Digital human element generation method, system and terminal

Abstract

The invention relates to a digital human element generation method, system and terminal, and relates to the field of digital human technology, and the method comprises the steps: obtaining a product image of a user product; extracting product elements according to the product image; determining a product area according to the product elements, and obtaining wearing elements of the digital human; determining a display area according to the wearing elements; and when the product area does not exceed the display area, generating digital human elements according to the product elements and the wearing elements. The method and the device have the effects of improving the identification degree of the user and reducing the condition that digital persons are similar.

Description

Technical Field

[0001] The present invention relates to the field of digital human technology, and in particular to a method, system and terminal for generating digital human elements. Background Art

[0002] Digital human refers to a comprehensive product that exists in the non-physical world, is created and used by computer means, and has multiple human characteristics.

[0003] In the existing technology, digital human technology is often used in the live broadcast industry. During the live broadcast, users first need to construct a unique digital human image to improve user recognition, and then adjust the digital human's appearance, clothing and other elements to form a digital human image that meets the requirements, and interact with the audience through the digital human image.

[0004] The wearable elements that users use to make up digital humans are generally retrieved from a unified material library, which can easily lead to similar digital human images generated by users in the same industry, thereby reducing user recognition. Summary of the invention

[0005] In order to improve user recognition and reduce the similarity of digital humans, the present invention provides a method, system and terminal for generating digital human elements.

[0006] In a first aspect, the present invention provides a method for generating digital human elements, which adopts the following technical solution: A method for generating digital human elements, comprising: Get product images of user products; Extract product elements based on product images; Determine the product area based on product elements and obtain the wearable elements of the digital human; Determine the display area based on the wearable elements; When the product area does not exceed the display area, digital human elements are generated based on product elements and wearable elements.

[0007] By adopting the above technical solution, the user's product is combined with the standard wearable elements to form a customized wearable element unique to the user, so that the customized wearable element can be selected according to the user's needs to reduce the similarity of digital people, thereby improving the user's recognition.

[0008] Optionally, also include: When the product area does not exceed the display area, determine the product model based on the product image; Determine product sales based on product models; Determine the area occupancy ratio based on product area and display area; Determine the priority coefficient of the product based on the product sales volume and occupancy ratio; Product elements are selected according to the priority coefficients, and digital human elements are generated based on the product elements and wearable elements.

[0009] By adopting the above technical solution, the user's main products or product elements with a high utilization rate of the display area are preferentially combined with standard wearable elements, so that the digital human can preferentially display the user's main products and improve the user's recognition.

[0010] Optionally, also include: Determine the display location according to the display area; Determine the wearing factor of the wearable according to the display position and wearing elements; Determine the display area according to the display area; Determine the display coefficient of the wearable according to the display area and the wear coefficient; Wearable elements are selected in sequence according to the display coefficient, and digital human elements are generated based on product elements and wearable elements.

[0011] By adopting the above technical solution, product elements are preferentially combined with wearable elements with obvious positions or larger display areas, so that the digital human can better display the user's product, improve the difference of the digital human, and thus the user's recognition.

[0012] Optionally, a product element correction method is also included, and the product element correction method includes: When the product area exceeds the display area, the excess area is determined based on the product area and the display area; Calculate the quotient of the excess area and the display area and define it as the excess ratio; Determine the correction factor based on product sales and excess percentage; When the correction factor is lower than the preset correction threshold, the reduction factor is determined based on the product area and the display area; Determine the reduction factor based on the reduction factor and product factors; Generate digital human elements based on reduced elements and wearable elements.

[0013] By adopting the above technical solution, when the display area cannot accommodate product elements, the feasibility and necessity of trimming the product elements are evaluated based on the product sales volume and the area exceeding the display area, and when the product elements need to be trimmed, the product elements are reduced so that the display area can accommodate the product elements.

