Picture generation method and device

Abstract

The invention discloses a picture generation method and device, and relates to the technical field of artificial intelligence and electronic commerce. A specific embodiment of the method comprises the following steps: in response to a received picture generation request, analyzing picture parameters from the picture generation request; determining at least one alternative picture template from a preset picture template library according to the picture parameters; respectively generating corresponding alternative pictures according to the picture parameters and each alternative picture template, and sending each generated alternative picture to a requester of the picture generation request; and in response to a picture selection instruction sent by the requester, taking a picture selected by the requester from the alternative pictures as a response result of the picture generation request. According to the embodiment, the alternative pictures corresponding to the alternative picture template are automatically generated through the picture parameters, so that the requester can select the required picture from the alternative pictures, and the fast, efficient, flexible and intelligent picture generation method is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence and e-commerce, and in particular to a method and device for generating an image. Background Art

[0002] With the promotion of Internet technology and the development of e-commerce, Internet trading platforms provide consumers with a variety of trading services for goods. In the online trading scenario, the quality of the main display image of the online goods (also called the main image) will greatly affect the click volume and traffic of the goods. The quality of the main image depends not only on the beauty of the goods image but also on the display of key information, such as promotions and feature information of the goods. For this reason, the main image of the goods often needs to be updated according to market feedback to improve the click rate and traffic of the goods. At present, the main image is mainly generated by merchants based on the main image template, and then submitted to the online trading platform for review and storage.

[0003] In the process of implementing the present invention, the inventors found that the prior art has the following problems:

[0004] The existing method of generating main pictures requires merchants to draw main pictures for each item being traded, which consumes a lot of manpower and material resources. Especially during promotional activities, it is necessary to update the main pictures of a large number of items. The existing method is difficult to ensure the timeliness of drawing and cannot meet the needs of use well. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a method and device for generating an image, which determines at least one candidate image template according to the image parameters parsed from the image generation request, sends the candidate images generated according to the image parameters to the requester, and uses the image selected by the requester as the response result of the generation request. The embodiment of the present invention automatically generates candidate images corresponding to the candidate image templates according to the image parameters, so that the requester can select the required images from the candidate images, thereby realizing a fast, efficient, flexible and intelligent image generation method.

[0006] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for generating an image is provided, comprising:

[0007] In response to receiving the image generation request, parsing the image parameters from the image generation request;

[0008] Determining at least one candidate image template from a preset image template library according to the image parameters;

[0009] Generate corresponding candidate images according to the image parameters and each candidate image template, and send each generated candidate image to the requester of the image generation request;

[0010] In response to the picture selection instruction issued by the requesting party, the picture selected by the requesting party from the candidate pictures is used as a response result of the picture generation request.

[0011] Optionally, before determining at least one alternative image template from a preset image template library, the method includes: obtaining each image template, performing regional element parsing on each image template to obtain image elements; naming the image elements according to a preset naming convention; filling a preset background image into the background elements of the image elements to obtain a preset image template library.

[0012] Optionally, the picture parameters include an object image; the picture template in the picture template library has composition attributes and tone attributes; based on the picture parameters, at least one alternative picture template is determined from a preset picture template library, including: matching the composition features and tone features of the object image with the composition attributes and tone attributes of the picture template; and determining at least one alternative picture template based on the matching result.

[0013] Optionally, the image parameters include an object image; the parameter name of the object image complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include image elements; and corresponding alternative images are generated according to the image parameters and each of the alternative image templates, including: for each of the alternative image templates: obtaining image elements and their position information that match the parameter name of the object image from the dictionary format file, adjusting the object image according to the image elements, and filling the adjusted object image into the alternative image template according to the position information to obtain the corresponding alternative image.

[0014] Optionally, the object image is adjusted according to the image element, including: extracting the mask area of ​​the image element and the object image respectively to obtain the element border of the image element and the item border of the object image; scaling and aligning the item border according to the element border so that the processed item border is consistent with at least one of the length and width of the element border; scaling and aligning the object image in accordance with the scaling and alignment processing method.

[0015] Optionally, the method further includes: when the size of the processed object border is smaller than the size of the element border, filling the object border with blanks so that the filled object border is consistent with the size of the element border; or, scaling and aligning the image border of the object image, and when the size of the processed image border exceeds the size of the element border, cropping the image border so that the size of the cropped image border is consistent with the size of the element border.

[0016] Optionally, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; corresponding alternative images are generated according to the image parameters and each of the alternative image templates, including: for each of the alternative image templates: obtaining each text element that matches the parameter name of the text information from the dictionary format file, obtaining the position information and font size information of the text element, adjusting the text information according to the font size information, and filling the adjusted text information into the alternative image template according to the position information to obtain the corresponding alternative image.

[0017] Optionally, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; the text elements have typesetting attributes; corresponding alternative images are generated according to the image parameters and each of the alternative image templates, including: for each of the alternative image templates: obtaining each text element that matches the parameter name of the text information from the dictionary format file, and obtaining the location information of the text element; matching the text information with the text style template in a preset text style template library, determining the target text style template corresponding to the text information according to the matching result, typeset the text information according to the target text style template, and filling the typeset text information into the alternative image template according to the location information to obtain the corresponding alternative image.

