An interaction method, apparatus, device, medium, product

Abstract

The application discloses a kind of interactive method, device, equipment, medium, product in the field of photographing, which includes: for the shooting interface being displayed, if detecting the operation of obtaining reference image triggered on the shooting interface, at least one pose shooting point is extracted from the reference image first;Then, according to the at least one pose shooting point, the detection result of the viewfinder picture displayed on the shooting interface is obtained by detecting, so that the detection result includes the matching result between each point in the at least one pose shooting point and the viewfinder picture, so as to update the shooting interface according to the detection result subsequently, so that the photographer can know from the updated shooting interface that there are some deficiencies in the current viewfinder picture, so that the photographed object can be guided to adjust the pose based on the updated shooting interface subsequently, so that high-quality images can be taken under the guidance of these points, thereby improving the shooting experience.

Description

Technical Field

[0001] This application relates to the field of photography technology, and more particularly to an interactive method, device, equipment, medium, and product. Background Technology

[0002] With the widespread use of electronic devices (such as terminal devices), these devices are becoming increasingly feature-rich. Among them, the camera function is widely used by users, making it a pressing technical problem to solve how to use electronic devices to capture high-quality images. Summary of the Invention

[0003] To address the aforementioned technical problems, this application provides an interactive method, apparatus, device, medium, and product.

[0004] To achieve the above objectives, the technical solution provided in this application is as follows:

[0005] This application provides an interactive method, the method comprising: displaying a shooting interface; in response to detecting an operation of acquiring a reference image triggered on the shooting interface, acquiring at least one pose shooting point from the reference image, wherein different pose shooting points describe different body parts; detecting a viewfinder image displayed on the shooting interface based on the at least one pose shooting point to obtain a detection result, the detection result including a matching result between each point in the at least one pose shooting point and the viewfinder image, and updating the shooting interface based on the detection result.

[0006] In one possible implementation, updating the shooting interface based on the detection result includes: in response to detecting that the detection result indicates that there is a mismatch between the at least one pose shooting point and the viewfinder image, updating the shooting interface based on the mismatched point, wherein the updated shooting interface highlights the mismatched point.

[0007] In one possible implementation, updating the shooting interface based on the mismatched points includes: in response to detecting that at least one pose shooting point is displayed on the viewfinder, adjusting the display state of the mismatched point on the viewfinder, wherein the salience of the adjusted display state is higher than that of the unadjusted display state; and / or, in response to detecting that the at least one pose shooting point is not displayed on the viewfinder, adding the mismatched point to the viewfinder according to the position of the body part described by the mismatched point in the viewfinder.

[0008] In one possible implementation, updating the shooting interface based on the mismatch includes: adding suggested information corresponding to the mismatch to the shooting interface, wherein the suggested information describes the adjustment process from the posture of the body part described by the mismatch in the viewfinder to the posture indicated by the mismatch.

[0009] In one possible implementation, after updating the shooting interface based on the detection result, the method further includes: in response to detecting an operation triggered on the shooting interface to display the reference image, displaying a thumbnail of the reference image at a preset position in the viewfinder, or adding a transparent layer to the viewfinder, on which the reference image is displayed.

[0010] In one possible implementation, the updated shooting interface displays at least one pose shooting point that does not match the viewfinder; the method further includes: in response to detecting an operation triggered on the updated shooting interface to ignore the mismatched point, updating the detection result, wherein the updated detection result indicates that the mismatched point matches the viewfinder or that the updated detection result indicates that the mismatched point does not exist in the at least one pose shooting point, and continuing to perform the step of updating the shooting interface based on the detection result.

[0011] In one possible implementation, after updating the shooting interface based on the detection result, the method further includes: in response to detecting that the detection result indicates that there is a point in the at least one posture shooting point that does not match the viewfinder, continuing to perform the step of detecting the viewfinder displayed on the shooting interface based on the at least one posture shooting point to obtain a detection result.

[0012] In one possible implementation, the method further includes: in response to the detection that the duration of the mismatch between the key point and the viewfinder image reaches a preset duration, updating the detection result, wherein the updated detection result indicates that the mismatch between the key point and the viewfinder image is in a matching state or the updated detection result indicates that there is no mismatch between the key point and the viewfinder image among the at least one pose shooting key point, and continuing to perform the step of updating the shooting interface based on the detection result.

[0013] In one possible implementation, updating the detection result in response to the duration for which the mismatched point and the viewfinder image are in a mismatched state reaches a preset duration includes: displaying preset information on the shooting interface in response to the duration for which the mismatched point and the viewfinder image are in a mismatched state reaching the preset duration, wherein the preset information asks whether to ignore the mismatched point; and updating the detection result in response to detecting a trigger operation instruction for the preset information to ignore the mismatched point.

[0014] In one possible implementation, updating the shooting interface based on the detection result includes: in response to detecting that the detection result indicates that there is a point in the at least one posture shooting point that matches the viewfinder, updating the shooting interface based on the matching point, wherein the updated shooting interface weakly displays or does not display the matching point.

[0015] In one possible implementation, updating the shooting interface based on the detection result includes: in response to detecting that the detection result indicates that each of the at least one posture shooting point matches the viewfinder, shooting the viewfinder; or, displaying a prompt message on the shooting interface, the prompt message indicating that the viewfinder meets the shooting requirements.

[0016] In one possible implementation, the method is applied to an electronic device, and the method further includes: synchronizing the shooting interface to a display device, the display device being independent of the electronic device.

[0017] In one possible implementation, the method further includes: converting text data generated based on the detection results into speech data for playback, wherein the text data indicates the matching results between some or all of the at least one posture shooting points and the viewfinder image; or, converting some or all of the updated shooting interface into speech data for playback.

[0018] In one possible implementation, the step of obtaining at least one pose shooting point from the reference image in response to detecting an operation triggered on the shooting interface to acquire a reference image includes: displaying the reference image in the display area of ​​the shooting interface in response to detecting an operation triggered on the shooting interface to acquire the reference image; analyzing the reference image to obtain the at least one pose shooting point in response to detecting an operation triggered on the shooting interface to analyze the reference image, and adding each of the pose shooting points to the reference image according to the position of the body parts described by each pose shooting point in the reference image; the step of detecting the viewfinder image displayed on the shooting interface based on the at least one pose shooting point to obtain a detection result includes: displaying the viewfinder image in the display area in response to detecting an operation triggered on the shooting interface to display the viewfinder image, and detecting the viewfinder image displayed on the shooting interface based on the at least one pose shooting point to obtain a detection result.

[0019] This application provides an interactive device, comprising: a first display unit for displaying a shooting interface; a key point acquisition unit for acquiring at least one pose shooting key point from the reference image in response to detecting an operation triggered on the shooting interface to acquire a reference image, wherein different pose shooting key points describe different body parts; and a first update unit for detecting the viewfinder image displayed on the shooting interface based on the at least one pose shooting key point to obtain a detection result, wherein the detection result includes a matching result between each key point in the at least one pose shooting key point and the viewfinder image, and updating the shooting interface based on the detection result.

[0020] This application provides an electronic device, the device comprising: a processor and a memory; the memory for storing instructions or computer programs; the processor for executing the instructions or computer programs in the memory to cause the electronic device to perform the interactive method provided in this application.

[0021] This application provides a computer-readable medium, characterized in that the computer-readable medium stores instructions or computer programs that, when executed on a device, cause the device to perform the interactive method provided in this application.

[0022] This application provides a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the interactive method provided in this application.

[0023] Compared with related technologies, this application has at least the following advantages:

[0024] In the shooting solution provided in this application, when a shooting interface is being displayed, if an operation to obtain a reference image (such as a high-aesthetic image) is detected triggered on the shooting interface, at least one pose shooting point (such as "head slightly raised", "holding a colorful umbrella", "both legs bent and placed on a bench") is first obtained from the reference image. Then, based on the at least one pose shooting point, the viewfinder image displayed on the shooting interface is detected to obtain a detection result. The detection result includes the matching result between each point in the at least one pose shooting point and the viewfinder image, so that the detection result can indicate whether the current viewfinder image can meet these points. This allows the shooting interface to be updated based on the detection result, so that the updated shooting interface can represent the detection result to a certain extent. This allows the photographer to know what deficiencies exist in the current viewfinder image from the updated shooting interface, so that the photographer can guide the subject to adjust their pose based on the updated shooting interface. This enables shooting under the guidance of these points, thereby enabling the capture of high-quality images under the guidance of the reference image, which in turn improves the shooting experience.

