Intelligent guidance method and intelligent guidance system

Abstract

The invention discloses an intelligent guidance method and an intelligent guidance system, which are used for improving the professional property of photography. The method comprises the steps that a photographing terminal photographs a first image according to a target photographing posture, the first image is sent to a user terminal, and the first image comprises a scene image and a portrait image; the user terminal uploads the first image and target hardware parameters of the photographing terminal to the cloud platform; the cloud platform extracts scene features and portrait features in the first image through the target model; the cloud platform matches a target photographing sample in a database through a matching rule according to the scene features, the portrait features and the target hardware parameters; the cloud platform sends the target photographing sample to the user terminal; the user terminal adjusts a photographing parameter of the photographing terminal into a target photographing parameter through the adjustment instruction according to the target photographing sample; and photographing a second image according to the photographing sample image in the target photographing sample through the photographing terminal.

Description

Technical Field

[0001] This application relates to the field of image processing, and in particular, to an intelligent guidance method and an intelligent guidance system. Background Art

[0002] Photography is an art of light and shadow. With the continuous improvement of people's living standards, people's artistic aesthetic ability has gradually improved. Ordinary tourist photos can no longer meet people's aesthetic needs, and the purpose of taking pictures has gradually evolved from simply taking pictures for memory in the past to the current pursuit of aesthetics.

[0003] However, to take professional photos, certain shooting skills are required. One not only needs to understand the distribution of light and shadow, but also the composition principle, and needs to adjust the poses of the people according to different environmental backgrounds so that the poses of the people and the environmental backgrounds complement each other.

[0004] However, it is difficult for most users to understand and use the composition principle. Although users can search for online pictures to guide the people being photographed to adjust their poses, the matching degree between the online pictures and the environmental backgrounds and the portraits may not be high, resulting in low practicality of the online pictures. Summary of the Invention

[0005] This application provides an intelligent guidance method and an intelligent guidance system for improving the professionalism of photography.

[0006] The first aspect of this application provides an intelligent guidance method, including:

[0007] The photography terminal takes a first image according to a target shooting pose and sends the first image to the user terminal, where the first image includes a scene image and a portrait image;

[0008] The user terminal uploads the first image and the target hardware parameters of the photography terminal to the cloud platform;

[0009] The cloud platform extracts the scene features and portrait features in the first image through a target model;

[0010] The cloud platform matches a target photography sample in a database according to the scene features, the portrait features, and the target hardware parameters through a matching rule;

[0011] The cloud platform sends the target photography sample to the user terminal;

[0012] The user terminal adjusts the photography parameters of the photography terminal to target photography parameters according to the target photography sample through an adjustment instruction;

[0013] The photography terminal takes a second image according to the photography sample image in the target photography sample.

[0014] Optionally, before the user captures a first image using a photography terminal according to a target shooting pose and sends the first image to the user terminal, the intelligent guidance method further includes:

[0015] The user terminal obtains the scene information and portrait information of the current photography;

[0016] The user terminal generates and displays a target shooting pose according to the scene information and the portrait information.

[0017] Optionally, after the user captures a second image using the photography terminal according to the photography sample image, the intelligent guidance method further includes:

[0018] The photography terminal sends the second image to the user terminal;

[0019] The user terminal packages the second image, the target hardware parameters, and the target photography parameters into a target photography sample;

[0020] The user terminal sends the target photography sample to the cloud platform so that the cloud platform updates the database of the cloud platform according to the target photography sample.

[0021] Optionally, after the terminal sends the target photography sample to the cloud platform so that the cloud platform updates the database of the cloud platform according to the target photography sample, the intelligent guidance method further includes:

[0022] The cloud platform obtains at least two scores of the target photography sample;

[0023] The cloud platform generates and displays the target score of the target photography sample according to the average value of the first score and the second score.

