Model scene graph recommendation method and device based on human body posture, equipment and medium

Abstract

The invention provides a model scene picture recommendation method and device based on human body postures, equipment and a medium, and the method comprises the steps: setting a scene picture library, carrying out the posture classification of pictures in the scene picture library, and printing a corresponding posture label for each picture; obtaining a model chart uploaded by a user, and obtaining a skeleton chart of the model chart; if the key point data does not exist in the skeleton diagram, ending the step; if key point data exist in the skeleton diagram, labeling a posture on the model icon according to posture classification; acquiring age and gender according to the model chart, matching a corresponding picture from the scene picture library according to the age, gender and the posture label, and displaying the picture; the accuracy of the recommended scene graph is ensured, and subsequent operation is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of scene graph recommendation, and particularly relates to a method, device, equipment and medium for recommending a model scene graph based on human poses. Background Art

[0002] The current AI model replacement function provides a large number of scene reference pictures with specific models. After a user uploads a model picture, it is necessary to make recommendations from a large number of scene reference pictures according to priorities. Whether the recommended reference picture is appropriate determines whether the generated model picture scene is natural. The existing technology recommends appropriate scene pictures for the user according to the age and gender of the uploaded model.

[0003] The disadvantages of the existing method are that the number of scene pictures recommended only by age and gender matching is too large and inaccurate. The user still needs to browse a lot of scene pictures to find the scene picture that truly matches the uploaded model picture. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, device, equipment and medium for recommending a model scene graph based on human poses, which makes a match between the pose of the uploaded model and the pose of the person in the scene graph, and then combines gender and age to achieve very accurate scene graph recommendation.

[0005] In a first aspect, the present invention provides a method for recommending a model scene graph based on human poses, including the following steps:

[0006] Step 1: Set up a scene picture library, classify the pictures in the scene picture library by pose, and label each picture with a corresponding pose label;

[0007] Step 2: Obtain the model picture uploaded by the user, and obtain the skeleton graph of the model picture;

[0008] Step 3: If there is no key point data in the skeleton graph, end the step; if there is key point data in the skeleton graph, label the model picture with a pose label according to the pose classification;

[0009] Step 4: Obtain the age and gender according to the model picture, and match and display the corresponding pictures from the scene picture library according to the age, gender and pose label.

[0010] In a second aspect, the present invention provides a device for recommending a model scene graph based on human poses, including:

[0011] A picture library setting module, which sets up a scene picture library, classifies the pictures in the scene picture library by pose, and labels each picture with a corresponding pose label;

[0012] Skeleton Map Acquisition Module, which acquires the model image uploaded by the user and obtains the skeleton map of the model image;

[0013] Labeling Module, if there is no key point data in the skeleton map, it ends; if there is key point data in the skeleton map, it labels the model image with a pose label according to the pose classification;

[0014] Matching Module, which obtains the age and gender according to the model image, and matches and displays the corresponding images from the scene picture library according to the age, gender and pose label.

[0015] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the method described in the first aspect.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method described in the first aspect.

[0017] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0018] By classifying the poses of the models and then performing matching, the accuracy of the recommended model scene pictures is greatly improved, effectively reducing the time cost for users to screen the scene pictures. In addition, more accurately recommended scene pictures are used, and the fit degree of the position and size of the generated models in the scene pictures is higher, improving the availability of the finally generated model pictures.

[0019] The above description is only an overview of the technical solutions of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the following specifically gives the specific implementation manners of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The present invention will be further described below with reference to the accompanying drawings in conjunction with embodiments.

[0021] Figure 1 is the flowchart of the method in Embodiment 1 of the present invention;

[0022] Figure 2 is the structural schematic diagram of the device in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0023] Embodiment 1

[0024] As Figure 1 shown, this embodiment provides a method for recommending model scene pictures based on human poses, including the following steps:

[0025] Step 1: Set up a scene picture library, classify the poses of the pictures in the scene picture library, and label each picture with the corresponding pose label; all the pictures in the scene picture library are pictures containing human models.

[0026] Step 2: Obtain the model picture uploaded by the user, and obtain the skeleton diagram of the model picture.

