Face area locating method and apparatus, wearable device, and beauty and skincare system

Abstract

A face area locating method, comprising: when a user wears a wearable device and initializes a beauty and skincare device on the basis of preset face key points, acquiring electromagnetic induction data corresponding to the preset face key points (S110); when the user uses the beauty and skincare device, acquiring real-time electromagnetic induction data between the wearable device and the beauty and skincare device (S120); and on the basis of the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data, using a preset face area locating model to determine a face area on which the beauty and skincare device currently acts (S130). The difference of face area distribution characteristics of different users is taken into account, a face area locating model capable of distinguishing different users is trained in advance, and on the basis of electromagnetic induction data of face key points of a user determined in an initialization stage and current electromagnetic induction data generated in real time, accurate locating of a beauty and skincare device in the face area of the user can be achieved. Further disclosed are a face area locating apparatus (500), a wearable device, and a beauty and skincare system.

Description

Face area positioning method, device, wearable device, and beauty care system

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed with the China Patent Office on June 30, 2023, with application number 202310803184.4, and entitled “Face Region Positioning Method, Device, Wearable Device, and Beauty Care System,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application relates to the field of beauty care technology, and in particular to a facial area positioning method, apparatus, wearable device, and beauty care system. Background Art

[0004] Traditional medical beauty equipment mainly switches between different beauty modes by setting buttons for different areas of the face. This solution is relatively reliable but the experience is poor.

[0005] In order to solve the problem that traditional medical beauty care equipment cannot achieve automatic switching of beauty care modes, automatic positioning of the facial area where the beauty care equipment is applied becomes the entry point. By automatically positioning the spatial area of ​​the facial area where the beauty care equipment is applied, precise skin care of the area can be achieved, and personalized care suggestions can be automatically generated.

[0006] Currently, the facial positioning solution for beauty care devices based on magnetic induction positioning technology mainly uses a magnetic field intensity distribution model for positioning. However, this solution does not take into account the differences in facial area distribution characteristics of different users. For example, for the same magnetic induction reading, it may correspond to the eye area of ​​user A and the cheek area of ​​user B at the same time. Therefore, simply using a magnetic field intensity distribution model to process the real-time magnetic induction data cannot achieve accurate positioning of the facial area.

[0007] Summary of the Invention

[0008] The embodiments of the present application provide a facial region positioning method, apparatus, wearable device, and beauty care system to improve the accuracy of facial region positioning for different users.

[0009] The embodiments of this application adopt the following technical solutions:

[0010] In a first aspect, an embodiment of the present application provides a method for locating a face region, the method comprising:

[0011] When a user wears the wearable device and initializes the beauty and protection device based on preset facial key points, obtaining electromagnetic induction data corresponding to the preset facial key points;

[0012] When the user uses the beauty care device, obtaining real-time electromagnetic induction data between the wearable device and the beauty care device;

[0013] According to the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data, positioning is performed using a preset facial area positioning model to obtain the facial area currently affected by the beauty and protection device.

[0014] Optionally, the preset face area positioning model includes a face key point recognition sub-model and a partition positioning sub-model. The face area currently affected by the beauty care device is obtained by positioning using the preset face area positioning model based on the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data.

[0015] According to the electromagnetic induction data corresponding to the preset facial key points, the user identity is identified using the facial key point recognition sub-model to obtain the user identity corresponding to the preset facial key points;

[0016] Obtaining a partition positioning sub-model corresponding to the user identity;

[0017] According to the real-time electromagnetic induction data, the partition positioning sub-model is used to perform partition positioning to obtain the facial area currently affected by the beauty care device.

[0018] Optionally, the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data are used to perform positioning using a preset facial region positioning model to obtain the facial region currently affected by the beauty care device, including:

[0019] The electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data are directly input into the preset facial area positioning model to obtain the facial area currently affected by the beauty care device.

[0020] Optionally, the preset face region positioning model includes a face key point recognition sub-model and a partition positioning sub-model, and the preset face region positioning model is trained in the following manner:

[0021] Obtain magnetic induction data of preset facial key points of multiple users;

[0022] Using the magnetic induction data of preset facial key points of multiple users to train the facial key point recognition sub-model;

[0023] Acquire magnetic induction data of facial regions of multiple users;

[0024] The magnetic induction data of the facial regions of multiple users are used to train the partition positioning sub-model corresponding to each user.

[0025] Optionally, the training of the facial key point recognition sub-model using the magnetic induction data of preset facial key points of multiple users includes:

[0026] Constructing facial key point feature vectors corresponding to each user based on the magnetic induction data of preset facial key points of multiple users;

[0027] The facial key point recognition sub-model is trained using the facial key point feature vector corresponding to each user.