[0024] Optionally, the cloud platform extracts the scene features and portrait features in the first image through a target model, including:

[0025] The cloud platform extracts the key scene features in the first image through a target model, and determines the scene main color feature and scene category feature of the key scene features. The key scene features are the features of the scene with the largest area in the first image scene;

[0026] The cloud platform determines the target scene label according to the scene main color feature, the scene category feature, and the key scene features;

[0027] The cloud platform extracts the key portrait features in the first image through a target model, and determines the portrait clothing feature and portrait gender feature of the key portrait features. The key portrait features are the features of the portrait with the largest area in the first image portrait;

[0028] The cloud platform determines a target portrait label based on the portrait dressing feature, the portrait gender feature, and the key portrait feature.

[0029] Optionally, the cloud platform matches a target photography sample in a database according to the scene feature, the portrait feature, and the target hardware parameter through a matching rule, including:

[0030] The cloud platform searches for a first photography sample according to the target hardware parameter, and the hardware parameter of the target photography terminal that captured the first photography sample is less than or equal to the target hardware parameter;

[0031] The cloud platform determines a first priority value of the scene feature and determines a second priority value of the portrait feature. The first priority value is determined according to a first proportion of the scene in the first image, and the second priority value is determined according to a second proportion of the portrait in the first image;

[0032] The cloud platform determines whether the first priority value is greater than the second priority value;

[0033] If the first priority value is greater than the second priority value, the cloud platform determines a second photography sample according to the scene label, and the matching value of the scene label of the second photography sample and the target scene label exceeds a preset matching value;

[0034] The cloud platform determines a target photography sample according to the second photography sample;

[0035] If the first priority value is less than the second priority value, the cloud platform determines a third photography sample according to the target portrait label, and the matching value of the portrait label of the third photography sample and the target portrait label exceeds a preset matching value;

[0036] The cloud platform determines a target photography sample according to the third photography sample.

[0037] Optionally, the cloud platform determines a target photography sample according to the second photography sample, including:

[0038] The cloud platform obtains a score of the second photography sample;

[0039] The cloud platform determines the photography sample with the highest score in the second photography sample as the target photography sample.

[0040] The second aspect of this application provides an intelligent guidance system, including a photography terminal, a user terminal, and a cloud platform;

[0041] The photography terminal is configured to capture a first image according to a target shooting pose and send the first image to the user terminal. The first image includes a scene image and a portrait image;

[0042] The user terminal is used to upload the first image and the target hardware parameters of the photography terminal to the cloud platform;

[0043] The cloud platform is used to extract the scene features and portrait features in the first image through a target model;

[0044] The cloud platform is used to match the target photography samples in the database according to the scene features, the portrait features and the target hardware parameters through a matching rule;

[0045] The cloud platform is used to send the target photography samples to the user terminal;

[0046] The user terminal is used to adjust the photography parameters of the photography terminal to target photography parameters according to the target photography samples through an adjustment instruction;

[0047] The photography terminal is used to take a second image according to the photography sample image in the target photography sample.

[0048] Optionally, the user terminal is further used to obtain the scene information and portrait information of the current photography;

[0049] The user terminal is further used to generate and display a target shooting pose according to the scene information and the portrait information.

[0050] Optionally, the photography terminal is further used to send the second image to the user terminal;

[0051] The user terminal is further used to package the second image, the target hardware parameters and the target photography parameters into a target photography sample;

[0052] The user terminal is further used to send the target photography sample to the cloud platform so that the cloud platform updates the database of the cloud platform according to the target photography sample.

[0053] Optionally, the cloud platform is further used to obtain at least two scores of the target photography sample;

[0054] The cloud platform is further used to generate and display the target score of the target photography sample according to the average value of the first score and the second score.