[0027] Step 3: If there is no key point data in the skeleton diagram, end the step, indicating that there is a problem with the model picture uploaded by the user, and the user can be reminded through a prompt box; if there is key point data in the skeleton diagram, label the model picture with a pose label according to the pose classification.

[0028] Step 4: Obtain the age and gender according to the model picture, and match and display the corresponding pictures from the scene picture library according to the age, gender, and pose label; this display method is to display all the matching pictures, and the front and back order of the pictures can be randomly sorted. The age and gender of the model picture can be obtained through existing algorithms. As long as the age is within the set range, the two pictures can be matched. There may be cases where the age and gender are empty. For example, when there is a close-up of the legs and feet, there is no age and gender.

[0029] In this embodiment, preferably, the pose classification is specifically as follows:

[0030] 5-point upper body picture:

[0031] If at least one of the right hip key point and the left hip key point exists, and the right hip key point or the left hip key point is less than 20 pixels away from the bottom of the skeleton diagram, and both the right knee key point and the left knee key point do not exist; then it is a 5-point upper body picture.

[0032] If both the left shoulder key point and the right shoulder key point exist, and the distance between the left shoulder key point and the right shoulder key point is less than 0.7 of the width of the skeleton diagram, and the right eye key point, the left eye key point, the right ear key point, the left ear key point, and the nose key point all exist, and the distance between the right ear key point and the left ear key point is less than 1 / 3 of the width of the skeleton diagram; then it is a 5-point upper body picture.

[0033] 7-point upper body picture:

[0034] Both the right hip key point and the left hip key point exist, at least one of the right knee key point and the left knee key point exists, and the right knee key point or the left knee key point is less than 20 pixels away from the bottom of the skeleton diagram, and both the right ankle key point and the left ankle key point do not exist, then it is a 7-point upper body picture.

[0035] 9-point upper body picture:

[0036] If both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, and at least one of the right ankle key point and the left ankle key point exists, and the right ankle key point or the left ankle key point is less than 20 pixels away from the bottom of the skeleton diagram, it is a 9-point upper body diagram;

[0037] Lower body diagram:

[0038] If the neck key point does not exist, both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, it is a lower body diagram;

[0039] Leg and foot close-up diagram:

[0040] If the neck key point does not exist, both the right hip key point and the left hip key point do not exist, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, it is a leg and foot close-up diagram;

[0041] First full body occupying the picture diagram:

[0042] If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance from the left knee key point to the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 80% of the height of the skeleton diagram, it is a first full body occupying the picture diagram;

[0043] Second full body occupying the picture diagram:

[0044] If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance from the left knee key point to the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 70% of the height of the skeleton diagram and less than or equal to 80% of the height of the skeleton diagram, it is a second full body occupying the picture diagram;

[0045] Third full body occupying the picture diagram:

[0046] If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance from the left knee key point to the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 60% of the height of the skeleton diagram and less than or equal to 70% of the height of the skeleton diagram, it is a third full body occupying the picture diagram;

[0047] Fourth full body occupying the picture diagram:

[0048] If the right eye key point, left eye key point, right ear key point, left ear key point, nose key point, left ankle key point, and right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance from the left knee key point to the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 50% of the height of the skeleton diagram and less than or equal to 60% of the height of the skeleton diagram, then it is the fourth full-body picture occupying the screen;

[0049] Fifth full-body picture occupying the screen:

[0050] If the right eye key point, left eye key point, right ear key point, left ear key point, nose key point, left ankle key point, and right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance from the left knee key point to the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is less than or equal to 50% of the height of the skeleton diagram, then it is the fifth full-body picture occupying the screen;

[0051] Head close-up picture:

[0052] If the right eye key point, left eye key point, right ear key point, left ear key point, and nose key point all exist and do not belong to the 5-point upper body picture, then they are all head close-up pictures;

[0053] Make judgments in sequence. If it meets the criteria, end the judgment and label it; for the above classification method, as long as it meets one of the classifications during the judgment process, stop further classification, ensuring that each picture has only one pose label, which is convenient for subsequent matching.