[0025] Furthermore, for at least one pose shooting point extracted from the reference image, since different pose shooting points describe different body parts, these points can fully describe the pose details described by the reference image, so that the image taken under the guidance of these points can reproduce the pose described by the reference image as much as possible, thereby helping to improve the shooting quality. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating an interaction method provided in an embodiment of this application;

[0028] Figure 2 A schematic diagram illustrating a reference image acquisition process provided in an embodiment of this application;

[0029] Figure 3 This application provides an embodiment of a schematic diagram for adding key shooting points to a reference image;

[0030] Figure 4 A schematic diagram illustrating the switching from a reference image to a viewfinder image, provided as an embodiment of this application;

[0031] Figure 5 This is a schematic diagram illustrating an update method that adds display points indicating mismatch, as provided in an embodiment of this application.

[0032] Figure 6 This application provides an embodiment of a schematic diagram showing the key shooting points displayed on the viewfinder.

[0033] Figure 7 A schematic diagram illustrating a highlighting method provided in an embodiment of this application;

[0034] Figure 8 This is a schematic diagram illustrating an update method that adds display adjustment suggestions, as provided in an embodiment of this application.

[0035] Figure 9 A schematic diagram illustrating a weak display method provided in an embodiment of this application;

[0036] Figure 10 This is a schematic diagram illustrating a reference image displayed via thumbnails, as provided in an embodiment of this application.

[0037] Figure 11 A schematic diagram illustrating the display of a reference image using a transparent layer, as provided in an embodiment of this application;

[0038] Figure 12 A schematic diagram illustrating a key point ignoring process provided in an embodiment of this application;

[0039] Figure 13 A schematic diagram of a shooting process provided for an embodiment of this application;

[0040] Figure 14 This is a schematic diagram of the structure of an interactive device provided in an embodiment of this application;

[0041] Figure 15 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0042] Research has found that in order to capture better quality images, electronic devices offer some photography assistance technologies, such as automatic parameter setting (such as exposure, white balance, etc.) and autofocus, so that these technologies can provide assistance in some shooting details.

[0043] The research also found that the photography assistance technologies shown above are more suitable for providing assistance to photographers with some photography knowledge, so that when the photographer has already conceived how to take the picture, these technologies can help the photographer to take the picture according to their concept, thereby enabling them to take better high-quality images with the help of these technologies.

[0044] The study also found that for some photographers (such as those with insufficient photography knowledge or those who cannot come up with ideas on how to take photos), because these photographers have almost no ideas on how to take photos in the current environment (such as what poses the subject should take to look better), it is difficult for them to take high-quality images with the photography assistance techniques shown in the two paragraphs above, thus affecting their photography experience.

[0045] Based on the above research, in order to better improve the photography experience, this application provides an interaction method, which includes: for a shooting interface being displayed, if an operation to acquire a reference image (such as a high-aesthetic image) triggered on the shooting interface is detected, then at least one pose shooting point (such as "head slightly raised", "holding a colorful umbrella", "both legs bent and placed on a bench") is first acquired from the reference image; then, based on the at least one pose shooting point, the viewfinder image displayed on the shooting interface is detected to obtain a detection result, so that the detection result includes the matching result between each point in the at least one pose shooting point and the viewfinder image, thereby making the detection result... If the system can indicate whether the current viewfinder meets these requirements, the shooting interface can be updated based on the detection results. The updated interface will then reflect these results to a certain extent, allowing the photographer to identify any shortcomings in the current viewfinder. This enables the photographer to guide the subject in adjusting their pose based on the updated interface, thus ensuring high-quality images are captured under the guidance of the reference image. This effectively overcomes the limitations caused by the photographer's inability to conceive of a shooting strategy, thereby improving the shooting experience. Furthermore, since different poses describe different body parts, these points can fully describe the pose details depicted in the reference image. Therefore, images captured under these points can reproduce the pose described in the reference image as closely as possible, further enhancing image quality.

[0046] Furthermore, this application does not limit the subject executing the interactive method provided herein. For example, the method can be applied to a terminal device. Alternatively, the method can be implemented using a data processing procedure between the terminal device and the server. The terminal device can be a smartphone, computer, personal digital assistant (PDA), tablet computer, etc. The server can be a standalone server, a cluster server, or a cloud server.

[0047] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0048] To better understand the technical solution provided in this application, the interaction method provided in this application will be explained below with reference to some accompanying drawings. For example... Figure 1 As shown, the interaction method provided in the embodiments of this application includes S1-S3 below.

[0049] S1: Display shooting interface.

[0050] The shooting interface (also known as the camera interface) refers to the interface used when taking a picture, such as... Figure 2 The shooting interface 200 shown is designed so that the photographer can take a picture by triggering certain operations on the shooting interface.

[0051] Furthermore, this application does not limit the implementation method of the shooting interface; for example, it can be implemented using any shooting interface.

[0052] For example, in one possible implementation, the shooting interface may include a display area (such as...) Figure 2 The display area shown) and the operation area (such as) Figure 2 The shooting interface 200 shown includes areas other than the display area. The display area is used to provide information display functionality, ensuring that it can display at least some content, such as the viewfinder image (e.g., from...). Figure 2 The viewfinder shown in the shooting interface 200 is for the user to view. This operation area is used to provide some operation functions (such as shooting operation, etc.) so that the operation area can at least provide some interactive functions for the photographer. It should be noted that the viewfinder refers to the scene selected by the framing device (such as the viewfinder) on the camera during shooting, which can limit the range of scenery to be captured on the film.

[0053] Furthermore, this application does not limit the access process to the shooting interface; for example, it can be implemented using any process that allows access to the shooting interface. For ease of understanding, two examples are provided below.

[0054] Example 1: When the interaction method provided in this application is applied to an electronic device, if an application (App) capable of providing a shooting function is deployed on the electronic device (such as a terminal device like a mobile phone), the above-mentioned entry process for the shooting interface may include: in response to detecting an operation triggered on the electronic device to open the App (such as a click operation triggered by the App's icon or an operation to select the App to run in the foreground from multiple background applications), displaying the shooting interface (such as...) on the electronic device. Figure 2 The shooting interface 200 shown, and the viewfinder displayed on the shooting interface.

[0055] Example 2: When the interaction method provided in this application is applied to an electronic device, if the electronic device is an image acquisition device (such as a camera, SLR camera, etc.), the above-mentioned entry process of the shooting interface may include: in response to detecting a power-on operation triggered for the electronic device (such as pressing the power button, etc.), displaying the shooting interface on the electronic device, and displaying the viewfinder on the shooting interface.

[0056] Based on the above content of S1, it can be seen that for any electronic device that can provide a photo-taking function (such as a mobile phone, computer, or camera), if an operation to enter the shooting interface is triggered on the electronic device, the shooting interface is displayed on the electronic device, and the viewfinder image is displayed in the display area of ​​the shooting interface.

[0057] S2: In response to detecting an operation to acquire a reference image triggered on the shooting interface, acquire at least one pose shooting point from the reference image, wherein different pose shooting points describe different body parts.

[0058] The reference image refers to the image referenced during the shooting process (such as...). Figure 2 The image shown (1) is used to illustrate how to capture a high-quality image under the current shooting conditions, so that the reference image can serve as a model to guide the current shooting, and further enable the reference image to provide some guidance for the current shooting (such as guidance on what poses the subject looks better), thus better overcoming the defects caused by the photographer's inability to conceive how to shoot.

[0059] Furthermore, this application does not limit the reference image. For example, the reference image may at least satisfy some or all of the following constraints: the similarity between the background of the reference image and the current shooting environment (such as color distribution, light distribution, etc.) exceeds a preset first threshold; the similarity between the clothing of the person in the reference image and the clothing (such as makeup, clothing, etc.) of the subject being photographed in the current shooting exceeds a preset second threshold; the reference image is a high-quality image or a high-aesthetic image (such as an image with a high score obtained by scoring using some or all of the indicators such as the number of reposts, the number of favorites, the number of likes, etc.).

[0060] It should be noted that this application does not limit the method of obtaining the aforementioned "current shooting environment state". For example, the "current shooting environment state" can be obtained using any method capable of acquiring the shooting environment, such as by having relevant personnel input environmental description information (such as text and / or images). Furthermore, to better improve flexibility, the "current shooting environment state" can also be obtained in real time using an electronic device displaying the shooting interface, so that the viewfinder displayed on the electronic device can describe the "current shooting environment state" in real time, thereby facilitating the photographer to capture the surrounding environment (e.g., by...). Figure 2 The scanning function shown in the shooting interface 200 obtains the "current shooting environment status".

[0061] It should also be noted that this application does not limit the method of obtaining the "attire of the subject under current shooting". For example, the "attire of the subject under current shooting" can be obtained by any method that can obtain the attire of the subject, such as by having relevant personnel input description information of the attire (such as text and / or images). Furthermore, to better improve flexibility, the "attire of the subject under current shooting" can also be obtained in real time using an electronic device displaying the shooting interface, so that the viewfinder displayed on the electronic device can describe the "attire of the subject under current shooting" in real time, thereby facilitating the photographer to obtain the "attire of the subject under current shooting" by shooting the subject.

