Photographing suggestion method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a photographing suggestion method and device, equipment and a storage medium, and the method comprises the steps: obtaining photographing information which comprises at least one of the following information: photographing image information, photographing position information or photographing posture information; obtaining a retrieval result based on a photographing retrieval mode corresponding to the photographing information, the photographing retrieval mode comprising: performing photographing suggestion retrieval based on a photographing suggestion library of the terminal device, or performing photographing suggestion retrieval based on the photographing suggestion library of the terminal device and performing photographing suggestion retrieval based on a scenic spot image library of a server; and outputting target suggestion content according to the photographing information and the retrieval result, wherein the target suggestion content is used for prompting the user to photograph according to the target mode. According to the method, the retrieval result can be obtained by flexibly adopting a proper photographing retrieval mode, so that the photographing suggestion can be flexibly generated.

Description

Technical Field

[0001] This application relates to photo optimization technology, including but not limited to a photo suggestion method, apparatus, device, and storage medium. Background Technology

[0002] When users take photos using their terminal devices, a search library for photo suggestions can be set up to recommend different ways for users to take photos.

[0003] The recommendation methods used in related technologies are relatively simple and suffer from problems such as high latency and frequent calls, which results in poor performance in generating photo recommendations during the photo-taking process. Summary of the Invention

[0004] In view of this, the photo suggestion method, apparatus, device, and storage medium provided in the embodiments of this application can flexibly adopt appropriate photo retrieval methods to obtain retrieval results, thereby flexibly generating photo suggestions. The photo suggestion method, apparatus, device, and storage medium provided in the embodiments of this application are implemented as follows:

[0005] One aspect of this application provides a photo-taking suggestion method, applied to a terminal device, including:

[0006] Acquire photographic information, which includes at least one of the following: photographic image information, photographic location information, or photographic posture information;

[0007] The search results are obtained based on the photo search methods corresponding to the photo information. The photo search methods include: searching for photo suggestions based on the photo suggestion library of the terminal device, or searching for photo suggestions based on the photo suggestion library of the terminal device and searching for photo suggestions based on the scenic spot image library of the server.

[0008] Based on the photo information and search results, the system outputs target suggestions to guide the user in taking photos in the desired manner.

[0009] Another aspect of this application embodiment also provides a photo suggestion device, applied to a terminal device, including: an acquisition module, a retrieval module, and an output module;

[0010] The acquisition module is used to acquire photographic information, which includes at least one of the following: photographic image information, photographic location information, or photographic posture information;

[0011] The retrieval module is used to obtain retrieval results based on the photo retrieval method corresponding to the photo information. The photo retrieval methods include: photo suggestion retrieval based on the photo suggestion library of the terminal device, or photo suggestion retrieval based on the photo suggestion library of the terminal device and photo suggestion retrieval based on the scenic spot image library of the server.

[0012] The output module is used to output target suggestions based on the photo information and search results. The target suggestions are used to prompt the user to take photos in the target manner.

[0013] The computer device provided in this application includes a memory and a processor. The memory stores a computer program that can run on the processor, and the processor executes the program to implement the method of this application.

[0014] The computer-readable storage medium provided in this application embodiment stores a computer program thereon, which, when executed by a processor, implements the method provided in this application embodiment.

[0015] The photo suggestion method, apparatus, device, and storage medium provided in this application can acquire photo information, which includes at least one of the following: photo image information, photo location information, or photo posture information; obtain search results based on the photo retrieval method corresponding to the photo information, including: photo suggestion retrieval based on the photo suggestion library of the terminal device, or photo suggestion retrieval based on the photo suggestion library of the terminal device and photo suggestion retrieval based on the scenic spot image library of the server; output target suggestion content according to the photo information and the search results, the target suggestion content is used to prompt the user to take photos in the target manner. The search results can be obtained by using the corresponding photo retrieval method based on the photo information, which may include a first search result obtained from the photo suggestion library on the terminal device side, or a combination of the first search result and a second search result obtained from the scenic spot image library on the server side. Different methods can yield search results corresponding to those methods, and photo suggestion recommendations can be implemented based on the corresponding search results. That is to say, it is possible to flexibly use appropriate photo retrieval methods to obtain search results, thereby flexibly generating photo suggestions. In addition, recommending through the photo suggestion library of the terminal device can avoid high latency and frequent calls, and further improve the quality of photo recommendation effects. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating the application scenario provided in the embodiments of this application;

[0018] Figure 2This is a flowchart illustrating the photo-taking suggestion method provided in the embodiments of this application;

[0019] Figure 3 This is a schematic diagram of the process for obtaining the first search result provided in the embodiments of this application;

[0020] Figure 4 This is a schematic diagram of the retrieval planning model provided in the embodiments of this application;

[0021] Figure 5 This is a schematic diagram of the process for obtaining the second search result provided in the embodiments of this application;

[0022] Figure 6 This is a schematic diagram of the overall logic for obtaining the search results provided in the embodiments of this application;

[0023] Figure 7 This is a schematic diagram of the structure of the photo-taking suggestion model provided in the embodiments of this application;

[0024] Figure 8 This is a schematic diagram of the process for generating target suggestion content provided in the embodiments of this application;

[0025] Figure 9 This is a schematic diagram of the parameter adjustment process provided in the embodiments of this application;

[0026] Figure 10 This is a schematic diagram of the interface for adjusting based on the target control provided in the embodiments of this application;

[0027] Figure 11 This is another flowchart illustrating the process of generating target suggestion content provided in the embodiments of this application;

[0028] Figure 12 This is a flowchart illustrating the update target suggestion content provided in the embodiments of this application;

[0029] Figure 13 This is a schematic diagram of the overall logic for generating target suggestions provided in the embodiments of this application;

[0030] Figure 14 This is a schematic diagram of the framework of the photo-taking suggestion method provided in the embodiments of this application;

[0031] Figure 15 This is a schematic diagram of the photographing suggestion device provided in the embodiments of this application;

[0032] Figure 16 This is a schematic diagram of the structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0035] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0036] It should be noted that the terms "first, second, third" used in the embodiments of this application are used to distinguish similar or different objects and do not represent a specific order of objects. It can be understood that "first, second, third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0037] When users take photos using their terminal devices, a search library for photo suggestions can be set up to recommend different ways for users to take photos.