[0014] Optionally, the product element correction method further includes: When the correction factor is lower than the preset correction threshold, the remaining proportion is determined based on the product area and display area; When the remaining proportion is not less than the excess proportion, the element corner is determined based on the product area and the display area; Determine the rotation factor based on the factor rotation angle and product factor; Determine the rotation area according to the rotation elements; The reduction factor is determined based on the rotation area and the display area.

[0015] By adopting the above technical solution, when the appearance of the product is greatly different from that of the display area, it is easy to cause a large amount of empty space when the display area accommodates the product elements. At this time, the product elements are rotated to find the angle with the highest space utilization rate, and then the product elements are reduced to reduce the reduction coefficient of the product, thereby improving the clarity of the product displayed through the wearable elements.

[0016] Optionally, a product image correction method is also included, and the product image correction method includes: Determine the reduction area according to the reduction coefficient and the rotation area; Determine the display threshold of products based on product models; When the reduced area is below the display threshold, the horizontal and vertical proportions are determined based on the product area and display area; Determine the horizontal rotation angle according to the horizontal proportion; Determine the longitudinal rotation angle according to the longitudinal proportion; The preset product is rotated according to the horizontal rotation angle and the vertical rotation angle, and the product image of the product is reacquired.

[0017] By adopting the above technical solution, when the product reduction coefficient is too large, it is easy to cause the product elements to be too small, which in turn leads to the inability to fully display the details of the product. By adjusting the product placement angle to adjust the viewing angle when acquiring the product image, the product area size and horizontal and vertical ratios in the product image are adjusted, and then the area size and horizontal and vertical ratios of the product elements are adjusted, thereby reducing the reduction coefficient.

[0018] Optionally, the product image correction method further includes: When the reduced area is below the display threshold, the product category is determined based on the product image; Determine the benchmark image of the product according to the product category; determining product features of the product based on the reference image and the product image; Determine characteristic areas based on product characteristics; Determine the zoom ratio based on the feature area and the display area; A feature image of the feature area is obtained according to the zoom ratio, and the feature image is used as the product image.

[0019] By adopting the above technical solution, the images of the user's product and conventional products are compared to find out the differences between the user's product, and then capture the differences as product elements, thereby improving the difference of product elements and improving user recognition.

[0020] Optionally, it also includes an element splicing method, and the element splicing method includes: When the product area does not exceed the display area, the remaining area is determined based on the product area and the display area; Determine the supplementary area based on the product area and the remaining area; Determine the supplementary elements based on the supplementary area; Generate digital human elements based on supplementary elements, product elements and wearable elements.

[0021] By adopting the above technical solution, when the product elements and the wearable elements are combined, the empty part in the display area is found, so as to find the product elements that can be accommodated in the empty part, and then as many products as possible are displayed in the same display area, thereby improving the utilization rate of the display area.

[0022] In the second aspect, the present application provides a digital human element generation system, which adopts the following technical solution: A digital human element generation system, comprising: An acquisition module, used to acquire product images, wearing elements and feature pictures; A memory for storing a program of any one of the above-mentioned methods for generating digital human elements; The program in the memory can be loaded and executed by the processor.

[0023] In a third aspect, the present application provides a smart terminal, which adopts the following technical solution: An intelligent terminal comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and execute any one of the above-mentioned digital human element generation methods.

[0024] By adopting the above technical solution, the user's product is combined with the standard wearable elements to form a customized wearable element unique to the user, so that the customized wearable element can be selected according to the user's needs to reduce the similarity of digital people, thereby improving the user's recognition.