[0055] Optionally, the cloud platform is specifically used to extract the key scene features in the first image through a target model, and determine the scene main color feature and scene category feature of the key scene features, where the key scene features are the features of the scene with the largest area in the first image scene;

[0056] The cloud platform is specifically configured to determine a target scene label according to the scene main color feature, the scene category feature, and the key scene feature;

[0057] The cloud platform is specifically configured to extract key portrait features from the first image through a target model, and determine the portrait dressing feature and portrait gender feature of the key portrait features, where the key portrait features are the features of the portrait with the largest area in the first image portrait;

[0058] The cloud platform is specifically configured to determine a target portrait label according to the portrait dressing feature, the portrait gender feature, and the key portrait feature.

[0059] Optionally, the cloud platform is specifically configured to search for a first photography sample according to the target hardware parameter, and the hardware parameter of the target photography terminal that captures the first photography sample is less than or equal to the target hardware parameter;

[0060] The cloud platform is specifically configured to determine a first priority value of the scene feature and a second priority value of the portrait feature, where the first priority value is determined according to the first proportion of the scene in the first image, and the second priority value is determined according to the second proportion of the portrait in the first image;

[0061] The cloud platform is specifically configured to determine whether the first priority value is greater than the second priority value;

[0062] If the first priority value is greater than the second priority value, the cloud platform is specifically configured to determine a second photography sample according to the scene label, and the matching value between the scene label of the second photography sample and the target scene label exceeds a preset matching value;

[0063] The cloud platform is specifically configured to determine a target photography sample according to the second photography sample;

[0064] If the first priority value is less than the second priority value, the cloud platform is specifically configured to determine a third photography sample according to the target portrait label, and the matching value between the portrait label of the third photography sample and the target portrait label exceeds a preset matching value;

[0065] The cloud platform is specifically configured to determine a target photography sample according to the third photography sample.

[0066] Optionally, the cloud platform is specifically configured to obtain a score of the second photography sample;

[0067] The cloud platform is specifically configured to determine the photography sample with the highest score in the second photography sample as the target photography sample.

[0068] A third aspect of the present application provides an intelligent guidance system, and the intelligent guidance system includes:

[0069] A processor, a memory, an input / output unit, and a bus;

[0070] The processor is connected to the memory, the input / output unit, and the bus;

[0071] The memory stores a program, and the processor calls the program to execute an intelligent guidance method according to the first aspect and any optional one in the first aspect.

[0072] A fourth aspect of the present application provides a computer-readable storage medium, on which a program is stored, and when the program is executed on a computer, it executes an intelligent guidance method according to the first aspect and any optional one in the first aspect.

[0073] As can be seen from the above technical solutions, the present application has the following advantages: The user takes an image according to the target shooting pose through the photography terminal and sends the first image to the user terminal. The first image includes a scene image and a portrait image; the user terminal uploads the first image and the target hardware parameters of the photography terminal to the cloud platform; the cloud platform extracts the scene features and portrait features in the first graph through the target model; the cloud platform matches the target photography sample in the database according to the scene features, portrait features, and target hardware parameters through the matching rule; the cloud platform sends the target photography sample to the user terminal; the user terminal adjusts the photography parameters of the photography terminal to the target photography parameters through the adjustment instruction according to the target photography sample, and the photography terminal takes the second image according to the photography sample image in the target photography sample; through the above method, the cloud platform matches the target photography sample in the database through the scene features, character features, and target hardware parameters through the matching rule, so as to match the target photography sample suitable for the current scene and the current person for the user, so that the user takes the second image through the photography terminal according to the photography sample image in the target photography sample, thereby improving the professionalism of photography. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions in the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0075] Figure 1 It is a schematic flowchart of an embodiment of an intelligent guidance method provided by the present application;

[0076] Figure 2 It is a schematic flowchart of another embodiment of an intelligent guidance method provided by the present application;

[0077] Figure 3Schematic structural diagram of an embodiment of an intelligent guidance system provided by the present application;

[0078] Figure 4 Schematic structural diagram of another embodiment of an intelligent guidance system provided by the present application. Detailed implementation manners

[0079] The present application provides an intelligent guidance method and an intelligent guidance system for improving the professionalism of photography.