[0054] In this embodiment, preferably, step 1 is specifically: set up a scene picture library, classify the pictures in the scene picture library by pose, and label each picture with the corresponding pose label; classify the pictures in the scene picture library by ratio, and label each picture with the corresponding ratio label;

[0055] Step 3 is specifically: if there is no key point data in the skeleton diagram, end the step; if there is key point data in the skeleton diagram, then label the model with a pose label according to the pose classification, and label the model with a ratio label according to the ratio classification;

[0056] Step 4 is specifically: obtain the age and gender according to the model picture, and match the corresponding picture from the scene picture library according to the age, gender, pose label, and ratio label for display.

[0057] In this embodiment, preferably, the ratio classification is specifically: if both the left ankle key point and the right ankle key point exist, then judge the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram;

[0058] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is less than 10% of the height of the skeleton diagram, it is the first proportional diagram;

[0059] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 10% of the height of the skeleton diagram and less than 20% of the height of the skeleton diagram, it is the second proportional diagram;

[0060] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 20% of the height of the skeleton diagram and less than 30% of the height of the skeleton diagram, it is the third proportional diagram;

[0061] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 30% of the height of the skeleton diagram and less than 40% of the height of the skeleton diagram, it is the fourth proportional diagram;

[0062] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 50% of the height of the skeleton diagram, it is the fifth proportional diagram;

[0063] Classify the pictures according to the above-mentioned proportion and label them with the corresponding proportion labels.

[0064] Based on the same inventive concept, the present application also provides a device corresponding to the method in Embodiment 1. For details, see Embodiment 2.

[0065] Embodiment 2

[0066] As Figure 2 shown, in this embodiment, a model scene map recommendation device based on human postures is provided, including:

[0067] A gallery module is set up to set up a scene picture library, classify the pictures in the scene picture library, and label each picture with a corresponding posture label;

[0068] A skeleton diagram acquisition module is used to acquire the model diagram uploaded by the user and acquire the skeleton diagram of the model diagram;

[0069] A label module, if there is no key point data in the skeleton diagram, end; if there is key point data in the skeleton diagram, label the model with a posture label according to the posture classification;

[0070] A matching module is used to acquire the age and gender according to the model diagram, and match and display the corresponding pictures from the scene picture library according to the age, gender and posture label.

[0071] Preferably, in this embodiment, the posture classification is specifically:

[0072] 5-point upper body diagram:

[0073] If at least one of the right hip key point and the left hip key point exists, and the distance of the right hip key point or the left hip key point from the bottom of the skeleton diagram is less than 20 pixels, and neither the right knee key point nor the left knee key point exists; then it is a 5-point upper body diagram;

[0074] If both the left shoulder key point and the right shoulder key point exist, and the distance between the left shoulder key point and the right shoulder key point is less than 0.7 of the width of the skeleton diagram, and the right eye key point, the left eye key point, the right ear key point, the left ear key point, and the nose key point all exist, and the distance between the right ear key point and the left ear key point is less than 1 / 3 of the width of the skeleton diagram; then it is a 5-point upper body diagram;

[0075] 7-point upper body diagram:

[0076] If both the right hip key point and the left hip key point exist, at least one of the right knee key point and the left knee key point exists, and the distance of the right knee key point or the left knee key point from the bottom of the skeleton diagram is less than 20 pixels, and neither the right ankle key point nor the left ankle key point exists, then it is a 7-point upper body diagram;

[0077] 9-point upper body diagram:

[0078] If both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, at least one of the right ankle key point and the left ankle key point exists, and the distance of the right ankle key point or the left ankle key point from the bottom of the skeleton diagram is less than 20 pixels, then it is a 9-point upper body diagram;

[0079] Lower body diagram:

[0080] If the neck key point does not exist, both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, then it is a lower body diagram;

[0081] Leg and foot close-up diagram:

[0082] If the neck key point does not exist, neither the right hip key point nor the left hip key point exists, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, then it is a leg and foot close-up diagram;

[0083] First full body covering the picture:

[0084] If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point, and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 80% of the height of the skeleton diagram, then it is the first full body covering the picture;