[0062] Furthermore, the aforementioned "operation to acquire a reference image" refers to an operation triggered on the shooting interface in display mode, requesting to acquire the reference image; and this application does not limit the implementation of the "operation to acquire a reference image." For example, the "operation to acquire a reference image" may include an operation triggered by the user on the shooting interface to provide an image (such as an image upload operation). As another example, the "operation to acquire a reference image" may include multiple candidate images provided by the shooting interface (such as those from...). Figure 2The image selection operation is performed using images 1 to 4 shown in the shooting interface 201. It can be seen that, in one possible implementation, the reference image may be provided by the user to the electronic device displaying the shooting interface in a certain way, or the reference image may refer to the image displayed by the electronic device (such as...). Figure 2 The selected image (such as...) is provided by the shooting interface 201) among some candidate images. Figure 2 Image 1 shown.

[0063] Furthermore, for the aforementioned reference image, at least one pose capture point extracted from the reference image is obtained through capture point analysis of the reference image (e.g., by...). Figure 3 The analysis assists this function shown in the shooting interface 201, so that the at least one shooting point of the posture (such as by) is obtained. Figure 3 The various points shown in the shooting interface 202 can describe the state of the person in the reference image, such as the posture of each body part. In particular, since different posture shooting points describe different body parts, the at least one posture shooting point can describe the state of the person in the reference image as comprehensively as possible, so that the at least one posture shooting point can be used as guidance information to influence the current shooting.

[0064] Furthermore, this application does not limit the method of obtaining the above-mentioned at least one posture shooting point. For example, the process of obtaining the at least one posture shooting point may include: if an operation to obtain a reference image is detected triggered on the shooting interface, then the posture shooting point corresponding to the reference image is searched from a pre-constructed mapping relationship and used as the at least one posture shooting point. The mapping relationship is used to record the posture shooting points corresponding to each reference image.

[0065] For example, the process of obtaining at least one pose shooting point may include: if an operation to acquire a reference image is detected triggered on the shooting interface, then a pre-built machine learning model with shooting point (such as pose shooting point) analysis function is used to analyze the reference image to obtain the at least one pose shooting point. It should be noted that this application does not limit the implementation method of the machine learning model; for example, it may be implemented using a visual language model. Therefore, in one possible implementation, after acquiring the reference image, the shooting point analysis can be performed on the reference image based on the visual language model to obtain the shooting points output by the visual language model, such as the at least one pose shooting point.

[0066] For example, in some scenarios, such as when there are reference images with advantages in comments and / or video reviews, the process of obtaining at least one pose shooting point may include: if an operation to obtain a reference image is detected on the shooting interface, then shooting point analysis is performed based on the reference image and its associated information (such as comments, explanatory videos, etc.) to obtain the at least one pose shooting point. This allows the at least one pose shooting point to more accurately represent the advantages of the reference image, thereby enabling the at least one pose shooting point to more accurately represent how to shoot high-quality images. Since the associated information can indicate the advantages of the reference image, the at least one pose shooting point determined based on the associated information can also represent those advantages. This allows images shot using the at least one pose shooting point as guidance to inherit those advantages as much as possible, thus improving the shooting experience. It should be noted that this application does not limit the method of obtaining the associated information.

[0067] S3: Based on at least one pose shooting point, detect the viewfinder image displayed on the shooting interface to obtain a detection result. The detection result includes the matching result between each point in the at least one pose shooting point and the viewfinder image, and updates the shooting interface based on the detection result.

[0068] The detection result is obtained by detecting the viewfinder image (such as a real-time captured viewfinder image) displayed on the shooting interface based on at least one of the above-mentioned posture shooting points. The detection result includes the matching result between each point in the at least one posture shooting point and the viewfinder image, so that the detection result can indicate whether the viewfinder image matches each point in the at least one posture shooting point. In turn, the detection result can indicate whether the viewfinder image can meet each point in the at least one posture shooting point, so that the shooting interface can be updated according to the detection result. The updated shooting interface can present the detection result to a certain extent, so that the photographer can know the detection result through the updated shooting interface.

[0069] It should be noted that this application does not limit the method of obtaining the above detection results. For example, it can be implemented using any method that can evaluate whether some information (such as text) matches an image. Furthermore, in some scenarios, the detection results can be determined using a visual language model with a dual-tower structure, such as a Contrastive Language-Image Pre-training (CLIP) model. This determination process can involve providing the viewfinder image as one input to the model and providing at least one of the above-mentioned pose shooting points (or the feature vector of the at least one pose shooting point) as another input to the model, so that the model can calculate the matching degree between the two inputs and output the detection result, thereby indicating whether the viewfinder image meets these points. It should be noted that this application does not limit the implementation method of the detection results; for example, it can be implemented using text or matching degree.

[0070] Furthermore, this application does not limit the implementation of the step "update the shooting interface based on the detection result" in S3 above. For example, it can specifically be: add the display of the detection result in the shooting interface so that the photographer can know the detection result through the shooting interface.

[0071] Based on the above-mentioned content of S1 to S3, it can be seen that the photo-taking process provided by this application includes: for a currently displayed shooting interface, if it detects that an event triggering the acquisition of a reference image (such as...) is occurring on the shooting interface... Figure 3 The operation shown in image 1) first obtains at least one pose capture point from the reference image (such as from...). Figure 3The shooting interface 202 shows shooting points such as "head slightly tilted up"; then, based on at least one posture shooting point, the viewfinder image displayed on the shooting interface is detected to obtain a detection result, so that the detection result includes the matching result between each point in the at least one posture shooting point and the viewfinder image, so that the detection result can indicate whether the current viewfinder image can meet these points, so that the shooting interface can be updated according to the detection result, so that the updated shooting interface can represent the detection result to a certain extent, so that the photographer can know what deficiencies exist in the current viewfinder image from the updated shooting interface, so that the photographer can guide the subject to adjust the posture based on the updated shooting interface. In this way, shooting can be carried out under the guidance of these points, so that high-quality images can be captured under the guidance of the reference image, thereby effectively overcoming the defects caused by the photographer's inability to conceive how to take the picture, thus improving the shooting experience. The key points for shooting different poses describe different body parts, so that these key points can fully describe the pose details described by the reference image. This allows the images taken under the guidance of these key points to reproduce the pose described by the reference image as much as possible, thereby improving the shooting quality.

[0072] Research has found that in some shooting scenarios, reference images can be used not only to guide the subject's posing, but also to guide aspects such as lighting, color, and composition, in order to capture higher quality images.

[0073] Based on the above research, in order to better improve the shooting effect, the process of obtaining the above detection results can at least include: detecting the viewfinder image displayed on the shooting interface based on multiple dimensions of shooting points extracted from the reference image, so that the detection results include the matching results between the shooting points of each dimension and the viewfinder image, thereby enabling the detection results to indicate whether the viewfinder image can meet the shooting points of each dimension. Since the multiple dimensions of shooting points include not only at least one pose shooting point, but also lighting shooting points, color shooting points, composition shooting points, etc., the multiple dimensions of shooting points can comprehensively describe the characteristics (such as advantages) of the reference image as much as possible. This allows the image captured under the guidance of the multiple dimensions of shooting points to inherit these characteristics as much as possible, thus contributing to a better shooting effect.

[0074] It should be noted that this application does not limit the determination method of the above-mentioned multiple dimensions. For example, it can be determined based on the shooting requirements of the actual application scenario (such as which dimensions of shooting quality are more important in the application scenario) and / or the related information of the reference image (such as comments, explanatory videos, etc.) so that the multiple dimensions can describe the advantages of the reference image as comprehensively as possible. This allows the subsequent shooting points of the multiple dimensions to describe as accurately as possible why the reference image is a high-quality image. Consequently, the images taken under the guidance of the shooting points of the multiple dimensions can inherit these advantages as much as possible, which is conducive to improving the shooting effect.

[0075] Research has found that in some scenarios, when shooting with a reference image as a guide, photographers may focus more on shooting points that are not yet met in the current framing. Therefore, to better meet the aforementioned needs, the step of "updating the shooting interface based on the detection result" in S3 may include: in response to detecting that the detection result indicates that there are points in at least one of the above-mentioned posture shooting points that do not match the framing, updating the shooting interface based on the mismatched points. The updated shooting interface highlights the mismatched points, so that photographers can quickly identify the problems in the current framing through the updated shooting interface, which is conducive to correcting these problems under the guidance of these points, thereby improving shooting efficiency.

[0076] As can be seen, for the viewfinder image currently displayed in the shooting interface (such as that shown by...), Figure 4 or Figure 5 Regarding the viewfinder shown in the shooting interface 203, after detecting the viewfinder based on at least one of the above-mentioned posture shooting points and obtaining the detection result, it is possible to first determine, based on the detection result, any points in the at least one posture shooting point that do not match the viewfinder (such as those from...). Figure 5 The shooting interface 204 shows the key point of "right hand holding the ball" so that the mismatched key point can indicate the area where the person in the frame needs improvement; then, the shooting interface is updated according to the mismatched key point so that the updated shooting interface can highlight the mismatched key point, so that the photographer can quickly know how to optimize the shooting through the updated shooting interface, thereby improving efficiency.