[0080] It should be noted that the intelligent guidance method provided by the present application can be applied to a terminal or a server. For example, the terminal can be a smart phone, a computer, a tablet computer, a smart TV, a smart watch, a portable computer terminal, or a fixed terminal such as a desktop computer. For the convenience of description, the terminal is taken as the execution subject in the present application for example.

[0081] Please refer to Figure 1 , Figure 1 which is an embodiment of an intelligent guidance method provided by the present application. The method includes:

[0082] 101. The photography terminal takes a first image according to a target shooting pose and sends the first image to the user terminal. The first image includes a scene image and a portrait image;

[0083] In this embodiment, the user takes a first image through the photography terminal according to the target shooting pose. Among them, the target shooting pose is generated by the user terminal searching for similar images according to the current photography scene information and portrait information, and generating a simple target shooting pose, which is displayed on the user terminal. The user takes a first image through the photography terminal according to the target shooting pose and sends the first image to the user terminal. The first image includes a scene image and a portrait image.

[0084] 102. The user terminal uploads the first image and the target hardware parameters of the photography terminal to the cloud platform;

[0085] In this embodiment, the user terminal obtains the target hardware parameters of the photography terminal and uploads the first image and the target hardware parameters of the photography terminal to the cloud platform, so that the cloud platform matches the target photography samples according to the first image and the target hardware parameters.

[0086] 103. The cloud platform extracts the scene features and portrait features in the first image through the target model;

[0087] In this embodiment, the cloud platform extracts the scene features and portrait features in the first image through a pre-trained target model, including: the cloud platform extracts the key scene features in the first image through the target model, and determines the scene main color feature and scene category feature of the key scene features, where the key scene features are the features of the scene with the largest area in the first image scene; the cloud platform determines the target scene label according to the scene main color feature, scene category feature and key scene features; the cloud platform extracts the key portrait features in the first image through the target model, and determines the portrait clothing feature and portrait gender feature of the key portrait features, where the key portrait features are the features of the portrait with the largest area in the first image; the cloud platform determines the target portrait label according to the portrait clothing feature, portrait gender feature and key portrait features; among them, the scene features include features such as mountains, trees, flowers and plants, buildings, indoor furniture, scenes, etc.; the portrait features include single-person portrait features or multi-person portrait features; the target model can be a convolutional neural network model.

[0088] 104. The cloud platform matches the target photographic sample in the database according to the scene features, portrait features and target hardware parameters through the matching rule;

[0089] In this embodiment, the cloud platform matches a target photography sample in the database according to the scene features, portrait features, and target hardware parameters through a matching rule, including: the cloud platform searches for a first photography sample according to the target hardware parameters, and the hardware parameters of the target photography terminal that captured the first photography sample are less than or equal to the target hardware parameters; the cloud platform determines a first priority value for the scene features and a second priority value for the portrait features. The first priority value is determined according to the first proportion of the scene in the first image, and the second priority value is determined according to the second proportion of the portrait in the second image; the cloud platform determines whether the first priority value is greater than the second priority value; if the first priority value is greater than the second priority value, the cloud platform determines a second photography sample according to the scene label, and the matching value between the scene label of the second photography sample and the target scene label exceeds a preset matching value; the cloud platform determines the target photography sample according to the second photography sample; if the first priority value is less than the second valid value, the cloud platform determines a third photography sample according to the target portrait label, and the matching value between the portrait label of the third photography sample and the target portrait label exceeds a preset matching value; the cloud platform determines the target photography sample according to the third photography sample; the hardware parameters of the target photography terminal that captured the first photography sample are less than or equal to the target hardware parameters, thus preventing the hardware parameters required for the finished film of the target photography sample matched by the cloud platform from being too high, causing the user to be unable to use the shooting terminal at hand to achieve the same photography effect; if the first image contains both scene features and portrait features, the cloud platform determines the priority of the scene or portrait according to the proportion of the scene features or portrait features. If the first proportion of the scene in the first image is greater than the second proportion of the portrait in the first image, the cloud platform determines that the scene has priority at this time and determines a second photography sample according to the scene label; if the first proportion of the scene in the first image is less than the second proportion of the portrait in the first image, the cloud platform determines that the portrait has priority at this time and determines a third photography sample according to the portrait label; the cloud platform determining the target photography sample according to the second photography sample includes: the cloud platform obtains the score of the second photography sample, and the cloud platform determines the photography sample with the highest score in the second photography sample as the target photography sample.