[0085] Second full body covering the picture:

[0086] If the right - eye key point, left - eye key point, right - ear key point, left - ear key point, nose key point, left - ankle key point, and right - ankle key point all exist, and the ratio of the distance between the left - ankle key point and the left - knee key point to the distance between the left - knee key point and the left - hip key point is within the set threshold, and the distance from the nose key point to the right - ankle key point is greater than 70% of the height of the skeleton diagram and less than or equal to 80% of the height of the skeleton diagram, then it is the second full - body - occupying - the - picture diagram;

[0087] Third full - body - occupying - the - picture diagram:

[0088] If the right - eye key point, left - eye key point, right - ear key point, left - ear key point, nose key point, left - ankle key point, and right - ankle key point all exist, and the ratio of the distance between the left - ankle key point and the left - knee key point to the distance between the left - knee key point and the left - hip key point is within the set threshold, and the distance from the nose key point to the right - ankle key point is greater than 60% of the height of the skeleton diagram and less than or equal to 70% of the height of the skeleton diagram, then it is the third full - body - occupying - the - picture diagram;

[0089] Fourth full - body - occupying - the - picture diagram:

[0090] If the right - eye key point, left - eye key point, right - ear key point, left - ear key point, nose key point, left - ankle key point, and right - ankle key point all exist, and the ratio of the distance between the left - ankle key point and the left - knee key point to the distance between the left - knee key point and the left - hip key point is within the set threshold, and the distance from the nose key point to the right - ankle key point is greater than 50% of the height of the skeleton diagram and less than or equal to 60% of the height of the skeleton diagram, then it is the fourth full - body - occupying - the - picture diagram;

[0091] Fifth full - body - occupying - the - picture diagram:

[0092] If the right - eye key point, left - eye key point, right - ear key point, left - ear key point, nose key point, left - ankle key point, and right - ankle key point all exist, and the ratio of the distance between the left - ankle key point and the left - knee key point to the distance between the left - knee key point and the left - hip key point is within the set threshold, and the distance from the nose key point to the right - ankle key point is less than or equal to 50% of the height of the skeleton diagram, then it is the fifth full - body - occupying - the - picture diagram;

[0093] Head close - up diagram:

[0094] If the right - eye key point, left - eye key point, right - ear key point, left - ear key point, and nose key point all exist and it does not belong to the 5 - point upper - body diagram, then they are all head close - up diagrams;

[0095] Make judgments in sequence. If it meets the requirements, then end the judgment and assign a label.

[0096] In this embodiment, preferably, the setting gallery module is specifically: setting a scene picture library, classifying the pictures in the scene picture library by poses, and attaching corresponding pose labels to each picture; classifying the pictures in the scene picture library by proportions, and attaching corresponding proportion labels to each picture.

[0097] The obtaining skeleton diagram module is specifically: if there is no key point data in the skeleton diagram, end the step; if there is key point data in the skeleton diagram, label the model with a pose label according to the pose classification, and label the model with a proportion label according to the proportion classification.

[0098] The matching module is specifically: obtaining the age and gender according to the model picture, and matching and displaying the corresponding pictures from the scene picture library according to the age, gender, pose label and proportion label.

[0099] In this embodiment, preferably, the proportion classification is specifically: if both the left ankle key point and the right ankle key point exist, judge the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram.

[0100] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is less than 10% of the height of the skeleton diagram, it is a first proportion diagram.

[0101] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 10% of the height of the skeleton diagram and less than 20% of the height of the skeleton diagram, it is a second proportion diagram.

[0102] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 20% of the height of the skeleton diagram and less than 30% of the height of the skeleton diagram, it is a third proportion diagram.

[0103] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 30% of the height of the skeleton diagram and less than 40% of the height of the skeleton diagram, it is a fourth proportion diagram.

[0104] If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 50% of the height of the skeleton diagram, it is a fifth proportion diagram.

[0105] For the pictures with the above proportion classification, attach the corresponding proportion labels.