[0018] According to a second aspect of an embodiment of the present invention, there is provided a device for generating a picture, including:

[0019] A picture parameter acquisition module, configured to parse the picture parameters from the picture generation request in response to receiving the picture generation request;

[0020] A candidate template screening module, used to determine at least one candidate image template from a preset image template library according to the image parameters;

[0021] A candidate image generation module, used to generate corresponding candidate images according to the image parameters and each candidate image template, and send each generated candidate image to the requester of the image generation request;

[0022] The target image generation module is used to respond to the image selection instruction issued by the requesting party and use the image selected by the requesting party from the candidate images as a response result of the image generation request.

[0023] Optionally, the device also includes a picture template library construction module, which is used to: before determining at least one alternative picture template from a preset picture template library, obtain each picture template, perform regional element analysis on each picture template, and obtain a picture element; name the picture element according to a preset naming convention; fill the preset background picture into the background element of the picture element to obtain a preset picture template library.

[0024] Optionally, the image parameters include an object image; the image template in the image template library has composition attributes and tone attributes; the alternative template screening module is also used to: match the composition features and tone features of the object image with the composition attributes and tone attributes of the image template; and determine at least one alternative image template based on the matching result.

[0025] Optionally, the image parameters include an object image; the parameter name of the object image complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include image elements; the alternative image generation module is also used to: for each alternative image template: obtain the image elements and their position information that match the parameter name of the object image from the dictionary format file, adjust the object image according to the image elements, and fill the adjusted object image into the alternative image template according to the position information to obtain the corresponding alternative image.

[0026] Optionally, the alternative image generation module is further used to: extract the mask areas of the image element and the object image respectively to obtain the element border of the image element and the item border of the object image; scale and align the item border according to the element border so that the processed item border is consistent with at least one of the length and width of the element border; scale and align the object image in accordance with the scaling and alignment processing method.

[0027] Optionally, the device also includes a border adjustment module, which is used to: when the size of the processed object border is smaller than the size of the element border, fill the object border with blanks so that the filled object border is consistent with the size of the element border; or, scale and align the image border of the object image, and when the size of the processed image border exceeds the size of the element border, crop the image border so that the size of the cropped image border is consistent with the size of the element border.

[0028] Optionally, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; the alternative image generation module is also used to: for each of the alternative image templates: obtain each text element that matches the parameter name of the text information from the dictionary format file, obtain the position information and font size information of the text element, adjust the text information according to the font size information, and fill the adjusted text information in the alternative image template according to the position information to obtain the corresponding alternative image.

[0029] Optionally, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; the text elements have typesetting attributes; the alternative image generation module is also used to: for each of the alternative image templates: obtain from the dictionary format file each text element that matches the parameter name of the text information, and obtain the location information of the text element; match the text information with the text style template in a preset text style template library, determine the target text style template corresponding to the text information based on the matching result, typeset the text information according to the target text style template, and fill the typeset text information in the alternative image template based on the location information to obtain the corresponding alternative image.

[0030] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for generating a picture, including:

[0031] one or more processors;

[0032] a storage device for storing one or more programs,

[0033] When the one or more programs are executed by the one or more processors, the one or more processors implement the method provided in the first aspect of the embodiment of the present invention.

[0034] According to a fourth aspect of an embodiment of the present invention, a computer-readable medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method provided by the first aspect of the embodiment of the present invention is implemented.

[0035] An embodiment of the invention has the following advantages or beneficial effects: by responding to receiving a picture generation request, parsing picture parameters from the picture generation request; determining at least one candidate picture template from a preset picture template library according to the picture parameters; generating corresponding candidate pictures according to the picture parameters and each candidate picture template, and sending the generated candidate pictures to the requester of the picture generation request; in response to a picture selection instruction issued by the requester, using the picture selected by the requester from each candidate picture as the response result of the picture generation request. The technical solution realizes automatic generation of candidate pictures corresponding to the candidate picture template according to the picture parameters, so that the requester can select the required picture from the candidate pictures, thereby quickly, efficiently, flexibly and intelligently generating pictures that meet the needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0037] Figure 1 is a schematic diagram of the main process of the method for generating an image according to an embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of regional element analysis of a picture template according to an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of the principle of generating candidate images based on object images according to an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of the overall process of the image generation method according to an embodiment of the present invention;

[0041] Figure 5 is a schematic diagram of main modules of a device for generating a picture according to an embodiment of the present invention;

[0042] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0043] Figure 7 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0045] At present, the method for generating the main picture of items on the Internet trading platform requires merchants to draw the main picture of each transaction item, which consumes a lot of manpower and material resources. Especially during promotional activities, it is necessary to update the main pictures of a large number of items. The existing method is difficult to ensure the timeliness of drawing and cannot meet the needs of use well.

[0046] In order to solve the above problems existing in the prior art, the present invention proposes a method for generating an image, which determines at least one candidate image template according to the image parameters parsed from the image generation request, generates a candidate image corresponding to the candidate image template according to the image parameters and sends it to the requester, and uses the image selected by the requester as the response result of the generation request. The embodiment of the present invention automatically generates a candidate image corresponding to the candidate image template according to the image parameters, so that the requester can select the required image from the candidate images, thereby realizing a fast, efficient, flexible and intelligent image generation method.

[0047] In the introduction to the embodiments of the present invention, the terms and their meanings are as follows:

[0048] Mask: refers to the outside of the selection box. Mask protects the selected area from operation.

[0049] Grouping: In drawing software tools, multiple image layers / text layers are merged together to form a unit. This operation is called grouping.

[0050] psd: is a graphic file format;

[0051] JSON: is a lightweight data exchange format.

