Information processing method and device, program product and electronic equipment

Abstract

The invention provides an information processing method and device, a program product and electronic equipment, and relates to the technical field of computers. The method comprises the following steps: determining basic information of a to-be-processed object; determining an initial picture of the to-be-processed object according to the basic information of the to-be-processed object; determining a main picture from the initial pictures; and generating a target picture according to the main body picture and the scene description information of the to-be-processed object. The target picture is automatically generated through the basic information of the to-be-processed object, manual participation is not needed in the whole process, and the efficiency of obtaining the effective propaganda information of the to-be-processed object is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology. More specifically, embodiments of the present disclosure relate to an information processing method, an information processing apparatus, a computer program product, and an electronic device. Background Art

[0002] This section aims to provide background or context for the embodiments of the present disclosure recited in the claims. The description herein is not admitted to be prior art merely by virtue of its inclusion in this section.

[0003] Currently, when individuals, enterprises, or institutions need to promote objects such as commodities, songs, and operas, they need to spend a relatively large amount of human cost to produce promotional materials. For example, when a merchant needs to promote the commodities it sells, it needs to photograph the commodities, obtain corresponding pictures, and perform scene processing on the pictures to obtain corresponding promotional information. Summary of the Invention

[0004] It can be seen that the process of obtaining promotional information in the related art is relatively cumbersome, and the efficiency of obtaining effective promotional information is relatively low.

[0005] In view of this, the present disclosure provides an information processing method, an information processing apparatus, a computer program product, and an electronic device to improve the efficiency of obtaining effective promotional information to a certain extent.

[0006] According to a first aspect of the present disclosure, there is provided an information processing method, the method including:

[0007] Determine the basic information of the object to be processed;

[0008] Determine the initial picture of the object to be processed according to the basic information of the object to be processed;

[0009] Determine the main picture from the initial picture;

[0010] Generate a target picture according to the main picture and the scene description information of the object to be processed.

[0011] In a possible implementation manner, the generating a target picture according to the main picture and the scene description information of the object to be processed includes:

[0012] Combine the main picture with a first background to obtain a basic picture;

[0013] Generate a mask picture for representing the background area in the basic picture;

[0014] Generate the target picture according to the basic picture, the mask picture, and the scene description information of the object to be processed.

[0015] In a possible implementation, determining the subject picture from the initial picture includes:

[0016] Performing subject extraction based on edge detection on the initial picture to obtain the subject picture.

[0017] In a possible implementation, performing subject extraction based on edge detection on the initial picture to obtain the subject picture includes:

[0018] Detecting the boundary color of the initial picture;

[0019] Detecting from the boundary of the initial picture towards the inside according to the boundary color to detect non-edge pixel points, and determining the subject area according to the positions of the non-edge pixel points;

[0020] Determining the subject picture from the initial picture according to the subject area.

[0021] In a possible implementation, the non-edge pixel points are pixel points whose color difference from the boundary color exceeds a first preset value, or pixel points whose color difference from adjacent edge pixel points exceeds a second preset value.

[0022] In a possible implementation, combining the subject picture with a first background to obtain a base picture includes:

[0023] Determining a white-background canvas picture with a first preset size as the first background;

[0024] Performing layer merging processing on the subject picture and the first background to obtain the base picture.

[0025] In a possible implementation, generating a mask picture for representing the background area in the base picture includes:

[0026] Determining a transparent-background canvas picture with a second preset size;

[0027] Performing layer merging processing on the subject picture and the transparent-background canvas picture to obtain a first processed picture;

[0028] Performing bright saturation adjustment processing on the first processed picture to obtain a second processed picture;

[0029] Performing layer merging processing on the second processed picture and the first background to obtain a mask picture.

[0030] In a possible implementation, generating the target picture according to the base picture, the mask picture, and the scene description information of the object to be processed includes:

[0031] Extract potential feature information from the base image;

[0032] Perform downsampling on the mask image to obtain downsampled feature information; and, perform image feature extraction on the mask image to obtain image feature information;

[0033] Generate a target image based on the potential feature information, downsampled feature information, image feature information, and scene description information.