[0106] Since the device introduced in the second embodiment of the present invention is the device used to implement the method of the first embodiment of the present invention, based on the method introduced in the first embodiment of the present invention, those skilled in the art can understand the specific structure and variations of the device, so it will not be elaborated here. Any device used in the method of the first embodiment of the present invention falls within the scope of protection of the present invention.

[0107] Based on the same inventive concept, this application provides an embodiment of an electronic device corresponding to the first embodiment, as detailed in the third embodiment.

[0108] Embodiment Three

[0109] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, any implementation manner in the first embodiment can be realized.

[0110] Since the electronic device introduced in this embodiment is the device used to implement the method in the first embodiment of this application, based on the method introduced in the first embodiment of this application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the details of how this electronic device implements the method in the embodiments of this application will not be introduced in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application falls within the scope of protection of this application.

[0111] Based on the same inventive concept, this application provides a storage medium corresponding to the first embodiment, as detailed in the fourth embodiment.

[0112] Embodiment Four

[0113] This embodiment provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, any implementation manner in the first embodiment can be realized.

[0114] The technical solutions provided in the embodiments of this application at least have the following technical effects or advantages: In this embodiment, by classifying the poses of models in detail and then performing matching, the accuracy of model scene graph recommendation is significantly improved. This improvement not only greatly reduces the time consumption of users when screening scene graphs, but also makes the position and size of the model in the scene graph more fitting through more accurate scene graph recommendation, thus significantly enhancing the practicality and usability of the finally generated model graph. In short, the present invention optimizes the generation process of model graphs through intelligent recommendation, bringing a more efficient and satisfactory experience to users.

[0115] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0116] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0117] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0119] Although the specific embodiments of the present invention have been described above, those skilled in the art of this technology should understand that the specific embodiments we described are illustrative rather than used to limit the scope of the present invention. Equivalent modifications and variations made by those skilled in the art in accordance with the spirit of the present invention should be covered by the scope protected by the claims of the present invention.

Claims

1. A method for recommending model scene pictures based on human postures, characterized in that: it includes the following steps: Step 1, set up a scene picture library, classify the pictures in the scene picture library by postures, and label each picture with a corresponding posture label; Step 2, obtain the model picture uploaded by the user, and obtain the skeleton picture of the model picture; Step 3, if there is no key point data in the skeleton picture, end the step; if there is key point data in the skeleton picture, label the model picture with a posture label according to the posture classification; Step 4, obtain the age and gender according to the model picture, and match and display the corresponding pictures from the scene picture library according to the age, gender and posture label.

2. The method for recommending model scene pictures based on human postures according to claim 1, characterized in that: the specific posture classification is: 5-point upper body picture: If at least one of the right hip key point and the left hip key point exists, and the right hip key point or the left hip key point is less than 20 pixels away from the bottom of the skeleton picture, and both the right knee key point and the left knee key point do not exist; then it is a 5-point upper body picture; If both the left shoulder key point and the right shoulder key point exist, and the distance between the left shoulder key point and the right shoulder key point is less than 0.7 of the width of the skeleton picture, and the right eye key point, the left eye key point, the right ear key point, the left ear key point and the nose key point all exist, and the distance between the right ear key point and the left ear key point is less than 1 / 3 of the width of the skeleton picture; then it is a 5-point upper body picture; 7-point upper body picture: Both the right hip key point and the left hip key point exist, at least one of the right knee key point and the left knee key point exists, and the right knee key point or the left knee key point is less than 20 pixels away from the bottom of the skeleton picture, and both the right ankle key point and the left ankle key point do not exist, then it is a 7-point upper body picture; 9-point upper body picture: Both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, at least one of the right ankle key point and the left ankle key point exists, and the right ankle key point or the left ankle key point is less than 20 pixels away from the bottom of the skeleton picture, then it is a 9-point upper body picture; Lower body picture: The neck key point does not exist, both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, then it is a lower body picture; Leg and foot close-up picture: The neck key point does not exist, both the right hip key point and the left hip key point do not exist, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, then it is a leg and foot close-up picture; First full body occupying the picture: The right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance from the left knee key point to the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 80% of the height of the skeleton picture, then it is the first full body occupying the picture; Second full body occupying the picture: If the right eye key point, left eye key point, right ear key point, left ear key point, nose key point, left ankle key point, and right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 70% of the height of the skeleton diagram and less than or equal to 80% of the height of the skeleton diagram, then it is the second full-body picture occupying the screen; Third full-body picture occupying the screen: If the right eye key point, left eye key point, right ear key point, left ear key point, nose key point, left ankle key point, and right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 60% of the height of the skeleton diagram and less than or equal to 70% of the height of the skeleton diagram, then it is the third full-body picture occupying the screen; Fourth full-body picture occupying the screen: If the right eye key point, left eye key point, right ear key point, left ear key point, nose key point, left ankle key point, and right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 50% of the height of the skeleton diagram and less than or equal to 60% of the height of the skeleton diagram, then it is the fourth full-body picture occupying the screen; Fifth full-body picture occupying the screen: If the right eye key point, left eye key point, right ear key point, left ear key point, nose key point, left ankle key point, and right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is less than or equal to 50% of the height of the skeleton diagram, then it is the fifth full-body picture occupying the screen; Close-up head picture: If the right eye key point, left eye key point, right ear key point, left ear key point, and nose key point all exist and do not belong to the 5-point upper body picture, then they are all close-up head pictures; Make judgments in sequence. If it meets the requirements, end the judgment and label it.

