Photographing recommendation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of image processing, in particular to a photographing recommendation method and device, equipment and a storage medium, and the method comprises the steps: obtaining a preview image and photographing annotation data of the preview image, carrying out the coding processing of the photographing annotation data of the preview image, and obtaining the photographing annotation coding representation of the preview image; inputting the photographing annotation coding representation of the preview image into a preset photographing recommendation model for image generation, obtaining a recommendation image corresponding to the preview image, carrying out scenery and figure segmentation on the recommendation image corresponding to the preview image, and obtaining a scenery contour curve graph and a figure contour curve graph; the method comprises the following steps: acquiring a real-time image, comparing the real-time image with a scenery outline drawing graph and a figure outline drawing graph to obtain moving direction prompt information, and displaying the scenery outline drawing graph, the figure outline drawing graph and the moving direction prompt information on a preset photographing interface to prompt a user to perform photographing adjustment. And the high-quality photo taking requirement of the user is met.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, apparatus and storage medium for recommending taking photos. Background Art

[0002] With the development of smartphone photography technology and the popularity of social media, people often use their mobile phones to take pictures to record moments of life, share on social networks, capture travel scenery, etc.

[0003] However, although modern mobile phones are equipped with high-resolution cameras and advanced image processing technology, existing commercial photo recommendation functions have many problems such as the recommendation process requiring frequent user interaction and the recommendation prompt interface being unintuitive. Non-professional users still face challenges in taking high-quality photos. Summary of the invention

[0004] Based on this, the purpose of the present invention is to provide a photo recommendation method, device, equipment and storage medium, which obtains the scene contour outline map and the character contour outline map corresponding to the preview image based on a pre-trained photo recommendation model, and generates moving direction prompt information, which is displayed on a preset photo interface to prompt the user to make photo adjustments and meet the user's high-quality photo taking needs.

[0005] In a first aspect, an embodiment of the present application provides a method for recommending photos, comprising the following steps:

[0006] Obtaining a preview image and photographic annotation data of the preview image, encoding the photographic annotation data of the preview image, and obtaining a photographic annotation encoding representation of the preview image;

[0007] Inputting the photographic annotation coding representation of the preview image into a preset photographic recommendation model to generate an image, thereby obtaining a recommended image corresponding to the preview image, wherein the photographic recommendation model is a neural network model based on deep learning;

[0008] Segmenting the recommended image corresponding to the preview image into a scene and a person to obtain a scene outline and a person outline;

[0009] A real-time image is obtained, and moving direction prompt information is obtained by comparing the real-time image, the scene outline line map, and the person outline line map, and the moving direction prompt information is displayed on a preset photographing interface, wherein the moving direction prompt information is used to prompt the photographing moving position and the photographing moving angle.

[0010] In a second aspect, an embodiment of the present application provides a photo recommendation device, comprising:

[0011] An image acquisition module, used to obtain a preview image and photographic annotation data of the preview image, and perform encoding processing on the photographic annotation data of the preview image to obtain a photographic annotation encoding representation of the preview image;

[0012] An image generation module, used for inputting the photographic annotation coding representation of the preview image into a preset photographic recommendation model to generate an image, and obtaining a recommended image corresponding to the preview image, wherein the photographic recommendation model is a neural network model based on deep learning;

[0013] An image segmentation module is used to segment the recommended image corresponding to the preview image into scenes and people, and obtain the scene outline line map and the person outline line map;

[0014] The prompt information display module is used to obtain a real-time image, compare the real-time image, the scene outline line map and the character outline line map, obtain the moving direction prompt information, and display the scene outline line map, the character outline line map and the moving direction prompt information on a preset photo interface, wherein the moving direction prompt information is used to prompt the photo moving position and the photo moving angle.

[0015] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the photo recommendation method described in the first aspect are implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the photo recommendation method as described in the first aspect are implemented.

[0017] In an embodiment of the present application, a photo recommendation method, apparatus, device and storage medium are provided. Based on a pre-trained photo recommendation model, a scene outline map and a person outline map corresponding to a preview image are obtained, and moving direction prompt information is generated and displayed on a preset photo interface to prompt the user to make photo adjustments to meet the user's high-quality photo taking needs.