[0038] In related technologies, the recommendation methods used are relatively simple. For example, relying solely on cloud-based recommendations may result in time delays during the recommendation process, leading to poor recommendation performance when users take photos. Alternatively, the recommended content may be too simple and incomplete.

[0039] In conclusion, the recommendation methods used in the relevant technologies are not suitable, which may result in poor photo recommendation effects during the photo-taking process, thus preventing users from receiving appropriate photo-taking suggestions.

[0040] To address the aforementioned problems in related technologies, this application provides a photo suggestion method, the application scenarios of which will be explained below.

[0041] Figure 1 This is a schematic diagram of the application scenario provided in the embodiments of this application. Please refer to it. Figure 1 This scenario may include: terminal device 110 and server 120.

[0042] The terminal device 110 may include, but is not limited to, mobile phones, wearable devices (such as smartwatches, smart bracelets, smart glasses, etc.), tablet computers, laptops, in-vehicle terminals, PCs (Personal Computers), and other electronic devices with camera functions. The functions implemented by this method can be achieved by the processor in the terminal device 110 calling program code. Of course, the program code can be stored in a computer storage medium. Therefore, the terminal device 110 includes at least a processor, a storage medium, and modules related to the camera function.

[0043] Among them, the terminal device 110 can be a device for taking pictures. The terminal device 110 can be configured with corresponding photography applications, such as camera, video recording and other related applications. Based on these applications, the terminal device 110 can take pictures.

[0044] It should be noted that during the photo-taking process, in order to ensure that users obtain higher quality photos, a corresponding photo search scheme will be set up. This scheme retrieves photo information and generates corresponding search results based on the relevant search database. The terminal device 110 can then provide photo suggestions based on these search results, such as recommending shooting angles, recommending reference photos, and recommending camera settings, such as lighting, brightness, and color tone. This allows users to take photos in a better manner and obtain better photo content.

[0045] Both the terminal device 110 and the server 120 can be configured with corresponding search databases. Users can choose to use the search database in the terminal device 110 for searching according to their actual needs, or they can choose to use both the search database in the terminal device 110 and the search database in the server 120 to obtain the corresponding search results and realize the recommendation of photo suggestions.

[0046] The following explains one feasible implementation process of the photo-taking suggestion method provided in the embodiments of this application.

[0047] Figure 2 This is a flowchart illustrating the photo-taking suggestion method provided in the embodiments of this application. Please refer to it. Figure 2 A method for suggesting how to take photos, including:

[0048] S210: Obtain photo information.

[0049] It should be noted that the subject executing this method can be the aforementioned terminal device.

[0050] In one embodiment, the terminal device can be equipped with sensors of various modes, such as cameras, positioning devices, and attitude acquisition devices, which can acquire the aforementioned photo information.

[0051] The photographic information includes at least one of the following: photographic image information, photographic location information, or photographic posture information.

[0052] It should be noted that the photographed image information can refer to the preview image obtained during the photographing process, such as an image obtained through the camera of the terminal device. The photographed image information can also be some image description information or image features extracted based on the preview image, and there are no specific restrictions here.

[0053] The location information for taking a photo can be GPS (Global Positioning System) information obtained through a positioning device. This positioning device can pinpoint the specific geographical location. For example, the location information can be used to determine the user's location when taking the photo.

[0054] The photo-taking posture information can be the device posture of the terminal device during the photo-taking process, which is collected by a posture acquisition device. The posture acquisition device can be, for example, an inertial measurement unit (IMU). The specific posture of the terminal device can be obtained through the inertial measurement unit, such as: landscape, portrait, tilt angle and other related information.

[0055] In one embodiment, when a user takes a photo using the camera application on a terminal device, the user can obtain corresponding photo information based on the aforementioned multiple sensors.

[0056] In one embodiment, a state control model can be set in the terminal device to uniformly acquire the above-mentioned various types of photographic information, thereby enabling retrieval of the search library based on this photographic information.

[0057] S220: Obtain search results based on the photo search method corresponding to the photo information.

[0058] In one embodiment, after obtaining the photo information, the photo retrieval method corresponding to the photo information can be determined first. The photo retrieval method includes: performing a photo suggestion retrieval based on the photo suggestion library of the terminal device, or performing a photo suggestion retrieval based on the photo suggestion library of the terminal device and performing a photo suggestion retrieval based on the scenic spot image library of the server.

[0059] Optionally, different photo retrieval methods can be used to retrieve photo suggestions for different types of photo information.

[0060] The local search database on the terminal device can be the aforementioned photo suggestion database.

[0061] In one embodiment, the photo suggestion library may include: a photography theory library, a popular techniques library, and a personalization library. The photography theory library covers fundamental photographic theories such as composition and lighting, and is used to reference the sources of those theories. The popular techniques library contains popular shooting poses and techniques, and is used to provide relevant suggestions. The personalization library stores user profiles, historical shooting preferences, and device information, and is used to provide suggestions based on the user's personalized needs.

[0062] Optionally, a personalized library is used to generate search results based on the user's historical preference information.

[0063] Among them, historical preference information can be obtained based on the user's historical information on taking photos with the camera. For example, if the user is used to taking photos with their right hand, the camera parameters given can be recommended based on the premise that the user holds the terminal device with their right hand.

[0064] The search database on the server cloud can be the aforementioned scenic spot image database.

[0065] In one embodiment, the scenic spot image library may contain photographic images of popular online scenic spots and photo spots, and can retrieve and return reference images of the same shooting location based on the photo information.