3. A method for recommending model scene pictures based on human postures according to claim 1, characterized in that: The specific steps of step 1 are as follows: Set up a scene picture library, classify the pictures in the scene picture library by posture, and label each picture with a corresponding posture label; classify the pictures in the scene picture library by ratio, and label each picture with a corresponding ratio label; The specific steps of step 3 are as follows: If there is no key point data in the skeleton diagram, end the step; if there is key point data in the skeleton diagram, label the model picture with a posture label according to the posture classification and label the model picture with a ratio label according to the ratio classification; The specific steps of step 4 are as follows: Obtain the age and gender according to the model picture, and match the corresponding pictures from the scene picture library according to the age, gender, posture label, and ratio label for display.

4. A method for recommending model scene pictures based on human postures according to claim 3, characterized in that: The specific proportion classification is as follows: If both the left ankle key point and the right ankle key point exist, then determine the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is less than 10% of the height of the skeleton diagram, it is the first proportion diagram; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 10% of the height of the skeleton diagram and less than 20% of the height of the skeleton diagram, it is the second proportion diagram; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 20% of the height of the skeleton diagram and less than 30% of the height of the skeleton diagram, it is the third proportion diagram; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 30% of the height of the skeleton diagram and less than 40% of the height of the skeleton diagram, it is the fourth proportion diagram; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 50% of the height of the skeleton diagram, it is the fifth proportion diagram; For the proportion classification of the picture, attach the corresponding proportion label.

5. A model scene picture recommendation device based on human postures, characterized in that: It includes: A gallery setting module that sets a scene picture library, classifies the pictures in the scene picture library by posture, and attaches a corresponding posture label to each picture; A skeleton diagram acquisition module that acquires the model picture uploaded by the user and acquires the skeleton diagram of the model picture; A label module. If there is no key point data in the skeleton diagram, end; if there is key point data in the skeleton diagram, label the model with a posture label according to the posture classification; A matching module that acquires the age and gender according to the model picture, and matches and displays the corresponding pictures from the scene picture library according to the age, gender, and posture label.