[0028] Optionally, the using the magnetic induction data of the facial regions of the multiple users to respectively train the partition positioning sub-model corresponding to each user includes:

[0029] Constructing a first region feature vector corresponding to each partition of each user according to the magnetic induction data of the facial regions of the plurality of users;

[0030] The partition positioning sub-model corresponding to each user is trained respectively using the first region feature vector corresponding to each partition of each user.

[0031] Optionally, the magnetic induction data of the facial region includes magnetic induction data of the left facial region and magnetic induction data of the right facial region, the partition positioning sub-model includes a left face partition positioning sub-model and a right face partition positioning sub-model, and using the magnetic induction data of the facial regions of multiple users to train the partition positioning sub-model corresponding to each user includes:

[0032] The magnetic induction data of each user's left face area is used to train the left face partition positioning sub-model corresponding to each user;

[0033] The magnetic induction data of each user's right face area is used to train the right face partition positioning sub-model corresponding to each user.

[0034] Optionally, the preset face area positioning model is trained in the following manner:

[0035] Obtain magnetic induction data of preset facial key points and facial regions of multiple users;

[0036] Constructing a second region feature vector corresponding to each user based on the magnetic induction data of preset facial key points and the magnetic induction data of facial regions of the plurality of users;

[0037] The preset face region positioning model is trained using the second region feature vector corresponding to each user.

[0038] In a second aspect, an embodiment of the present application further provides a face region positioning device, the face region positioning device comprising:

[0039] The first acquisition unit is configured to acquire electromagnetic induction data corresponding to preset facial key points when the user wears the wearable device and initializes the beauty and protection device based on the preset facial key points;

[0040] A second acquiring unit is configured to acquire real-time electromagnetic induction data between the wearable device and the beauty care device when the user uses the beauty care device;

[0041] The positioning unit is used to perform positioning using a preset face area positioning model based on the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data, so as to obtain the face area currently affected by the beauty care device.

[0042] In a third aspect, an embodiment of the present application further provides a wearable device, comprising:

[0043] processor; and

[0044] A memory is arranged to store computer-executable instructions, which, when executed, cause the processor to perform any of the aforementioned face region locating methods.

[0045] In a fourth aspect, an embodiment of the present application further provides a beauty care system, which includes a beauty care device and the wearable device as described above.

[0046] In a fifth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by a wearable device including multiple applications, the wearable device executes any of the aforementioned methods.

[0047] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the facial region positioning method of the embodiments of the present application first obtains electromagnetic induction data corresponding to preset facial key points when the user wears the wearable device and initializes the beauty care device based on the preset facial key points; then obtains real-time electromagnetic induction data between the wearable device and the beauty care device when the user uses the beauty care device; finally, based on the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data, the preset facial region positioning model is used for positioning to obtain the facial region currently affected by the beauty care device. The facial region positioning method of the embodiments of the present application takes into account the different facial region distribution characteristics of different users, and pre-trains a facial region positioning model that can distinguish different users. By using this facial region positioning model, combined with the electromagnetic induction data of the user's facial key points determined in the initialization phase and the electromagnetic induction data currently generated in real time, the beauty care device can be accurately positioned in the facial region of the user, thereby improving the accuracy of facial region positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0049] FIG1 is a schematic diagram of a flow chart of a method for locating a face region in an embodiment of the present application;

[0050] FIG2 is a schematic diagram of face area division in an embodiment of the present application;

[0051] FIG3 is a schematic diagram of a face region positioning process according to an embodiment of the present application;

[0052] FIG4 is a schematic diagram of another face region positioning process in an embodiment of the present application;

[0053] FIG5 is a schematic structural diagram of a face region positioning device according to an embodiment of the present application;

[0054] FIG6 is a schematic structural diagram of a wearable device according to an embodiment of the present application;

[0055] FIG7 is a schematic diagram of the architecture of a beauty care system according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0057] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0058] The present application provides a method for locating a facial region. FIG1 shows a flow chart of a method for locating a facial region according to an embodiment of the present application. The method for locating a facial region includes at least the following steps S110 to S130:

[0059] Step S110: When the user wears the wearable device and initializes the beauty and protection device based on preset facial key points, electromagnetic induction data corresponding to the preset facial key points are obtained.