[0090] 105. The cloud platform sends the target photography sample to the user terminal;

[0091] In this embodiment, the cloud platform establishes a communication connection with the user terminal and sends the target photography sample to the user terminal.

[0092] 106. The user terminal adjusts the photography parameters of the photography terminal to the target photography parameters according to the target photography sample through an adjustment instruction;

[0093] In this embodiment, the user terminal obtains the target photography parameters of the target photography sample and adjusts the photography parameters of the photography terminal to the target photography parameters through an adjustment instruction, so that the photography parameters of the photography terminal are the same as those of the target photography terminal that captured the target photography sample.

[0094] 107. The second image is captured by the photography terminal according to the photographic sample image in the target photographic sample.

[0095] In this embodiment, the user terminal displays the photographic sample image in the target photographic sample on the display screen. The user adjusts the pose of the person and the composition of the picture of the person and the scene according to the photographic sample image in the target photographic sample through the photography terminal, and captures the second image.

[0096] In the embodiment of the present application, through the above method, the cloud platform matches the target photographic sample in the database through the scene features, human features and target hardware parameters through the matching rule, so as to match the target photographic sample suitable for the current scene and the current person for the user, so that the user captures the second image through the photography terminal according to the photographic sample image in the target photographic sample, thereby improving the professionalism of photography.

[0097] To make the intelligent guidance method provided by the present application more obvious and easy to understand, the intelligent guidance method provided by the present application will be described in detail below:

[0098] Please refer to Figure 2 , Figure 2 which is another embodiment of the intelligent guidance method provided by the present application. The intelligent guidance method includes:

[0099] 201. The user terminal obtains the scene information and portrait information of the current photography.

[0100] In this embodiment, the user can input the scene information and portrait information of the current photography through the user terminal. For example, the current scene information is that the scene is a mountain, and the portrait information is the height, weight or color of the clothing of the portrait, etc.

[0101] 202. The user terminal generates and displays the target shooting pose according to the scene information and portrait information.

[0102] In this embodiment, the user terminal generates and displays a simple target shooting pose according to the scene information and portrait information, so that the user can perform a positive simple shooting of the current scene and the current portrait through the photography terminal to obtain the first image.

[0103] 203. The first image is captured by the photography terminal according to the target pose, and the first image is sent to the user terminal. The first image includes a scene image and a portrait image.

[0104] 204. The user terminal uploads the first image and the target hardware parameters of the photography terminal to the cloud platform.

[0105] 205. The cloud platform extracts the scene features and portrait features in the first image through the target model.

[0106] 206. The cloud platform matches the target photography sample in the database according to the scene characteristics, portrait characteristics, and target hardware parameters through the matching rules;

[0107] 207. The cloud platform sends the target photography sample to the user terminal;

[0108] 208. The user terminal adjusts the photography parameters of the photography terminal to the target photography parameters according to the target photography sample through the adjustment instruction;

[0109] 209. The photography terminal takes a second image according to the photography sample image in the target photography sample;

[0110] Steps 203 to 209 in this embodiment are similar to steps 101 to 107 in the foregoing Figure 1 embodiment, and will not be elaborated here specifically.

[0111] 210. The photography terminal sends the second image to the user terminal;

[0112] In this embodiment, the photography terminal establishes a Bluetooth connection with the user terminal or establishes a communication connection with the user terminal through WIFI, so that the photography terminal sends the second image to the user terminal.