[0018] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of a photo recommendation method provided in the first embodiment of the present application;

[0020] Figure 2 A schematic diagram of a process flow of a photo recommendation method provided in the second embodiment of the present application;

[0021] Figure 3 This is a flowchart of S6 in the photo recommendation method provided in the third embodiment of the present application;

[0022] Figure 4 This is a flowchart of S6 in the photo recommendation method provided in the fourth embodiment of the present application;

[0023] Figure 5 A flowchart of a photo recommendation method provided in the fifth embodiment of the present application;

[0024] Figure 6 A schematic diagram of the structure of a photo recommendation device provided in the sixth embodiment of the present application;

[0025] Figure 7 A schematic diagram of the structure of a computer device provided for the seventh embodiment of the present application. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0027] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0028] It should be understood that, although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" / "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0029] See also Figure 1 , Figure 1 This is a flow chart of a method for recommending photos provided in the first embodiment of the present application, the method comprising the following steps:

[0030] S1: obtaining a preview image and photographic annotation data of the preview image, encoding the photographic annotation data of the preview image, and obtaining a photographic annotation encoding representation of the preview image.

[0031] The execution subject of the photograph recommendation method is a recommendation device of the photograph recommendation method (hereinafter referred to as the recommendation device). In an optional embodiment, the recommendation device can be a computer device, a server, or a server cluster formed by a combination of multiple computer devices.

[0032] In this embodiment, the recommendation device can obtain the preview image input by the user, or obtain the preview image sent by the photographing terminal by establishing a data transmission connection with the photographing terminal, wherein the photographing terminal can be a device with a photographing function such as a mobile phone, a tablet or an interactive tablet. The preview image is generated by the user performing a photographing operation in the preview interface through the photographing terminal.

[0033] The recommendation device obtains the photographic annotation data of the preview image, wherein the photographic annotation data is constructed by synchronously recording relevant information of the preview image through a sensor device or a public API interface when the photographing terminal generates the preview image, wherein the photographic annotation data includes character information, scene information and environmental information, wherein the character information includes the number of characters, skin color, clothing and height information of each person; the scene information includes background building information and building angle information; the environmental information includes weather, sunshine, light, humidity, temperature, time period and geographical location information.

[0034] The recommendation device may use a one-hot encoding method or a numerical encoding method to encode the photographic annotation data of the preview image to obtain a photographic annotation encoding representation of the preview image.

[0035] S2: Inputting the photographic annotation coding representation of the preview image into a preset photographic recommendation model to generate an image, and obtaining a recommended image corresponding to the preview image.

[0036] The photo recommendation model is a neural network model based on deep learning.

[0037] In this embodiment, the recommendation device inputs the photographic annotation data of the preview image into a preset photographic recommendation model for image generation. The photographic recommendation model generates an optimal shooting position and angle image based on the preview image and the geographic location information in the photographic annotation coding representation, locks on the specific scenic spot, and performs a comprehensive analysis based on the character information, scenery information and environmental information in the photographic annotation coding representation, and obtains a recommended image corresponding to the preview image, wherein the recommended image includes the optimal order and position for taking photos of each character.

[0038] In an optional embodiment, the step S5 is also included: training the neural network model to be trained, see Figure 2 , Figure 2 The flowchart of S5 in the photo recommendation method provided in the second embodiment of the present application includes steps S51 to S52, which are specifically as follows:

[0039] S51: Obtain a plurality of test images and photographic annotation coding representations of a plurality of the test images.

[0040] In this embodiment, the recommendation device obtains a plurality of test images and a plurality of photographic annotation coding representations of the test images.

[0041] S52: Inputting a plurality of test images and a plurality of photographic annotation coding representations of the test images into a photographic recommendation model to be trained, and using an attention mechanism to extract feature vectors of the test images to obtain image feature representations of the plurality of test images.