[0060] The facial area positioning method of the embodiment of the present application is mainly used to determine the facial area on which the beauty care device is currently acting. The "facial area" defined here can be a facial skin area divided according to the functional requirements of the beauty care device. As shown in Figure 2, a facial area division schematic diagram in the embodiment of the present application is provided. For example, it can include the forehead area, eye area and cheek area. This partitioning method specifically corresponds to five partitions, namely, the forehead area, left eye area, right eye area, left cheek area and right cheek area. Of course, the facial area can be further divided into more detailed areas. For example, the cheek area can be further divided into the jawline area and the apple muscle area. This partitioning method corresponds to seven partitions. Of course, how to divide the facial area specifically can be flexibly defined by those skilled in the art according to actual needs, and no specific limitation is made here.

[0061] The more detailed the division of facial areas, the higher the accuracy requirement for regional positioning. The beauty care device positioning solution in the embodiment of the present application can support sufficiently fine-grained facial area division, providing strong support for the user's precise zone skin care.

[0062] The facial area positioning method of the embodiment of the present application can be divided into two stages: initialization of the beauty care device and real-time positioning. In the initialization stage, the user needs to wear the wearable device first, and then complete the initialization operation of the beauty care device according to the guidance or known pre-defined facial key points.

[0063] The aforementioned wearable device can be considered an auxiliary positioning device independent of the beauty and protection device. It can be worn securely on the user's head, neck, or wrist, taking the form of a headband, hairpin, barrette, necklace, neck ring, bracelet, or wristband. One of the wearable and beauty devices is equipped with a magnetic source, i.e., a structure that generates a magnetic field, such as an electromagnet, and the other is equipped with a magnetic sensor, also known as a Hall effect sensor (abbreviated as a "Hall sensor"). This is a transducer that converts changes in the magnetic field into changes in the output voltage. The wearable and beauty devices constructed in this manner can generate real-time electromagnetic induction data when the beauty device enters the facial area covered by the wearable device.

[0064] The above-mentioned preset facial key points can be flexibly defined according to actual needs. For example, they can include facial features of areas such as eyebrows, eyelids, lips, and nose. Compared with the feature points in other areas of the face, the feature differences of different users in facial key points are more obvious. Different users can be distinguished more accurately through multiple pre-defined facial key points. In the initialization stage, the user is required to hold the beauty care device and act on the position of each preset facial key point in turn. At this time, the electromagnetic induction data corresponding to each preset facial key point can be obtained. Since the spatial posture relationship between the user's facial key points and the head-mounted device is basically fixed after the user wears the wearable device, the electromagnetic induction data corresponding to each preset facial key point obtained in the initialization stage can be regarded as data that can characterize the user's facial features.

[0065] Step S120: When the user uses the beauty care device, real-time electromagnetic induction data between the wearable device and the beauty care device is obtained.

[0066] After the user completes the initialization operation of the beauty care device, he or she begins to use the beauty care device for skin care. At this time, the stage of locating the facial area where the beauty care device acts enters, and the real-time electromagnetic induction data generated between the wearable device and the beauty care device can be obtained.

[0067] Step S130: Based on the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data, a preset facial region positioning model is used to perform positioning to obtain the facial region currently affected by the beauty care device.

[0068] The embodiment of the present application takes into account the differences in the distribution of facial area features of different users and pre-trains a facial area positioning model. The facial area positioning model can be trained based on the electromagnetic induction data corresponding to the facial key points of different users and the real-time electromagnetic induction data. The electromagnetic induction data corresponding to the facial key points can characterize the facial features of the user and can therefore be used to distinguish the identity of the user. The electromagnetic induction data obtained in real time can further determine which area of ​​the user's face it corresponds to on the basis of distinguishing the identity of the user, so that the model can ensure the accuracy of facial area positioning of different users on the basis of distinguishing the identities of different users.

[0069] Therefore, based on the above-mentioned preset face area positioning model, the electromagnetic induction data corresponding to the preset face key points obtained in the above steps and the real-time electromagnetic induction data can be input into the preset face area positioning model to obtain the face area on which the beauty care device is currently acting.

[0070] The facial area positioning method of the embodiment of the present application takes into account the different facial area distribution characteristics of different users, and pre-trains a facial area positioning model that can distinguish different users. By using this facial area positioning model, combined with the electromagnetic induction data of the user's facial key points determined in the initialization phase and the electromagnetic induction data currently generated in real time, the beauty care device can be accurately positioned in the facial area of ​​the user, thereby improving the accuracy of facial area positioning.

[0071] In some embodiments of the present application, the preset face area positioning model includes a face key point recognition sub-model and a partition positioning sub-model. The positioning is performed using the preset face area positioning model according to the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data to obtain the face area on which the beauty care device is currently active. The method includes: performing user identity recognition using the face key point recognition sub-model according to the electromagnetic induction data corresponding to the preset face key points to obtain the user identity corresponding to the preset face key points; obtaining the partition positioning sub-model corresponding to the user identity; and performing partition positioning using the partition positioning sub-model according to the real-time electromagnetic induction data to obtain the face area on which the beauty care device is currently active.