[0066] It should be noted that the method of photo retrieval can be based on the corresponding photo information. For example, for photos of famous scenic spots, a combination of local search databases on the terminal device and cloud search databases on the server can be used to generate search results; for photos of lesser-known scenic spots, local search databases on the terminal device can be used to generate search results.

[0067] S230: Output target suggestions based on the photo information and search results.

[0068] In one embodiment, the search results may include a first search result and a second search result, wherein the first search result may be a search result obtained after searching based on the terminal device's photo suggestion library; and the second search result may be a search result obtained after searching based on the server's scenic spot image library.

[0069] After obtaining the corresponding search results, the system can generate corresponding target suggestions based on the photo information and search results, and output the target suggestions. The output methods can include: prompting in the photo preview interface with text, images, etc., or voice prompts, etc. There are no specific restrictions here. You can choose one or more methods to output the target suggestions according to actual needs.

[0070] The target suggestion content is used to guide users to take photos in the desired way.

[0071] It should be noted that the target suggestion content can be a recommendation that prompts users to take photos according to the corresponding target method. Users can choose to adopt the target method to take photos based on their actual needs, or they can choose not to adopt the target method to take photos. There are no specific restrictions here.

[0072] The photo suggestion method provided in this application can acquire photo information, which includes at least one of the following: photo image information, photo location information, or photo posture information; obtain search results based on the photo retrieval method corresponding to the photo information, which includes: photo suggestion retrieval based on the photo suggestion library of the terminal device, or photo suggestion retrieval based on the photo suggestion library of the terminal device and photo suggestion retrieval based on the scenic spot image library of the server; output target suggestion content based on the photo information and the search results, which is used to prompt the user to take photos in the target manner. The search results can be obtained by using the corresponding photo retrieval method based on the photo information, which may include a first search result obtained from the photo suggestion library on the terminal device side, or a combination of the first search result and a second search result obtained from the scenic spot image library on the server side. Different methods can yield search results corresponding to those methods, and photo suggestion recommendations can be implemented based on the corresponding search results. That is to say, it is possible to flexibly adopt appropriate photo retrieval methods to obtain search results, thereby flexibly generating photo suggestions. In addition, recommending through the photo suggestion library of the terminal device can avoid high latency and frequent calls, and further improve the quality of photo recommendation effects.

[0073] The following explains the implementation methods for obtaining various search results provided in the embodiments of this application.

[0074] Figure 3 This is a schematic diagram of the process for obtaining the first search result provided in the embodiments of this application. Please refer to it. Figure 3 Before obtaining the search results based on the photo retrieval method corresponding to the photo information, the method further includes:

[0075] S310: Generate search terms based on photo information.

[0076] It should be noted that after obtaining the photo information, the terminal device can generate search terms based on the photo information. The search terms can be text used to search in the terminal device's photo suggestion library.

[0077] In one embodiment, the generated search terms can be terms related to the photographed information, for example, search terms can be extracted based on the content of the photographed information.

[0078] Optionally, the search term can be the text used for retrieval, such as text features extracted from photographed image information, or the coordinates of a region of interest (ROI) determined from photographed image information, which are presented in text form.

[0079] When the retrieval method corresponding to the photo information is based on the photo suggestion database of the terminal device, the retrieval results obtained based on the photo retrieval method corresponding to the photo information include:

[0080] S320: The first search result is obtained by searching the photo suggestion database based on the search terms.

[0081] It should be noted that when using the local database of the terminal device, namely the aforementioned photo suggestion database, the search can be performed based on search terms. For example, the photo suggestion database can be traversed to determine the first search result corresponding to the search terms.

[0082] For example, the first search result may be the source of basic photography theories such as composition and lighting obtained from a photography theory database, or it may be popular shooting poses and techniques obtained from a popular techniques database, or it may be information such as user habit poses obtained from a personalization database.

[0083] It should be noted that search results are usually discrete textual information and cannot form a complete recommendation statement. A complete recommendation statement can be obtained by using the photo information and search results to obtain the target suggestion content.

[0084] These recommended statements can be the target methods mentioned above in the target suggestion content.

[0085] In the photo suggestion method provided in this application embodiment, search terms can be generated based on photo information. When the search method corresponding to the photo information is to perform a photo suggestion search based on the photo suggestion library of the terminal device, a first search result is obtained by searching the photo suggestion library according to the search terms. In particular, during the search process through the local database of the terminal device's photo suggestion library, the photo suggestion search can be achieved more quickly and efficiently by generating search terms, thereby obtaining a more accurate first search result.

[0086] In one embodiment, the search terms can be extracted based on photographic information, or they can be calculated based on a corresponding neural network model. The following uses the example of using a neural network model for calculation to explain the specific structure of the search planning model provided in the photographic suggestion method provided in this application embodiment.

[0087] Figure 4This is a schematic diagram of the retrieval planning model provided in the embodiments of this application. Please refer to... Figure 4 The retrieval planning model can be a model used to generate retrieval terms. The input of the retrieval planning model can be photographic information, and the output can include retrieval terms and decision information.

[0088] The search terms can be words determined from the photo information for making photo suggestions, and the decision information is used to indicate whether to upload the photo information to the server.

[0089] In one embodiment, decision information can be used to determine the retrieval method. If the decision information indicates that the photo information should be uploaded to the server, the retrieval can be performed by combining the local photo suggestion library of the terminal device and the cloud-based scenic spot image library of the server, thereby obtaining the first retrieval result and the second retrieval result. If the decision information indicates that the photo information should not be uploaded to the server, the retrieval can be performed by using the local photo suggestion library of the terminal device, thereby obtaining the first retrieval result.

[0090] In one embodiment, generating search terms based on photographic information includes:

[0091] The photo information is input into the retrieval planning model to obtain the search terms and decision information. The retrieval planning model is a neural network model that is trained based on the sample photo information, sample search terms and sample decision information.