[0077] It should be noted that the above-mentioned "highlighting" refers to highlighting certain content (such as the mismatched points mentioned above) so that users can easily notice the content, which helps to strengthen users' attention to the content; moreover, this application does not limit the implementation method of the above-mentioned "highlighting". For example, it can be implemented in any way that can highlight some information, such as colored text, text with dynamic changing effects, or using eye-catching borders for marking.

[0078] Additionally, in some scenarios, such as when the shooting point is not displayed in the viewfinder, to improve shooting results, the aforementioned step of "updating the shooting interface based on the mismatched point" can include: responding to the detection of the viewfinder (e.g., by...). Figure 5 If at least one of the above-mentioned pose shooting points is not displayed on the viewfinder shown in the shooting interface 203, the viewfinder is updated to display the mismatched point by adding the mismatched point to the viewfinder based on the position of the body part described in the viewfinder. This allows for the shooting of the body part in the viewfinder (as described by the shooting interface 203) without displaying the pose shooting points. Figure 5 The mismatch is highlighted by marking the corresponding position in the viewfinder (as shown in the shooting interface 204), allowing the photographer to quickly identify the problem in the viewfinder, thus improving the efficiency of problem discovery and resolution, and ultimately improving shooting efficiency.

[0079] As can be seen, for the viewfinder image currently displayed in the shooting interface (such as that shown by...), Figure 5 Taking the viewfinder shown in the shooting interface 203 as an example, if the viewfinder does not display at least one of the above-mentioned posture shooting points, then after detecting the viewfinder based on the at least one posture shooting point and obtaining a detection result, the points that do not match the viewfinder indicated by the detection result (such as those indicated by the at least one posture shooting point) can be... Figure 5 The key point of "right hand holding the ball" shown in the shooting interface 204 is directly added to the corresponding position in the viewfinder, so that the photographer can quickly know where the problem is in the viewfinder. This helps to improve the efficiency of problem discovery and resolution, thereby improving shooting efficiency.

[0080] It should be noted that this application does not limit the method of obtaining the "position of the body part described by the mismatched point in the viewfinder". For example, the position can be obtained by processing the mismatched point (or the feature vector of the mismatched point) with the viewfinder using a pre-built machine learning model with localization capabilities, so that the position can represent the marked position of the mismatched point in the viewfinder. Furthermore, this application does not limit the implementation method of the machine learning model. For example, it can be implemented using a pre-built visual localization model. This visual localization model is used to predict the position of information (such as text) in an image.

[0081] Furthermore, in some scenarios, such as when the viewfinder is displaying various shooting points, to improve shooting results, the aforementioned step of "updating the shooting interface based on the mismatched points" may include: responding to the detection of the viewfinder (e.g., by...) Figure 6 or Figure 7 The viewfinder shown in the shooting interface 205 displays at least one of the above-mentioned pose shooting points. Adjust the display state of the mismatched point on the viewfinder. The adjusted display state (e.g., from...) Figure 7 The "right hand holding the ball" key point displayed in the shooting interface 206 is more prominent than the display state before the adjustment (as shown in the previous state). Figure 7 The degree of prominence of the "right hand holding the ball" key point shown in the shooting interface 205 can be adjusted to highlight the mismatched key point by adjusting its display state in the viewfinder. This allows the photographer to quickly identify where the problem is in the viewfinder, improving the efficiency of problem discovery and resolution, and thus improving shooting efficiency.

[0082] As can be seen, for the viewfinder image currently displayed in the shooting interface (such as that shown by...), Figure 7 Taking the viewfinder shown in the shooting interface 205 as an example, if the viewfinder is displaying at least one of the above-mentioned posture shooting points, after detecting the viewfinder based on the at least one posture shooting point and obtaining the detection result, the display state of the points that do not match the viewfinder indicated by the detection result can be adjusted to a prominent state (e.g., by...). Figure 7 The display status of the "right hand holding the ball" point shown in the shooting interface 206 is used to make the mismatched point more eye-catching, so that the photographer can quickly know where the problem is in the frame. This helps to improve the efficiency of problem discovery and resolution, thereby improving shooting efficiency.

[0083] It should be noted that the "display state" described in the above two paragraphs describes the state in which a key shooting point is displayed on the viewfinder, such as text color, font size, etc. Furthermore, this application does not limit the implementation method of this display state.

[0084] It should also be noted that this application is not limited to a control method that displays at least one pose shooting point on the viewfinder. For example, the control method could be a control with the control function deployed on the shooting interface (such as a...). Figure 6 This can be achieved using the prompt button shown in the shooting interface 203. Alternatively, this control method can also be achieved using some pre-set trigger operations (such as a left swipe operation triggered in the viewfinder).

[0085] Research has found that in some scenarios, such as when the details of a person's pose are difficult to understand or notice, the photographer may not know how to improve the pose of the person in the current frame to achieve the same effect as the person in the reference image. This may affect the shooting results, such as shooting quality and shooting efficiency.

[0086] Based on the above research, in order to better improve shooting results, the step of "updating the shooting interface according to the mismatch point" may include: adding suggested information (such as suggestions from...) to the shooting interface to display the mismatch point. Figure 8 The adjustment suggestions shown in the shooting interface 207 describe the process of adjusting the posture of the body part described by the mismatch point in the viewfinder to the posture indicated by the mismatch point. This allows the photographer to better understand how to optimize the current viewfinder from the adjustment suggestions, thereby improving the shooting effect, such as increasing shooting efficiency and improving shooting quality.

[0087] As can be seen, for the viewfinder image currently displayed in the shooting interface (such as that shown by...), Figure 8 Regarding the viewfinder shown in the shooting interface 205, after detecting the viewfinder based on at least one of the above-mentioned shooting posture points and obtaining the detection result, the suggested information corresponding to the mismatched points can be determined based on the points indicated by the detection result that do not match the viewfinder (such as suggestions from...). Figure 8 The adjustment suggestions shown in the shooting interface 207 are intended to indicate how to position the body parts described by the mismatched points in the viewfinder (e.g., by...). Figure 8 Adjust the right hand position shown in the shooting interface 205 to the posture indicated by the mismatched key point (such as by...). Figure 2The shooting interface 201 shows the right-hand state, which allows the photographer to quickly learn how to optimize the current framing from the adjustment suggestions, thereby improving the optimization effect and thus improving the shooting effect.

[0088] Research has found that in some scenarios, such as when shooting points are being displayed in the viewfinder, to avoid interference from already matched points, the photographer's attention to these matched points can be reduced by adjusting their display status. Therefore, to better meet the aforementioned needs, the step of "updating the shooting interface based on the detection result" in S3 may include: in response to detecting that the detection result indicates that at least one of the above-mentioned posture shooting points contains a point that matches the viewfinder, updating the shooting interface based on the matched point. The updated shooting interface (e.g., ...) Figure 9 The shooting interface 208 shown may display or not display the matching key points, making it difficult for the photographer to see the matching key points directly through the updated shooting interface. This helps to reduce the interference caused by the matching key points to the photographer, and in turn encourages the photographer to pay more attention to the non-matching key points, thus improving the shooting effect.

[0089] As can be seen, for the viewfinder image currently displayed in the shooting interface (such as that shown by...), Figure 9 Taking the viewfinder shown in the shooting interface 205 as an example, if the viewfinder is displaying at least one of the above-mentioned pose shooting points, after detecting the viewfinder based on the at least one pose shooting points and obtaining the detection result, the points that exist in the at least one pose shooting points and match the viewfinder can be determined based on the detection result, so that the matching points can indicate the parts of the person in the viewfinder that do not need improvement; then, the shooting interface is updated based on the matching points, so that the updated shooting interface can be faintly displayed (e.g., from...). Figure 9 The shooting interface 208, as shown, uses a collapsed bubble to weaken or conceal the matching key point, allowing the photographer to ignore it through the updated shooting interface. This, in turn, encourages the photographer to focus more on the non-matching key points (such as those shown in the image). Figure 9 The key point shown in the shooting interface 208 is "holding the ball with your right hand," which helps to improve the shooting effect.

[0090] Research has revealed that in certain scenarios (such as those with mismatched elements), users may need to "review the reference image" during shooting. This allows them to compare their current viewfinder image with the reference image to ensure the framing is satisfactory. Example 1: If the current viewfinder image doesn't match some shooting elements, the photographer might want to review the reference image to more accurately identify the problems and how to optimize it. Example 2: If the current viewfinder image matches some shooting elements, the photographer might want to review the reference image to more accurately determine if minor adjustments are needed to overcome the subtle differences between the viewfinder and the reference image.