[0042] In this embodiment, the recommendation device inputs several test images and several photographic annotation coding representations of the test images into a photographic recommendation model to be trained, and uses an attention mechanism to extract feature vectors of the test images to obtain image feature representations of the test images to capture information such as color, texture, and shape of the images, thereby improving the accuracy of image generation.

[0043] S53: splicing the image feature representation of the test image with the corresponding photographic annotation coding representation to obtain a spliced ​​representation of several test images; using an unsupervised training method to train the photographic recommendation model to be trained according to the spliced ​​representations of several test images to obtain the photographic recommendation model.

[0044] In this embodiment, the recommendation device splices the image feature representation of the test image with the corresponding photographic annotation coding representation to obtain a spliced ​​representation of several test images; an unsupervised training method is used to train the photographic recommendation model to be trained according to the spliced ​​representation of several test images to obtain the photographic recommendation model, so that the photographic recommendation model can pay more attention to important information, can lock on specific scenic spots according to the geographical location information in the test image and the photographic annotation coding representation, and can perform a comprehensive analysis based on the character information, scenery information and environmental information in the photographic annotation coding representation to generate the best shooting position and angle image.

[0045] In an optional embodiment, step S6 is further included: adjusting the model parameters of the photo recommendation model, see Figure 3 , Figure 3The flowchart of S6 in the photo recommendation method provided in the third embodiment of the present application includes steps S61 to S62, which are specifically as follows:

[0046] S61: obtaining photographic annotation coding representations of several verification images, inputting the photographic annotation coding representations corresponding to the several verification images into the photographic recommendation model for image generation, and obtaining the recommended images corresponding to the several verification images and the image feature representations of the recommended images.

[0047] In this embodiment, the recommendation device obtains photographic annotation coding representations of several verification images, inputs the photographic annotation coding representations corresponding to the several verification images into the photographic recommendation model for image generation, and obtains the recommended images corresponding to the several verification images and the image feature representations of the recommended images.

[0048] S62: Using a consistency calculation method, a consistency calculation is performed based on the photographic annotation coding representations of the plurality of verification images and the photographic annotation coding representations of the corresponding recommended images to obtain the consistency between the plurality of verification images and the corresponding recommended images, and according to the consistency between the plurality of verification images and the corresponding recommended images, the model parameters of the photographic recommendation model are adjusted.

[0049] In this embodiment, the recommendation device uses a consistency calculation method to perform consistency calculation based on the photographic annotation coding representations of the plurality of verification images and the photographic annotation coding representations of the corresponding recommended images to obtain the consistency between the plurality of verification images and the corresponding recommended images. Specifically, the consistency calculation method may be a Kappa test method, an ICC intraclass correlation coefficient calculation method, and a Kendall coordination coefficient calculation method.

[0050] The recommended image adjusts the model parameters of the photographing recommendation model according to the consistency between the plurality of verification images and the corresponding recommended images, so as to adjust the degree to which the model emphasizes important information, thereby improving the accuracy of the model in generating the recommended image.

[0051] See also Figure 4 , Figure 4 The flowchart of S6 in the photo recommendation method provided in the fourth embodiment of the present application also includes steps S63 to S64, which are as follows:

[0052] S63: Obtain image feature representations of several verification images, input the photographic annotation coding representations corresponding to the several verification images into the photographic recommendation model for image generation, and obtain the recommended images corresponding to the several verification images and the image feature representations of the recommended images.

[0053] In this embodiment, the recommendation device obtains image feature representations of several verification images, inputs the photographic annotation coding representations corresponding to the several verification images into the photographic recommendation model for image generation, and obtains recommended images corresponding to the several verification images and image feature representations of the recommended images.

[0054] S64: Using a similarity calculation method, perform similarity calculation based on image feature representations of the verification images and image feature representations of corresponding recommended images to obtain similarities between the verification images and the corresponding recommended images, and adjust model parameters of the photo recommendation model based on the similarities between the verification images and the corresponding recommended images.

[0055] In this embodiment, the recommendation device uses a similarity calculation method to perform similarity calculation based on the image feature representations of the verification images and the image feature representations of the corresponding recommended images to obtain the similarity between the verification images and the corresponding recommended images. Specifically, the similarity calculation method can be a structural similarity index (SSIM) calculation method and a peak signal-to-noise ratio (PSNR) calculation method.

