Ear periphery massage method and device applied to ear periphery massage device

Abstract

The embodiment of the invention discloses an ear periphery massage method and device applied to an ear periphery massage device. A specific embodiment of the method comprises the following steps: collecting a head image sequence; performing three-dimensional head reconstruction according to the head image sequence; positioning acupuncture points around ears of the three-dimensional head model to obtain an acupuncture point information set; in response to determining that the to-be-massaged object has worn the ear circumference massage device, collecting a target image; according to the target image, determining a wearing state corresponding to the ear periphery massage device; in response to the wearing state, representing that the wearing angle needs to be adjusted, and prompting the to-be-massaged object to adjust the wearing angle; responding to the wearing state characterization that the wearing angle does not need to be adjusted, and controlling a head fixing band included in the ear periphery massage device to fix the head; and in response to completion of head fixation, controlling a matrix type micro air bag included in the ear circumference massage device, and performing ear circumference massage on the to-be-massaged object according to the acupuncture point information set. According to the embodiment, the massage treatment effect is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to a method and device for massaging the peri-auricular area applied to a peri-auricular area massage device. Background Art

[0002] Chronic fatigue syndrome is a disease characterized by persistent or recurrent fatigue of more than 6 months for unknown reasons, involving multiple systems, and common accompanying symptoms include memory loss, headache, joint pain, sleep disorders, depression and other somatic and neuropsychiatric symptoms. Depression, anxiety, and sleep disorders are currently mental and emotional diseases with a high incidence rate, often accompanied by symptoms such as headache and cognitive dysfunction. Currently in the field of traditional Chinese medicine, treatments for neuropsychiatric diseases such as chronic fatigue syndrome, depression, anxiety, and sleep disorders are usually carried out using methods such as cognitive behavioral therapy, acupuncture, scraping, and auricular acupoint pressing. The above-mentioned treatment methods rely on manual labor, are inefficient, and are difficult to ensure standardization and continuity. The present invention solves the problem of dependence on manual labor and guarantees continuity and standardization.

[0003] In traditional Chinese medicine theory, the head is the seat of intelligence, and the essence of the five internal organs is all poured into the head and face. Massaging local acupoints and meridians through the ear massage device can not only regulate the local gallbladder meridian and triple burner meridian qi and blood, dredge the gallbladder meridian and triple burner meridian qi, play the role of promoting qi and relieving depression, improve the fatigue symptoms and emotional disorders of neuropsychiatric diseases, but also relieve headaches, sleep disorders and other discomfort symptoms by relaxing the muscles and fascia of the head.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure provide a peri-auricular massage method and a peri-auricular massage device applied to a peri-auricular massage device to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide an ear periarthritis massage method applied to an ear periarthritis massage device, the method comprising: acquiring a head image sequence, wherein the head images in the head image sequence are images of the head of an object to be massaged acquired at different angles; performing three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged; locating ear periarthritis acupoints on the three-dimensional head model to obtain an acupoint information set, wherein the acupoint information in the acupoint information set includes: acupoint type and acupoint location; in response to determining that the object to be massaged has worn the ear periarthritis massage device, acquiring a target image, wherein the The target image includes the face of the object to be massaged and a front view of the above-mentioned peri-auricular massage device; based on the above-mentioned target image, the wearing state corresponding to the above-mentioned peri-auricular massage device is determined; in response to the above-mentioned wearing state indicating that the wearing angle needs to be adjusted, the above-mentioned object to be massaged is prompted to adjust the wearing angle; in response to the above-mentioned wearing state indicating that the wearing angle does not need to be adjusted, the head fixing belt included in the above-mentioned peri-auricular massage device is controlled to fix the head; in response to the head fixation being completed, the matrix micro-airbags included in the above-mentioned peri-auricular massage device are controlled to perform peri-auricular massage on the above-mentioned object to be massaged according to the above-mentioned acupoint information set, wherein the above-mentioned matrix micro-airbags are embedded in the inner side of the above-mentioned peri-auricular massage device.

[0008] In a second aspect, some embodiments of the present disclosure provide an ear periocular massage device for use in an ear periocular massage device, the device comprising: a first acquisition unit, configured to acquire a head image sequence, wherein the head images in the head image sequence are images of the head of an object to be massaged acquired at different angles; a three-dimensional head reconstruction unit, configured to perform three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged; an ear periocular acupoint positioning unit, configured to perform ear periocular acupoint positioning on the three-dimensional head model to obtain an acupoint information set, wherein the acupoint information in the acupoint information set includes: acupoint type and acupoint position; a second acquisition unit, configured to acquire a target image in response to determining that the object to be massaged has worn the ear periocular massage device, wherein The target image includes the face of the object to be massaged and a front view of the auricular massage device; a determining unit is configured to determine the corresponding wearing state of the auricular massage device according to the target image; a prompting unit is configured to prompt the object to be massaged to adjust the wearing angle in response to the wearing state indicating that the wearing angle needs to be adjusted; a first control unit is configured to control the head fixing belt included in the auricular massage device to fix the head in response to the wearing state indicating that the wearing angle does not need to be adjusted; a second control unit is configured to control the matrix micro airbags included in the auricular massage device to perform auricular massage on the object to be massaged according to the acupoint information set in response to the completion of head fixation, wherein the matrix micro airbags are embedded in the inner side of the auricular massage device.