[0091] Based on the above research, and to better meet the aforementioned needs, this application also provides a possible implementation of the interaction method. In this implementation, the interaction method may further include: after the above-mentioned step of "updating the shooting interface based on the detection result", responding to the detection of an operation triggering the display of a reference image on the shooting interface (such as by...). Figure 10 The operation of clicking the prompt button shown in the shooting interface 209 will display a thumbnail of the reference image at a preset position in the viewfinder (such as...). Figure 10 The thumbnail 211 shown in the shooting interface 210 allows the photographer to better understand how to optimize the viewfinder by comparing the viewfinder with the thumbnail, thereby facilitating the capture of higher quality images.

[0092] As can be seen, for the viewfinder image currently displayed in the shooting interface, after detecting the viewfinder image based on at least one of the above-mentioned posture shooting points and obtaining the detection result, the shooting interface is first updated based on the detection result, so that the updated shooting interface (e.g., Figure 10 The shooting interface 209 shown displays the matching between the viewfinder and these shooting points, so that when an operation to display a reference image triggered on the updated shooting interface is detected (such as by...), the matching is updated to match the viewfinder view with these shooting points. Figure 10 When the user clicks the prompt button shown in the shooting interface 209, a thumbnail of the reference image is added to the preset position of the viewfinder, so that the photographer can see the thumbnail and the viewfinder at the same time. This allows the photographer to better understand how to optimize the viewfinder by comparing the viewfinder with the thumbnail, which is conducive to capturing higher quality images.

[0093] It should be noted that the preset positions shown in the above two paragraphs refer to the display position of the thumbnail of the reference image. This application does not limit the implementation of this preset position; for example, it can be implemented using a pre-fixed position (such as the lower left corner of the viewfinder). Furthermore, in some scenarios (such as those focusing on the aforementioned mismatched points), for better comparison, the preset position can be determined based on the position of the body part described in the mismatched point within the viewfinder. This ensures that the distance between the preset position and the "position of the body part described in the mismatched point within the viewfinder" is less than a preset distance. This effectively ensures that the thumbnail is displayed around the mismatched point, facilitating easier comparison between the viewfinder and the thumbnail, and ultimately leading to higher-quality image capture.

[0094] It should also be noted that, for the thumbnails of the reference images shown in the above three paragraphs, the thumbnails can describe the information carried by the reference images with a smaller image size, so that the thumbnails can occupy a smaller area to present the information carried by the reference images, thereby helping to reduce the obstruction of the viewfinder and thus better overcome the problems caused by obstruction.

[0095] It should also be noted that, regarding the aforementioned "operation of displaying a reference image triggered on the shooting interface," this operation requests the addition of the reference image to the shooting interface; and this application does not limit the implementation method of this operation. For example, it can be implemented using some pre-set triggering operations (such as a right swipe operation triggered in the viewfinder). Alternatively, it can employ a control deployed on the shooting interface that has the function of adding the display of the reference image (such as a control provided by...). Figure 10 The click operation is performed by the prompt button shown in the image on the shooting interface 209. This prompt button controls whether the prompt appears on the viewfinder in a certain manner (e.g., ...). Figure 10 The thumbnail view shown adds a reference image; and the key point prompt button in the shooting interface 209 can control whether to add at least one pose shooting point extracted from the reference image to the viewfinder.

[0096] It should also be noted that, regarding the control shown above that adds the function of displaying the reference image (such as the prompt button in the above figure), this application does not limit the timing of the control's display. For example, the control may be displayed when the content displayed in the shooting interface's display area is switched from the reference image to the viewfinder. Furthermore, in some scenarios (such as scenarios where attention is focused on the aforementioned mismatched points), the display process of the control may be as follows: in response to detecting that the above detection result indicates that at least one of the above-mentioned posture shooting points contains a point that does not match the viewfinder, the control is added to the shooting interface so that the photographer can subsequently use the control to meet their need to view the reference image.

[0097] In addition, in some scenarios, such as when the pose of a person in the reference image is complex or when it is necessary to reproduce the pose of a person in the reference image as accurately as possible, this application also provides a possible implementation of the interaction method to better improve the image shooting effect. In this implementation, the interaction method may further include: after the above-mentioned step of "updating the shooting interface according to the detection result", responding to the detection of an operation to display the reference image triggered on the shooting interface (such as by...). Figure 11 The operation of clicking the prompt button shown in image 209 of the shooting interface) adds a transparent layer to the viewfinder (such as a layer made of...). Figure 11 The transparent layer shown in the shooting interface 212 displays the reference image, allowing the photographer to see both the reference image and the viewfinder simultaneously. This enables the photographer to better understand how to optimize the viewfinder by comparing it with the reference image, thus facilitating the capture of higher-quality images.

[0098] As can be seen, for the viewfinder image currently displayed in the shooting interface, after detecting the viewfinder image based on at least one of the above-mentioned posture shooting points and obtaining the detection result, the shooting interface is first updated based on the detection result, so that the updated shooting interface (e.g., Figure 11 The shooting interface 209 shown displays the matching between the viewfinder and these shooting points, so that when an operation to display a reference image triggered on the updated shooting interface is detected (such as by...), the matching is updated to match the viewfinder view with these shooting points. Figure 11When the user clicks the prompt button shown in the shooting interface 209, a transparent layer (such as a mask) is added above the viewfinder to display a reference image. This allows the photographer to see both the reference image and the viewfinder simultaneously, enabling them to better understand how to optimize the viewfinder by comparing it with the reference image. This leads to higher-quality images. Furthermore, the transparent layer can align the person in the reference image with the person in the viewfinder to a certain extent, allowing the photographer to more accurately identify problems in the current viewfinder and how to solve them, thus improving the shooting results.

[0099] It should be noted that this application does not limit the implementation method of the transparent layer shown in the above two paragraphs. For example, it can be implemented using any layer with a certain degree of transparency (such as a semi-transparent layer). Furthermore, to better improve the comparison effect, the transparent layer can at least satisfy the following constraint: the bounding box of the person in the reference image displayed on the transparent layer is completely aligned with the bounding box of the person in the viewfinder. This maximizes the alignment of the two images, thereby better representing the difference between the posture of different body parts in the viewfinder and the ideal posture described by the reference image. This allows the photographer to more accurately understand what problems exist in the current viewfinder and how to solve them, thus improving the shooting effect.

[0100] Research has revealed that in some scenarios, certain shooting techniques may be impossible or difficult to execute. Therefore, to avoid the impact of these shooting techniques on the shooting process, this application also provides a possible implementation of the interaction method. In this method, when the updated shooting interface (such as...) is accessed... Figure 12 When the shooting interface 208 shown displays at least one of the above-mentioned pose shooting points that does not match the viewfinder, the interaction method may further include: in response to detecting an operation triggered on the updated shooting interface to ignore the mismatched point, updating the detection result, wherein the updated detection result indicates that the mismatched point is in a matching state with the viewfinder or the updated detection result indicates that the mismatched point does not exist in the at least one pose shooting point, and returning to continue executing the above-mentioned step of "updating the shooting interface according to the detection result" and its subsequent steps. In this way, the shooting difficulty can be reduced by manually ignoring some mismatched points, thereby improving the shooting experience.

[0101] As can be seen, in one possible implementation, the photographing process provided by this application includes: for a currently displayed shooting interface, if an operation to acquire a reference image is detected triggered on the shooting interface, then based on at least one pose shooting point extracted from the reference image, the viewfinder image displayed on the shooting interface is detected to obtain a detection result, and the shooting interface is updated based on the detection result, so that the updated shooting interface (e.g., ...) Figure 12 The shooting interface 208 shown displays points in the at least one pose shooting point that do not match the viewfinder. When an operation to ignore the mismatched point is detected on the updated shooting interface, the detection result is updated so that the updated detection result indicates that the mismatched point matches the viewfinder (or the updated detection result indicates that the mismatched point does not exist in the at least one pose shooting point). This makes the updated detection result no longer indicate that the current viewfinder cannot meet the mismatched point, and returns to continue executing the aforementioned step of "updating the shooting interface based on the detection result" and its subsequent steps. In this way, the shooting difficulty can be reduced by manually ignoring some mismatched points, thereby improving the shooting experience.

[0102] It should be noted that, regarding the "ignore the mismatched point" operation shown in the above two paragraphs, this operation requests that the mismatched point not be used to guide the shooting, and this application does not limit the implementation method of this operation. For example, it can be implemented in any way that can delete content from the page (such as first long-pressing the mismatched point to reveal the delete button of the mismatched point; then clicking the delete button, etc.).

[0103] Research has shown that to improve shooting results, shooting can be completed through multiple iterations. Based on this, this application also provides a possible implementation of the interaction method. In this method, the interaction method may further include: after the aforementioned step of "updating the shooting interface based on the detection result," in response to detecting that the detection result indicates that at least one of the above-mentioned posture shooting points contains a point that does not match the viewfinder image, returning to continue executing the aforementioned step of "detecting the viewfinder image displayed on the shooting interface based on at least one posture shooting point to obtain a detection result" and its subsequent steps. This enables multiple rounds of optimization of the viewfinder image under the guidance of these shooting points, which is beneficial for capturing higher-quality images.

