in the user image with red dots to obtain the location pictures of the recommended acupuncture points. The controller controls the recommended acupuncture points at the user-specified position, the location pictures of the recommended acupuncture points, and the acupuncture point information of each recommended acupuncture point to be sent to the terminal.

[0065] In the embodiment of the present application, the user lies flat, and in response to the terminal's shooting instruction of the user's upper body position, the user image is acquired, and the recommended acupoints in the user image, such as the Niliu acupoint and the Tanzhong acupoint, are determined. The Niliu acupoint and the Tanzhong acupoint are separately displayed in the user image with red dot marks. At the same time, the controller also sends the acupoint information of the Niliu acupoint and the Tanzhong acupoint to the terminal.

[0066] The acupuncture point information of Ni Chang is: Acupoint name: Niliu Point Acupoint location: The Niliu acupoint is located in the depression at the lower edge of the sternum, corresponding to the depression between the lower corners of the sternum. When locating it, you can find the lower edge of the sternum from the center of the sternum downward, and then press slightly inward at the depression at the lower edge to find the Niliu acupoint.

[0067] Acupoint efficacy: Niliu acupoint is an important acupoint for regulating chest qi. It has the effects of soothing the liver and relieving depression, soothing the liver and regulating qi, and relieving symptoms such as chest tightness, dyspnea, and chest pain. Niliu acupoint is also widely used to treat heart disease, asthma, stomach disease and other related diseases.

[0068] Acupoint manipulation: You can press the Niliu acupoint with your fingers or thumb. You can press the Niliu acupoint with moderate force until you feel a certain soreness. You can rotate your fingers or knead the acupoint appropriately when pressing. Each press lasts for 1-2 minutes. You can adjust the strength and time of the press appropriately according to your personal feelings. When pressing the Niliu acupoint, you should relax your body and keep breathing normally.

[0069] The acupuncture point information of Shan Zhong is: Acupoint name: Tanzhong point Acupoint location: Tanzhong acupoint is located on the midline of the sternum, corresponding to the depression between the fourth costal cartilage. To locate the acupoint, you can find the depression of the sternum upward from the center of the sternum, and then press down slightly on the depression to find the Tanzhong acupoint.

[0070] Acupoint efficacy: Tanzhong acupoint is an important acupoint for regulating heart function. It has the effects of calming the mind, regulating heart function, and relieving symptoms such as chest tightness, panic, and palpitations. Tanzhong acupoint is also often used to regulate emotions, relieve anxiety and insomnia.

[0071] Acupoint manipulation: You can press the Tanzhong point with your fingers or thumb. You can press the Tanzhong point with moderate force until you feel a certain soreness. You can rotate your fingers or knead them appropriately while pressing. Each press lasts for 1-2 minutes. You can adjust the strength and time of the press appropriately according to your personal feelings. When pressing the Tanzhong point, you should relax your body and keep breathing normally.

[0072] S208, in response to the terminal selecting the recommended acupoint, displaying the acupoint information of the recommended acupoint on the terminal; The user selects a recommended acupuncture point on the terminal, and the controller displays the acupuncture point information of the recommended acupuncture point on the terminal in response to the terminal's selection of the recommended acupuncture point.

[0073] S209, determining a user posture change according to the user image; The controller estimates the pose of the user image using algorithms and techniques such as target detection, pose estimation, or motion tracking, and detects changes in the user's pose by comparing the pose estimation results between consecutive user image frames and calculating the pose differences between adjacent frames. For example, the coordinate differences of key points are compared or the differences between rotation matrices or rotation vectors are calculated.

[0074] S210, determining a change in acupoint position according to a change in user posture; As the user's posture changes, the acupoint location also changes accordingly. The controller determines the target user model based on the user's posture, and the target user model is associated with the health data to obtain a personalized health model. Therefore, when the user's posture changes, the target user model also changes, the personalized health model also changes, and the obtained acupoint location also changes.

[0075] S211. Projecting the changes in the acupoint positions on the user in real time via a projector.

[0076] The controller is connected to the projector and adjusts the position, angle and projection range of the projector according to the user's body size and posture to ensure that the projection can accurately cover the user's body area. The controller projects the changes in the acupoint position on the user in real time. The following describes the controller in the embodiment of the present application from the perspective of the module. Figure 3 , which is a schematic diagram of a functional module structure of a controller in an embodiment of the present application.

[0077] The controller includes: An acquisition module 301 is used to acquire the user's health data and the user's image captured by the camera; A first determination module 302, configured to determine a user posture according to the user image, wherein the user posture is used to represent the position and direction of the user's posture in a three-dimensional space; A second determination module 303, for determining a personalized health model of the user according to the health data and the user's posture; A third determination module 304 is used to determine a list of acupoint locations related to the user's health status according to the personalized health model; A sending module 305 is used to send the acupoint location list to the terminal; The projection module 306 is used to project the acupoint mark of the target acupoint on the user through a projector in response to the terminal selecting the target acupoint.

[0078] In some embodiments, the first determining module 302 is specifically configured to: Determine a user bounding box according to the user image, where the user bounding box is used to represent a user position detected in the user image; Detect user key points in the user bounding box to obtain the coordinates of the user key points, where the user key points include specific body parts of the user; The user posture is determined according to the coordinates of the user's key points, and the user posture is used to represent the position and direction of the user's posture in three-dimensional space.

[0079] In some embodiments, the second determining module 303 is specifically used to: Calculating the similarity between the user's posture and corresponding preset user postures in a plurality of preset user models; Determine the preset user model corresponding to the preset user posture whose similarity exceeds the set threshold as the target user model; Associate the health data with the target user model to obtain a personalized health model.