[0009] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the ear massage method applied to the ear massage device of some embodiments of the present disclosure, the massage efficiency, standardization and sustainability are improved. Specifically, the manual massage treatment method has low massage efficiency, and at the same time, different massagers have different massage methods and techniques, which makes it difficult to ensure the standardization of massage. In addition, the manual massage method often requires the object to be massaged to go to a specific place (such as the rehabilitation department of a hospital, etc.) for massage treatment, so it is difficult to make the object to be massaged undergo massage treatment at any time, and thus it is difficult to ensure the sustainability of massage treatment. Based on this, the ear massage method applied to the ear massage device of some embodiments of the present disclosure, first, collects a head image sequence, wherein the head image in the head image sequence is an image of the head of the object to be massaged collected at different angles. Secondly, a three-dimensional head reconstruction is performed according to the head image sequence to generate a three-dimensional head model for the object to be massaged. The head model of the object to be massaged with different head shapes and sizes is established by combining the images. Next, the acupuncture points around the ear are located on the three-dimensional head model to obtain an acupuncture point information set, wherein the acupuncture point information in the acupuncture point information set includes: acupuncture point type and acupuncture point position. In practice, due to the different head shapes and head sizes of different objects to be massaged, the acupuncture points around the ear for different objects to be massaged are located by combining the three-dimensional head model. Further, in response to determining that the object to be massaged has worn the acupuncture point massage device, a target image is collected, wherein the target image includes the face of the object to be massaged and the front view of the acupuncture point massage device. Next, according to the target image, the wearing state corresponding to the acupuncture point massage device is determined. In this way, it is judged whether the object to be massaged is suitable to wear the acupuncture point massage device to avoid affecting the massage treatment effect due to inappropriateness. In addition, in response to the wearing state indicating that the wearing angle needs to be adjusted, the object to be massaged is prompted to adjust the wearing angle. In addition, in response to the wearing state indicating that the wearing angle does not need to be adjusted, the head fixing belt included in the acupuncture point massage device is controlled to fix the head. The head is fixed by the head fixing belt, so that the acupuncture point massage device can be firmly fixed on the head of the object to be massaged. Finally, in response to the head being fixed, the matrix micro-airbags included in the above-mentioned peri-auricular massage device are controlled to perform peri-auricular massage on the above-mentioned object to be massaged according to the above-mentioned acupoint information set, wherein the above-mentioned matrix micro-airbags are embedded in the inner side of the above-mentioned peri-auricular massage device. Compared with the traditional massage method such as hard massage head massage, the peri-auricular massage performed by the matrix micro-airbags is more in line with the skin surface, and the matrix design massage is more accurate, which greatly improves the effect of massage therapy. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flow chart of some embodiments of the periauricular massage method applied to the periauricular massage device according to the present disclosure; Figure 2 It is a schematic diagram of the acquisition process of the head image sequence; Figure 3 is a schematic diagram of the process of determining the first acupuncture point information; Figure 4 It is a schematic diagram of the process of determining the length of the upper longitudinal boundary and the length of the lower longitudinal boundary; Figure 5 is a schematic structural diagram of some embodiments of the peri-auricular massage device applied to the peri-auricular massage device according to the present disclosure; Figure 6 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0015] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0017] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0020] refer to Figure 1 , shows a process 100 of some embodiments of the periauricular massage method applied to the periauricular massage device according to the present disclosure. The periauricular massage method applied to the periauricular massage device comprises the following steps: Step 101: Acquire a head image sequence.

[0021] In some embodiments, the execution subject (e.g., computing device) of the peri-auricular massage method applied to the peri-auricular massage device can collect a head image sequence. The head images in the head image sequence are images of the head of the object to be massaged collected at different angles. In practice, the computing device can be a mobile device bound to the peri-auricular massage device through an account. Specifically, the computing device can be a mobile device including a camera and data processing capabilities. For example, a mobile phone.

[0022] As an example, the execution subject may guide the object to be massaged to rotate its head, so as to collect images of the head of the object to be massaged at different angles. Figure 2 The schematic diagram of the acquisition process of the head image sequence shown in the figure, wherein the computing device 201 can acquire the head image of the object to be massaged 202 through the front camera to obtain the head image sequence. The screen of the computing device 201 can display the acquired head image in real time, and display the prompt "Please rotate your head clockwise" for guiding the object to be massaged 202 to rotate its head. In addition, the prompt can also be "Please shake your head up and down".

[0023] It should be noted that the computing device 201 can be hardware or software. When the computing device is hardware, it can be implemented as a single mobile terminal device (e.g., a mobile phone). When the computing device is software, it can be installed in the hardware devices listed above. It can be implemented as a single software or software module. No specific limitation is made here.

[0024] Step 102: Perform three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged.

[0025] In some embodiments, the execution subject may perform three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged. The three-dimensional head model is a three-dimensional modeling model of the head of the object to be massaged. In practice, the execution subject may perform three-dimensional head reconstruction according to the head image sequence through the DeepMVS model to generate a three-dimensional head model for the object to be massaged. The DeepMVS model is a deep convolutional neural network that takes images collected from multiple perspectives as input to output a three-dimensional model.

[0026] In some optional implementations of some embodiments, the execution subject performs three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged, including: In the first step, edge feature points are extracted from each head image in the head image sequence to generate an image edge information group.

[0027] Among them, the image edge information group includes 4 image edge information. The image edge information corresponds to the image edge of the above-mentioned head image. The image edge information in the above-mentioned image edge information group includes: an edge feature point feature group. In practice, since each head image contains 4 image edges, in order to realize the splicing of the head images in the head image sequence, it is necessary to extract edge feature points for the four image edges of each head image respectively to obtain the image edge information group. Specifically, the above-mentioned execution subject can extract edge feature points of the head image through the SURF (Speeded Up Robust Features) algorithm to generate an image edge information group. In practice, since it is only necessary to extract feature points from the image edge of the head image, the extraction of edge feature points can be performed within a preset extraction area. By presetting the area size of the extraction area, the amount of data processing can be reduced, thereby further improving the extraction speed.

[0028] In the second step, a head image is randomly selected from the above head image sequence as a reference head image.

[0029] As an example, the head image sequence may include: head image A, head image B, head image C, head image D, head image E, and head image F. In practice, the head images A to F may be images of the head of the object to be massaged, collected at different angles. Among them, head image D may be selected as the reference head image.

[0030] In the third step, the head image sequence excluding the reference head image is used as a candidate head image sequence.

[0031] As an example, the candidate head image sequence may include: (candidate) head image A, (candidate) head image B, (candidate) head image C, (candidate) head image D, (candidate) head image E, and (candidate) head image F.

[0032] Step 4: Based on the reference head image and the candidate head image sequence, perform the following image stitching steps: Sub-step 1: Take the candidate head image at the first position from the candidate head image sequence as the head image to be stitched.