[0025] In summary, the present application includes at least one of the following beneficial technical effects: Combine the user's products with standard wearable elements to form customized wearable elements unique to the user, so that customized wearable elements can be selected according to the user's needs to reduce the similarity of digital humans, thereby improving the user's recognition; give priority to combining the user's main products or product elements with a high utilization rate of the display area with standard wearable elements, so that the digital human can give priority to displaying the user's main products and improve the user's recognition; give priority to combining product elements with wearable elements with obvious positions or larger display areas, so that the digital human can better display the user's products, improve the difference of the digital human, and thus the user's recognition. BRIEF DESCRIPTION OF THE DRAWINGS Figure 1 It is a process of generating digital human elements. Figure 1 ; Figure 2 It is a process of generating digital human elements. Figure 2 ; Figure 3 It is a process of generating digital human elements. Figure 3 ; Figure 4 It is the process of product element correction method Figure 1 ; Figure 5 It is the process of product element correction method Figure 2 ; Figure 6 Is the process of product image correction method Figure 1 ; Figure 7 Is the process of product image correction method Figure 2 ; Figure 8 It is a flowchart of the feature stitching method. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0027] The embodiment of the present invention discloses a method for generating digital human elements, which combines the user's products with standard wearable elements to form customized wearable elements unique to the user, and preferentially displays the user's main products according to the user's business situation, so that customized wearable elements can be selected according to the user's needs to reduce the situation where digital humans are similar, thereby improving the user's recognition.

[0028] Reference Figure 1 , a method for generating digital human elements, comprising: Step 100: Obtain product images of user products.

[0029] Product images refer to pictures of user products. Product images can be obtained through a camera. The method for obtaining product images is selected by the staff based on actual conditions and will not be elaborated here.

[0030] Step 101: extract product elements based on the product image.

[0031] Product elements refer to the three-dimensional data of user products. Product elements can be extracted from product images using deep learning technology. The method of extracting product elements is common knowledge among people in this field and will not be elaborated here.

[0032] Step 102: Determine the product area according to the product elements, and obtain the wearable elements of the digital human.

[0033] The product area refers to the range of product elements mapped on a plane. The product area can be extracted from the product elements. The method of extracting the product area is common knowledge among people in this field and will not be elaborated here.

[0034] Wearable elements refer to standard clothing elements that digital humans can choose to wear. Wearable elements can be retrieved from pre-set wearable element data. The method for obtaining wearable elements is selected by the staff based on actual conditions and will not be elaborated here.

[0035] Step 103: Determine a display area according to the wearable elements.

[0036] The display area refers to the range on the wearable element where product elements can be attached. Each wearable element is pre-set with a certain display area. The display area can be extracted from the wearable element. The method for extracting the display area is common knowledge among people in this field and will not be elaborated here.

[0037] Step 104: When the product area does not exceed the display area, a digital human element is generated according to the product element and the wearable element.

[0038] The product area does not exceed the display area, which means that the display area can fully accommodate the product elements. At this time, the product elements are added to the display area of ​​the wearable elements to form new customized wearable elements that meet the user's situation. In this way, customized wearable elements can be selected according to the user's needs to reduce the similarity of digital people, thereby improving user recognition.

[0039] Reference Figure 2 , a method for generating digital human elements, further comprising: Step 105: When the product area does not exceed the display area, determine the product model according to the product image.

[0040] The product model refers to a number set artificially to distinguish products. The product model can be identified from the product image using image recognition technology. The method for identifying the product model is common knowledge among people in this field and will not be elaborated here.

[0041] Step 106: Determine product sales volume based on the product model.

[0042] Product sales volume refers to the unit sales volume of the product. Product sales volume can be extracted from the main sales platform of the user's products. The method for determining product sales volume is selected by the staff based on actual conditions and will not be elaborated here.

[0043] Step 107: Determine the area occupancy ratio according to the product area and the display area.

[0044] The occupancy ratio refers to the quotient of the area of ​​the product area and the area of ​​the display area. The occupancy ratio is used to show the spatial utilization rate of the display area by product elements. The method for determining the occupancy ratio is selected by the staff based on actual conditions and will not be elaborated here.

[0045] Step 108: Determine the priority coefficient of the product according to the product sales volume and occupancy ratio.

[0046] The priority coefficient refers to a value used to reflect the necessity of displaying products. The higher the product sales volume and the greater the occupancy ratio, the larger the limited coefficient, and the more necessary it is to display the product elements. The setting method of the priority coefficient is selected by the staff based on actual conditions and will not be elaborated here.