[0052] Figure 1 is a schematic diagram of the main process of the method for generating an image according to an embodiment of the present invention, such as Figure 1 As shown, the method for generating a picture according to the embodiment of the present invention includes the following steps S101 to S104.

[0053] Step S101: In response to receiving a picture generation request, parse picture parameters from the picture generation request.

[0054] Specifically, when merchants on the Internet trading platform need to generate or update the main image of an item, they can send a picture generation request to the system through an agreed instruction, which includes the relevant parameters of the item to be generated. They can also determine the relevant parameters of the item to be generated through a visual interactive interface by selection, input, etc., and send a picture generation request to the system. After receiving the picture generation request, the system parses the picture parameters of the item to be generated according to the agreed parsing rules.

[0055] Step S102: Determine at least one candidate picture template from a preset picture template library according to the picture parameters.

[0056] According to one embodiment of the present invention, before determining at least one alternative image template from a preset image template library, the method includes: obtaining each image template, performing regional element parsing on each image template to obtain image elements; naming the image elements according to a preset naming convention; filling a preset background image into the background elements of the image elements to obtain a preset image template library.

[0057] Specifically, before determining the alternative image templates from the preset image template library, it is necessary to build a standardized image template library that is convenient for the subsequent automatic generation of alternative images. Obtain various image templates commonly used on the current Internet trading platform, and perform the following processing on each image template: retain the visible layers in the image template, cancel the grouping in the original image template, so that each image layer / text layer can be processed separately, cancel the font effect, and retain the color. Then parse the processed image template according to the content for regional elements to obtain the image elements of each image template. These image elements constitute a complete image template. According to the preset naming specifications, the names of the image elements are standardized to facilitate name search when generating alternative images later. Considering that the image template needs to have a certain stability, other image elements are offset, position determined, and filled on the background element, which is the basic image layer. Therefore, it is necessary to fill the preset background image into the background element of the image element to provide a benchmark for other image elements. For example, the resolution of the background element can be defined as 800×800, that is, an image with a length and width of 800 pixels. Then, after the preset background image is filled in the background element, other image elements are only allowed to be in this area, and the excess part will be discarded. In addition, a picture template is filled with different background images to derive a variety of scene picture templates to adapt to different business scenarios, such as mid-year promotion business scenarios, holiday promotion business scenarios, etc. Of course, the visits and click-through rates of pictures generated by different picture templates of the same category of items can also be tested and analyzed, and picture templates suitable for different business scenarios of the category can be precipitated to maximize the business value of the picture template. In order to provide better image generation services, these image templates are uploaded to the system for review. After the review is passed, the image module library can be managed based on business scenarios, or based on categories. The image template library can also be managed based on aspect ratios, layouts, styles, or tones. These multi-dimensional image template libraries facilitate the flexible generation of images of items for various needs.

[0058] Figure 2: It is a schematic diagram of regional element analysis of a picture template of an embodiment of the present invention. According to the layout of each copy and picture in the picture template, the regional analysis result can be obtained, that is, the picture elements of the picture template: brand elements, activity name elements, discount keyword elements, characteristic elements of items, activity date elements, image elements, and background elements. Through the regional element analysis, it can be known that under normal circumstances, the picture elements of the picture template are mainly divided into two categories: image elements and copy elements. In addition, for these picture elements, they are standardized and named according to the preset naming specifications. In the embodiment of the present invention, the brand element is defined as logo, the activity name element is huodongming, the discount keyword element is liyidian_1 (if there are multiple discount keyword elements, they can be named liyidian_2, liyidian_3, etc. in sequence), the characteristic element of the item is maidian_1 (if there are multiple characteristic elements of the item, they can be named maidian_2, maidian_3, etc. in sequence), the activity date element is huodongshijian, the image element is tuxiang, and the background element is beijing.

[0059] According to another embodiment of the present invention, the picture parameters include an object image; the picture templates in the picture template library have composition attributes and tone attributes; based on the picture parameters, at least one alternative picture template is determined from a preset picture template library, including: matching the composition features and tone features of the object image with the composition attributes and tone attributes of the picture template; and determining at least one alternative picture template based on the matching result.

[0060] Specifically, in the embodiment of the present invention, the template strategy model is used to calculate the matching degree between the item features and the image template attributes, and the candidate image template is determined according to the matching degree. Some image templates are suitable for horizontal object images, while others are suitable for vertical object images. Figure 2 The image elements in the image are suitable for vertical object images. The composition matching degree between the object image and the image template is determined by combining whether the object image itself is horizontal or vertical. In addition, the image templates retain the colors of each image element. According to the colors of each existing image element, the hue of the image template can be obtained. Then, the hue matching degree between the object image and the image template is determined by combining the hue characteristics of the object image. According to the composition matching degree and the hue matching degree, the matching degree between the object image and the image template is obtained. When the matching degree exceeds the preset matching threshold, the image template is determined as an alternative image template. According to this method, the image template library is traversed to screen the alternative image templates to obtain at least one alternative image template.

[0061] In addition, the embodiment of the present invention also supports merchants to directly select multiple or one candidate image template from the image template library according to their preferences or needs, and to generate subsequent candidate images based on these candidate image templates.

[0062] By determining the above-mentioned alternative image templates, a variety of recommended image templates are provided for the requester of the image generation request. The requester can select an image that best meets the actual needs based on the visual effects of the generated alternative images, or can select the image template by himself to generate the required image, so that the requester can flexibly choose the image generation method and the image generation effect.