[0092] It should be noted that the retrieval planning model can specifically be a dynamic retrieval planning model. This model can be trained based on a lightweight MLLM (Multimodal Large Language Model), integrating the ability to understand the shooting scene and the understanding of hierarchical retrieval databases. This model combines multimodal information to determine whether the current shooting scene involves taking photos and decides whether to retrieve images from the cloud-based scenic spot image database, while simultaneously generating necessary search terms for local retrieval on the terminal device.

[0093] The photo suggestion method provided in this application embodiment can input photo information into a retrieval planning model to obtain search terms and decision information. The retrieval planning model is a neural network model trained based on sample photo information, sample search terms, and sample decision information. Through the retrieval planning model, search terms and decision information can be obtained quickly, accurately, and reasonably, thereby accurately determining the photo retrieval method used and the search terms used in the local photo suggestion database of the terminal device.

[0094] The foregoing has explained one possible implementation process for obtaining the first search result. The following explains one possible implementation process for obtaining the second search result provided in the embodiments of this application.

[0095] Figure 5 This is a schematic diagram of the process for obtaining the second search result provided in the embodiments of this application. Please refer to it. Figure 5 When the decision information is used to instruct the uploading of photo information to the server, the photo retrieval method is to retrieve photo suggestions based on the photo suggestion library of the terminal device and to retrieve photo suggestions based on the scenic spot image library of the server.

[0096] The search results obtained based on the photo retrieval method corresponding to the photo information also include:

[0097] S510: Uploads the captured information to the server.

[0098] It should be noted that after obtaining decision information through the above retrieval planning model, it is possible to determine whether the photo information needs to be uploaded to the server based on the decision information, thereby determining the photo retrieval method to be adopted.

[0099] If the decision-making information instructs that the photo information be uploaded to the server, then the photo information can be uploaded to the server.

[0100] It should be noted that the terminal device and the server can communicate with each other. The terminal device can upload the photo information to the server. After receiving the photo information, the server can perform a search based on the photo information. The photo information uploaded by the terminal device can be, for example, photo image information and photo location information. The server can use this information to search for photo suggestions from the cloud-based scenic spot image library, obtain matching cloud reference images, and send these cloud reference images as secondary search results to the terminal device.

[0101] In one embodiment, the terminal device and the server can be connected via the Internet, and both the photo information and the second search result can be transmitted via the Internet.

[0102] S520: Receive the second search result sent by the server.

[0103] The second search result is obtained by the server from the scenic spot image database based on the photo information.

[0104] It should be noted that after the server obtains the second search result through the cloud-based scenic spot image database, it can send it to the terminal device via the Internet. The terminal device can receive the second search result and generate target suggestion content based on the photo information, the first search result, and the second search result, thereby providing relevant photo suggestions to the user.

[0105] In the photo suggestion method provided in this application embodiment, when decision information is used to instruct the uploading of photo information to the server, the photo retrieval method includes searching for photo suggestions based on the terminal device's photo suggestion library and searching for photo suggestions based on the server's scenic spot image library; uploading the photo information to the server; and receiving the second search result sent by the server. The second search result is obtained by the server from the scenic spot image library based on the photo information. Since the content in the scenic spot image library is usually large, storing it locally on the terminal device would cause a heavy load problem. Therefore, communication between the terminal device and the server allows the terminal device to obtain the second search result more quickly and conveniently.

[0106] The following explains the overall implementation process of obtaining search results in the embodiments of this application.

[0107] Figure 6 This is a schematic diagram illustrating the overall logic of obtaining the search results provided in the embodiments of this application. Please refer to... Figure 6 First, photographic information can be acquired and input into the aforementioned retrieval planning model. Based on the retrieval planning model, search terms and decision information are obtained. After obtaining the search terms, a search can be generated from the local photographic suggestion database on the terminal device to obtain the first search result. If the decision information indicates that the photographic information does not need to be uploaded to the server, the target suggested content can be obtained based on the photographic information and the first search result. If the decision information indicates that the photographic information needs to be uploaded to the server, the photographic information can be uploaded to the server, and the second search result sent by the server can be received. Then, the target suggested content can be obtained based on the photographic information, the first search result, and the second search result.

[0108] It should be noted that after obtaining the search results, target suggested content can be generated based on the photo information and the search results. In one embodiment, the target suggested content can be generated based on the photo suggestion model. The specific structural relationship of the photo suggestion model will be explained below.

[0109] Figure 7 This is a schematic diagram of the photographic suggestion model provided in the embodiments of this application. Please refer to... Figure 7 The input to this photo suggestion model can be photo information and search results, and the output of this photo suggestion model can be the target suggestion content mentioned above.

[0110] The search results may include either the first search result or the first search result and the second search result.

[0111] In one embodiment, if a second search result is received from the server, target suggestion content can be generated based on the photo information, the first search result, and the second search result; if no second search result is received from the server, target suggestion content can be generated based on the photo information and the first search result.

[0112] Optionally, the target suggestion content can be output based on the photo information and search results, including: inputting the photo information and search results into the photo suggestion model to obtain the target suggestion content.

[0113] The photo suggestion model is a neural network model trained based on sample photo information, sample retrieval results, and sample suggestion content.

[0114] The target recommendations include at least one of the following: camera parameter recommendations, shooting action recommendations, theoretical basis for the recommendations, and reference images for shooting.

[0115] It should be noted that camera parameter suggestions can be suggestions for camera settings during shooting, such as contrast settings, image quality settings, lighting settings, and shooting mode settings; shooting action suggestions can be suggestions for the user's own posture when taking pictures, and the theoretical basis for the suggestions can be the theoretical basis for a certain parameter that is not found in the aforementioned photography theory library; and the reference images can be reference images retrieved from the server cloud, such as existing shooting examples of the same area or the same scene.

[0116] In one embodiment, the photo suggestion model can be obtained by fine-tuning a lightweight MLLM. This model takes the aforementioned photo information and search results as input and returns structured photo suggestions to the user, covering parameter suggestions, action suggestions, theoretical basis, and reference images, providing at least one of the aforementioned suggestions. Furthermore, through training, the photo suggestion model possesses a certain aesthetic evaluation capability, and can return a composition suggestion when the camera's framing effect no longer requires adjustment. The suggestions generated in this step are then processed by the front end and displayed to the user in different formats.