[0104] As can be seen, in one possible implementation, the photo-taking process provided by this application includes: for a currently displayed shooting interface, if an operation to acquire a reference image is detected triggered on the shooting interface, then based on at least one pose shooting point extracted from the reference image, the viewfinder image displayed on the shooting interface is detected to obtain a detection result, and the shooting interface is updated based on the detection result, so that when it is determined that the updated shooting interface (or the detection result) indicates a point in the at least one pose shooting point that does not match the viewfinder image, the process returns to continue executing the aforementioned step of "detecting the viewfinder image displayed on the shooting interface based on at least one pose shooting point extracted from the reference image" and its subsequent steps to achieve the next round of processing, thus enabling the capture of high-quality images through multiple iterations.

[0105] In addition, to further improve the shooting experience, this application also provides a possible implementation of the interaction method. In this method, when the interaction method is implemented through the multi-round iteration method shown in the above two paragraphs, the interaction method may further include: in response to the detection that the duration of the mismatch between the above-mentioned key points and the viewfinder image reaches a preset duration, updating the detection result, wherein the updated detection result indicates that the mismatch between the key points and the viewfinder image is in a matching state or the updated detection result indicates that there are no mismatched key points in at least one pose shooting key point, and returning to continue executing the above-mentioned step of "updating the shooting interface according to the detection result" and its subsequent steps. In this way, the shooting difficulty can be reduced by automatically ignoring some mismatched key points, thereby improving the shooting experience.

[0106] As can be seen, in one possible implementation, the photographing process provided by this application includes: for a currently displayed shooting interface, if an operation to acquire a reference image is detected triggered on the shooting interface, then based on at least one pose shooting point extracted from the reference image, the viewfinder image displayed on the shooting interface is detected to obtain a detection result; and the shooting interface is updated based on the detection result, so that when it is determined that the updated shooting interface (or the detection result) indicates a point in the at least one pose shooting point that does not match the viewfinder image, the process returns to continue executing the aforementioned step of "detecting the viewfinder image displayed on the shooting interface based on at least one pose shooting point extracted from the reference image to obtain a detection result" and its subsequent steps, to achieve the next round of processing. The process iterates until the duration of the mismatch between the key point and the viewfinder reaches a preset duration. At this point, it can be determined that the subject may have difficulty meeting the mismatch. Therefore, to reduce the shooting difficulty, the detection result is updated so that the updated detection result indicates that the mismatch is in a matching state with the viewfinder (or the updated detection result indicates that the mismatch does not exist in the at least one pose shooting key point). This makes the updated detection result no longer indicate that the current viewfinder cannot meet the mismatch, and returns to continue executing the aforementioned "update shooting interface based on the detection result" step and its subsequent steps. This reduces the shooting difficulty by automatically ignoring some mismatches, thereby improving the shooting experience.

[0107] Furthermore, to better improve the shooting experience, the step of "updating the detection result in response to the duration for which the mismatched key point and the viewfinder image are in a mismatched state reaching a preset duration" may include: in response to the duration for which the mismatched key point and the viewfinder image are in a mismatched state reaching a preset duration, displaying preset information on the shooting interface, which asks whether to ignore the mismatched key point; and updating the detection result in response to the detection of an operation instruction triggered by the preset information to ignore the mismatched key point. This reduces the shooting difficulty by asking the photographer to ignore some mismatched key points, thereby improving the shooting experience.

[0108] As can be seen, in one possible implementation, the photo-taking process provided by this application includes: for a currently displayed shooting interface, if an operation to acquire a reference image is detected triggered on the shooting interface, then based on at least one pose shooting point extracted from the reference image, the viewfinder image displayed on the shooting interface is detected to obtain a detection result, and the shooting interface is updated based on the detection result. If it is determined that the updated shooting interface (or the detection result) indicates a point in the at least one pose shooting point that does not match the viewfinder image, the process returns to continue executing the aforementioned step of "detecting the viewfinder image displayed on the shooting interface based on at least one pose shooting point extracted from the reference image" and its subsequent steps to achieve the next round of processing. This process iterates until the duration for which the mismatched point is determined to be in a mismatched state with the viewfinder image reaches a preset duration, at which point it can be determined that the subject may be difficult to photograph. If the mismatch requirement is met, preset information can be displayed on the shooting interface. This preset information can then ask the photographer whether to ignore the mismatch requirement. If the photographer's action triggered by the preset information indicates that the mismatch requirement should be ignored, it can be confirmed that the subject does not meet the mismatch requirement. Therefore, the detection result can be updated so that the updated detection result indicates that the mismatch requirement matches the viewfinder (or the updated detection result indicates that the mismatch requirement does not exist in the at least one pose shooting requirement). This prevents the updated detection result from indicating that the current viewfinder cannot meet the mismatch requirement, and the process returns to continue executing the aforementioned step of "updating the shooting interface based on the detection result" and subsequent steps. By asking the photographer to ignore some mismatch requirements, the shooting difficulty can be reduced, thereby improving the shooting experience.

[0109] Furthermore, to better improve the shooting experience, the step of "updating the shooting interface based on the detection result" in S3 above may include: in response to detecting that the detection result indicates that each of the at least one of the above-mentioned posture shooting points matches the viewfinder, taking a picture of the viewfinder, or displaying a prompt message on the shooting interface (such as from...). Figure 12 The information in the pop-up window 214 shown in the shooting interface 213 indicates that the viewfinder meets the shooting requirements, so that the photographer can know that the current viewfinder is ready to shoot based on the information. This allows the photographer to flexibly determine the shooting time based on these shooting points, which is conducive to shooting high-quality images.

[0110] As can be seen, for the viewfinder image currently displayed by the shooting interface, after obtaining the above detection results, if the detection results indicate that each of the above at least one posture shooting points matches the viewfinder image, it can be determined that the viewfinder image has met all the points. Therefore, the user can be prompted to take a picture or take an automatic picture, which is beneficial to improve the shooting experience.

[0111] Research has found that in some scenarios, such as selfies, users not only need to pose as the subject but also guide the entire shooting process as the photographer. This requires users to constantly switch roles and perform corresponding operations during the shooting process, resulting in high shooting difficulty and low shooting efficiency.

[0112] Based on the above research, and to address the aforementioned problems, this application also provides a possible implementation of the interaction method. In this implementation, when the interaction method is applied to an electronic device, it may further include: synchronizing the shooting interface to a display device, so that the shooting interface displayed on the display device is consistent with the shooting interface displayed on the electronic device in real time. Since the display device is independent of the electronic device, the user can view the state and any problems of the viewfinder image captured by the electronic device while posing, effectively avoiding the defects caused by the user constantly switching poses during shooting, thus improving the selfie effect.

[0113] It should be noted that this application does not limit the implementation of the above-mentioned display device. For example, it can be implemented using any device (such as another electronic device) capable of synchronizing the shooting interface with the electronic device. Furthermore, in some scenarios, the display device can at least satisfy the following constraint: the angle between the orientation of the display device's screen and the orientation of the camera used to capture the viewfinder image in the electronic device is less than a preset threshold, so that the screen and the camera are facing the same person as much as possible.

[0114] It should also be noted that this application does not limit the placement of the display device. For example, the display device can be placed where the user is posing, so that the user can view relevant information from the viewfinder image captured by the electronic device without moving. Alternatively, the display device can follow the user's face (or eyes) so that it is always directly in front of the face (or eyes). This effectively avoids the impact of head turning when viewing the display device (such as adding new mismatched points), thereby improving the shooting experience.

[0115] In addition, in some scenarios, such as selfie scenarios, in order to save costs, this application also provides a possible implementation of the interaction method. In this method, the interaction method may further include: converting the text data generated based on the above detection results into voice data for playback, wherein the text data indicates the matching results between some or all (such as mismatched points) of the above at least one posture shooting point and the viewfinder; or, converting some or all (such as mismatched points) of the updated shooting interface into voice data for playback, so that the user can learn from the voice data what problems exist in the current viewfinder. This can realize the use of voice playback to guide the user to adjust the posture during selfies, thereby effectively avoiding the defects caused by the user having to constantly switch roles during the shooting process, and thus helping to improve the selfie effect.

[0116] In addition, in order to better improve the shooting experience, this application also provides a possible implementation of the interaction method, in which the interaction method may include at least steps 11-14 below.

[0117] Step 11: Show the shooting interface (e.g.) Figure 2 The shooting interface 200 shown is used to display the viewfinder image in the display area of ​​the shooting interface.

[0118] It should be noted that for details regarding step 11, please refer to the relevant content of S1 above.