[0063] Step S103: Generate corresponding candidate images according to the image parameters and each candidate image template, and send each generated candidate image to the requester of the image generation request.

[0064] According to one embodiment of the present invention, the picture parameters include an object image; the parameter name of the object image complies with the preset naming convention; the alternative picture template is a dictionary format file; the picture elements include image elements; and corresponding alternative pictures are generated according to the picture parameters and each of the alternative picture templates, including: for each of the alternative picture templates: obtaining the image elements and their position information that match the parameter name of the object image from the dictionary format file, adjusting the object image according to the image elements, and filling the adjusted object image into the alternative picture template according to the position information to obtain the corresponding alternative picture.

[0065] Specifically, in order to automatically generate alternative images, the format of the image template needs to be converted from psd format to a JSON dictionary format file. The dictionary format file includes the name of the image element, as well as the position information, style information, color information, scaling information and other related information of the image element in the image template. For the object image in the image parameter, generally speaking, it is a real photo of the object, and the parameter name of the object image must also comply with the above-mentioned preset naming specifications. For example, in the generation of the image template library mentioned above, the image element is defined as tuxiang, then the name of the object image in the image parameter must also be tuxiang. For each alternative image template that has been screened above, according to the parameter name of the object image in the image parameter, the image element consistent with the parameter name of the object image is searched from the JSON dictionary format file of each alternative image template, and the image element and position information are obtained.

[0066] According to another embodiment of the present invention, the object image is adjusted according to the image element, including: extracting the mask area of ​​the image element and the object image respectively to obtain the element border of the image element and the item border of the object image; scaling and aligning the item border according to the element border so that the processed item border is consistent with at least one of the length and width of the element border; scaling and aligning the object image in accordance with the scaling and alignment processing method.

[0067] Specifically, in order to ensure that the generated candidate image and the image element in the image template have the same area in the image template, the object image needs to be adjusted according to the image element. The mask area of ​​the image element and the object image are extracted respectively, and the element border of the image element and the object border of the object image can be obtained according to the mask area of ​​the image element and the mask area of ​​the object image. According to the element frame, the item frame is adjusted, and the aspect ratio of the element frame and the aspect ratio of the item frame are calculated. If the aspect ratio of the element frame is greater than the aspect ratio of the item frame, that is, the item frame is narrower than the element frame, in the embodiment of the present invention, it is agreed that the frame parallel to the X axis of the plane coordinate system is long, and the frame parallel to the Y axis of the plane coordinate system is wide. At this time, the width of the item frame and the element frame are selected to be consistent, and the midpoints of the lower boundaries of the item frame and the element frame are aligned, and the width of the item frame is proportionally scaled according to the width of the element frame; if the aspect ratio of the element frame is less than the aspect ratio of the item frame, that is, the item frame is wider than the element frame, at this time, the length of the item frame and the element frame is selected to be consistent, and the midpoints of the lower boundaries of the item frame and the element frame are aligned, and the width of the item frame is proportionally scaled according to the width of the element frame. Of course, if the aspect ratio of the element frame is equal to the aspect ratio of the item frame, it is proportional scaling at this time, and the midpoints of the lower boundaries of the item frame and the element frame are aligned, and the width or length of the item frame is proportionally scaled according to the width or length of the element frame to obtain an item frame consistent with the length and width of the element frame. According to the above-mentioned method for adjusting the object border, the object image is aligned and scaled in the same manner to obtain the transformed object image; according to the position information of the image elements, the transformed object image is filled into the alternative image template to obtain the alternative image for updating the object image.

[0068] According to another embodiment of the present invention, the method further includes: when the size of the processed object border is smaller than the size of the element border, filling the object border with blanks so that the filled object border is consistent with the size of the element border; or, scaling and aligning the image border of the object image, and when the size of the processed image border exceeds the size of the element border, cropping the image border so that the size of the cropped image border is consistent with the size of the element border.

[0069] Specifically, after the alignment and scaling of the object image, the length and / or width of the object border and the element border are guaranteed to be consistent. For the case where the length or width of the object border is consistent with that of the element border, there will be a corresponding case where the width or length of the object border and the element border are inconsistent. If after the alignment and scaling, the size (length or width) of the object border is smaller than the corresponding size (length or width) of the element border, that is, the object border is inside the element border, then it is necessary to fill the area between the element border and the object border according to the size of the element border to ensure that the size of the filled object border is consistent with that of the element border. Further, in the process of obtaining the object border according to the object image, an image border is generally generated. The image border represents the outermost border of the object image, and the object border represents the border of the image content, that is, the image border is outside the object border, and the area between the image border and the object border is a perspective image without content area. As the object border is aligned and scaled, the image border will also be aligned and scaled. If the size of the processed image border exceeds the size of the feature border, of course the object border will definitely not exceed the feature border. The area where the processed image border exceeds the feature border can be cropped to make the cropped image border size consistent with the feature border size.