[0034] In a possible implementation, the method further includes:

[0035] Expand the basic information of the object to be processed according to a preset information expansion model to determine the scene description information of the object to be processed.

[0036] In a possible implementation, the method further includes:

[0037] Determine the recommended text information of the object to be processed according to the basic information of the object to be processed;

[0038] Generate target recommendation information according to the recommended text information and the target image.

[0039] In a possible implementation, the method further includes:

[0040] Determine the display channel of the target recommendation information;

[0041] Adjust the target recommendation information according to the display form corresponding to the display channel.

[0042] According to a second aspect of the present disclosure, there is provided an information processing apparatus, the apparatus including:

[0043] A first determination unit for determining the basic information of the object to be processed;

[0044] A second determination unit for determining the initial image of the object to be processed according to the basic information of the object to be processed;

[0045] A processing unit for determining the main image from the initial image;

[0046] A generation unit for generating a target image according to the main image and the scene description information of the object to be processed.

[0047] In a possible implementation, the generation unit is configured to:

[0048] Combine the main image with a first background to obtain a base image;

[0049] Generate a mask image for representing the background area in the base image;

[0050] Generate the target image according to the base image, the mask image, and the scene description information of the object to be processed.

[0051] In a possible implementation manner, the processing unit is configured to:

[0052] Perform body extraction on the initial image based on edge detection to obtain the body image.

[0053] In a possible implementation manner, the processing unit is configured to:

[0054] Detect the boundary color of the initial image;

[0055] Detect from the boundary of the initial image to the inside according to the boundary color to detect non-edge pixel points, and determine the body area according to the positions of the non-edge pixel points;

[0056] Determine the body image from the initial image according to the body area.

[0057] In a possible implementation manner, the non-edge pixel points are pixel points whose color difference from the boundary color exceeds a first preset value, or pixel points whose color difference from adjacent edge pixel points exceeds a second preset value.

[0058] In a possible implementation manner, the generating unit is configured to:

[0059] Determine a white-background canvas image with a first preset size as the first background;

[0060] Perform layer merging processing on the body image and the first background to obtain the base image.

[0061] In a possible implementation manner, the generating unit is configured to:

[0062] Determine a transparent-background canvas image with a second preset size;

[0063] Perform layer merging processing on the body image and the transparent-background canvas image to obtain a first processed image;

[0064] Perform bright saturation adjustment processing on the first processed image to obtain a second processed image;

[0065] Perform layer merging processing on the second processed image and the first background to obtain a mask image.

[0066] In a possible implementation manner, the generating unit is configured to:

[0067] Extract potential feature information from the base image;

[0068] Perform downsampling processing on the mask image to obtain downsampled feature information; and, perform image feature extraction processing on the mask image to obtain image feature information;

[0069] Generate a target image based on the potential feature information, downsampled feature information, image feature information, and scene description information.

[0070] In a possible implementation manner, the apparatus further includes an expansion unit for:

[0071] Expand the basic information of the object to be processed according to a preset information expansion model to determine the scene description information of the object to be processed.

[0072] In a possible implementation manner, the generation unit is further configured to:

[0073] Determine the recommended text information of the object to be processed according to the basic information of the object to be processed;

[0074] Generate target recommendation information according to the recommended text information and the target image.

[0075] In a possible implementation manner, the apparatus further includes an adjustment unit for:

[0076] Determine the display channel of the target recommendation information;

[0077] Adjust the target recommendation information according to the display form corresponding to the display channel.

[0078] According to the third aspect of the present disclosure, there is provided a computer program product including a computer program, which when executed by a processor implements the method of the first aspect and its possible implementation manners.

[0079] According to the fourth aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein, the processor is configured to execute the above-mentioned method of the first aspect and its possible implementation manners by executing the executable instructions.