[0119] Step 12: In response to detecting an operation triggered on the shooting interface to acquire a reference image (such as by...) Figure 2 The operation of selecting image 1 shown in the shooting interface 201), in this shooting interface (such as Figure 2 The reference image is displayed in the display area of ​​the shooting interface 201 shown.

[0120] It should be noted that the relevant content of step 12 can be found in the relevant content of S2 above. Therefore, in one possible implementation, for an electronic device, when the shooting interface (e.g., ...) is opened on the electronic device... Figure 2 After the shooting interface 200 is shown, some information (such as shooting environment information) is first collected through the scanning button deployed on the shooting interface; then, based on this information, some candidate images (such as images from...) are recommended. Figure 2 Images 1 to 4 shown on the shooting interface 201, or images under the "Favorites" or "Popular" categories shown on the shooting interface 201, etc., are used to select images from these candidate images (such as...). Figure 2 The image shown in Figure 1) is displayed in this display area for the user to view.

[0121] Step 13: In response to detecting an operation triggered on the shooting interface to analyze the reference image (such as by...) Figure 3 (As shown in the shooting interface 201, clicking the analysis assistance button) analyzes the reference image to obtain at least one of the above-mentioned posture shooting points, and the position of the body parts in the reference image according to the description of each posture shooting point. The reference image is then augmented with displays of each posture shooting point (e.g., ...). Figure 3 The shooting interface 202 is relative to this Figure 3 (The content added to the shooting interface 201).

[0122] The aforementioned "operation to analyze the reference image" requests the analysis of key points captured in the reference image; however, this application does not limit the implementation method of the "operation to analyze the reference image".

[0123] Furthermore, this application does not limit the implementation method analyzed in step 13 above; for example, it can be implemented by means of... Figure 13 The pre-built visual language model with the function of understanding shooting points is implemented as shown.

[0124] Furthermore, this application does not limit the process of determining "the position of the body parts described in each pose shooting point in the reference image" in step 13 above. For example, it can be: for any pose shooting point, after analyzing the pose shooting point from the reference image, using a pre-built machine learning model (such as...) Figure 13 The visual positioning model shown determines the position of the key points of the pose in the reference image, which is the position of the body part described by the key points of the pose in the reference image, so that the key points of the pose can be labeled on the reference image according to the position.

[0125] Step 14: In response to detecting an operation that triggers the display of the viewfinder on the shooting interface (such as for an operation triggered by...). Figure 4 The operation of clicking the prompt button shown in the shooting interface 202) displays the viewfinder image in the display area of ​​the shooting interface (such as by...). Figure 4 The viewfinder shown on the shooting interface 203 is used to detect the viewfinder displayed on the shooting interface based on at least one of the above-mentioned posture shooting points to obtain a detection result. The detection result includes the matching result between each point in the at least one posture shooting point and the viewfinder, and the shooting interface is updated based on the detection result. Different body parts are described by different posture shooting points.

[0126] It should be noted that for the relevant content of step 14, please refer to the relevant content of S2 above.

[0127] Based on the relevant content of steps 11 to 14 above, it can be seen that in some scenarios, the process of selecting a reference image, extracting shooting points from the reference image, and guiding shooting based on shooting points can be realized through the interactive operation between the user and the electronic device. This is conducive to better meeting the needs of users at different stages and thus improving the user experience.

[0128] Based on the interaction method provided in the embodiments of this application, the embodiments of this application also provide an interaction device, which will be described below in conjunction with... Figure 14 Explanation and clarification will be provided. Among them, Figure 14 This is a schematic diagram of an interactive device provided in an embodiment of this application. It should be noted that for technical details of the interactive device provided in this embodiment, please refer to the relevant content of the interactive method described above.

[0129] like Figure 14 As shown, the interactive device 1400 provided in this application embodiment includes:

[0130] The first display unit 1401 is used to display the shooting interface;

[0131] The key point acquisition unit 1402 is used to acquire at least one posture shooting key point from the reference image in response to detecting an operation of acquiring a reference image triggered on the shooting interface, wherein different posture shooting key points describe different body parts;

[0132] The first update unit 1403 is used to detect the viewfinder image displayed on the shooting interface based on the at least one posture shooting point to obtain a detection result. The detection result includes the matching result between each point in the at least one posture shooting point and the viewfinder image, and updates the shooting interface based on the detection result. Different posture shooting points describe different body parts.

[0133] In one possible implementation, the first updating unit 1403 is specifically configured to: in response to detecting that the detection result indicates that there is a mismatch between the at least one pose shooting point and the viewfinder image, update the shooting interface according to the mismatched point, and the updated shooting interface highlights the mismatched point.

[0134] In one possible implementation, the first updating unit 1403 is specifically configured to: in response to detecting that at least one pose shooting point is displayed on the viewfinder, adjust the display state of the mismatched point on the viewfinder, wherein the prominence of the adjusted display state is higher than that of the original display state; and / or, in response to detecting that the at least one pose shooting point is not displayed on the viewfinder, add the mismatched point to the viewfinder according to the position of the body part described by the mismatched point in the viewfinder.

[0135] In one possible implementation, the first updating unit 1403 is specifically used to: add and display suggested information corresponding to the mismatched point on the shooting interface, wherein the suggested information describes the adjustment process from the posture of the body part described by the mismatched point in the viewfinder to the posture indicated by the mismatched point.

[0136] In one possible implementation, the interactive device 1400 further includes: a second display unit, configured to, after updating the shooting interface based on the detection result, in response to detecting an operation triggered on the shooting interface to display the reference image, display a thumbnail of the reference image at a preset position in the viewfinder, or add a transparent layer to the viewfinder, on which the reference image is displayed.

[0137] In one possible implementation, the updated shooting interface displays points in the at least one pose shooting point that do not match the viewfinder; the interactive device 1400 further includes: a second updating unit, configured to update the detection result in response to detecting an operation triggered on the updated shooting interface to ignore the mismatched points, wherein the updated detection result indicates that the mismatched points match the viewfinder or that the updated detection result indicates that the at least one pose shooting point does not contain the mismatched points, and to return to the first updating unit 1403 to continue executing the step of updating the shooting interface based on the detection result.

[0138] In one possible implementation, the interactive device 1400 further includes: a first processing unit, configured to, after updating the shooting interface based on the detection result, in response to detecting that the detection result indicates that there is a point in the at least one posture shooting point that does not match the viewfinder, return to the first updating unit 1403 to continue executing the step of detecting the viewfinder displayed on the shooting interface based on the at least one posture shooting point to obtain a detection result.

[0139] In one possible implementation, the interactive device 1400 further includes: a third update unit, configured to update the detection result in response to the detection that the duration of the mismatch between the key point and the viewfinder image reaches a preset duration, wherein the updated detection result indicates that the mismatch between the key point and the viewfinder image is in a matching state or the updated detection result indicates that there is no mismatch between the key point and the viewfinder image among the at least one pose shooting key point, and return to the first update unit 1403 to continue executing the step of updating the shooting interface based on the detection result.

[0140] In one possible implementation, the third updating unit is specifically configured to: in response to the detection that the duration of the mismatch between the key point and the viewfinder image reaches the preset duration, display preset information on the shooting interface, wherein the preset information queries whether to ignore the mismatch key point; and in response to the detection of a trigger operation instruction for the preset information to ignore the mismatch key point, update the detection result.

[0141] In one possible implementation, the first updating unit 1403 is specifically configured to: in response to detecting that the detection result indicates that there is a point in the at least one posture shooting point that matches the viewfinder, update the shooting interface according to the matching point, and the updated shooting interface may weakly display or not display the matching point.

[0142] In one possible implementation, the first updating unit 1403 is specifically configured to: in response to detecting that the detection result indicates that each of the at least one pose shooting point matches the viewfinder, capture the viewfinder, or display a prompt message on the shooting interface, the prompt message indicating that the viewfinder meets the shooting requirements.

[0143] In one possible implementation, the interactive device 1400 further includes a data synchronization unit for synchronizing the shooting interface to a display device, the display device being independent of the interactive device 1400.

[0144] In one possible implementation, the interactive device 1400 further includes: a voice broadcasting unit, configured to convert text data generated based on the detection results into voice data for playback, wherein the text data indicates the matching results between some or all of the at least one posture shooting points and the viewfinder image; or, to convert some or all of the updated shooting interface into voice data for playback.

[0145] In one possible implementation, the key point acquisition unit 1402 is specifically configured to: in response to detecting an operation triggered on the shooting interface to acquire the reference image, display the reference image in the display area of ​​the shooting interface; in response to detecting an operation triggered on the shooting interface to analyze the reference image, analyze the reference image to obtain at least one posture shooting key point, and the position of the body parts described by each posture shooting key point in the reference image, and add display of each posture shooting key point on the reference image;

[0146] The first updating unit 1403 is specifically configured to: in response to detecting an operation triggered on the shooting interface to display the viewfinder, display the viewfinder in the display area, and detect the viewfinder displayed on the shooting interface according to the at least one posture shooting point to obtain a detection result.