[0072] The preset face area positioning model pre-trained in the embodiment of the present application can be divided into a face key point recognition sub-model and a partition positioning sub-model. The face key point recognition sub-model and the partition positioning sub-model can be regarded as two independent models and can be trained in parallel.

[0073] The facial landmark recognition model is primarily trained based on electromagnetic induction data from different users' facial landmarks, aiming to develop the model's ability to identify and distinguish facial landmarks, and thus, identify each user. The partitioned localization sub-model is trained separately for each user based on electromagnetic induction data from each facial region. This means each user has their own corresponding partitioned localization sub-model, minimizing the impact of differences in facial feature distribution across different users on localization accuracy.

[0074] During the facial region localization phase, the electromagnetic induction data corresponding to the currently acquired preset facial key points can be input into the aforementioned facial key point recognition model to identify the facial key points and thus determine the user's identity. After determining the user's identity, the corresponding sub-region localization model can be further invoked and the real-time electromagnetic induction data can be input into the sub-region localization model to determine the area of ​​the user's face currently being affected by the beauty care device.

[0075] In some embodiments of the present application, the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data are positioned using a preset facial area positioning model to obtain the facial area on which the beauty protection device is currently acting, including: directly inputting the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data into the preset facial area positioning model to obtain the facial area on which the beauty protection device is currently acting.

[0076] In addition to the method of separately training the facial key point recognition sub-model and the partition positioning sub-model in the aforementioned embodiment to respectively realize the functions of user identity recognition and partition positioning, the embodiment of the present application can also pre-train a comprehensive facial area positioning model. The facial area positioning model can be trained based on the electromagnetic induction data of facial key points of different users and the real-time electromagnetic induction data of different partitions, thereby having the ability to accurately locate the facial areas of different users.

[0077] Based on the above-mentioned face area positioning model, the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data currently obtained can be directly input into the model, and the face area currently affected by the beauty care device can be directly obtained as output by the model.

[0078] It should be noted that the above-mentioned implementation methods of separately training the facial key point recognition sub-model and the partition positioning sub-model and the implementation method of comprehensively training a facial area positioning model can both achieve accurate positioning of the facial areas of different users. In actual application, technical personnel in this field can flexibly choose according to actual needs, and no specific limitations are made here.

[0079] The former implementation method has more obvious advantages in the model training stage, because the training of the two sub-models is carried out independently, the data collection requirements are lower than those for comprehensive training of a single model, and the model training efficiency is higher. The latter implementation method has more obvious advantages in the model application stage. After obtaining the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data, they can be input into the comprehensive facial area positioning model together to obtain the final facial area positioning result. There is no need to first perform user identity recognition and then perform partition positioning, nor is there any need to pay attention to the processing logic within the model. This simplifies the positioning processing logic and improves the efficiency of facial area positioning.

[0080] In some embodiments of the present application, the preset face area positioning model includes a face key point recognition sub-model and a partition positioning sub-model, and the preset face area positioning model is trained in the following manner: obtaining magnetic induction data of preset face key points of multiple users; using the magnetic induction data of preset face key points of multiple users to train the face key point recognition sub-model; obtaining magnetic induction data of face areas of multiple users; and using the magnetic induction data of face areas of multiple users to train the partition positioning sub-model corresponding to each user.

[0081] As previously mentioned, the embodiments of the present application can train the facial key point recognition sub-model and the partition positioning sub-model separately, and the training processes of the two are independent of each other. For training the facial key point recognition sub-model, magnetic induction data corresponding to a certain number of users at various preset facial key point locations can be first obtained. The magnetic induction data corresponding to these users at the preset facial key point locations can be used as training sample data to train the facial key point recognition sub-model's ability to identify user identities.

[0082] For the training of the partition positioning sub-model, since the facial area feature distributions of different users are different, the partition positioning sub-models corresponding to different users can be trained separately. In order to reduce training costs and improve training efficiency, the embodiment of the present application can also divide users into different user groups. The facial area feature distributions of users in different user groups are obviously different, and the facial area feature distributions of users in the same user group are relatively small. Therefore, the corresponding partition positioning sub-models can be trained separately for different user groups. This method does not require that the user set data collected when training the facial key point recognition sub-model be completely corresponding or consistent with the user set data collected when training the partition positioning sub-model.

[0083] Of course, the specific way to divide user groups can be flexibly set by technicians in this field according to actual needs. For example, the magnetic induction data of different facial areas of a large number of users can be clustered to group similar users into one user group, or a finer division can be made according to region, age, and gender. I will not elaborate on this here.