[0047] Step 109: Select product elements according to the priority coefficients, and generate digital human elements according to the product elements and wearable elements.

[0048] Prioritize combining the user's main products or product elements with high display area utilization with standard wearable elements, so that the digital human can prioritize displaying the user's main products, thereby improving the user's recognition.

[0049] Reference Figure 3 , a method for generating digital human elements, further comprising: Step 110: Determine the display position according to the display area.

[0050] The display position refers to the coordinates of the center point of the display area. The display position can be extracted from the display area. The method of extracting the display position is common knowledge among those skilled in the art and will not be described in detail here.

[0051] Step 111: Determine the wearing coefficient of the wearable according to the display position and the wearing elements.

[0052] The wearing coefficient refers to a numerical value used to reflect the degree of prominence of the display position on the digital human. The more obvious the wearable element is on the digital human and the closer the display position is to the center of the wearable element, the larger the wearing coefficient is and the more obvious the display position is on the digital human. The setting method of the wearing coefficient is selected by the staff based on actual conditions and will not be elaborated here.

[0053] Step 112: Determine the display area according to the display region.

[0054] The display area refers to the area value of the display region. The display area can be extracted from the display area. The method of extracting the display area is common knowledge among those skilled in the art and will not be elaborated here.

[0055] Step 113: Determine the wearable display coefficient according to the display area and the wear coefficient.

[0056] The display coefficient refers to a numerical value used to reflect the obviousness of the display area on the digital human. The larger the display area, the greater the wear coefficient, and the more obvious the display area is on the wearable elements, and the more obvious the display area is on the digital human. The setting method of the display coefficient is selected by the staff according to the actual situation and will not be elaborated here.

[0057] Step 114: Select wearable elements in sequence according to the display coefficients, and generate digital human elements according to the product elements and the wearable elements.

[0058] Prioritize combining product elements with wearable elements that are prominently located or have larger display areas, so that the wearable elements can better display the user's products, and the digital human can better display the user's products, thereby improving the differentiation of the digital human and thus the user's recognition.

[0059] Reference Figure 4 , product element correction methods include: Step 200: When the product area exceeds the display area, the excess area is determined based on the product area and the display area.

[0060] The product area exceeds the display area, which means that the display area cannot fully accommodate the product elements. The excess area refers to the area value of the part of the product area that exceeds the display area. The method for determining the excess area is common knowledge among people in this field and will not be elaborated here.

[0061] Step 201: Calculate the quotient of the excess area and the display area, and define it as the excess ratio.

[0062] The excess ratio refers to the comparative relationship between the excess area and the display area. The excess ratio is used to reflect the extent to which the product area exceeds the display area.

[0063] Step 202: Determine a correction factor based on product sales and excess ratio.

[0064] The correction coefficient refers to a numerical value used to reflect the necessity and necessity of adjusting product elements. The higher the product sales volume, the higher the necessity of adjusting the product elements. The lower the excess ratio, the higher the feasibility of adjusting the product elements and the lower the correction coefficient. The method of setting the correction coefficient is selected by the staff based on actual conditions and will not be elaborated here.

[0065] Step 203: When the correction coefficient is lower than a preset correction threshold, a reduction coefficient is determined according to the product area and the display area.

[0066] The correction threshold refers to the maximum value of the correction coefficient that needs to be adjusted for the product element. The correction threshold is selected by the staff according to the actual situation and will not be described in detail here. If the correction coefficient is lower than the correction threshold, it means that the product element needs to be adjusted at this time. The reduction coefficient refers to the minimum ratio of reducing the product element so that the display area can fully accommodate the product element. The method for determining the reduction coefficient is common knowledge among people in this field and will not be described in detail here.

[0067] Step 204: Determine the reduction factor according to the reduction coefficient and the product factor.