[0033] In practice, the candidate head image sequence is an ordered image sequence, and specifically the candidate head image sequence can be stored in a stack. Since the stack has a first-in-first-out feature, the first candidate head image can be taken from the candidate head image sequence as the head image to be stitched.

[0034] As an example, the head image to be stitched may be a (candidate) head image A.

[0035] Sub-step 2: Determine an edge matching degree group according to the image edge information group corresponding to the head image to be stitched and the image edge information group corresponding to the reference head image.

[0036] The edge matching degree group characterizes the matching degree between the candidate head image and the image edge of the reference head image at the four image edges. In practice, each head image includes four image edges, and there is an image edge between two head images that can be used for splicing between images. Since the head image to be spliced ​​includes four image edges, and the reference head image includes four image edges, by calculating the edge matching degree between the image edges at most 16 times, it can be determined whether there is an image edge between the head image to be spliced ​​and the reference head image that can be used for splicing between images. Specifically, since the image edge information includes the edge feature point feature group, the above-mentioned execution subject can use the method of calculating the feature similarity between the edge feature point features to obtain the edge matching degree when calculating the edge matching degree between the two image edges. The edge matching degree group can be stored in the form of a 4×4 matrix.

[0037] Sub-step 3: In response to the presence of an edge matching degree satisfying the matching condition in the edge matching degree group, the head image to be stitched is stitched with the reference head image along the image edge corresponding to the edge matching degree satisfying the matching condition to obtain an updated reference head image.

[0038] The above matching condition is: the edge matching degree is greater than a preset edge matching degree.

[0039] Sub-step 4: In response to the presence of an edge matching degree that satisfies the matching condition in the edge matching degree group, and the candidate head image sequence excluding the head image to be spliced ​​is empty, a three-dimensional head reconstruction is performed based on the updated reference head image and the three-dimensional head reconstruction model to generate a three-dimensional head model for the above-mentioned object to be massaged.

[0040] The 3D head reconstruction model takes the updated reference head image as input. The 3D head reconstruction model includes: an image encoder, an image to 3D plane decoder and a neural radiance field network. The image encoder is used to extract the global image features and local image features of the updated reference head image. The image to 3D plane decoder is used to decode the global image features and local image features into NeRF representations in a 3D scene. The neural radiance field network is used to combine the NeRF representations in the 3D scene for volume rendering to obtain a 3D head model.

[0041] In the fifth step, in response to the absence of an edge matching degree that meets the matching condition in the edge matching degree group, the head image to be stitched is placed as a candidate head image at the end of the candidate head image sequence to obtain an updated candidate head image sequence as the candidate head image sequence; the updated reference head image is used as the reference head image, and the above image stitching step is performed again.

[0042] Step 103: locate the acupoints around the ears on the three-dimensional head model to obtain an acupoint information set.

[0043] In some embodiments, the above-mentioned execution subject can locate the acupoints around the ears of the three-dimensional head model to obtain an acupoint information set. Among them, the acupoint information in the acupoint information set includes: acupoint type and acupoint location. Acupoint types include but are not limited to: Fengchi point, Chengling point, Toulinqi point, Yangbai point, Tianchong point, Xuanluo point, Shangguan point, Tongziliao point. The acupoint location represents the position coordinates of the acupoint. In practice, a model such as YOLO (You Only Look Once) can be used to locate the acupoints around the ears of the three-dimensional head model to obtain an acupoint information set. Among them, considering that the input of the YOLO model is an image, the images of the three-dimensional head model projected onto different projection surfaces can be used as the input of the YOLO model to obtain the acupoint information set.

[0044] In some optional implementations of some embodiments, the execution subject locates acupoints around the ear on the three-dimensional head model to obtain an acupoint information set, including: The first step is to project the above three-dimensional head model to a frontal perspective to obtain a frontal perspective image.

[0045] The second step is to locate facial organs in the above-mentioned frontal view image to obtain a first organ information set, wherein the first organ information in the above-mentioned first organ information set includes: organ type and organ position.

[0046] In order to improve the positioning speed, a one-stage positioning model can be used to locate the facial organs in the above-mentioned frontal view image to obtain the first organ information set. The one-stage positioning model can adopt the SSD (Single Shot MultiBox Detector) model. Specifically, the one-stage positioning model is trained in a supervised training method, that is, the training samples are frontal view images, and the training labels are the organ positions and corresponding organ types.

[0047] The third step is to determine the central axis plane based on the first organ information set.

[0048] Among them, since facial organs, such as eyes and ears, are symmetrical, the central axis can be determined according to the symmetry characteristics of the symmetrical facial organs. Among them, the central axis is the central axis of the two-dimensional coordinate system where the front view image is located. When converted to the three-dimensional coordinate system where the three-dimensional head model is located, the central axis is correspondingly converted to the central axis plane.

[0049] The fourth step is to symmetrically segment the three-dimensional head model along the median axis to obtain a segmented three-dimensional head model.

[0050] The segmented three-dimensional head model is a half three-dimensional head model with the medial axis plane as the segmentation plane.

[0051] In the fifth step, the segmented three-dimensional head model is projected to a top-down perspective and a left-side perspective to obtain a top-down perspective image and a left-side perspective image.

[0052] In practice, the reason why the images collected from the top view and left view in the head image sequence are not directly selected as the top view image and the left view image is that the collected head image includes not only the head shape and the head size, but also the hair, hair color and other information. However, when locating acupoints, the hair, hair color and other information are not very helpful for acupoint locating, and will also increase the amount of data processing. The top view image and the left view image obtained by the three-dimensional head model after segmentation in the top view and the left view, because the three-dimensional head model only contains the features such as the head shape and the head size, and after projection, the amount of data processing is greatly reduced.

[0053] The sixth step is to perform acupoint positioning on the top-view image and the left-view image to determine the first acupoint information and obtain the first acupoint information set.

[0054] As an example, take the left view image as an example, see Figure 3As shown in the schematic diagram of the process of determining the first acupoint information, first, the execution subject can evenly divide the left-view image into K acupoint regions of interest. Figure 3 The left view image is divided into 35 acupoint regions of interest, which are distributed in a 5×7 matrix. Secondly, for each of the K acupoint regions of interest, the acupoint region of interest is organ-localized using the one-stage localization model. Among them, the acupoint region of interest 301 includes the ear organ.