[0117] The photo suggestion method provided in this application embodiment allows for the input of photo information and search results into a photo suggestion model to obtain target suggestion content. The photo suggestion model is a neural network model trained based on sample photo information, sample search results, and sample suggestion content. This photo suggestion model enables faster and more accurate acquisition of target suggestion content, thereby achieving more efficient and effective recommendation of photos to users.

[0118] It should be noted that in the process of generating target suggestion content, since it may be based on the first search result and the photo information, or it may be based on the first search result, the second search result and the photo information, it is necessary to determine whether the second search result has been received.

[0119] The following explains one feasible implementation process for determining whether to use the second search result to generate target suggestion content, as provided in the embodiments of this application.

[0120] Figure 8 This is a flowchart illustrating the process of generating target suggestion content provided in the embodiments of this application. Please refer to... Figure 8 The photo information and search results are input into the photo suggestion model to obtain the target suggestion content, including:

[0121] S810: Determine whether the second search result has been received within the preset time period.

[0122] It should be noted that a timer can be set on the terminal device. After the terminal device sends the photo information to the server, the timer can start. The timer can be set to a preset duration. If the second search result is received within the preset duration, it can be determined that the timeout has not occurred; conversely, if the second search result is not received within the preset duration, it can be determined that the timeout has occurred.

[0123] If the second search result is received within the preset time period, S820: Input the photo information, the first search result and the second search result into the photo suggestion model to obtain the target suggestion content.

[0124] In one embodiment, if no timeout occurs, the target suggested content can be obtained by inputting the photo information, the first search result, and the second search result into the photo suggestion model during the generation of the target suggested content.

[0125] If no second search result is received within the preset time period, S830: Input the photo information and the first search result into the photo suggestion model to obtain the target suggestion content.

[0126] In one embodiment, if a timeout occurs, the photo information and the first search result can be input into the photo suggestion model during the generation of the target suggestion content to obtain the target suggestion content.

[0127] The photo suggestion method provided in this application embodiment can determine whether a second search result is received within a preset time period. If the second search result is received within the preset time period, the photo information, the first search result, and the second search result are input into the photo suggestion model to obtain the target suggestion content. If the second search result is not received within the preset time period, the photo information and the first search result are input into the photo suggestion model to obtain the target suggestion content. By setting a preset time period, the waiting time for the second search result can be avoided, thus ensuring the timely generation of the target suggestion content and avoiding additional delays caused by waiting for the second search result, thereby improving the real-time performance of generating the target suggestion content.

[0128] It should be noted that, in the process of generating target suggestion content, the specific implementation method can be adopted based on the specific type of target suggestion content being generated.

[0129] Suggestions regarding photo-taking actions, their theoretical basis, and reference images can be displayed as text on the device to prompt the user to make the necessary adjustments. However, suggestions for camera parameters can be implemented using other methods, as detailed below:

[0130] Figure 9 This is a schematic diagram of the parameter adjustment process provided in the embodiments of this application. Please refer to it. Figure 9 When the target suggestion includes camera parameter suggestions, the method also includes:

[0131] S910: Suggests generating target controls based on camera parameters.

[0132] It should be noted that the camera parameter suggestions can be based on the corresponding parameters to set the camera, such as: focal length setting, camera position setting, contrast setting, image quality setting, lighting setting, shooting mode setting, etc. In order to prevent users from making mistakes during the adjustment process, a corresponding target control can be generated based on the camera parameter suggestions. This target control can be displayed in the camera interface of the terminal device.

[0133] S920: In response to triggering the target control, adjust the camera parameters to the target parameters indicated by the camera parameter suggestion.

[0134] This target control allows users to adjust parameters. By clicking on the target control, users can adjust the camera parameters to the target parameters indicated by the camera parameter suggestions.

[0135] The triggering method can be user tap, swipe, or voice control, etc. There are no specific restrictions here, and the corresponding settings can be made according to actual needs.

[0136] It should be noted that for camera parameter suggestions, you can simply display the above target controls to provide prompts to the user, or you can generate corresponding text information while displaying the above target controls to provide prompts, so that the user can understand the function of the target controls and how to trigger them in a timely manner.

[0137] The photo suggestion method provided in this application embodiment can generate a target control based on camera parameter suggestions; in response to triggering the target control, the camera parameters are adjusted to the target parameters indicated by the camera parameter suggestions. The method of triggering via the target control allows for faster adjustment of camera parameters, thereby avoiding user errors and improving the convenience and efficiency of camera parameter adjustment.

[0138] The following is a specific interface diagram to explain one of the feasible implementation processes of camera parameter suggestion based on target control provided in the embodiments of this application.

[0139] Figure 10 This is a schematic diagram of the interface for adjusting based on the target control provided in the embodiments of this application. Please refer to... Figure 10 Please refer to Figure 10 The screen in the middle of the interface can be the camera-based photo-taking interface of the terminal device. After generating camera parameter suggestions in the above manner, the camera parameter suggestions can be executed based on the target control 1010 displayed in the photo-taking interface.

[0140] Users can adjust the camera parameters to the target parameters indicated by the camera parameter suggestions by clicking the target control 1010.

[0141] It should be noted that, as explained above, the photo suggestion model, through training, possesses a certain aesthetic evaluation ability and can return a composition suggestion when the camera's framing effect no longer needs adjustment.

[0142] The following is a detailed explanation of one feasible implementation process for the above-mentioned photo suggestion model to determine whether the target suggestion content needs to be adjusted.

[0143] Figure 11 For another flowchart illustrating the generation of target suggestion content provided in this application embodiment, please refer to... Figure 11 After outputting target suggestions based on the photographed information and search results, the method also includes:

[0144] S1110: Get the preview image for taking a picture.

[0145] The photo preview image can be the photo image information in the photo information, and the photo preview image can be obtained through the camera sensor.