[0080] In some embodiments, the third determination module 304 is specifically configured to: Predict health data based on personalized health models to obtain health prediction results; Determine acupuncture points related to the user's health status according to the health prediction results; The acupoints related to the user's health condition are arranged in a preset order to obtain an acupoint location list.

[0081] In some embodiments, the controller further includes a display module, specifically configured to: In response to a shooting instruction of a user-specified position by a terminal, a recommended acupoint at the user-specified position, a position picture of the recommended acupoint, and acupoint information of each recommended acupoint are sent to the terminal, where the acupoint information includes acupoint name, acupoint location, acupoint efficacy, and acupoint operation; In response to the terminal selecting the recommended acupoint, acupoint information of the recommended acupoint is displayed on the terminal.

[0082] In some embodiments, the controller further includes a fourth determining module, specifically configured to: Obtain the user's three-dimensional data in different postures; Determine a preset user posture model according to the three-dimensional data of the user in different postures; The preset user posture model is associated with the corresponding acupoint position to obtain a preset user model.

[0083] In some embodiments, the controller further includes an adjustment module, specifically configured to: Determine a user posture change based on the user image; Determine the change of acupoint position according to the change of user posture; The changes in acupoint positions are projected onto the user in real time through a projector.

[0084] The controller in the embodiment of the present application is described above from the perspective of modular functional entities. The controller in the embodiment of the present application is described below from the perspective of hardware processing. Figure 4 , which is a schematic diagram of a physical device structure of a controller in an embodiment of the present application.

[0085] It should be noted that Figure 4 The structure of the controller shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0086] like Figure 4 As shown, the controller includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In RAM 403, various programs and data required for system operation are also stored. CPU 401, ROM 402 and RAM 403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0087] The following components are connected to the I / O interface 405: an input section 406 including a camera, etc.; an output section 407 including a liquid crystal display (LCD) and a microphone, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0088] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the present invention are performed.

[0089] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0091] Specifically, the controller of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the intelligent acupoint recognition and projection method applicable to multiple postures provided in the above embodiment is implemented.

[0092] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the controller described in the above embodiment; or may exist independently without being assembled into the controller. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the controller, the controller implements the method provided in the above embodiment.

[0093] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0094] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0095] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0096] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for intelligent acupoint recognition projection suitable for multiple postures, characterized in that: An AI controller is applied to a system, wherein the system further includes a camera and a projector, and the method includes: Acquiring health data of the user and an image of the user captured by the camera; Determine a user posture according to the user image, wherein the user posture is used to represent the position and direction of the user's posture in a three-dimensional space; Determining a personalized health model of the user according to the health data and the user posture; Determining a list of acupuncture point locations related to the user's health status according to the personalized health model; Sending the acupuncture point location list to a terminal; In response to the terminal selecting a target acupuncture point, the acupuncture point mark of the target acupuncture point is projected onto the user through the projector.

2. The method according to claim 1, characterized in that Determining the user posture according to the user image specifically includes: determining a user bounding box according to the user image, wherein the user bounding box is used to represent a user position detected in the user image; Detecting user key points in the user boundary box to obtain coordinates of the user key points, wherein the user key points include specific body parts of the user; The user posture is determined according to the coordinates of the user key points, and the user posture is used to represent the position and direction of the user's posture in the three-dimensional space.

3. The method according to claim 1, characterized in that Determining the personalized health model of the user according to the health data and the user posture specifically includes: Calculating the similarity between the user posture and corresponding preset user postures in a plurality of preset user models; Determine the preset user model corresponding to the preset user posture whose similarity exceeds the set threshold as the target user model; The health data is associated with the target user model to obtain the personalized health model.

4. The method according to claim 1, characterized in that Determining a list of acupoint locations related to the user's health status according to the personalized health model specifically includes: Predicting the health data according to the personalized health model to obtain a health prediction result; Determining acupuncture points related to the user's health status according to the health prediction result; The acupoints related to the user's health condition are arranged in a preset order to obtain the acupoint location list.

5. The method according to claim 1, characterized in that After the step of sending the acupuncture point location list to the terminal, the method further includes: In response to a shooting instruction of a user-specified position by a terminal, a recommended acupoint of the user-specified position, a position picture of the recommended acupoint, and acupoint information of each recommended acupoint are sent to the terminal, wherein the acupoint information includes acupoint name, acupoint location, acupoint efficacy, and acupoint operation; In response to the terminal selecting the recommended acupoint, the acupoint information of the recommended acupoint is displayed on the terminal.

6. The method according to claim 3, characterized in that Before the step of calculating the similarity between the user posture and corresponding preset user postures in the plurality of preset user models, the method further comprises: Obtain the user's three-dimensional data in different postures; Determine a preset user posture model according to the three-dimensional data of the user in different postures; The preset user posture model is associated with the corresponding acupuncture point position to obtain a preset user model.

7. The method according to claim 1, characterized in that After the step of projecting the target acupuncture point on the user's body by the projector in response to the terminal selecting the target acupuncture point, the method further includes: Determining a user posture change according to the user image; Determining acupoint position changes according to the user's posture changes; The changes in the acupoint positions are projected onto the user in real time by the projector.

8. A controller, characterized in that: include: An acquisition module, used to acquire the user's health data and the user's image captured by the camera; A first determination module, configured to determine a user posture according to the user image, wherein the user posture is used to represent a position and direction of the user's posture in a three-dimensional space; A second determination module, configured to determine a personalized health model of the user according to the health data and the user posture; A third determination module is used to determine a list of acupoint locations related to the user's health status according to the personalized health model; A sending module, used for sending the acupoint location list to a terminal; The projection module is used for projecting the acupoint mark of the target acupoint on the user through a projector in response to the terminal selecting the target acupoint.

9. A controller, characterized in that: include: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the controller to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a controller, the controller is caused to execute the method according to any one of claims 1 to 7.

Images