[0055] Next, the acupoint region of interest containing organs among the K acupoint regions of interest is used as the benchmark region of interest. Among them, the acupoint region of interest 301 can be used as the benchmark region of interest. Then, the distance vector between the K acupoint regions of interest and the benchmark region of interest is determined. Secondly, through multiple classifiers, whether the region of interest contains acupoints and acupoint types is determined according to the distance vector. When contained, the location of the acupoints contained in the region of interest is obtained according to the distance vector and the location of the benchmark region of interest. In this way, the first acupoint information is obtained. Among them, the upper left corner acupoint region of interest is used as the area where the origin is located, so as to obtain the coordinate values ​​corresponding to the K acupoint regions of interest, and the distance vector between every 2 acupoint regions of interest is calculated by the coordinate values. Figure 3 Take the acupoint region of interest 302 in the example, where the acupoint region of interest 302 includes Fengchi acupoint. Since the distance vector can be decomposed into a horizontal distance vector and a vertical distance vector, and the horizontal distance vector, the vertical distance vector and the distance vector can be combined to determine the relative direction angle between the acupoint region of interest 301 (reference region of interest) and the acupoint region of interest 302, the multi-classifier takes the vertical distance vector, the horizontal distance vector and the relative azimuth as input to classify the acupoint type corresponding to the acupoint region of interest 302. In practice, in the training stage of the multi-classifier, a supervised method is used for training. The training samples are the vertical distance vector, the horizontal distance vector and the relative azimuth corresponding to the acupoint region of interest and the reference region of interest, and the sample label is the acupoint type corresponding to the acupoint region of interest, so as to construct a positive sample. The sample label of the negative sample is that it does not contain an acupoint. Specifically, the vertical distance vector, the horizontal distance vector, the ratio of the relative azimuth to 90 degrees are spliced ​​as the input of the multi-classifier. The relative azimuth is normalized by the ratio of the relative azimuth to 90 degrees.

[0056] The seventh step is to determine symmetrical acupoints along the above-mentioned central axis plane based on the above-mentioned first acupoint information set to obtain the second acupoint information set.

[0057] In practice, since acupoints are often symmetrical, symmetrical mapping can be performed along the median axis according to the first acupoint information set to obtain acupoint information on the left and right sides and the top of the head of the three-dimensional head model.

[0058] In the eighth step, the first acupoint information set and the second acupoint information set are determined as the acupoint information set.

[0059] Step 104 : In response to determining that the object to be massaged has worn the peri-auricular massage device, a target image is acquired.

[0060] In some embodiments, in response to determining that the object to be massaged has worn the peri-ear massage device, the execution subject may capture a target image. In practice, after the object to be massaged wears the peri-ear massage device, the execution subject may prompt the user to capture the target image, so that the object to be massaged captures the target image through the execution subject. The target image includes the face of the object to be massaged and a front view of the peri-ear massage device. That is, the target image is a front view of the face of the object to be massaged when wearing the peri-ear massage device. Since the peri-ear massage device is difficult to guarantee a massage effect when worn improperly, it is necessary to guide the object to be massaged to adjust the wearing angle of the peri-ear massage device in combination with the target image.

[0061] Step 105, determining the corresponding wearing state of the peri-auricular massage device according to the target image.

[0062] In some embodiments, the execution entity may determine the corresponding wearing state of the peri-auricular massage device according to the target image.

[0063] In some optional implementations of some embodiments, the execution subject determines the wearing state corresponding to the ear massage device according to the target image, including: The first step is to convert the above target image into a grayscale image.

[0064] The second step is to perform edge detection on the grayscale image through an edge detection model to obtain an edge image.

[0065] The edge image is a grayscale image with edges marked. The edge detection model may use a lightweight UHNet model. The UHNet model is a lightweight edge detection model with the advantages of a small number of parameters, fast calculation speed, and low training cost.

[0066] The third step is to perform edge filtering on the edge image to determine candidate edges and obtain a candidate edge set.

[0067] In practice, the execution entity may filter the edges in the edge image whose corresponding edge inclination is greater than a preset inclination, and take the edges whose corresponding edge inclination is less than or equal to the preset inclination as candidate edges to obtain a candidate edge set.

[0068] The fourth step is to determine the edge confidence corresponding to each candidate edge in the above candidate edge set.

[0069] Among them, the edge confidence characterizes the confidence that the candidate edge is the edge of the above-mentioned peri-ear massage device. In practice, in order to reduce the amount of data processing, the local image where the candidate edge is located is used as input, and the edge confidence and edge type are determined by a feature pyramid network composed of 3 layers of serially connected convolutional neural networks and a binary classifier. The classification results of the binary classifier include: the candidate edge is the edge of the peri-ear massage device and the candidate edge is not the edge of the peri-ear massage device, and the classification results of the binary classifier are all correspondingly set with confidence.

[0070] The fifth step is to select candidate edges that meet the screening conditions from the above candidate edge set as target edges.

[0071] The above screening condition is: the edge confidence corresponding to the candidate edge is the largest. Specifically, the screening condition also includes: the classification result corresponding to the candidate edge indicates that the candidate edge is the edge of the peri-ear massage device.

[0072] The sixth step is to determine the edge inclination of the target edge.

[0073] In practice, first, the execution subject may uniformly sample edge points of the target edge to obtain an edge point sequence. Then, a straight line is fitted according to the edge point sequence. Then, the angle between the fitted straight line and the horizontal line is taken as the edge inclination.

[0074] In a seventh step, in response to the difference between the edge inclination and the preset edge inclination being greater than the preset difference, a wearing state indicating that a wearing angle adjustment is required is generated.

[0075] In the eighth step, in response to the difference between the edge inclination and the preset edge inclination being less than or equal to the preset difference, generating a wearing state indicating that no wearing angle adjustment is required.

[0076] Step 106 , in response to the wearing state indicating that the wearing angle needs to be adjusted, prompting the object to be massaged to adjust the wearing angle.