[0146] S1120: If the image previewed in the photo meets the target suggestion content, stop outputting the target suggestion content.

[0147] During the process of generating target suggestion content, the photo suggestion model can determine whether the current photo preview image meets the corresponding suggestions given in the target suggestion content. If it does, it can be determined that the framing effect in the photo preview image does not need to be adjusted, that is, the suggestion of completing the composition can be returned, and thus the target suggestion content does not need to be generated again.

[0148] Correspondingly, if the conditions are not met, it can be determined that the framing effect in the photo preview image still needs to be adjusted, and the suggestion that the composition is complete will not be returned, so the target suggestion content can continue to be generated.

[0149] The photo suggestion method provided in this application embodiment can acquire a photo preview image; if the photo preview image meets the target suggestion content, the output of the target suggestion content is stopped. Since the preview image already meets the target suggestion content, the output of the target suggestion content can be stopped, thereby reducing the power consumption of the terminal device.

[0150] The above explains that if the captured preview image meets the target suggestions, the output of target suggestions can be stopped. However, if the target suggestions are not met, the output of target suggestions can continue. The following explains a feasible implementation process for determining the specific timing for continuing to output target suggestions.

[0151] Figure 12 For a flowchart illustrating the updated target suggestion content provided in this application embodiment, please refer to... Figure 12 After obtaining the preview image, the method also includes:

[0152] S1210: If the preview image does not meet the target suggested content, determine whether the suggested update conditions are met.

[0153] S1220: Update the target recommendation content if the conditions for recommendation update are met.

[0154] It should be noted that if the preview image does not meet the target suggested content, the target suggested content can continue to be output. This target suggested content can be updated periodically, for example, it can be updated periodically according to suggested update conditions.

[0155] The suggested update conditions include: whether user action was detected, or whether the output duration of the target suggested content reached the target threshold.

[0156] The user operation can be based on the aforementioned sensors. For example, if the IMU sensor detects an angle change in the terminal device, it can be determined that the recommended update conditions are met. Alternatively, it can be determined based on image recognition of the captured preview image. If image recognition determines that the change between two adjacent frames is significant, then the recommended update conditions can be determined.

[0157] A timer associated with the output target suggestion content can also be set on the terminal device. The timer duration can be set according to actual needs, such as 10 seconds. If no update is performed within this time, it can be determined whether the output duration of the target suggestion content has reached the target threshold, and it can be determined that the suggestion update condition is met.

[0158] It should be noted that if none of the above suggested update conditions are met, no new target suggested content will be output until the suggested update conditions are met.

[0159] The photo suggestion method provided in this application embodiment can determine whether suggestion update conditions are met when the photo preview image does not meet the target suggestion content. If the suggestion update conditions are met, the target suggestion content is updated. By setting suggestion update conditions, real-time updates of the target suggestion content can be achieved, allowing changes to the target suggestion content based on the user's real-time photo capture situation. This improves the real-time nature and accuracy of suggestions. Furthermore, setting the aforementioned update conditions can avoid the problem of excessive power consumption on the terminal device caused by frequent updates.

[0160] The following explains the overall implementation process of generating target suggestions provided in the embodiments of this application.

[0161] Figure 13 This is a schematic diagram of the overall logic for generating target suggestions provided in the embodiments of this application. Please refer to... Figure 13 After generating the target suggestion content, we can first obtain a photo preview image and determine whether the photo preview image meets the target suggestion content. If it does, we can determine that the composition is complete and no further updates are needed. If it does not meet the requirements, we can determine whether an update is needed based on the corresponding suggestion update conditions. For example, we can first determine whether user operation has been detected, and then determine whether the output duration of the target suggestion content has reached the target threshold. If both of the above conditions are met, or if any one of the conditions is met, we can update and generate new target suggestion content. If neither of the two conditions is met, we do not generate new target suggestion content.

[0162] To more clearly explain the photo-taking suggestion method provided in the embodiments of this application, the following is a detailed explanation of the method using a framework diagram.

[0163] Figure 14 This is a schematic diagram illustrating the framework of the photo-taking suggestion method provided in the embodiments of this application. Please refer to... Figure 14 First, the above-mentioned photo information can be obtained through corresponding sensors, including the camera, IMU sensor and GPS locator. The state control module of the terminal device can determine how to input this photo information into the corresponding model, which may include the retrieval planning model and the photo suggestion model.

[0164] The retrieval planning model can determine the corresponding retrieval method and obtain the retrieval terms, thereby achieving the first retrieval result from the local photo suggestion library on the terminal device, or the second retrieval result from the cloud-based scenic spot image library on the server.

[0165] The local photo suggestion library can include the aforementioned photography theory library, popular technique library, and personalization library.

[0166] For the photo suggestion model, corresponding target suggestion content can be generated based on the search results and photo information, and the state control module can determine whether to update the target suggestion content.

[0167] It should be noted that for the above retrieval planning model, dynamic retrieval planning and timeout abandonment mechanisms can effectively reduce the frequency of retrieval tool calls, optimize cloud load balancing, reduce the overall latency of the retrieval process, and improve user experience.

[0168] For the above photo suggestion model, the scene understanding ability can be enhanced by fine-tuning MLLM, thereby improving the relevance of photo suggestions to the actual shooting scene; the usability of suggestions can be further improved by combining a multi-layer retrieval mechanism, and customized suggestion capabilities can be achieved through user and device personalized retrieval, thereby effectively improving the adoption rate of suggestions and user satisfaction.

[0169] In practice, manual tag selection or classification decision-making mechanisms can be used to replace the aforementioned retrieval planning model at the dynamic retrieval decision-making level. For example, users can manually select scene tags such as "landscape / portrait / pet" before taking photos, or use classification models and rules to make retrieval calls and judgments.

[0170] For the aforementioned search database, a single-layer flat storage structure or a pure cloud-side / end-side dependency mode can be adopted.