[0084] The users in the training phase can be real users or users simulated based on a deformable 3D facial model. The number of users can be flexibly adjusted based on the effectiveness of model training and is not specifically limited here. Both the facial landmark recognition sub-model and the partition positioning sub-model can be considered multi-classification models and can be trained based on existing convolutional neural network structures. The specific form of convolutional neural network used can be flexibly selected by those skilled in the art based on actual needs and is not specifically limited here.

[0085] In some embodiments of the present application, the method of training the facial key point recognition sub-model using the magnetic induction data of preset facial key points of multiple users includes: constructing a facial key point feature vector corresponding to each user based on the magnetic induction data of preset facial key points of multiple users; and training the facial key point recognition sub-model using the facial key point feature vector corresponding to each user.

[0086] When the embodiment of the present application uses the magnetic induction data of preset facial key points of multiple users to train the facial key point recognition sub-model, the feature vector of each facial key point of each user can be first constructed according to the magnetic induction data of the preset facial key points of each user, and this can be used as the input for model training.

[0087] Taking the three-axis transmitting coil as an example, the three-axis transmitting coil is composed of three circular electromagnetic coils perpendicular to each other, corresponding to the three coordinate axes of X, Y, and Z. Under the action of the sinusoidal voltage value, the three-axis transmitting coil will generate a high-frequency oscillating magnetic field. This magnetic field will be received by the magnetic sensor, i.e., the magnetic receiver, set on the wearable device in space. The magnetic receiver is also composed of three circular electromagnetic coils perpendicular to each other. The frequency of the receiving coil is the same as that of the transmitting coil. At an instant, the coil of each axis of the receiving coil can respectively receive the magnetic field strength from the coil of the X, Y, and Z axis of the transmitting coil. In this way, the vector value of the magnetic field strength of the X, Y, and Z axis of the transmitting coil corresponding to the X, Y, and Z axis of the receiving coil can be generated, thereby generating a 9-dimensional feature vector data, which can be regarded as a unique scalar of the spatial relative position relationship between the receiving coil and the transmitting coil at this instant.

[0088] Based on this, when the beauty protection device acts on each preset facial key point, a corresponding 9-dimensional feature vector data will be generated. By fusing the 9-dimensional feature vector data of multiple preset facial key points corresponding to each user separately, unique feature vector data that can represent the facial features of each user can be obtained.

[0089] In some embodiments of the present application, the use of magnetic induction data of facial regions of multiple users to respectively train the partition positioning sub-model corresponding to each user includes: constructing a first region feature vector corresponding to each partition of each user based on the magnetic induction data of facial regions of multiple users; and using the first region feature vector corresponding to each partition of each user to respectively train the partition positioning sub-model corresponding to each user.

[0090] When the embodiment of the present application uses the magnetic induction data of the facial regions of multiple users to train the partition positioning sub-model corresponding to each user, the magnetic induction data of each user in each facial region can be collected separately, and the first regional feature vector of each partition can be constructed with the partition as the dimension. The first regional feature vector can be regarded as a unique scalar that characterizes the characteristics of the facial region.

[0091] For example, if electromagnetic induction data corresponding to 100 points on a user's forehead is collected, and each point is composed of a 9-dimensional feature vector, then the 100 9-dimensional feature vectors can be fused together to form a unique scalar for the forehead region. The same applies to other regions. This way, the first regional feature vector corresponding to each user's facial region can be obtained, and the corresponding partitioned positioning sub-model for each user can be trained to enable the model to distinguish different facial regions of the user.

[0092] In some embodiments of the present application, the magnetic induction data of the facial area includes magnetic induction data of the left facial area and magnetic induction data of the right facial area, the partition positioning sub-model includes a left face partition positioning sub-model and a right face partition positioning sub-model, and the using the magnetic induction data of the facial areas of multiple users to respectively train the partition positioning sub-model corresponding to each user includes: using the magnetic induction data of the left facial area of ​​each user to respectively train the left face partition positioning sub-model corresponding to each user; using the magnetic induction data of the right facial area of ​​each user to respectively train the right face partition positioning sub-model corresponding to each user.

[0093] In order to further improve the training effect and positioning accuracy of the partition positioning sub-model, the embodiment of the present application can also divide the user's facial area into the left face facial area and the right face facial area, and train corresponding partition positioning sub-models for the left face facial area and the right face facial area respectively.

[0094] For example, magnetic induction data can be collected for the left facial region, such as the left forehead, left eye area, left cheek, and left jawline. Regional feature vectors corresponding to these regions can then be constructed. These feature vectors can then be used as training samples for the left facial region localization sub-model, enabling it to distinguish between the various left facial regions. The training logic for the right facial region localization sub-model is similar and will not be elaborated on here.