[0077] In some embodiments, in response to the wearing state indicating that the wearing angle needs to be adjusted, the above-mentioned execution body can prompt the object to be massaged to adjust the wearing angle through text prompts. For example, the above-mentioned execution body can display "There is a tilt when wearing. To ensure the massage effect, please adjust the ear massage device with -[wearing tilt]". Among them, "[wearing tilt]" is filled in according to the specific angle value.

[0078] Optionally, after the object to be massaged is adjusted, step 105, step 106 and step 107 may be repeatedly performed until the wearing state indicates that the wearing angle adjustment is not required.

[0079] Step 107 , in response to the wearing state indicating that the wearing angle does not need to be adjusted, controlling the head fixing belt included in the peri-auricular massage device to fix the head.

[0080] In some embodiments, in response to the wearing state indicating that the wearing angle adjustment is not required, the execution subject may control the head fixing belt included in the peri-auricular massage device to fix the head. The head fixing belt may be embedded inside the peri-auricular massage device, and the head fixing belt may be tightened by applying a lateral or longitudinal force to fix the head of the object to be massaged.

[0081] Optionally, the head fixing belt includes: a transverse head fixing belt and a longitudinal head fixing belt, and the transverse head fixing belt and the longitudinal head fixing belt are embedded between the shell of the above-mentioned peri-auricular massage device and the above-mentioned matrix micro-airbags.

[0082] In some optional implementations of some embodiments, the execution subject controls the head fixing belt included in the ear massage device to fix the head, including: The first step is to obtain a three-dimensional periauricular massage device model corresponding to the above-mentioned periauricular massage device.

[0083] In practice, the three-dimensional model corresponding to the peri-ear massage device can be pre-stored in the above-mentioned execution body. Since the three-dimensional peri-ear massage device model is used for subsequent calculation of the transverse boundary ratio and the longitudinal boundary ratio, the three-dimensional peri-ear massage device model can adopt a low-precision model to reduce the subsequent data processing amount.

[0084] The second step is to determine the cavity area based on the above-mentioned three-dimensional ear periorbital massage device model and the above-mentioned three-dimensional head model.

[0085] In practice, the closed area formed by the inner side of the three-dimensional ear massage device model and the outer side of the three-dimensional head model can be used as the cavity area. In this case, there is no need to load the entire three-dimensional ear massage device model, which can achieve the purpose of reducing the amount of data processing.

[0086] The third step is to determine the upper horizontal boundary length, the lower horizontal boundary length, the upper vertical boundary length and the lower vertical boundary length corresponding to the above-mentioned cavity area.

[0087] In practice, the above-mentioned execution entity may use the boundary length of the horizontal line passing through the center of the upper surface inside the cavity area and along the upper surface as the horizontal upper boundary length. Similarly, the boundary length of the horizontal line passing through the center of the lower surface inside the cavity area and along the lower surface may be used as the horizontal lower boundary length. The boundary length of the horizontal line passing through the center of the upper surface inside the cavity area and along the upper surface may be used as the vertical upper boundary length. The boundary length of the horizontal line passing through the center of the lower surface inside the cavity area and along the lower surface may be used as the vertical lower boundary length.

[0088] As an example, see Figure 4 The schematic diagram of the process of determining the longitudinal upper boundary length and the longitudinal lower boundary length is shown, wherein when the object to be massaged wears the ear massage device, Figure 4 The invention comprises: a three-dimensional head model 401 at a side view angle and a three-dimensional ear massage device model 402 at a side view angle. At this time, the boundary length of the longitudinal upper boundary 403 can be used as the longitudinal upper boundary length. And the boundary length of the longitudinal lower boundary 404 can be used as the longitudinal lower boundary length. Constrained by the surface center and the horizontal line, thus, a unique transverse upper boundary length, transverse lower boundary length, longitudinal upper boundary length and longitudinal lower boundary length are obtained.

[0089] In the fourth step, the ratio of the above-mentioned upper horizontal boundary length to the above-mentioned lower horizontal boundary length is determined as the horizontal boundary ratio.

[0090] Among them, the lateral boundary ratio = lateral upper boundary length / lateral lower boundary length.

[0091] The fifth step is to determine the ratio of the length of the upper longitudinal boundary to the length of the lower longitudinal boundary as the longitudinal boundary ratio.

[0092] Among them, the longitudinal boundary ratio = longitudinal upper boundary length / longitudinal lower boundary length.

[0093] The sixth step is to control the above-mentioned transverse head fixing belt to shrink according to the above-mentioned transverse boundary ratio.

[0094] In practice, the execution body may control the contraction of the transverse head fixing belt by taking the transverse line boundary ratio as the contraction coefficient.

[0095] The seventh step is to control the longitudinal head fixing belt to shrink according to the longitudinal boundary ratio.

[0096] In practice, the execution body may control the longitudinal head fixing belt to shrink by taking the longitudinal boundary ratio as the shrinkage coefficient.

[0097] Step 108, in response to the head being fixed, controlling the matrix micro-airbags included in the peri-auricular massage device to perform peri-auricular massage on the massage subject according to the above-mentioned acupoint information set.

[0098] In some embodiments, in response to the head being fixed, the execution subject may control the matrix micro-airbags included in the peri-auricular massage device to perform peri-auricular massage on the massage subject according to the acupoint information set.

[0099] Optionally, the matrix micro-airbags include: at least one airbag unit. The side of the airbag unit facing inward includes: at least one micropore. A microneedle is arranged in the micropore. The microneedle is used to output microcurrent. In practice, the airbag unit adopts a pillow-shaped structure. The side of the airbag unit facing the ear of the object to be massaged includes at least one micropore, and a microneedle is embedded in the micropore to output microcurrent, so as to stimulate the acupuncture points through the microcurrent.

[0100] Optionally, in order to reduce costs, the airbag units included in the matrix micro-airbags may be filled with gel-like substances as fillers to replace the inflation and deflation functions of the airbag units, thereby further reducing costs while ensuring the use effect.

[0101] Optionally, the peri-auricular massage device further comprises: a power supply device for outputting microcurrent and supplying power to the micro-pump so that the micro-pump controls the inflation and deflation of the airbag. In practice, the peri-auricular massage device may further comprise a charging interface to charge the power supply device through the charging result.