[0068] The reduced elements are three-dimensional data obtained after reducing the product elements according to the reduction coefficient. The method for determining the reduced elements is common knowledge among those skilled in the art and will not be elaborated here.

[0069] Step 205: Generate digital human elements according to the reduction elements and the wearing elements.

[0070] When the display area cannot accommodate product elements, the feasibility and necessity of trimming the product elements are evaluated based on the product sales volume and the area exceeding the display area, and when trimming of the product elements is necessary, the product elements are reduced so that the display area can accommodate the product elements.

[0071] Reference Figure 5 , the product element correction method also includes: Step 206: When the correction coefficient is lower than a preset correction threshold, the remaining proportion is determined according to the product area and the display area.

[0072] The remaining proportion refers to the proportion of the product elements that do not exceed the display area occupied by the display area. The method for determining the remaining proportion is common knowledge among people in this field and will not be elaborated here.

[0073] Step 207: When the remaining proportion is not less than the excess proportion, the element corner is determined according to the product area and the display area.

[0074] If the remaining proportion is not less than the exceeding proportion, it means that there is sufficient space for product elements to occupy in the display area. The element rotation angle refers to the angle value that needs to be rotated to achieve the highest space utilization rate of product elements in the display area. The utilization rate of product elements to the display area at different angles can be calculated respectively, and then the angle value with the highest utilization rate can be selected as the element rotation angle.

[0075] Step 208: Determine the rotation element according to the element rotation angle and the product element.

[0076] The rotation element is the three-dimensional data obtained by rotating the product element according to the element angle. The method for determining the rotation element is common knowledge among people in this field and will not be elaborated here.

[0077] Step 209: Determine the rotation area according to the rotation elements.

[0078] The rotation area is the range of the rotation element mapped on the plane. The rotation area can be extracted from the rotation element. The method of extracting the rotation area is common knowledge to those skilled in the art and will not be elaborated here.

[0079] Step 210: Determine the reduction coefficient according to the rotation area and the display area.

[0080] When the appearance of the product is significantly different from that of the display area, it is easy to cause a large amount of empty space when the display area accommodates the product elements. At this time, the product elements are rotated to find the angle with the highest space utilization rate, and then the product elements are reduced to reduce the reduction coefficient of the product, thereby improving the clarity of the product displayed through the wearable elements.

[0081] Reference Figure 6 , the product image correction method includes: Step 300: Determine the reduced area according to the reduction coefficient and the rotation area.

[0082] The reduced area refers to the area value of the range of the rotating element mapped on the plane after the rotating element is reduced according to the reduction coefficient. The calculation method of the reduced area is common knowledge among people in this field and will not be elaborated here.

[0083] Step 301: Determine a display threshold of a product according to the product model.

[0084] The display threshold refers to the minimum area value required to clearly display the product. The display threshold can be obtained from the display threshold corresponding table. The display threshold corresponding table refers to a data table that records the model of each product and its corresponding display threshold in advance.

[0085] Step 302: When the reduced area is lower than the display threshold, the horizontal proportion and the vertical proportion are determined according to the product area and the display area.

[0086] The reduced area below the display threshold means that the product elements at this time cannot clearly display the product. The horizontal proportion refers to the ratio of the horizontal length of the product area to the horizontal length of the display area. The vertical proportion refers to the ratio of the vertical length of the product area to the vertical length of the display area. The calculation method of the horizontal proportion and the vertical proportion is selected by the staff according to the actual situation and will not be elaborated here.

[0087] Step 303: Determine the horizontal rotation angle according to the horizontal ratio.

[0088] The horizontal rotation angle refers to the angle value for rotating the product horizontally so that the horizontal ratio tends to 1. The horizontal rotation angle can be obtained from the horizontal rotation angle table. The horizontal rotation angle table records the length ratio relationship of products at different horizontal angles, where the horizontal rotation angle table sets the length value of the product in the horizontal direction of the product in the product image to a unit length of 1.

[0089] Step 304: Determine the longitudinal rotation angle according to the longitudinal ratio.