[0095] In some embodiments of the present application, the preset face area positioning model is trained in the following manner: obtaining magnetic induction data of preset face key points and magnetic induction data of face areas of multiple users; constructing a second area feature vector corresponding to each user based on the magnetic induction data of preset face key points and magnetic induction data of face areas of multiple users; and using the second area feature vector corresponding to each user to train the preset face area positioning model.

[0096] As mentioned above, the preset face region positioning model of the embodiment of the present application can also be a comprehensive training model, that is, it has the ability to distinguish different face regions of different users. When training the face region positioning model, it is also necessary to obtain the magnetic induction data corresponding to each preset face key point of a certain number of users. In addition, it is also necessary to obtain the magnetic induction data of each user in each face region, and construct the second region feature vector corresponding to each user based on the magnetic induction data corresponding to each preset face key point and the magnetic induction data in each face region, which is equivalent to the fusion of the feature vector of the input face key point recognition sub-model and the feature vector of the input partition positioning sub-model in the aforementioned embodiment.

[0097] Since the above-mentioned second region feature vector contains both the feature information of the facial key points that can represent the user's identity and the feature information of different facial regions that can represent the user, the feature vector obtained by fusing the two can be used as a unique scalar for different facial regions of different users.

[0098] Similarly, the users here can be real users or users simulated based on a deformable 3D face model. The number of users can be flexibly adjusted according to the effect of model training and is not specifically limited here.

[0099] To facilitate understanding of the various embodiments of the present application, the face area positioning process of the embodiments of the present application can be divided into two stages: the face area positioning model training stage and the face area positioning model application stage.

[0100] As shown in Figure 3, a schematic diagram of a facial region positioning process in an embodiment of the present application is provided. During the facial region positioning model training phase, the facial key point recognition sub-model and the partition positioning sub-model can be trained separately. The facial key point recognition sub-model is trained by collecting magnetic induction data of preset facial key points of multiple users, and the partition positioning sub-model corresponding to each user is trained by collecting magnetic induction data of the facial regions of multiple users.

[0101] In the application stage of the face area positioning model, the electromagnetic induction data corresponding to the preset face key points collected in the initialization stage is first obtained, and then the real-time electromagnetic induction data between the wearable device and the beauty care device is obtained. The electromagnetic induction data corresponding to the preset face key points collected in the initialization stage is converted into feature vectors and input into the face key point recognition sub-model to obtain the user corresponding to the face key points, and then the partition positioning sub-model corresponding to the user is called, and the real-time electromagnetic induction data between the wearable device and the beauty care device is input into the partition positioning sub-model to obtain the positioning result of the beauty care device in the face area of ​​the user.

[0102] As shown in Figure 4, another face region positioning process diagram of an embodiment of the present application is provided. In the face region positioning model training phase, a face region positioning model is comprehensively trained by collecting magnetic induction data of preset facial key points and magnetic induction data of facial regions of multiple users.

[0103] During the application stage of the face area positioning model, the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data between the wearable device and the beauty care device can be directly converted into feature vectors and then fused into the face area positioning model, thereby directly obtaining the positioning result of the beauty care device in the current user's face area.

[0104] The present embodiment further provides a face region positioning device 500. As shown in FIG5 , a schematic structural diagram of a face region positioning device in the present embodiment is provided. The face region positioning device 500 includes: a first acquisition unit 510, a second acquisition unit 520, and a positioning unit 530, wherein:

[0105] The first acquisition unit 510 is configured to acquire electromagnetic induction data corresponding to preset facial key points when a user wears the wearable device and initializes the beauty and protection device based on preset facial key points;

[0106] The second acquisition unit 520 is configured to acquire real-time electromagnetic induction data between the wearable device and the beauty care device when the user uses the beauty care device;

[0107] The positioning unit 530 is used to perform positioning based on the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data using a preset facial area positioning model to obtain the facial area currently affected by the beauty care device.

[0108] In some embodiments of the present application, the preset face area positioning model includes a face key point recognition sub-model and a partition positioning sub-model, and the positioning unit 530 is specifically used to: perform user identity identification using the face key point recognition sub-model according to the electromagnetic induction data corresponding to the preset face key points, and obtain the user identity corresponding to the preset face key points; obtain the partition positioning sub-model corresponding to the user identity; perform partition positioning using the partition positioning sub-model according to the real-time electromagnetic induction data, and obtain the face area currently affected by the beauty care device.

[0109] In some embodiments of the present application, the positioning unit 530 is specifically used to: directly input the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data into the preset facial area positioning model to obtain the facial area on which the beauty care device is currently acting.