[0102] Optionally, the ear massage device further includes a communication module, so that the control signal sent by the execution subject can be received through the communication module. Specifically, the ear massage device can communicate with the execution subject through the communication module by using Bluetooth connection, Zigbee connection, UWB (UltraWide Band) connection, etc.

[0103] In some optional implementations of some embodiments, the execution subject controls the matrix micro-airbags included in the ear periorbital massage device to perform ear periorbital massage on the object to be massaged according to the acupoint information set, including: The first step is to control the micro air pump to inflate at least one airbag unit included in the matrix type micro airbags to perform acupoint massage around the ear on the acupoint positions included in the acupoint information set.

[0104] In practice, since the acupoint information includes the acupoint location, the airbag unit corresponding to the acupoint location can be inflated and deflated by a micro-pump to achieve regional massage of the acupoint at the acupoint location.

[0105] The second step is to control the microneedles included in the airbag unit of the at least one airbag unit to release microcurrent to perform acupoint massage around the ear on the acupoint positions included in the acupoint information set.

[0106] In practice, after the airbag unit is inflated, it will fit the skin surface more closely. At this time, microcurrent can be released through microneedles to achieve more precise local massage.

[0107] Optionally, the ear periarthritis massage device further comprises: a temperature sensor and a blood flow velocity sensor. The temperature sensor can collect temperature changes around the ear periarthritis of the object to be massaged. The blood flow velocity sensor can collect blood flow velocity changes around the ear periarthritis of the object to be massaged.

[0108] In some optional implementations of some embodiments, after controlling the matrix micro-airbags included in the above-mentioned peri-auricular massage device to perform peri-auricular massage on the above-mentioned object to be massaged according to the above-mentioned acupoint information set, the above-mentioned method further includes: The first step is to collect the skin temperature corresponding to the acupoint position during the ear massage process through the above-mentioned temperature sensor.

[0109] Among them, the skin temperature can characterize the skin temperature curve during the massage process.

[0110] The second step is to collect the blood flow velocity corresponding to the acupoint position during the ear massage process through the above-mentioned blood flow velocity sensor.

[0111] Among them, the blood flow velocity represents the skin blood flow velocity curve during massage.

[0112] The third step is to generate a massage result for the object to be massaged according to the skin temperature and blood flow rate.

[0113] The massage result represents the massage effect on the object to be massaged. In practice, since skin temperature and blood flow rate are time series data, a time series model, such as LSTM (Long Short-Term Memory) model, can be used to take skin temperature and blood flow rate as input and output massage results.

[0114] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the ear massage method applied to the ear massage device of some embodiments of the present disclosure, the massage efficiency, standardization and sustainability are improved. Specifically, the manual massage treatment method has low massage efficiency, and at the same time, different massagers have different massage methods and techniques, which makes it difficult to ensure the standardization of massage. In addition, the manual massage method often requires the object to be massaged to go to a specific place (such as the rehabilitation department of a hospital, etc.) for massage treatment, so it is difficult to make the object to be massaged undergo massage treatment at any time, and thus it is difficult to ensure the sustainability of massage treatment. Based on this, the ear massage method applied to the ear massage device of some embodiments of the present disclosure, first, collects a head image sequence, wherein the head image in the head image sequence is an image of the head of the object to be massaged collected at different angles. Secondly, a three-dimensional head reconstruction is performed according to the head image sequence to generate a three-dimensional head model for the object to be massaged. The head model of the object to be massaged with different head shapes and sizes is established by combining the images. Next, the acupuncture points around the ear are located on the three-dimensional head model to obtain an acupuncture point information set, wherein the acupuncture point information in the acupuncture point information set includes: acupuncture point type and acupuncture point position. In practice, due to the different head shapes and head sizes of different objects to be massaged, the acupuncture points around the ear for different objects to be massaged are located by combining the three-dimensional head model. Further, in response to determining that the object to be massaged has worn the acupuncture point massage device, a target image is collected, wherein the target image includes the face of the object to be massaged and the front view of the acupuncture point massage device. Next, according to the target image, the wearing state corresponding to the acupuncture point massage device is determined. In this way, it is judged whether the object to be massaged is suitable to wear the acupuncture point massage device to avoid affecting the massage treatment effect due to inappropriateness. In addition, in response to the wearing state indicating that the wearing angle needs to be adjusted, the object to be massaged is prompted to adjust the wearing angle. In addition, in response to the wearing state indicating that the wearing angle does not need to be adjusted, the head fixing belt included in the acupuncture point massage device is controlled to fix the head. The head is fixed by the head fixing belt, so that the acupuncture point massage device can be firmly fixed on the head of the object to be massaged. Finally, in response to the head being fixed, the matrix micro-airbags included in the above-mentioned peri-auricular massage device are controlled to perform peri-auricular massage on the above-mentioned object to be massaged according to the above-mentioned acupoint information set, wherein the above-mentioned matrix micro-airbags are embedded in the inner side of the above-mentioned peri-auricular massage device. Compared with the traditional massage method such as hard massage head massage, the peri-auricular massage performed by the matrix micro-airbags is more in line with the skin surface, and the matrix design massage is more accurate, which greatly improves the effect of massage therapy.

[0115] Further references Figure 5As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an ear periarthritis massage device applied to an ear periarthritis massage device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the peri-auricular massage device applied to the peri-auricular massage device can be specifically applied to various electronic devices.