[0090] The longitudinal rotation angle refers to the angle value for rotating the product longitudinally so that the longitudinal ratio tends to 1. The longitudinal rotation angle can be obtained from the longitudinal rotation angle table. The longitudinal rotation angle table refers to a table that records the length ratio relationship of products at different longitudinal angles. The longitudinal rotation angle table sets the length value of the longitudinal placement direction of the product in the product image to a unit length of 1.

[0091] Step 305: Rotate the preset product according to the horizontal rotation angle and the vertical rotation angle, and reacquire the product image of the product.

[0092] When the reduction coefficient of product elements is too large, it is easy to cause the product elements to be too small, which in turn causes the product elements to fail to fully display the details of the product. By adjusting the product placement angle to adjust the viewing angle when acquiring the product image, the product area size and horizontal and vertical proportions in the product image can be adjusted, and then the area size and horizontal and vertical proportions of the product elements can be adjusted, thereby reducing the reduction coefficient and enlarging the product elements.

[0093] Reference Figure 7 , the product image correction method also includes: Step 306: When the reduced area is lower than the display threshold, determine the product category according to the product image.

[0094] Product category refers to the official name of the product. The product category can be identified from the product image through image recognition technology. The method for determining the product category is common knowledge among people in this field and will not be elaborated here.

[0095] Step 307: Determine a reference image of the product according to the product category.

[0096] The benchmark image refers to a picture of a product of that product category on the market. The benchmark image can be obtained by querying competitors on the main sales platform of the user's product, or it can be manually input by the user. The method for determining the benchmark image is selected by the staff based on actual conditions and will not be elaborated here.

[0097] Step 308: Determine product features of the product based on the reference image and the product image.

[0098] Product features refer to the differences between the reference image and the product image. Image recognition technology can be used to select the differences between the reference image and the product image, and then the selection can be manually confirmed for the second time. Product features can also be directly determined through image recognition technology. The method for determining product features is selected by the staff based on actual conditions and will not be elaborated here.

[0099] Step 309: Determine the characteristic area based on the product characteristics.

[0100] The characteristic area refers to the range of product characteristics. The characteristic area can be obtained through image recognition technology. The method for determining the characteristic area is common knowledge among people in this field and will not be elaborated here.

[0101] Step 310: Determine the zoom ratio according to the feature area and the display area.

[0102] The zoom ratio refers to the zoom ratio by which the product image is zoomed so that the feature area is just included in the display area. The method for determining the zoom ratio is common knowledge among those skilled in the art and will not be elaborated here.

[0103] Step 311: Obtain a feature image of the feature area according to the zoom ratio, and use the feature image as the product image.

[0104] Compare the images of the user's product and regular products to find out the differences between the user's product, and then capture the differences as product elements, thereby improving the differences in product elements and improving user recognition.

[0105] Reference Figure 8 , feature stitching methods include: Step 400: When the product area does not exceed the display area, determine the remaining area according to the product area and the display area.

[0106] The remaining area refers to the area remaining after the display area accommodates the product elements. The method for determining the remaining area is common knowledge among those skilled in the art and will not be elaborated here.

[0107] Step 401: Determine a supplementary area according to the product area and the remaining area.

[0108] The supplementary area refers to a product area that can be completely accommodated in the remaining area. The method for determining the product area is common knowledge among those skilled in the art and will not be elaborated here.

[0109] Step 402: Determine supplementary elements according to the supplementary area.

[0110] The supplementary elements refer to the three-dimensional data of the product corresponding to the supplementary area. The method for determining the supplementary elements is common knowledge to those skilled in the art and will not be elaborated here.

[0111] Step 403: Generate digital human elements according to supplementary elements, product elements and wearable elements.

[0112] When product elements and wearable elements are combined, the empty part in the display area is found, so as to find product elements that can be accommodated in the empty part, and then as many products as possible can be displayed in the same display area to improve the utilization rate of the display area.