[0070] Figure 3It is a schematic diagram of the principle of generating alternative pictures based on the object image in an embodiment of the present invention. The system detects the image element ("object 1" in the alternative picture template) and obtains the corresponding image element ("object 1" in the picture); performs mask extraction on the image element ("object 1" in the picture) and the object image ("object 2" in the picture parameter) respectively to obtain the mask area of ​​the image element and the mask area of ​​the object image; locates the position of the image element in the mask area and the position of the object image in the mask area according to the mask area to obtain the element border, the item border of the object image and the image border; aligns the midpoint of the lower border of the item border and the element border, and the aspect ratio of the element border in the picture is greater than or equal to the aspect ratio of the item border. The widths of the item border and the element border are selected to be the same, and the width of the item border is scaled in proportion to the width of the element border to obtain a position relationship diagram of the three types of borders (element border, item border and image border) after scaling; based on the size of the element border, the image border is cropped and the item border is filled to obtain an optimized item border; the above-mentioned method for processing the item border (alignment, scaling, cropping and filling) is applied to the processing of the item image, and the item image is transformed to obtain a transformed adjustment diagram of the item image; and the transformed and adjusted item image is filled into the candidate image template according to the position information to obtain the corresponding candidate image.

[0071] Compared with the traditional deep learning model to determine the location of image elements, the above-mentioned search and filling method based on JSON dictionary format files can not only obtain location information quickly and lightweight, avoiding the training of the model with a large amount of training data, but also obtain relevant information such as pixel-level high-precision location, ensuring the efficiency of the solution.

[0072] According to one embodiment of the present invention, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; corresponding alternative images are generated according to the image parameters and each of the alternative image templates, including: for each of the alternative image templates: obtaining each text element that matches the parameter name of the text information from the dictionary format file, obtaining the position information and font size information of the text element, adjusting the text information according to the font size information, and filling the adjusted text information into the alternative image template according to the position information to obtain the corresponding alternative image.

[0073] Specifically, in addition to the item image, the image parameters also include text information, that is, the brand information, event name information, discount keyword information, item feature information, and event date information mentioned above. The brand information can be either a brand image or store information. If it is a brand image, it can be filled in the image template according to the above-mentioned object image processing method. Similarly, in order to automatically generate alternative images based on alternative image templates, the parameter names of the text information in the image parameters must also comply with the above-mentioned preset naming specifications. According to different business scenarios, the types and numbers of text elements may be different. In the embodiment of the present invention, the corresponding text element can be found from the JSON dictionary format file based on the only one type of text information in the text information, and the corresponding position information and font size information can be obtained to adjust and fill in the text information. It is also possible to find the corresponding multiple text elements from the JSON dictionary format file based on the parameter names of multiple types of text information in the text information, and establish a correspondence with the text elements in the alternative image template according to the parameter names of the text information, as well as a correspondence between the position information and the font size information, so as to find the position information and font size information of the corresponding text element according to the type of text information, adjust the font size, and adaptively align in a way that the horizontal and vertical directions are simultaneously centered, and then fill the adjusted text information into the alternative image template according to the corresponding position information. For example, the above Figure 2 The input copy information includes brand information (parameter name is logo), activity name information (parameter name is huodongming), discount keyword information (parameter name is liyidian_1), item feature information (parameter name is maidian_1) and activity date information (parameter name is huodongshijian). According to the parameter name of the copy information in the image parameter, the copy elements that are consistent with the parameter names of the copy information are searched from the JSON dictionary format file of the alternative image template, and the position information and font size information of each copy element are obtained. According to the font size information corresponding to each copy information, the font size of the copy information is adjusted, and adaptively aligned in the horizontal and vertical directions at the same time. Then, according to the position information of each copy information, the adjusted copy information is filled in the alternative image template to obtain the corresponding alternative image.

[0074] According to another embodiment of the present invention, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; the text elements have typesetting attributes; corresponding alternative images are generated according to the image parameters and each of the alternative image templates, including: for each of the alternative image templates: obtaining each text element that matches the parameter name of the text information from the dictionary format file, and obtaining the position information of the text element; matching the text information with the text style template in a preset text style template library, determining the target text style template corresponding to the text information according to the matching result, typeset the text information according to the target text style template, and filling the typeset text information into the alternative image template according to the position information to obtain the corresponding alternative image.

[0075] Specifically, the candidate image template usually includes a variety of copywriting elements. Among the various copywriting elements, individual copywriting elements that have a greater impact on the number of clicks and views of the item can be adaptively optimized and adjusted to achieve the purpose of increasing the number of clicks and views of the item. For example, the preferential keyword elements and the characteristic elements of the item in the above-mentioned copywriting elements directly and accurately express the price and quality of the item, which are the two aspects that consumers of the Internet trading platform pay the most attention to. For such important copywriting elements, typesetting attributes can be set to support the optimization of copywriting elements with typesetting attributes during the image generation process. Through the JSON dictionary format file, the corresponding position information is obtained according to the copywriting elements with typesetting attributes corresponding to the parameter name of the copywriting information in the image parameters. According to the content and number of words of the copywriting information, the copywriting style template in the preset copywriting style module library is matched, and the copywriting style template with the highest matching degree is selected as the target copywriting style template. The copywriting information is typeset according to the target copywriting style template, and the typesetting copywriting information is filled in the candidate image template according to the position information of the copywriting elements corresponding to the copywriting information.

[0076] Exemplarily, for the above-mentioned preferential keyword elements (whose copy content is similar to "cross-store consumption of XXX minus YY"), the copy style template usually needs to add a line break at the specified position, and the font size between the two lines is scaled proportionally. Since the preferential keyword information in the copy information corresponding to the preferential keyword element usually varies greatly according to the business scenario and price, the font size setting for this type of copy information is based on: horizontal and center alignment, adaptively filling the entire preferential keyword element text box as much as possible. For the characteristic elements of the items mentioned above, such copy elements are generally in a relatively high and central position on the page. The characteristic information of the corresponding item in the copy information is matched with the copy style template in the copy style template library for the length of the copy word, and the score range of the recommendation level corresponding to different copy style templates (the recommendation level determined by historical clicks, views and other parameters) and other effect factors are comprehensively considered, and the copy style template with the highest score is used as the target copy style template, and the characteristic information of the item is typeset according to the target copy style template.