[0110] In some embodiments of the present application, the preset face area positioning model includes a face key point recognition sub-model and a partition positioning sub-model, and the preset face area positioning model is trained in the following manner: obtaining magnetic induction data of preset face key points of multiple users; using the magnetic induction data of preset face key points of multiple users to train the face key point recognition sub-model; obtaining magnetic induction data of face areas of multiple users; and using the magnetic induction data of face areas of multiple users to train the partition positioning sub-model corresponding to each user.

[0111] In some embodiments of the present application, the method of training the facial key point recognition sub-model using the magnetic induction data of preset facial key points of multiple users includes: constructing a facial key point feature vector corresponding to each user based on the magnetic induction data of preset facial key points of multiple users; and training the facial key point recognition sub-model using the facial key point feature vector corresponding to each user.

[0112] In some embodiments of the present application, the use of magnetic induction data of facial regions of multiple users to respectively train the partition positioning sub-model corresponding to each user includes: constructing a first region feature vector corresponding to each partition of each user based on the magnetic induction data of facial regions of multiple users; and using the first region feature vector corresponding to each partition of each user to respectively train the partition positioning sub-model corresponding to each user.

[0113] In some embodiments of the present application, the magnetic induction data of the facial area includes magnetic induction data of the left facial area and magnetic induction data of the right facial area, the partition positioning sub-model includes a left face partition positioning sub-model and a right face partition positioning sub-model, and the using the magnetic induction data of the facial areas of multiple users to respectively train the partition positioning sub-model corresponding to each user includes: using the magnetic induction data of the left facial area of ​​each user to respectively train the left face partition positioning sub-model corresponding to each user; using the magnetic induction data of the right facial area of ​​each user to respectively train the right face partition positioning sub-model corresponding to each user.

[0114] In some embodiments of the present application, the preset face area positioning model is trained in the following manner: obtaining magnetic induction data of preset face key points and magnetic induction data of face areas of multiple users; constructing a second area feature vector corresponding to each user based on the magnetic induction data of preset face key points and magnetic induction data of face areas of multiple users; and using the second area feature vector corresponding to each user to train the preset face area positioning model.

[0115] It can be understood that the above-mentioned face area positioning device can implement each step of the face area positioning method provided in the aforementioned embodiment. The relevant explanations about the face area positioning method are applicable to the face area positioning device and will not be repeated here.

[0116] An embodiment of the present application also provides a wearable device, comprising: a processor; and a memory arranged to store computer-executable instructions, wherein when the executable instructions are executed, the processor executes any of the aforementioned face area positioning methods.

[0117] FIG6 is a schematic diagram of the structure of a wearable device according to an embodiment of the present application. Referring to FIG6 , at the hardware level, the wearable device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage device. Of course, the wearable device may also include hardware required for other services.

[0118] The processor, network interface, and memory can be interconnected via an internal bus, such as an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. These buses can be classified into address buses, data buses, and control buses. For ease of illustration, FIG6 shows only one bidirectional arrow, but this does not imply that there is only one bus or only one type of bus.

[0119] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0120] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a face area positioning device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0121] When a user wears the wearable device and initializes the beauty and protection device based on preset facial key points, obtaining electromagnetic induction data corresponding to the preset facial key points;

[0122] When the user uses the beauty care device, obtaining real-time electromagnetic induction data between the wearable device and the beauty care device;

[0123] According to the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data, positioning is performed using a preset facial area positioning model to obtain the facial area currently affected by the beauty and protection device.

[0124] The method performed by the face region localization device disclosed in the embodiment shown in FIG1 of the present application can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the method can be completed by hardware integrated logic circuits in the processor or by software instructions. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0125] The wearable device can also execute the method executed by the face area positioning device in Figure 1, and realize the functions of the face area positioning device in the embodiment shown in Figure 1, and the embodiments of this application will not be repeated here.

[0126] The present application also provides a computer-readable storage medium that stores one or more programs. The one or more programs include instructions that, when executed by a wearable device that includes multiple application programs, enable the wearable device to execute the method executed by the face region positioning apparatus in the embodiment shown in FIG. 1 , and are specifically configured to execute:

[0127] When a user wears the wearable device and initializes the beauty and protection device based on preset facial key points, obtaining electromagnetic induction data corresponding to the preset facial key points;

[0128] When the user uses the beauty care device, obtaining real-time electromagnetic induction data between the wearable device and the beauty care device;

[0129] According to the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data, positioning is performed using a preset facial area positioning model to obtain the facial area currently affected by the beauty and protection device.