[0113] Based on the same inventive concept, an embodiment of the present invention provides a digital human element generation system, including: An acquisition module, used to acquire product images, wearing elements and feature pictures; A memory for storing a program of any one of the above-mentioned methods for generating digital human elements; The program in the memory can be loaded and executed by the processor.

[0114] Based on the same inventive concept, an embodiment of the present invention provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any of the above-mentioned digital human element generation methods.

[0115] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0116] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for generating digital human elements, characterized in that: include: Get product images of user products; Extract product elements based on product images; Determine the product area based on product elements and obtain the wearable elements of the digital human; Determine the display area based on the wearable elements; When the product area does not exceed the display area, determine the product model based on the product image; Determine product sales based on product models; Determine the area occupancy ratio based on product area and display area; Determine the priority coefficient of the product based on the product sales volume and occupancy ratio; Product elements are selected according to the priority coefficients, and digital human elements are generated based on the product elements and wearable elements.

2. A method for generating digital human elements according to claim 1, characterized in that: Also includes: Determine the display location according to the display area; Determine the wearing factor of the wearable according to the display position and wearing elements; Determine the display area according to the display area; Determine the display coefficient of wearable according to the display area and the wear coefficient; Wearable elements are selected in sequence according to the display coefficient, and digital human elements are generated based on product elements and wearable elements.

3. A method for generating digital human elements according to claim 2, characterized in that: Also included is a product element correction method, the product element correction method comprising: When the product area exceeds the display area, the excess area is determined based on the product area and the display area; Calculate the quotient of the excess area and the display area and define it as the excess ratio; Determine the correction factor based on product sales and excess percentage; When the correction factor is lower than the preset correction threshold, the reduction factor is determined based on the product area and the display area; Determine the reduction factor based on the reduction factor and product factors; Generate digital human elements based on reduced elements and wearable elements.

4. A method for generating digital human elements according to claim 3, characterized in that: The product element correction method further includes: When the correction factor is lower than the preset correction threshold, the remaining proportion is determined based on the product area and display area; When the remaining proportion is not less than the excess proportion, the element corner is determined based on the product area and the display area; Determine the rotation factor based on the factor rotation angle and product factor; Determine the rotation area according to the rotation elements; The reduction factor is determined based on the rotation area and the display area.

5. A method for generating digital human elements according to claim 4, characterized in that: Also included is a product image correction method, the product image correction method comprising: Determine the reduction area according to the reduction coefficient and the rotation area; Determine the display threshold of the product based on the product model; When the reduced area is below the display threshold, the horizontal and vertical proportions are determined based on the product area and display area; Determine the horizontal rotation angle according to the horizontal proportion; Determine the longitudinal rotation angle according to the longitudinal proportion; The preset product is rotated according to the horizontal rotation angle and the vertical rotation angle, and the product image of the product is reacquired.

6. A method for generating digital human elements according to claim 5, characterized in that: The product image correction method further comprises: When the reduced area is below the display threshold, the product category is determined based on the product image; Determine the benchmark image of the product according to the product category; determining product features of the product based on the reference image and the product image; Determine characteristic areas based on product characteristics; Determine the zoom ratio based on the feature area and the display area; A feature image of the feature area is obtained according to the zoom ratio, and the feature image is used as the product image.

7. A method for generating digital human elements according to claim 1, characterized in that: Also included is an element splicing method, the element splicing method comprising: When the product area does not exceed the display area, the remaining area is determined based on the product area and the display area; Determine the supplementary area based on the product area and the remaining area; Determine the supplementary elements based on the supplementary area; Generate digital human elements based on supplementary elements, product elements and wearable elements.

8. A digital human element generation system, characterized in that: include: An acquisition module, used to acquire product images, wearing elements and feature pictures; A memory for storing a program of a method for generating digital human elements according to any one of claims 1 to 7; The program in the memory can be loaded and executed by the processor.

9. An intelligent terminal, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a method for generating digital human elements as claimed in any one of claims 1 to 7.

Images