[0113] 211. The user terminal packs the second image, the target hardware parameters, and the target photography parameters into the target photography sample;

[0114] In this embodiment, the user terminal packs the second image, the target hardware parameters of the photography terminal, and the target photography parameters into the target photography sample, so that other user terminals can obtain the target hardware parameters and target photography parameters of the photography terminal from the target photography sample as a photography reference or photography guidance.

[0115] 212. The user terminal sends the target photography sample to the cloud platform, so that the cloud platform updates the database of the cloud platform according to the target photography sample;

[0116] In this embodiment, the user terminal establishes a communication connection with the cloud platform, and the user terminal sends the photography sample to the cloud platform, so that the cloud platform updates the database of the cloud platform according to the target photography sample, so that other user terminals can search for the target photography sample in the database of the cloud platform.

[0117] 213. The cloud platform obtains at least two scores of the target photography sample;

[0118] In this embodiment, the cloud platform obtains at least two scores of the target photography sample from other user terminals.

[0119] 214. The cloud platform generates and displays the target score of the target photography sample according to the average value of the first score and the second score;

[0120] In this embodiment, the cloud platform generates a target score for the target photography sample according to the average value of the first score and the second score, and displays the target score so that other users can refer to the target score.

[0121] The above describes an intelligent guidance method provided by this application. Next, an intelligent guidance system provided by this application will be described:

[0122] Please refer to Figure 3 , Figure 3 which is an embodiment of an intelligent guidance system provided by this application. The system includes a photography terminal, a user terminal, and a cloud platform;

[0123] The photography terminal 301 is used to capture a first image according to the target shooting pose and send the first image to the user terminal 302. The first image includes a scene image and a portrait image;

[0124] The user terminal 302 is used to upload the first image and the target hardware parameters of the photography terminal 301 to the cloud platform 303;

[0125] The cloud platform 303 is used to extract the scene features and portrait features in the first image through the target model;

[0126] The cloud platform 303 is used to match the target photography sample in the database according to the scene features, the portrait features, and the target hardware parameters through the matching rule;

[0127] The cloud platform 303 is used to send the target photography sample to the user terminal 302;

[0128] The user terminal 302 is used to adjust the photography parameters of the photography terminal 301 to the target photography parameters according to the target photography sample through the adjustment instruction;

[0129] The photography terminal 301 is used to capture a second image according to the photography sample image in the target photography sample.

[0130] Optionally, the user terminal 302 is further used to obtain the scene information and portrait information of the current photography;

[0131] The user terminal 302 is further used to generate and display the target shooting pose according to the scene information and the portrait information.

[0132] Optionally, the photography terminal 301 is further used to send the second image to the user terminal 302;

[0133] The user terminal 302 is further used to package the second image, the target hardware parameters, and the target photography parameters into a target photography sample;

[0134] The user terminal 302 is further configured to send the target photographic sample to the cloud platform 303, so that the cloud platform 303 updates the database of the cloud platform 303 according to the target photographic sample.

[0135] Optionally, the cloud platform 303 is further configured to obtain at least two scores of the target photographic sample;

[0136] The cloud platform 303 is further configured to generate and display a target score of the target photographic sample according to the average value of the first score and the second score.

[0137] Optionally, the cloud platform 303 is specifically configured to extract key scene features in the first image through a target model, and determine the scene main color feature and scene category feature of the key scene feature, where the key scene feature is the feature of the scene with the largest area in the first image scene;

[0138] The cloud platform 303 is specifically configured to determine a target scene label according to the scene main color feature, the scene category feature, and the key scene feature;

[0139] The cloud platform 303 is specifically configured to extract key portrait features in the first image through a target model, and determine the portrait clothing feature and portrait gender feature of the key portrait feature, where the key portrait feature is the feature of the portrait with the largest area in the first image portrait;

[0140] The cloud platform 303 is specifically configured to determine a target portrait label according to the portrait clothing feature, the portrait gender feature, and the key portrait feature.