[0077] Through the layout and filling processing of the above-mentioned copy information, the important copy information of the item can be flexibly layout and adaptively adjusted, so as to maximize the clicks and views after the item picture is online.

[0078] Step S104: In response to the picture selection instruction issued by the requesting party, the picture selected by the requesting party from the candidate pictures is used as a response result of the picture generation request.

[0079] Specifically, after receiving the various alternative images corresponding to the various alternative image templates, the requester of the image generation request selects an image from the multiple alternative images as the target image based on personal preference or business needs, and sends the target image to the system through an image selection instruction. The system uses the target image selected by the requester as the response result of this image generation request.

[0080] Figure 4: This is a schematic diagram of the overall process of the image generation method of an embodiment of the present invention. The image template is parsed and named in a standardized manner to produce a standardized image template; each standardized image template is converted into a JSON dictionary format file and uploaded to the system. After the system passes the review, the image template library is managed according to the business scenario dimension to build the image template library. In this process, the image parameters are divided into two categories: item image and text information. The requester of the image generation request first uploads the item identification of the image to be generated to the system. The system obtains the item image through the item identification, and can also directly upload the item image. If there is a brand image of the item, it can also be uploaded in this step. The system determines at least one candidate image template from the image template library based on the composition characteristics and color characteristics of the item image, or the composition characteristics and color characteristics of the item image and the brand image. Then, according to the image parameters (item image and text information) of the item to be generated, combined with the candidate image template, the candidate image is automatically generated through the search and fill operation of the JSON dictionary format file. Finally, the requester of the image generation request selects a picture from the candidate images as the main picture of the item. In addition, this method is also applicable to the generation of main images of batch items. The image parameters of each item for which the main image is to be generated are uploaded to the system through multi-threaded concurrency. The system determines the corresponding alternative image template based on the item image of each item, and then combines the text information of each item to automatically generate alternative images through multi-threading. Finally, the requesting party selects the corresponding main image for each item from the alternative images to complete the generation of batch images.

[0081] The embodiment of the present invention provides a fast, efficient, flexible and lightweight image generation method, which is based on establishing a standard and standardized JSON dictionary format image template library, according to the input image parameters named in accordance with the standard specifications, combined with the alternative image templates, through the mapping, searching and filling of the JSON dictionary format file, to achieve fast, accurate and intelligent automatic generation of object images.

[0082] Figure 5 Schematic diagram of the main modules of the apparatus for generating pictures according to an embodiment of the present invention. Figure 5 As shown, the image generation device 500 mainly includes an image parameter acquisition module 501 , a candidate template screening module 502 , a candidate image generation module 503 and a target image generation module 504 .

[0083] The picture parameter acquisition module 501 is used for parsing the picture parameters from the picture generation request in response to receiving the picture generation request;

[0084] A candidate template screening module 502, configured to determine at least one candidate picture template from a preset picture template library according to the picture parameters;

[0085] The candidate image generation module 503 is used to generate corresponding candidate images according to the image parameters and each candidate image template, and send each generated candidate image to the requester of the image generation request;

[0086] The target image generation module 504 is configured to respond to the image selection instruction issued by the requesting party and use the image selected by the requesting party from the candidate images as a response result of the image generation request.

[0087] According to one embodiment of the present invention, the image generation device 500 also includes a picture template library construction module (not shown in the figure), which is used to: before determining at least one alternative picture template from a preset picture template library, obtain each picture template, perform regional element analysis on each picture template to obtain a picture element; name the picture element according to a preset naming convention; fill the preset background picture into the background element of the picture element to obtain a preset picture template library.

[0088] According to another embodiment of the present invention, the image parameters include an object image; the image templates in the image template library have composition attributes and tone attributes; the alternative template screening module 502 is also used to: match the composition features and tone features of the object image with the composition attributes and tone attributes of the image template; and determine at least one alternative image template based on the matching result.

[0089] According to another embodiment of the present invention, the picture parameters include an object image; the parameter name of the object image complies with the preset naming convention; the alternative picture template is a dictionary format file; the picture elements include image elements; the alternative picture generation module 503 is further used to: for each of the alternative picture templates: obtain the image elements and their position information that match the parameter name of the object image from the dictionary format file, adjust the object image according to the image elements, and fill the adjusted object image into the alternative picture template according to the position information to obtain the corresponding alternative picture.

[0090] According to another embodiment of the present invention, the alternative image generation module 503 is further used to: respectively extract the mask areas of the image element and the object image to obtain the element border of the image element and the item border of the object image; scale and align the item border according to the element border so that the processed item border is consistent with at least one of the length and width of the element border; scale and align the object image in accordance with the scaling and alignment processing method.

[0091] According to another embodiment of the present invention, the image generating device 500 further includes a border adjustment module (not shown in the figure), which is used to: fill the object border with blanks when the size of the processed object border is smaller than the size of the element border, so that the filled object border is consistent with the size of the element border; or scale and align the image border of the object image, and when the size of the processed image border exceeds the size of the element border, crop the image border to make the size of the cropped image border consistent with the size of the element border.