[0116] like Figure 5 As shown, in some embodiments, the peri-auricular massage device 500 applied to the peri-auricular massage device includes: a first acquisition unit 501, a three-dimensional head reconstruction unit 502, a peri-auricular acupoint positioning unit 503, a second acquisition unit 504, a determination unit 505, a prompt unit 506, a first control unit 507 and a second control unit 508. The first acquisition unit 501 is configured to acquire a head image sequence, wherein the head images in the head image sequence are images of the head of the object to be massaged acquired at different angles; the three-dimensional head reconstruction unit 502 is configured to perform three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged; the peri-auricular acupoint positioning unit 503 is configured to perform peri-auricular acupoint positioning on the three-dimensional head model to obtain an acupoint information set, wherein the acupoint information in the acupoint information set includes: acupoint type and acupoint position; the second acquisition unit 504 is configured to acquire a target image in response to determining that the object to be massaged has worn the peri-auricular massage device, wherein the target image includes the face and A front view of the above-mentioned peri-auricular massage device; a determination unit 505, configured to determine the corresponding wearing state of the above-mentioned peri-auricular massage device according to the above-mentioned target image; a prompting unit 506, configured to prompt the above-mentioned object to be massaged to adjust the wearing angle in response to the above-mentioned wearing state indicating that the wearing angle adjustment is required; a first control unit 507, configured to control the head fixing belt included in the above-mentioned peri-auricular massage device to fix the head in response to the above-mentioned wearing state indicating that the wearing angle adjustment is not required; a second control unit 508, configured to control the matrix micro-airbags included in the above-mentioned peri-auricular massage device to perform peri-auricular massage on the above-mentioned object to be massaged according to the above-mentioned acupoint information set in response to the head fixation being completed. The matrix micro-airbags are embedded in the inner side of the above-mentioned peri-auricular massage device.

[0117] It is understood that the units described in the ear periarthritis massage device 500 for use in the ear periarthritis massage device are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the peri-auricular massage device 500 and the units contained therein applied to the peri-auricular massage device, and will not be described in detail here.

[0118] Reference below Figure 6, which shows a structural schematic diagram of an electronic device (eg, a computing device) 600 suitable for implementing some embodiments of the present disclosure. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0119] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory 602 or a program loaded from a storage device 608 to a random access memory 603. Various programs and data required for the operation of the electronic device 600 are also stored in the random access memory 603. The processing device 601, the read-only memory 602, and the random access memory 603 are connected to each other via a bus 604. An input / output interface 605 is also connected to the bus 604.

[0120] Typically, the following devices may be connected to the input / output interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 6 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0121] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network through a communication device 609, or installed from a storage device 608, or installed from a read-only memory 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0122] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure 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 or 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 some embodiments of the present disclosure, 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 some embodiments of the present disclosure, 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 program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0123] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0124] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: acquires a head image sequence, wherein the head images in the above-mentioned head image sequence are images of the head of the object to be massaged acquired at different angles; performs three-dimensional head reconstruction according to the above-mentioned head image sequence to generate a three-dimensional head model for the above-mentioned object to be massaged; locates the acupoints around the ear on the above-mentioned three-dimensional head model to obtain an acupoint information set, wherein the acupoint information in the above-mentioned acupoint information set includes: acupoint type and acupoint location; in response to determining that the above-mentioned object to be massaged has worn the above-mentioned auricular massage device, acquires a target image, wherein In the embodiment, the target image includes the face of the object to be massaged and a front view of the auricular massage device; according to the target image, the wearing state corresponding to the auricular massage device is determined; in response to the wearing state indicating that the wearing angle needs to be adjusted, the object to be massaged is prompted to adjust the wearing angle; in response to the wearing state indicating that the wearing angle does not need to be adjusted, the head fixing belt included in the auricular massage device is controlled to fix the head; in response to the completion of head fixation, the matrix micro-airbags included in the auricular massage device are controlled to perform auricular massage on the object to be massaged according to the acupoint information set, wherein the matrix micro-airbags are embedded in the inner side of the auricular massage device.

[0125] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart 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.

[0127] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including a first acquisition unit, a three-dimensional head reconstruction unit, an auricular acupoint positioning unit, a second acquisition unit, a determination unit, a prompt unit, a first control unit, and a second control unit. Among them, the names of these units do not constitute limitations on the units themselves in certain circumstances. For example, the first control unit may also be described as "a unit for controlling the head fixing belt included in the above-mentioned auricular massage device to fix the head in response to the above-mentioned wearing state indicating that no wearing angle adjustment is required".

[0128] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0129] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. An ear periarthritis massage method applied to an ear periarthritis massage device, comprising: Acquiring a head image sequence, wherein the head images in the head image sequence are images of the head of the object to be massaged acquired at different angles; Performing three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged; Performing acupoint positioning around the ear on the three-dimensional head model to obtain an acupoint information set, wherein the acupoint information in the acupoint information set includes: acupoint type and acupoint location; In response to determining that the object to be massaged has worn the peri-auricular massage device, acquiring a target image, wherein the target image includes a face of the object to be massaged and a front view of the peri-auricular massage device; Determining a wearing state corresponding to the peri-auricular massage device according to the target image; In response to the wearing state indicating that the wearing angle needs to be adjusted, prompting the object to be massaged to adjust the wearing angle; In response to the wearing state indicating that the wearing angle adjustment is not required, controlling the head fixing belt included in the peri-auricular massage device to fix the head; In response to the head being fixed, the matrix micro-airbags included in the peri-auricular massage device are controlled to perform peri-auricular massage on the object to be massaged according to the acupoint information set, wherein the matrix micro-airbags are embedded inside the peri-auricular massage device.

2. The method according to claim 1, wherein: The ear massage device further includes: a temperature sensor and a blood flow rate sensor; and After controlling the matrix micro-airbags included in the peri-auricular massage device to perform peri-auricular massage on the object to be massaged according to the acupoint information set, the method further includes: The temperature sensor is used to collect the skin temperature corresponding to the acupoint position during the ear massage process; The blood flow velocity sensor is used to collect the blood flow velocity corresponding to the acupoint position during the ear massage process; A massage result for the object to be massaged is generated according to the skin temperature and the blood flow rate.