[0147] Based on the aforementioned content regarding the interactive device 1400, its working principle includes: for a currently displayed shooting interface, if an operation to acquire a reference image (such as a high-aesthetic image) is detected on the shooting interface, at least one pose shooting point (such as "head slightly raised", "holding a colorful umbrella", "both legs bent and placed on a bench") is first acquired from the reference image; then, based on the at least one pose shooting point, the viewfinder image displayed on the shooting interface is detected to obtain a detection result, such that the detection result includes the relationship between each point in the at least one pose shooting point and the viewfinder image. The matching results allow the detection results to indicate whether the current framing meets these requirements. This enables the shooting interface to be updated based on the detection results, ensuring the updated interface accurately reflects the detection findings. The photographer can then identify any deficiencies in the current framing and guide the subject to adjust their posture accordingly. This guidance, based on the reference image, allows for high-quality image capture, improving the overall shooting experience. Furthermore, since different postures require different body parts to be described by the key points, these points effectively depict the posture details described in the reference image. This ensures that images captured using these points accurately reproduce the posture described in the reference image, further enhancing image quality.

[0148] In addition, this application also provides an electronic device, the device including a processor and a memory: the memory is used to store instructions or computer programs; the processor is used to execute the instructions or computer programs in the memory so that the electronic device performs any implementation of the interaction method provided in this application.

[0149] See Figure 15 The diagram illustrates a structural schematic of an electronic device 1500 suitable for implementing embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 15 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0150] like Figure 15 As shown, electronic device 1500 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 1501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1502 or a program loaded from storage device 1508 into random access memory (RAM) 1503. RAM 1503 also stores various programs and data required for the operation of electronic device 1500. Processing device 1501, ROM 1502, and RAM 1503 are interconnected via bus 1504. Input / output (I / O) interface 1505 is also connected to bus 1504.

[0151] Typically, the following devices can be connected to I / O interface 1505: input devices 1506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1509. Communication device 1509 allows electronic device 1500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 15 An electronic device 1500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0152] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1509, or installed from storage device 1508, or installed from ROM 1502. When the computer program is executed by processing device 1501, it performs the functions defined in the methods of embodiments of this disclosure.

[0153] The electronic device provided in this embodiment belongs to the same inventive concept as the method provided in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0154] This application also provides a computer-readable medium storing instructions or a computer program that, when executed on a device, causes the device to perform any implementation of the interaction method provided in this application.

[0155] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0156] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0157] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0158] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, enable the electronic device to perform the aforementioned methods.

[0159] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0160] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0161] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units / modules do not necessarily limit the specific unit itself.

[0162] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0163] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0164] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0165] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0166] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0167] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0168] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An interaction method, characterized in that, The method includes: Show the shooting interface; In response to detecting an operation to acquire a reference image triggered on the shooting interface, at least one pose shooting point is acquired from the reference image, and different pose shooting points describe different body parts; Based on the at least one posture shooting point, the viewfinder image displayed on the shooting interface is detected to obtain a detection result. The detection result includes the matching result between each point in the at least one posture shooting point and the viewfinder image, and the shooting interface is updated based on the detection result.

2. The method according to claim 1, characterized in that, The step of updating the shooting interface based on the detection results includes: In response to the detection result indicating that there is a mismatch between the at least one pose shooting point and the viewfinder image, the shooting interface is updated according to the mismatched point, and the updated shooting interface highlights the mismatched point.

3. The method according to claim 2, characterized in that, The step of updating the shooting interface based on the mismatch points includes: In response to detecting that at least one of the pose shooting points is displayed on the viewfinder, the display state of the mismatched points on the viewfinder is adjusted, and the prominence of the adjusted display state is higher than that of the original display state. And / or, In response to detecting that the at least one pose shooting point is not displayed in the viewfinder, the mismatched point is added to the viewfinder according to the position of the body part described by the mismatched point in the viewfinder.

4. The method according to claim 2, characterized in that, The step of updating the shooting interface based on the mismatch points includes: The shooting interface is enhanced with suggested information corresponding to the mismatched points. The suggested information describes the adjustment process from the change in posture of the body part described by the mismatched point in the viewfinder to the posture indicated by the mismatched point.

5. The method according to claim 1, characterized in that, After updating the shooting interface based on the detection result, the method further includes: In response to detecting an operation triggered on the shooting interface to display the reference image, a thumbnail of the reference image is displayed at a preset position on the viewfinder, or a transparent layer is added to the viewfinder displaying the reference image.

6. The method according to claim 1, characterized in that, The updated shooting interface displays at least one of the shooting posture points that do not match the viewfinder image. The method further includes: In response to detecting an operation triggered on the updated shooting interface to ignore the mismatched point, the detection result is updated, wherein the updated detection result indicates that the mismatched point is in a matching state with the viewfinder or the updated detection result indicates that there is no mismatched point among the at least one pose shooting point, and the step of updating the shooting interface based on the detection result is continued.

7. The method according to claim 1, characterized in that, After updating the shooting interface based on the detection result, the method further includes: In response to the detection result indicating that there is a mismatch between the at least one pose shooting point and the viewfinder image, the step of detecting the viewfinder image displayed on the shooting interface based on the at least one pose shooting point to obtain a detection result continues.

8. The method according to claim 7, characterized in that, The method further includes: In response to the detection that the mismatched point and the viewfinder are in a mismatched state for a duration of a preset duration, the detection result is updated. The updated detection result indicates that the mismatched point and the viewfinder are in a matching state, or the updated detection result indicates that there is no mismatched point among the at least one pose shooting point. The step of updating the shooting interface based on the detection result is then performed.

9. The method according to claim 8, characterized in that, The response to the detection result being updated after a preset duration of time during which the mismatched key point and the viewfinder image are in a mismatched state includes: In response to the fact that the duration of the detected mismatch between the key point and the viewfinder image reaches the preset duration, preset information is displayed on the shooting interface, and the preset information asks whether to ignore the mismatch. In response to the detection of a trigger operation instruction for the preset information to ignore the mismatch, the detection result is updated.

10. The method according to claim 1, characterized in that, The step of updating the shooting interface based on the detection results includes: In response to the detection result indicating that there is a point in the at least one pose shooting point that matches the viewfinder, the shooting interface is updated according to the matching point, and the updated shooting interface may weakly display or not display the matching point.

11. The method according to claim 1, characterized in that, The step of updating the shooting interface based on the detection results includes: In response to detecting that the detection result indicates that each of the at least one pose shooting point matches the viewfinder, the viewfinder is captured, or a prompt message is displayed on the shooting interface, the prompt message indicating that the viewfinder meets the shooting requirements.

12. The method according to claim 1, characterized in that, The method is applied to an electronic device, and the method further includes: The shooting interface is synchronized to the display device, which is independent of the electronic device.

13. The method according to claim 1, characterized in that, The method further includes: The text data generated based on the detection results is converted into speech data and played, wherein the text data indicates the matching results between some or all of the at least one posture shooting point and the viewfinder image; or, The updated shooting interface will convert some or all of the data into audio for playback.

14. The method according to any one of claims 1-13, characterized in that, The step of obtaining at least one pose shooting point from the reference image in response to detecting an operation triggered on the shooting interface includes: In response to detecting an operation triggered on the shooting interface to acquire the reference image, the reference image is displayed in the display area of ​​the shooting interface; In response to detecting an operation triggered on the shooting interface to analyze the reference image, the reference image is analyzed to obtain at least one pose shooting point, and the position of the body parts described by each pose shooting point in the reference image is added to the reference image to display each pose shooting point. The step of detecting the viewfinder image displayed on the shooting interface based on at least one posture shooting point to obtain a detection result includes: In response to detecting an operation triggered on the shooting interface to display the viewfinder, the viewfinder is displayed in the display area, and a detection result is obtained by detecting the viewfinder displayed on the shooting interface based on the at least one posture shooting point.

15. An interactive device, characterized in that, include: The first display unit is used to showcase the shooting interface; The key point acquisition unit is used to acquire at least one pose shooting key point from the reference image in response to detecting an operation of acquiring a reference image triggered on the shooting interface, wherein different pose shooting key points describe different body parts; The first update unit is used to detect the viewfinder image displayed on the shooting interface based on the at least one posture shooting point to obtain a detection result. The detection result includes the matching result between each point in the at least one posture shooting point and the viewfinder image, and updates the shooting interface based on the detection result.

16. An electronic device, characterized in that, The device includes: a processor and a memory; The memory is used to store instructions or computer programs; The processor is configured to execute the instructions or computer program in the memory to cause the electronic device to perform the method according to any one of claims 1-14.

17. A computer-readable medium, characterized in that, The computer-readable medium stores instructions or computer programs that, when executed on the device, cause the device to perform the method according to any one of claims 1-14.

18. A computer program product, characterized in that, It includes a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the method of any one of claims 1-14.

Images