[0141] Optionally, the cloud platform 303 is specifically configured to search for a first photographic sample according to target hardware parameters, and the hardware parameters of the target photographic terminal 301 that captured the first photographic sample are less than or equal to the target hardware parameters;

[0142] The cloud platform 303 is specifically configured to determine a first priority value of the scene feature and a second priority value of the portrait feature, where the first priority value is determined according to the first proportion of the scene in the first image, and the second priority value is determined according to the second proportion of the portrait in the first image;

[0143] The cloud platform 303 is specifically configured to determine whether the first priority value is greater than the second priority value;

[0144] If the first priority value is greater than the second priority value, the cloud platform 303 is specifically configured to determine a second photographic sample according to the scene label, and the matching value of the scene label of the second photographic sample and the target scene label exceeds a preset matching value;

[0145] The cloud platform 303 is specifically configured to determine a target photographic sample according to the second photographic sample;

[0146] If the first priority value is less than the second priority value, the cloud platform 303 is specifically configured to determine a third photographic sample according to the target portrait label, and the matching value between the portrait label of the third photographic sample and the target portrait label exceeds a preset matching value;

[0147] The cloud platform 303 is specifically configured to determine a target photographic sample according to the third photographic sample.

[0148] Optionally, the cloud platform 303 is specifically configured to obtain the score of the second photographic sample;

[0149] The cloud platform 303 is specifically configured to determine the photographic sample with the highest score in the second photographic sample as the target photographic sample.

[0150] In the system of this embodiment, the functions executed by each unit correspond to the steps in the foregoing Figure 1 and Figure 2 method embodiment shown, and will not be elaborated herein specifically.

[0151] This application also provides an intelligent guidance system. Please refer to Figure 4 , Figure 4 which is an embodiment of an intelligent guidance system provided by this application. The intelligent guidance system includes:

[0152] A processor 401, a memory 402, an input / output unit 403, and a bus 404;

[0153] The processor 401 is connected to the memory 402, the input / output unit 403, and the bus 404;

[0154] The memory 402 stores a program, and the processor 401 calls the program to execute any one of the intelligent guidance methods as described above.

[0155] This application also relates to a computer-readable storage medium, on which a program is stored. When the program runs on a computer, the computer is enabled to execute any one of the intelligent guidance methods as described above.

[0156] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0157] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0160] If the integrated 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 such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, and other various media that can store program codes.

Claims

1. An intelligent guidance method, characterized in that: The intelligent guidance method comprises: Taking a first image according to a target shooting posture by a photographing terminal, and sending the first image to a user terminal, wherein the first image includes a scene image and a portrait image; The user terminal uploads the first image and the target hardware parameters of the photographing terminal to the cloud platform; The cloud platform extracts scene features and portrait features in the first image through a target model; The cloud platform matches the target photography sample in the database through matching rules according to the scene features, the portrait features and the target hardware parameters; The cloud platform sends the target photography sample to the user terminal; The user terminal adjusts the photographic parameters of the photographic terminal to target photographic parameters through an adjustment instruction according to the target photographic sample; A second image is captured by the photographic terminal according to the photographic sample image in the target photographic sample.

2. The intelligent guidance method according to claim 1, characterized in that: Before the user captures the first image according to the target shooting posture through the photography terminal and sends the first image to the user terminal, the intelligent guidance method further includes: The user terminal obtains scene information and portrait information of the current photography; The user terminal generates and displays a target shooting posture according to the scene information and the portrait information.

3. The intelligent guidance method according to claim 1, characterized in that: After the user captures a second image according to the photographic sample image through the photographic terminal, the intelligent guidance method further includes: The photographing terminal sends the second image to the user terminal; The user terminal packages the second image, the target hardware parameter, and the target photography parameter into a target photography sample; The user terminal sends the target photography sample to the cloud platform, so that the cloud platform updates the database of the cloud platform according to the target photography sample.