[0056] The recommendation device adjusts the model parameters of the photo recommendation model according to the similarities between the plurality of verification images and the corresponding recommended images, so as to further adjust the degree to which the model emphasizes important information, thereby improving the accuracy of the model in generating the recommended images.

[0057] S3: Segment the recommended image corresponding to the preview image into scenes and characters to obtain the scene outline map and the character outline map.

[0058] In this embodiment, the recommendation device adopts an image segmentation model to segment the recommended image corresponding to the preview image into scenes and characters in accordance with category segmentation to obtain the scene outline map and the character outline map. The scene outline map and the character outline map in the recommended image can be determined by category selection or one by one.

[0059] S4: obtaining a real-time image, comparing the real-time image, the outline map of the scene, and the outline map of the person, obtaining moving direction prompt information, and displaying the outline map of the scene, the outline map of the person, and the moving direction prompt information on a preset photographing interface.

[0060] In this embodiment, the recommendation device obtains a real-time image sent by the photographing terminal, wherein the real-time image is an image acquired in real time by the photographing terminal on a photographing interface.

[0061] The recommendation device compares the preview image, the scene outline line map and the person outline line map to obtain movement direction prompt information, wherein the movement direction prompt information is used to prompt the moving position and the moving angle of the photo. Specifically, the recommendation device compares the scene area in the real-time image with the scene outline line map to obtain movement direction prompt information about the scene, and compares the person area in the real-time image with the person outline line map to obtain movement direction prompt information about the person.

[0062] The recommendation device sends the moving direction prompt information about the scene and the moving direction prompt information about the person to the photo terminal, and displays the scene outline and the person outline as well as the moving direction prompt information on the preset photo interface of the photo terminal. Specifically, the moving direction prompt information can be a simple arrow direction prompt or a position and direction description. Based on the pre-trained photo recommendation model, the scene outline and the person outline corresponding to the preview image are obtained, and the moving direction prompt information is generated and displayed on the preset photo interface to prompt the user to make photo adjustments to meet the user's high-quality photo shooting needs.

[0063] In an alternative embodiment, see Figure 5 , Figure 5 The flowchart of the photo recommendation method provided in the fifth embodiment of the present application includes step S7. Step S7 is after step S4 and is specifically as follows:

[0064] S7: Determine whether the scene and the person in the real-time image are consistent with the scene outline and the person outline, and control the photographing terminal to perform a photographing operation.

[0065] The judgment result includes a correct judgment result and a failed judgment result

[0066] In this embodiment, the recommendation device determines whether the scenery and characters in the real-time image are consistent with the scene outline map and the character outline map. If the scene area in the real-time image is consistent with the scene outline map, and the character area in the real-time image is consistent with the character outline map, a correct judgment result is obtained, otherwise a failed judgment result is obtained.

[0067] If the judgment result is a correct judgment result, the recommendation device sends a photo-taking instruction to the photo-taking terminal, and the photo-taking terminal responds to the photo-taking instruction and performs a photo-taking operation to control the photo-taking terminal to perform a photo-taking operation, thereby achieving convenient and accurate acquisition of the best photos and meeting the user's high-quality photo-taking needs.

[0068] Please refer to Figure 6 , Figure 6This is a schematic diagram of the structure of a photograph recommendation device provided in the sixth embodiment of the present application. The device can implement all or part of the photograph recommendation device through software, hardware, or a combination of both. The device 6 includes:

[0069] An image acquisition module 61 is used to obtain a preview image and photographic annotation data of the preview image, and to encode the photographic annotation data of the preview image to obtain a photographic annotation encoding representation of the preview image;

[0070] An image generation module 62 is used to input the photographic annotation code representation of the preview image into a preset photographic recommendation model to generate an image, and obtain a recommended image corresponding to the preview image, wherein the photographic recommendation model is a neural network model based on deep learning;

[0071] An image segmentation module 63 is used to segment the recommended image corresponding to the preview image into a scene and a person, and obtain a line drawing of the scene outline and a line drawing of the person outline;

[0072] The prompt information display module 64 is used to obtain a real-time image, compare the real-time image, the scene outline line map and the character outline line map, obtain the moving direction prompt information, and display the scene outline line map, the character outline line map and the moving direction prompt information on a preset photo interface, wherein the moving direction prompt information is used to prompt the photo moving position and the photo moving angle.