3. The method according to claim 2, wherein: The three-dimensional head reconstruction is performed according to the head image sequence to generate a three-dimensional head model for the object to be massaged, comprising: Extracting edge feature points from each head image in the head image sequence to generate an image edge information group, wherein the image edge information group includes four pieces of image edge information corresponding to the image edge of the head image, and the image edge information in the image edge information group includes: an edge feature point feature group; Randomly select a head image from the head image sequence as a reference head image; using the head image sequence excluding the reference head image as a candidate head image sequence; Based on the reference head image and the candidate head image sequence, perform the following image stitching steps: Take the first candidate head image from the candidate head image sequence as the head image to be stitched; Determine an edge matching degree group according to an image edge information group corresponding to the head image to be stitched and an image edge information group corresponding to the reference head image, wherein the edge matching degree group represents the matching degree between the candidate head image and the image edge of the reference head image at four image edges; In response to the presence of an edge matching degree satisfying a matching condition in the edge matching degree group, the head image to be spliced ​​is spliced ​​with the reference head image along an image edge corresponding to the edge matching degree satisfying the matching condition to obtain an updated reference head image, wherein the matching condition is that the edge matching degree is greater than a preset edge matching degree; In response to the presence of an edge matching degree satisfying a matching condition in the edge matching degree group and the candidate head image sequence excluding the head image to be spliced ​​is empty, performing a three-dimensional head reconstruction according to the updated reference head image and the three-dimensional head reconstruction model to generate a three-dimensional head model for the object to be massaged; In response to the absence of an edge matching degree satisfying the matching condition in the edge matching degree group, the head image to be stitched is placed as a candidate head image at the end of the candidate head image sequence to obtain an updated candidate head image sequence as the candidate head image sequence; the updated reference head image is used as the reference head image, and the image stitching step is performed again.

4. The method according to claim 3, wherein: The method of locating acupoints around the ears of the three-dimensional head model to obtain an acupoint information set includes: Projecting the three-dimensional head model to a frontal perspective to obtain a frontal perspective image; Performing facial organ positioning on the frontal view image to obtain a first organ information set, wherein the first organ information in the first organ information set includes: organ type and organ position; Determining a median axis plane according to the first organ information set; symmetrically segmenting the three-dimensional head model along the median axis to obtain a segmented three-dimensional head model; Respectively projecting the segmented three-dimensional head model to a top-down perspective and a left-side perspective to obtain a top-down perspective image and a left-side perspective image; Performing acupoint positioning on the top-view image and the left-view image to determine first acupoint information and obtain a first acupoint information set; According to the first acupoint information set, symmetrical acupoints are determined along the median axis to obtain a second acupoint information set; The first acupoint information set and the second acupoint information set are determined as the acupoint information set.

5. The method according to claim 4, wherein: Determining the wearing state corresponding to the peri-ear massage device according to the target image includes: Converting the target image into a grayscale image; Performing edge detection on the grayscale image by using an edge detection model to obtain an edge image, wherein the edge image is a grayscale image with edges marked; Performing edge filtering on the edge image to determine candidate edges and obtain a candidate edge set; Determine an edge confidence corresponding to each candidate edge in the candidate edge set, wherein the edge confidence represents the confidence that the candidate edge is the edge of the peri-ear massage device; Selecting a candidate edge that satisfies a screening condition from the candidate edge set as a target edge, wherein the screening condition is: the edge confidence corresponding to the candidate edge is the largest; determining an edge inclination of the target edge; In response to a difference between the edge inclination and a preset edge inclination being greater than a preset difference, generating a wearing state indicating that a wearing angle adjustment is required; In response to the difference between the edge inclination and the preset edge inclination being less than or equal to the preset difference, a wearing state indicating that no wearing angle adjustment is required is generated.

6. The method according to claim 5, wherein: The head fixing belt comprises: a transverse head fixing belt and a longitudinal head fixing belt, wherein the transverse head fixing belt and the longitudinal head fixing belt are embedded between the housing of the peri-ear massage device and the matrix micro airbag; and The method of controlling the head fixing belt included in the peri-auricular massage device to fix the head comprises: Acquire a three-dimensional periauricular massage device model corresponding to the periauricular massage device; Determining a cavity area according to the three-dimensional ear periarthritis massage device model and the three-dimensional head model; Determine the upper horizontal boundary length, the lower horizontal boundary length, the upper vertical boundary length and the lower vertical boundary length corresponding to the cavity area; Determine the ratio of the upper horizontal boundary length to the lower horizontal boundary length as the horizontal boundary ratio; Determine the ratio of the length of the upper longitudinal boundary to the length of the lower longitudinal boundary as the longitudinal boundary ratio; According to the lateral boundary ratio, controlling the lateral head fixing belt to contract; The longitudinal head fixing belt is controlled to shrink according to the longitudinal boundary ratio.

7. The method according to claim 6, wherein: The matrix micro-airbag comprises: at least one airbag unit, the side of the airbag unit facing inward comprises: at least one microhole, a microneedle is arranged in the microhole, and the microneedle is used to output microcurrent; and The method of controlling the matrix micro-airbags included in the peri-auricular massage device to perform peri-auricular massage on the object to be massaged according to the acupoint information set comprises: Controlling a micro air pump to inflate at least one airbag unit included in the matrix type micro-airbag, so as to perform acupoint massage around the ear on the acupoint positions included in the acupoint information set; The microneedles included in the airbag unit in the at least one airbag unit are controlled to release microcurrent to perform acupoint massage around the ear on the acupoint positions included in the acupoint information set.

8. An ear massage device for use in an ear massage device, comprising: A first acquisition unit is configured to acquire a head image sequence, wherein the head images in the head image sequence are images of the head of the object to be massaged acquired at different angles; a three-dimensional head reconstruction unit, configured to perform three-dimensional head reconstruction according to the head image sequence to generate a three-dimensional head model for the object to be massaged; The acupoint positioning unit is configured to perform acupoint positioning on the three-dimensional head model to obtain an acupoint information set, wherein the acupoint information in the acupoint information set includes: acupoint type and acupoint position; A second acquisition unit is configured to acquire a target image in response to determining that the object to be massaged has worn the peri-auricular massage device, wherein the target image includes a face of the object to be massaged and a front view of the peri-auricular massage device; a determination unit, configured to determine a wearing state corresponding to the peri-ear massage device according to the target image; a prompting unit configured to prompt the object to be massaged to adjust the wearing angle in response to the wearing state indicating that the wearing angle adjustment is required; A first control unit is configured to control the head fixing belt included in the peri-auricular massage device to fix the head in response to the wearing state indicating that the wearing angle adjustment is not required; The second control unit is configured to control the matrix micro-airbags included in the peri-auricular massage device in response to the head being fixed, and perform peri-auricular massage on the object to be massaged according to the acupoint information set, wherein the matrix micro-airbags are embedded inside the peri-auricular massage device.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images