[0130] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0132] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0134] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0135] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0136] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0137] An embodiment of the present application further provides a beauty care system. As shown in FIG7 , a schematic diagram of the architecture of a beauty care system in an embodiment of the present application is provided. The beauty care system includes a beauty care device and the aforementioned wearable device.

[0138] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0139] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0140] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for locating a face region, wherein: The face area positioning method comprises: When the user wears the wearable device and initializes the beauty and protection device based on preset facial key points, obtaining electromagnetic induction data corresponding to the preset facial key points; When the user uses the beauty care device, obtaining real-time electromagnetic induction data between the wearable device and the beauty care device; According to the electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data, positioning is performed using a preset facial area positioning model to obtain the facial area currently affected by the beauty care device.

2. The method for locating a face region according to claim 1, wherein: The preset face area positioning model includes a face key point recognition sub-model and a partition positioning sub-model. The preset face area positioning model is used for positioning according to the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data to obtain the face area currently affected by the beauty care device, including: According to the electromagnetic induction data corresponding to the preset facial key points, the user identity is identified using the facial key point recognition sub-model to obtain the user identity corresponding to the preset facial key points; Obtaining a partition positioning sub-model corresponding to the user identity; According to the real-time electromagnetic induction data, the partition positioning sub-model is used to perform partition positioning to obtain the face area currently acted upon by the beauty care device.

3. The method for locating a face region according to claim 1, wherein: The face area currently affected by the beauty care device is obtained by positioning using the preset face area positioning model according to the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data, including: The electromagnetic induction data corresponding to the preset facial key points and the real-time electromagnetic induction data are directly input into the preset facial region positioning model to obtain the facial region currently acted upon by the beauty care device.

4. The method for locating a face region according to claim 1 or 2, wherein: The preset face region positioning model includes a face key point recognition sub-model and a partition positioning sub-model, and the preset face region positioning model is trained in the following manner: Acquire magnetic induction data of preset facial key points of multiple users; Using magnetic induction data of preset facial key points of multiple users to train a facial key point recognition sub-model; Acquire magnetic sensing data of facial regions of multiple users; The magnetic induction data of the face areas of multiple users are used to train the partition positioning sub-model corresponding to each user.

5. The method for locating a face region according to claim 4, wherein: The method of training the facial key point recognition sub-model using the magnetic induction data of preset facial key points of multiple users comprises: According to the magnetic induction data of preset facial key points of multiple users, construct the facial key point feature vector corresponding to each user respectively; The facial key point recognition sub-model is trained using the facial key point feature vector corresponding to each user.

6. The method for locating a face region according to claim 4, wherein: The method of using the magnetic induction data of the face regions of multiple users to respectively train the partition positioning sub-model corresponding to each user comprises: Constructing a first region feature vector corresponding to each partition of each user respectively according to the magnetic induction data of the face regions of the multiple users; The partition positioning sub-model corresponding to each user is trained respectively using the first region feature vector corresponding to each partition of each user.

7. The method for locating a face region according to claim 4, wherein: The magnetic induction data of the face area includes magnetic induction data of the left face area and magnetic induction data of the right face area, the partition positioning sub-model includes a left face partition positioning sub-model and a right face partition positioning sub-model, and the method of using the magnetic induction data of the face areas of multiple users to respectively train the partition positioning sub-model corresponding to each user includes: The magnetic induction data of each user's left face area is used to train the left face partition positioning sub-model corresponding to each user; The magnetic induction data of the right face area of ​​each user is used to train the right face partition positioning sub-model corresponding to each user.

8. The method for locating a face region according to claim 1 or 3, wherein: The preset face area positioning model is trained by the following method: Acquire magnetic induction data of preset facial key points and facial regions of multiple users; Constructing a second region feature vector corresponding to each user according to the magnetic induction data of preset facial key points and the magnetic induction data of facial regions of the plurality of users; The preset face region positioning model is trained using the second region feature vector corresponding to each user.

9. A facial region positioning device, wherein: The face area positioning device comprises: A first acquisition unit is used to acquire electromagnetic induction data corresponding to preset facial key points when a user wears the wearable device and initializes the beauty and protection device based on preset facial key points; A second acquisition unit is used to acquire real-time electromagnetic induction data between the wearable device and the beauty care device when the user uses the beauty care device; The positioning unit is used to perform positioning using a preset face area positioning model according to the electromagnetic induction data corresponding to the preset face key points and the real-time electromagnetic induction data, so as to obtain the face area currently acted upon by the beauty care device.

10. A wearable device comprising: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the face area positioning method according to any one of claims 1 to 8.

11. A beauty care system, wherein: The beauty care system comprises a beauty care device and the wearable device as claimed in claim 10.

Images