[0171] It should be understood that although the steps in the above flowcharts are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the above flowcharts may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0172] Based on the foregoing embodiments, this application provides a photo suggestion device, which includes various modules and units included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits; in the implementation process, the processor can be a central processing unit (CPU), microprocessor (MPU), digital signal processor (DSP) or field programmable gate array (FPGA), etc.

[0173] Figure 15 This is a schematic diagram of the photographing suggestion device provided in the embodiments of this application. Please refer to... Figure 15 In another aspect of the embodiments of this application, a photo suggestion device is also provided, which is applied to a terminal device, including: an acquisition module 1510, a retrieval module 1520 and an output module 1530;

[0174] The acquisition module 1510 is used to acquire photographic information, which includes at least one of the following: photographic image information, photographic location information, or photographic posture information;

[0175] The retrieval module 1520 is used to obtain retrieval results based on the photo retrieval method corresponding to the photo information. The photo retrieval method includes: photo suggestion retrieval based on the photo suggestion library of the terminal device, or photo suggestion retrieval based on the photo suggestion library of the terminal device and photo suggestion retrieval based on the scenic spot image library of the server.

[0176] The output module 1530 is used to output target suggestions based on the photo information and search results. The target suggestions are used to prompt the user to take photos in the target manner.

[0177] In one embodiment, the retrieval module 1520 is specifically used to generate retrieval terms based on the photo information; when the retrieval method corresponding to the photo information is to perform a photo suggestion retrieval based on the photo suggestion library of the terminal device, the first retrieval result is obtained by retrieving the photo suggestion library according to the retrieval terms.

[0178] In one embodiment, the retrieval module 1520 is specifically used to input the photographed information into the retrieval planning model to obtain the search terms and decision information. The decision information is used to indicate whether to upload the photographed information to the server. The retrieval planning model is a neural network model obtained after training based on sample photographed information, sample search terms and sample decision information.

[0179] In one embodiment, the retrieval module 1520 is specifically configured to, when the decision information is used to instruct the uploading of photographic information to the server, perform photographic retrieval by performing photographic suggestion retrieval based on the photographic suggestion library of the terminal device and by performing photographic suggestion retrieval based on the scenic spot image library of the server; upload the photographic information to the server; and receive a second retrieval result issued by the server, wherein the second retrieval result is obtained by the server from the scenic spot image library based on the photographic information.

[0180] In one embodiment, the device includes a photo suggestion library comprising a personalized library; the personalized library is used to generate search results based on the user's historical preference information.

[0181] In one embodiment, the output module 1530 is specifically used to input the photo-taking information and the retrieval results into the photo-taking suggestion model to obtain the target suggestion content. The photo-taking suggestion model is a neural network model trained based on the sample photo-taking information, the sample retrieval results and the sample suggestion content. The target suggestion content includes at least one of the following: camera parameter suggestions, photo-taking action suggestions, suggestion theoretical basis and photo-taking reference images.

[0182] In one embodiment, the output module 1530 is specifically used to input the photo information, the first search result and the second search result into the photo suggestion model if the second search result is received within a preset time period, so as to obtain the target suggestion content.

[0183] If no second search result is received within the preset time period, the photo information and the first search result are input into the photo suggestion model to obtain the target suggestion content.

[0184] In one embodiment, when the target suggestion content includes camera parameter suggestions, the output module 1530 is further configured to generate a target control based on the camera parameter suggestions; and in response to triggering the target control, adjust the camera parameters to the target parameters indicated by the camera parameter suggestions.

[0185] In one embodiment, the output module 1530 is further configured to acquire a photographic preview image; and stop outputting the target suggested content if the photographic preview image meets the target suggested content.

[0186] In one embodiment, the output module 1530 is further configured to determine whether the suggestion update conditions are met when the captured preview image does not meet the target suggestion content. The suggestion update conditions include: whether a user operation is detected, or whether the output duration of the target suggestion content reaches a target threshold. If the suggestion update conditions are met, the target suggestion content is updated.

[0187] The photo suggestion device provided in this application embodiment can acquire photo information, including at least one of the following: photo image information, photo location information, or photo posture information; obtain search results based on the photo retrieval method corresponding to the photo information, which includes: photo suggestion retrieval based on the photo suggestion library of the terminal device, or photo suggestion retrieval based on the photo suggestion library of the terminal device and photo suggestion retrieval based on the scenic spot image library of the server; and output target suggestion content based on the photo information and the search results, which is used to prompt the user to take photos in the target manner. The search results can be obtained by using the corresponding photo retrieval method based on the photo information, which may include a first search result obtained from the photo suggestion library on the terminal device side, or a combination of the first search result and a second search result obtained from the scenic spot image library on the server side. Different methods can yield search results corresponding to those methods, and photo suggestion recommendations can be implemented based on the corresponding search results. That is to say, it can flexibly adopt appropriate photo retrieval methods to obtain search results, thereby flexibly generating photo suggestions. In addition, recommending through the photo suggestion library of the terminal device can avoid high latency and frequent calls, further improving the quality of photo recommendation effects.

[0188] The descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0189] It should be noted that, in the embodiments of this application... Figure 15 The module division of the illustrated photo-taking suggestion device is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, exist as separate physical units, or be integrated into one unit by two or more units. The integrated units described above can be implemented in hardware, as software functional units, or in a combination of software and hardware.

[0190] It should be noted that, in the embodiments of this application, if the above-described methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0191] Figure 16 This is a schematic diagram of the structure of the computer device provided in the embodiments of this application. Please refer to... Figure 16 This application provides a computer device, which can be the aforementioned terminal device, and its internal structure diagram can be as follows. Figure 16 As shown, the computer device includes a processor 1620, memory, and a network interface 1640 connected via a system bus 1610. The processor 1620 provides computing and control capabilities. The memory includes a non-volatile storage medium 1631 and internal memory 1632. The non-volatile storage medium 1631 stores an operating system, computer programs, and a database. The internal memory 1632 provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium 1631. The database is used to store data. The network interface 1640 is used to communicate with external terminals via a network connection. When the computer program is executed by the processor 1620, it implements the aforementioned methods.