[0092] According to another embodiment of the present invention, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; the alternative image generation module 503 is also used to: for each of the alternative image templates: obtain each text element that matches the parameter name of the text information from the dictionary format file, obtain the position information and font size information of the text element, adjust the text information according to the font size information, fill the adjusted text information in the alternative image template according to the position information, and obtain the corresponding alternative image.

[0093] According to another embodiment of the present invention, the image parameters include text information; the parameter name of the text information complies with the preset naming convention; the alternative image template is a dictionary format file; the image elements include text elements; the text elements have typesetting attributes; the alternative image generation module 503 is also used to: for each of the alternative image templates: obtain each text element that matches the parameter name of the text information from the dictionary format file, and obtain the position information of the text element; match the text information with the text style template in a preset text style template library, determine the target text style template corresponding to the text information according to the matching result, typeset the text information according to the target text style template, and fill the typeset text information in the alternative image template according to the position information to obtain the corresponding alternative image.

[0094] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention can be applied.

[0095] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0096] Users can use terminal devices 601, 602, 603 to interact with server 605 through network 604 to receive or send messages, etc. Various communication client applications, such as picture generation applications, etc., can be installed on terminal devices 601, 602, 603 (only as an example).

[0097] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0098] The server 605 may be a server that provides various services, such as a background management server that provides support for the image generation performed by the user using the terminal devices 601, 602, and 603 (for example only). The background management server may parse the image parameters from the image generation request in response to receiving the image generation request; determine at least one candidate image template from a preset image template library according to the image parameters; generate corresponding candidate images according to the image parameters and each candidate image template, and send the generated candidate images to the requester of the image generation request; in response to the image selection instruction issued by the requester, process the image selected by the requester from the candidate images as the response result of the image generation request, and feed back the processing result (such as the selected image, etc. - for example only) to the terminal device.

[0099] It should be noted that the method for generating an image provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for generating an image is generally arranged in the server 605 .

[0100] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0101] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device or a server suitable for implementing an embodiment of the present invention. Figure 7 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0102] like Figure 7As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0103] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0104] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0105] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination thereof.

[0106] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The units involved in the embodiments of the present invention may be implemented by software or hardware. The units described may also be arranged in a processor, for example, may be described as follows: a processor includes: an image parameter acquisition module, an alternative template screening module, an alternative image generation module, and a target image generation module.

[0108] Among them, the names of these modules do not constitute a limitation on the modules themselves in some cases. For example, the image parameter acquisition module can also be described as "a module for parsing image parameters from an image generation request in response to receiving an image generation request."

[0109] On the other hand, the present invention also provides a computer-readable medium, which may be included in the device described in the embodiment; or may exist independently without being assembled into the device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by a device, the device includes: in response to receiving a request for image generation, parsing image parameters from the image generation request; according to the image parameters, determining at least one candidate image template from a preset image template library; generating corresponding candidate images according to the image parameters and each candidate image template, and sending the generated candidate images to the requester of the image generation request; in response to the image selection instruction issued by the requester, using the image selected by the requester from the candidate images as the response result of the image generation request.

[0110] The technical solution according to the embodiment of the present invention has the following advantages or beneficial effects: by responding to receiving a picture generation request, parsing picture parameters from the picture generation request; determining at least one candidate picture template from a preset picture template library according to the picture parameters; generating corresponding candidate pictures according to the picture parameters and each candidate picture template, and sending the generated candidate pictures to the requester of the picture generation request; in response to a picture selection instruction issued by the requester, using the picture selected by the requester from each candidate picture as the technical solution of the response result of the picture generation request, realizing automatic generation of candidate pictures corresponding to the candidate picture template according to the picture parameters, so that the requester can select the required picture from the candidate pictures, thereby quickly, efficiently, flexibly and intelligently generating pictures that meet the needs.

[0111] The specific implementation methods described herein do not constitute limitations on the scope of protection of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A method for generating an image, characterized in that: include: In response to receiving the image generation request, parsing the image parameters from the image generation request; Determining at least one candidate image template from a preset image template library according to the image parameters; Generate corresponding candidate images according to the image parameters and each candidate image template, and send each generated candidate image to the requester of the image generation request; In response to the picture selection instruction issued by the requesting party, the picture selected by the requesting party from the candidate pictures is used as a response result of the picture generation request.

2. The method according to claim 1, characterized in that Before determining at least one candidate picture template from a preset picture template library, the method includes: Obtain each image template, perform regional element analysis on each image template, and obtain image elements; Naming the image elements according to a preset naming convention; Fill the preset background image into the background element of the picture element to obtain a preset picture template library.

3. The method according to claim 1, characterized in that The picture parameters include an object image; the picture templates in the picture template library have composition attributes and tone attributes; Determining at least one candidate image template from a preset image template library according to the image parameters includes: Matching the composition features and the tone features of the object image with the composition attributes and the tone attributes of the picture template; At least one candidate image template is determined according to the matching result.

4. The method according to claim 2, characterized in that: The picture parameters include an item image; the parameter name of the item image complies with the preset naming specification; the candidate picture template is a dictionary format file; The picture element includes an image element; Generating corresponding candidate images according to the image parameters and each candidate image template respectively includes: For each of the alternative picture templates: obtain the image elements and their position information that match the parameter name of the object image from the dictionary format file, adjust the object image according to the image elements, fill the adjusted object image into the alternative picture template according to the position information, and obtain the corresponding alternative picture.