4. The intelligent guidance method according to claim 3, characterized in that: After the terminal sends the target photography sample to the cloud platform so that the cloud platform updates the database of the cloud platform according to the target photography sample, the intelligent guidance method further includes: The cloud platform obtains at least two scores of the target photography sample; The cloud platform generates and displays a target score for the target photography sample according to an average value of the first score and the second score.

5. The intelligent guidance method according to any one of claims 1 to 4, characterized in that: The cloud platform extracts scene features and portrait features in the first image through the target model, including: The cloud platform extracts key scene features in the first image through the target model, and determines scene main color features and scene category features of the key scene features, wherein the key scene features are features of the scene with the largest area in the first image scene; The cloud platform determines a target scene label according to the scene main color feature, the scene category feature and the key scene feature; The cloud platform extracts key portrait features in the first image through the target model, and determines portrait clothing features and portrait gender features of the key portrait features, wherein the key portrait features are features of the portrait with the largest area among the portraits in the first image; The cloud platform determines the target portrait label according to the portrait clothing features, portrait gender features and key portrait features.

6. The intelligent guidance method according to claim 5, characterized in that: The cloud platform matches the target photographic sample in the database according to the scene feature, the portrait feature and the target hardware parameter through a matching rule, including: The cloud platform searches for a first photographic sample according to the target hardware parameter, and the hardware parameter of the target photographic terminal that photographed the first photographic sample is less than or equal to the target hardware parameter; The cloud platform determines a first priority value of the scene feature and determines a second priority value of the portrait feature, wherein the first priority value is determined according to a first proportion of the scene to the first image, and the second priority value is determined according to a second proportion of the portrait to the first image; The cloud platform determines whether the first priority value is greater than the second priority value; If the first priority value is greater than the second priority value, the cloud platform determines a second photographic sample according to the scene tag, and a matching value between the scene tag of the second photographic sample and the target scene tag exceeds a preset matching value; The cloud platform determines a target photographic sample according to the second photographic sample; If the first priority value is less than the second priority value, the cloud platform determines a third photographic sample according to the target portrait tag, and a matching value between the portrait tag of the third photographic sample and the target portrait tag exceeds a preset matching value; The cloud platform determines a target photographic sample according to the third photographic sample.

7. The intelligent guidance method according to claim 6, characterized in that: The cloud platform determines the target photographic sample according to the second photographic sample, including: The cloud platform obtains a score of the second photographic sample; The cloud platform determines that the photographic sample with the highest score among the second photographic samples is the target photographic sample.

8. An intelligent guidance system, characterized in that: The intelligent guidance system includes a photography terminal, a user terminal and a cloud platform; The photographing terminal is used to capture a first image according to a target shooting posture, and send the first image to a user terminal, wherein the first image includes a scene image and a portrait image; The user terminal is used to upload the first image and the target hardware parameters of the photographic terminal to the cloud platform; The cloud platform is used to extract scene features and portrait features in the first image through a target model; The cloud platform is used to match the target photography sample in the database through matching rules according to the scene features, the portrait features and the target hardware parameters; The cloud platform is used to send the target photography sample to the user terminal; The user terminal is used to adjust the photographic parameters of the photographic terminal to the target photographic parameters through the adjustment instruction according to the target photographic sample; The photographic terminal is used to capture a second image based on the photographic sample image in the target photographic sample.

9. The intelligent guidance system according to claim 8, characterized in that: The user terminal is also used to obtain scene information and portrait information of the current photography; The user terminal is also used to generate and display a target shooting posture according to the scene information and the portrait information.

10. The intelligent guidance system according to claim 8, characterized in that: The photographing terminal is further used to send the second image to the user terminal; The user terminal is further used to package the second image, the target hardware parameters and the target photography parameters into a target photography sample; The user terminal is further used to send the target photography sample to the cloud platform, so that the cloud platform updates the database of the cloud platform according to the target photography sample.

Images