6. The model scene picture recommendation device based on human postures according to claim 5, characterized in that: The specific posture classification is as follows: 5-point upper body picture: If at least one of the right hip key point and the left hip key point exists, and the distance from the right hip key point or the left hip key point to the bottom of the skeleton diagram is less than 20 pixels, and both the right knee key point and the left knee key point do not exist; then it is a 5-point upper body picture; If both the left shoulder key point and the right shoulder key point exist, and the distance between the left shoulder key point and the right shoulder key point is less than 0.7 of the width of the skeleton diagram, and the right eye key point, the left eye key point, the right ear key point, the left ear key point, and the nose key point all exist, and the distance between the right ear key point and the left ear key point is less than 1 / 3 of the width of the skeleton diagram; then it is a 5-point upper body picture; 7-point upper body picture: If both the right hip key point and the left hip key point exist, at least one of the right knee key point and the left knee key point exists, and the distance from the right knee key point or the left knee key point to the bottom of the skeleton diagram is less than 20 pixels, and both the right ankle key point and the left ankle key point do not exist, then it is a 7-point upper body picture; 9-point upper body picture: If both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, and at least one of the right ankle key point and the left ankle key point exists, and the right ankle key point or the left ankle key point is less than 20 pixels away from the bottom of the skeleton diagram, it is a 9-point upper body diagram; Lower body diagram: If the neck key point does not exist, both the right hip key point and the left hip key point exist, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, it is a lower body diagram; Close-up of legs and feet diagram: If the neck key point does not exist, both the right hip key point and the left hip key point do not exist, both the right knee key point and the left knee key point exist, and both the right ankle key point and the left ankle key point exist, it is a close-up of legs and feet diagram; First full body occupying the picture diagram: If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 80% of the height of the skeleton diagram, it is a first full body occupying the picture diagram; Second full body occupying the picture diagram: If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 70% of the height of the skeleton diagram and less than or equal to 80% of the height of the skeleton diagram, it is a second full body occupying the picture diagram; Third full body occupying the picture diagram: If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 60% of the height of the skeleton diagram and less than or equal to 70% of the height of the skeleton diagram, it is a third full body occupying the picture diagram; Fourth full body occupying the picture diagram: If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is greater than 50% of the height of the skeleton diagram and less than or equal to 60% of the height of the skeleton diagram, it is a fourth full body occupying the picture diagram; Fifth full body occupying the picture diagram: If the right eye key point, the left eye key point, the right ear key point, the left ear key point, the nose key point, the left ankle key point and the right ankle key point all exist, and the ratio of the distance between the left ankle key point and the left knee key point to the distance between the left knee key point and the left hip key point is within the set threshold, and the distance from the nose key point to the right ankle key point is less than or equal to 50% of the height of the skeleton diagram, it is a fifth full body occupying the picture diagram; Close-up of the head diagram: If the key points of the right eye, left eye, right ear, left ear, and nose all exist and do not belong to the upper body picture of 5 points, they are all close-up pictures of the head; Make judgments in sequence. If it meets the requirements, end the judgment and label it.

7. A model scene picture recommendation device based on human body postures according to claim 5, characterized in that: The setting picture library module is specifically: set a scene picture library, classify the pictures in the scene picture library by postures, and label each picture with a corresponding posture label; classify the pictures in the scene picture library by proportions, and label each picture with a corresponding proportion label; The obtaining skeleton diagram module is specifically: if there is no key point data in the skeleton diagram, end the step; if there is key point data in the skeleton diagram, label the model picture with a posture label according to the posture classification, and label the model picture with a proportion label according to the proportion classification; The matching module is specifically: obtain the age and gender according to the model picture, and match and display the corresponding pictures from the scene picture library according to the age, gender, posture label, and proportion label.

8. A model scene picture recommendation device based on human body postures according to claim 7, characterized in that: The proportion classification is specifically: if both the left ankle key point and the right ankle key point exist, judge the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is less than 10% of the height of the skeleton diagram, it is the first proportion picture; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 10% of the height of the skeleton diagram and less than 20% of the height of the skeleton diagram, it is the second proportion picture; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 20% of the height of the skeleton diagram and less than 30% of the height of the skeleton diagram, it is the third proportion picture; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 30% of the height of the skeleton diagram and less than 40% of the height of the skeleton diagram, it is the fourth proportion picture; If the distance from the left ankle key point or the right ankle key point to the bottom of the skeleton diagram is greater than or equal to 50% of the height of the skeleton diagram, it is the fifth proportion picture; For the pictures with the above proportion classification, label them with the corresponding proportion labels.

9. An electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, when the processor executes the program, it implements the method according to any one of claims 1 to 4.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that, when the program is executed by the processor, it implements the method according to any one of claims 1 to 4.

Images