[0192] In one embodiment, the computer device may be, for example, a mobile phone, and the program running may be, for example, a camera application.

[0193] It should be noted that the computer device may also include sensors, such as the aforementioned camera, IMU sensor, and GPS locator, etc., without specific limitations.

[0194] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method provided in the above embodiments.

[0195] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the method provided in the above-described method embodiments.

[0196] Those skilled in the art will understand that Figure 16 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0197] In one embodiment, the photo-taking suggestion device provided in this application can be implemented as a computer program, which can be implemented as follows: Figure 16 The device operates on the computer device shown. The memory of the computer device can store the various program modules that make up the above-described apparatus. The computer program, composed of the various program modules, causes the processor to execute the steps of the methods in the various embodiments of this application described in this specification.

[0198] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0199] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" mentioned throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, they will not be repeated here.

[0200] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three kinds of relationships. For example, object A and / or object B can represent three situations: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0201] It should be noted that, in this document, 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. Unless otherwise specified, 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 that element.

[0202] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or modules can be electrical, mechanical, or other forms.

[0203] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0204] In addition, each functional module in the various embodiments of this application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated modules can be implemented in hardware or in the form of hardware plus software functional units.

[0205] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0206] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0207] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0208] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0209] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0210] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A photographing suggestion method, characterized by, Applied to a terminal device, comprising: Obtaining photographing information, the photographing information comprising at least one of photographing image information, photographing position information or photographing posture information; Obtaining a search result based on a photographing search mode corresponding to the photographing information, the photographing search mode comprising: photographing suggestion search based on a photographing suggestion library of the terminal device, or photographing suggestion search based on the photographing suggestion library of the terminal device and photographing suggestion search based on a scenic spot image library of a server; Outputting target suggestion content based on the photographing information and the search result, the target suggestion content being used to prompt a user to take a photograph in a target mode.

2. The method of claim 1, wherein, Before the step of obtaining a search result based on a photographing search mode corresponding to the photographing information, the method further comprises: Generating a search term based on the photographing information; In a case where the photographing search mode corresponding to the photographing information is photographing suggestion search based on a photographing suggestion library of the terminal device, the step of obtaining a search result based on a photographing search mode corresponding to the photographing information comprises: Retrieving a first search result from the photographing suggestion library based on the search term.

3. The method of claim 2, wherein, The step of generating a search term based on the photographing information comprises: Inputting the photographing information into a search planning model to obtain the search term and decision information, the decision information being used to indicate whether to upload the photographing information to the server, the search planning model being a neural network model trained based on sample photographing information, sample search terms and sample decision information.

4. The method of claim 3, wherein, In a case where the decision information is used to indicate that the photographing information is uploaded to the server, the photographing search mode is photographing suggestion search based on the photographing suggestion library of the terminal device and photographing suggestion search based on the scenic spot image library of the server; The step of obtaining a search result based on a photographing search mode corresponding to the photographing information further comprises: Uploading the photographing information to the server; Receiving a second search result issued by the server, the second search result being retrieved from the scenic spot image library by the server based on the photographing information.

5. The method of claim 2, wherein, The photographing suggestion library comprises a personalized library; The personalized library is used to generate a search result based on historical preference information of a user.

6. The method of claim 1, wherein, The step of outputting target suggestion content based on the photographing information and the search result comprises: Inputting the photographing information and the search result into a photographing suggestion model to obtain the target suggestion content, the photographing suggestion model being a neural network model trained based on sample photographing information, sample search results and sample suggestion content, the target suggestion content comprising at least one of camera parameter suggestion, photographing action suggestion, suggestion theoretical basis and photographing reference image.

7. The method of claim 6, wherein, The step of inputting the photographing information and the search result into a photographing suggestion model to obtain the target suggestion content comprises: If a second search result is received within a preset time length, inputting the photographing information, the first search result and the second search result into a photographing suggestion model to obtain the target suggestion content; If the second search result is not received within a preset time length, the photographing information and the first search result are input into a photographing suggestion model to obtain the target suggestion content.

8. The method of claim 6, wherein, In a case where the target suggestion content includes a camera parameter suggestion, the method further includes: generating a target control based on the camera parameter suggestion; in response to triggering the target control, adjusting the camera parameter to a target parameter indicated by the camera parameter suggestion.

9. The method of claim 1, wherein, After the target suggestion content is output according to the photographing information and the search result, the method further includes: obtaining a photographing preview image; in a case where the photographing preview image meets the target suggestion content, stopping output of the target suggestion content.

10. The method of claim 9, wherein, After the photographing preview image is obtained, the method further includes: in a case where the photographing preview image does not meet the target suggestion content, determining whether a suggestion update condition is met, the suggestion update condition including whether a user operation is detected or whether an output time length of the target suggestion content reaches a target threshold; in a case where the suggestion update condition is met, updating the target suggestion content.

11. A photograph suggestion apparatus, characterized by, The application is applied to a terminal device, and includes an obtaining module, a searching module, and an output module. The obtaining module is configured to obtain photographing information, the photographing information including at least one of photographing image information, photographing position information, or photographing posture information. The searching module is configured to obtain a search result based on a photographing search manner corresponding to the photographing information, the photographing search manner including photographing suggestion search based on a photographing suggestion library of the terminal device or photographing suggestion search based on the photographing suggestion library of the terminal device and photographing suggestion search based on a scenic spot image library of a server. The output module is configured to output target suggestion content according to the photographing information and the search result, the target suggestion content being used to prompt a user to take a photograph in a target manner.

12. A computer device comprising a memory and a processor, the memory storing a computer program capable of running on the processor, characterized in that, The processor implements the steps of the method in any one of claims 1 to 10 when executing the program.

13. A computer readable storage medium having stored thereon a computer program, characterized in that The computer program, when executed by the processor, implements the method in any one of claims 1 to 10.

Images