[0073] In an embodiment of the present application, a preview image and photographic annotation data of the preview image are obtained through an image acquisition module, and the photographic annotation data of the preview image are encoded to obtain a photographic annotation encoded representation of the preview image; through an image generation module, the photographic annotation encoded representation of the preview image is input into a preset photographic recommendation model for image generation to obtain a recommended image corresponding to the preview image, wherein the photographic recommendation model is a neural network model based on deep learning; through an image segmentation module, the recommended image corresponding to the preview image is segmented into scenery and characters to obtain the scenery contour outline map and the character contour outline map; through a prompt information display module, a real-time image is obtained, and a comparison is made between the real-time image, the scenery contour outline map and the character contour outline map to obtain moving direction prompt information, and the scenery contour outline map, the character contour outline map and the moving direction prompt information are displayed on a preset photographing interface, wherein the moving direction prompt information is used to prompt the photographing moving position and the photographing moving angle. Based on the pre-trained photo recommendation model, the corresponding scene outline map and person outline map of the preview image are obtained, and the moving direction prompt information is generated and displayed on the preset photo interface to prompt the user to make photo adjustments and meet the user's high-quality photo taking needs.

[0074] Please refer to Figure 7 , Figure 7 A structural diagram of a computer device provided for the seventh embodiment of the present application, wherein the computer device 7 comprises: a processor 71, a memory 72, and a computer program 73 stored in the memory 72 and executable on the processor 71; the computer device may store a plurality of instructions, and the instructions are suitable for being loaded by the processor 71 and executing the method steps shown in the first to fifth embodiments above. For the specific execution process, reference may be made to the specific descriptions shown in the first to fifth embodiments, which will not be described in detail here.

[0075] Among them, the processor 71 may include one or more processing cores. The processor 71 uses various interfaces and lines to connect various parts in the server, and executes various functions and processes data of the photo recommendation device 6 by running or executing instructions, programs, code sets or instruction sets stored in the memory 72, and calling the data in the memory 72. Optionally, the processor 71 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programble Logic Array, PLA). The processor 71 can integrate one or a combination of a central processing unit 71 (Central Processing Unit, CPU), a graphics processor 71 (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the touch display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 71, and it can be implemented by a single chip.

[0076] Among them, the memory 72 may include a random access memory 72 (Random Access Memory, RAM), and may also include a read-only memory 72 (Read-Only Memory). Optionally, the memory 72 includes a non-transitory computer-readable storage medium. The memory 72 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 72 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 72 may also be optionally at least one storage device located away from the aforementioned processor 71.

[0077] An embodiment of the present application also provides a storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing the method steps shown in the first to fifth embodiments above. The specific execution process can refer to the specific description shown in the first to fifth embodiments, which will not be repeated here.

[0078] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0079] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0080] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraint algorithm of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0081] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0085] The present invention is not limited to the above-mentioned embodiments. If various changes or modifications to the present invention do not depart from the spirit and scope of the present invention, and if these changes and modifications fall within the scope of the claims and equivalent technologies of the present invention, the present invention is also intended to include these changes and modifications.

Claims

1. A photo recommendation method, characterized in that: The following steps are involved: Obtaining a preview image and photographic annotation data of the preview image, encoding the photographic annotation data of the preview image, and obtaining a photographic annotation encoding representation of the preview image; Inputting the photographic annotation coding representation of the preview image into a preset photographic recommendation model to generate an image, thereby obtaining a recommended image corresponding to the preview image, wherein the photographic recommendation model is a neural network model based on deep learning; Segmenting the recommended image corresponding to the preview image into a scene and a person to obtain a scene outline and a person outline; A real-time image is obtained, and moving direction prompt information is obtained by comparing the real-time image, the scene outline line map, and the person outline line map, and the moving direction prompt information is displayed on a preset photographing interface, wherein the moving direction prompt information is used to prompt the photographing moving position and the photographing moving angle.