5. The method according to claim 4, characterized in that The step of adjusting the item image according to the image elements includes: Extracting the image elements and the mask areas of the object image respectively to obtain element frames of the image elements and object frames of the object image; According to the element border, scaling and aligning the item border so that the processed item border is consistent with at least one of the length and width of the element border; The object image is scaled and aligned according to the scaling and alignment processing method.

6. The method according to claim 5, characterized in that The method further comprises: When the size of the processed item border is smaller than the size of the element border, the item border is filled with blanks so that the filled item border is consistent with the size of the element border; Alternatively, the image border of the object image is scaled and aligned, and when the size of the processed image border exceeds the size of the element border, the image border is cropped to make the size of the cropped image border consistent with the size of the element border.

7. The method according to claim 2, characterized in that: The picture parameters include text information; the parameter name of the text information complies with the preset naming specification; the candidate picture template is a dictionary format file; The picture elements include text elements; Generating corresponding candidate images according to the image parameters and each candidate image template respectively includes: For each of the alternative image templates: obtain each text element that matches the parameter name of the text information from the dictionary format file, obtain the position information and font size information of the text element, adjust the text information according to the font size information, fill the adjusted text information in the alternative image template according to the position information, and obtain the corresponding alternative image.

8. The method according to claim 2, characterized in that: The picture parameters include text information; the parameter name of the text information complies with the preset naming specification; the candidate picture template is a dictionary format file; The picture elements include text elements; The copywriting elements have typesetting attributes; Generating corresponding candidate images according to the image parameters and each candidate image template respectively includes: For each candidate image template: acquiring each text element that matches the parameter name of the text information from the dictionary format file, and obtaining the position information of the text element; The copy information is matched with the copy style templates in a preset copy style template library, and a target copy style template corresponding to the copy information is determined according to the matching result, and the copy information is typeset according to the target copy style template. According to the position information, the typeset copy information is filled in the alternative picture template to obtain the corresponding alternative picture.

9. A device for generating a picture, characterized in that: include: A picture parameter acquisition module, configured to parse the picture parameters from the picture generation request in response to receiving the picture generation request; A candidate template screening module, used to determine at least one candidate image template from a preset image template library according to the image parameters; A candidate image generation module, used to generate corresponding candidate images according to the image parameters and each candidate image template, and send each generated candidate image to the requester of the image generation request; The target image generation module is used to respond to the image selection instruction issued by the requesting party and use the image selected by the requesting party from the candidate images as a response result of the image generation request.

10. The device according to claim 9, characterized in that The device also includes a picture template library construction module, which is used to: Before determining at least one candidate picture template from a preset picture template library, obtaining each picture template, performing regional element analysis on each picture template to obtain a picture element; and naming the picture element according to a preset naming specification; Fill the preset background image into the background element of the picture element to obtain a preset picture template library.

11. The device according to claim 9, characterized in that The picture parameters include an object image; the picture templates in the picture template library have composition attributes and tone attributes; The candidate template screening module is also used for: Matching the composition features and the tone features of the object image with the composition attributes and the tone attributes of the picture template; At least one candidate image template is determined according to the matching result.

12. The device according to claim 10, characterized in that The picture parameters include an item image; the parameter name of the item image complies with the preset naming specification; the candidate picture template is a dictionary format file; the picture elements include image elements; The candidate image generation module is also used for: For each of the alternative picture templates: obtain the image elements and their position information that match the parameter name of the object image from the dictionary format file, adjust the object image according to the image elements, fill the adjusted object image into the alternative picture template according to the position information, and obtain the corresponding alternative picture.

13. The device according to claim 12, characterized in that The candidate image generation module is also used for: Extracting the image elements and the mask areas of the object image respectively to obtain element frames of the image elements and object frames of the object image; According to the element border, scaling and aligning the item border so that the processed item border is consistent with at least one of the length and width of the element border; The object image is scaled and aligned according to the scaling and alignment processing method.

14. The device according to claim 13, characterized in that The device also includes a frame adjustment module, which is used to: When the size of the processed item border is smaller than the size of the element border, the item border is filled with blanks so that the filled item border is consistent with the size of the element border; Alternatively, the image border of the object image is scaled and aligned, and when the size of the processed image border exceeds the size of the element border, the image border is cropped to make the size of the cropped image border consistent with the size of the element border.

15. The device according to claim 10, characterized in that The picture parameters include text information; the parameter name of the text information complies with the preset naming specification; the candidate picture template is a dictionary format file; the picture elements include text elements; The candidate image generation module is also used for: For each of the alternative image templates: obtain each text element that matches the parameter name of the text information from the dictionary format file, obtain the position information and font size information of the text element, adjust the text information according to the font size information, fill the adjusted text information in the alternative image template according to the position information, and obtain the corresponding alternative image.

16. The method according to claim 10, characterized in that The picture parameters include text information; the parameter name of the text information complies with the preset naming specification; the candidate picture template is a dictionary format file; the picture elements include text elements; the text elements have typesetting attributes; The candidate image generation module is also used for: For each candidate image template: acquiring each text element that matches the parameter name of the text information from the dictionary format file, and obtaining the position information of the text element; The copy information is matched with the copy style templates in a preset copy style template library, and a target copy style template corresponding to the copy information is determined according to the matching result, and the copy information is typeset according to the target copy style template. According to the position information, the typeset copy information is filled in the alternative picture template to obtain the corresponding alternative picture.

17. A mobile electronic device terminal, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

18. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images