2. The photo recommendation method according to claim 1, characterized in that: The photographic annotation data includes character information, scene information and environmental information. The character information includes the number of characters, skin color, clothing and height information of each person; the scene information includes background building information and building angle information; the environmental information includes weather, sunshine, light, humidity, temperature, time period and geographical location information.

3. The photo recommendation method according to claim 2, characterized in that: Also included are steps of training the neural network model to be trained; The step of training the photo recommendation model to be trained comprises the following steps: Obtaining a plurality of test images and a plurality of photographic annotation coding representations of the test images; Inputting a plurality of test images and a plurality of photographic annotation encoding representations of the test images into a photographic recommendation model to be trained, extracting feature vectors of the test images using an attention mechanism, and obtaining image feature representations of the plurality of test images; The image feature representation of the test image is spliced ​​with the corresponding photographic annotation coding representation to obtain a spliced ​​representation of several test images; an unsupervised training method is adopted to train the photographic recommendation model to be trained according to the spliced ​​representation of several test images to obtain the photographic recommendation model.

4. The photo recommendation method according to claim 3, characterized in that: The steps also include: adjusting the model parameters of the photo recommendation model; The step of adjusting the model parameters of the photo recommendation model comprises the following steps: Obtaining photographic annotation coding representations of a plurality of verification images, inputting the photographic annotation coding representations corresponding to the plurality of verification images into the photographic recommendation model for image generation, and obtaining a plurality of recommended images corresponding to the verification images and image feature representations of the recommended images; A consistency calculation method is adopted to perform consistency calculation based on the photographic annotation coding representations of the plurality of verification images and the photographic annotation coding representations of the corresponding recommended images to obtain the consistency between the plurality of verification images and the corresponding recommended images, and according to the consistency between the plurality of verification images and the corresponding recommended images, the model parameters of the photographic recommendation model are adjusted.

5. The photo recommendation method according to claim 4, characterized in that: The step of adjusting the model parameters of the photo recommendation model further includes the following steps: Obtaining image feature representations of a plurality of the verification images, inputting the photographic annotation coding representations corresponding to the plurality of the verification images into the photographic recommendation model for image generation, and obtaining a plurality of recommended images corresponding to the verification images and image feature representations of the recommended images; A similarity calculation method is adopted to perform similarity calculation based on image feature representations of the verification images and image feature representations of corresponding recommended images to obtain similarities between the verification images and corresponding recommended images, and model parameters of the photo recommendation model are adjusted based on the similarities between the verification images and corresponding recommended images.

6. The photo recommendation method according to claim 5, characterized in that: Also includes the steps: It is determined whether the scene and the person in the real-time image are consistent with the scene outline and the person outline, and the photographing terminal is controlled to perform a photographing operation.

7. A photo recommendation device, characterized in that: include: An image acquisition module, used to obtain a preview image and photographic annotation data of the preview image, and perform encoding processing on the photographic annotation data of the preview image to obtain a photographic annotation encoding representation of the preview image; An image generation module, used for inputting the photographic annotation coding representation of the preview image into a preset photographic recommendation model to generate an image, and obtaining a recommended image corresponding to the preview image, wherein the photographic recommendation model is a neural network model based on deep learning; An image segmentation module is used to segment the recommended image corresponding to the preview image into scenes and people, and obtain the scene outline line map and the person outline line map; The prompt information display module is used to obtain a real-time image, compare the real-time image, the scene outline line map and the character outline line map, obtain the moving direction prompt information, and display the scene outline line map, the character outline line map and the moving direction prompt information on a preset photo interface, wherein the moving direction prompt information is used to prompt the photo moving position and the photo moving angle.

8. A computer device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the photo recommendation method as described in any one of claims 1 to 6 are implemented.

9. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the photo recommendation method according to any one of claims 1 to 6 are implemented.

Images