[0080] The technical solution of the present disclosure has the following beneficial effects:

[0081] In the embodiments of the present disclosure, the basic information of the object to be processed can be determined first, and then the initial image of the object to be processed can be determined according to the basic information of the object to be processed. Next, the main image can be determined from the initial image. Finally, the target image can be generated according to the main image and the scene description information of the object to be processed. It can be seen that the present disclosure can directly automatically expand and obtain the initial image according to the basic information of the object to be processed, then automatically process the initial image, and finally automatically generate the target image. The entire process of generating the target image does not require manual participation, improving the efficiency of obtaining the effective promotional information of the object to be processed and reducing the cost of obtaining the effective promotional information of the object to be processed. Moreover, since the target image is generated in combination with the scene description information of the object to be processed, on the basis of obtaining the effective promotional information, promotional information that is more in line with the actual usage scenario is also obtained, improving the content richness of the target image and avoiding the situation where users need to perform additional optimization and adjustment on the image, thereby improving the user experience.

[0082] Other features and advantages of the present disclosure will be described in the following description, and some of them will become obvious from the description or be understood by implementing the present disclosure. The objectives and other advantages of the present disclosure can be achieved and obtained through the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required to be used in the embodiments of the present disclosure will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0084] Figure 1 Showing a schematic diagram of an application scenario in this exemplary embodiment;

[0085] Figure 2 Showing a schematic flowchart of an information processing method in this exemplary embodiment;

[0086] Figure 3 Showing a schematic diagram of the process of obtaining the main image in this exemplary embodiment;

[0087] Figure 4 Showing a schematic flowchart of the process of generating the target image in this exemplary embodiment;

[0088] Figure 5 Showing a schematic diagram of the process of generating the target image in this exemplary embodiment;

[0089] Figure 6Schematic diagram showing a way to obtain target recommendation information in this exemplary embodiment;

[0090] Figure 7 Schematic structural diagram of an information processing device in this exemplary embodiment;

[0091] Figure 8 Schematic structural diagram of an electronic device in this exemplary embodiment. Detailed implementation manners

[0092] To make the objectives, technical solutions and advantages of the present disclosure clearer and more understandable, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part rather than all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope of protection of the present disclosure. Without conflict, the embodiments in the present disclosure and the features in the embodiments may be combined with each other arbitrarily. And although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0093] The terms "including" and any variations thereof in the specification and claims of the present disclosure are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0094] One or more in the embodiments of the present disclosure, "more than one" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B may be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one (item)" or similar expressions thereof refer to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b or c may represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c may be single or multiple.

[0095] It should be noted that in the description and claims of the present disclosure and the above-mentioned drawings, terms such as "first", "second", etc. are used to distinguish similar objects, and do not necessarily need to describe a specific order, sequence, size, and priority. For example, in the embodiments of the present disclosure, the first object to be processed and the second object to be processed are only used to distinguish different objects to be processed. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0096] The following describes exemplary embodiments of the present disclosure with reference to the drawings. The drawings are schematic diagrams of the present disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the drawings may be functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in hardware modules or integrated circuits, or in networks, processors, or microcontrollers. The embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein. The features, structures, or characteristics described in the present disclosure can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to give a full understanding of the embodiments of the present disclosure. However, those skilled in the art should be aware that one or more specific details can be omitted when implementing the technical solutions of the present disclosure, or other methods, components, devices, steps, etc. can be used to replace one or more specific details.

[0097] It should be noted that in the embodiments of the present disclosure, some existing industry solutions such as certain software, components, models, etc. may be mentioned. They should be considered exemplary. The purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present disclosure, but it does not mean that the applicant has already or necessarily used this solution. In the technical solutions of the present disclosure, the collection, dissemination, use, and display of various information of the object to be processed all comply with relevant national laws and regulations. Summary of the Invention

[0099] Currently, in the e-commerce scenarios of traditional categories such as publications, discs, albums, etc., it is always time-consuming and laborious for merchants to promote the products they sell. Specifically, first, merchants may not have attractive product scene pictures. Therefore, if they consider hiring professional designers or photographers to produce and shoot product scene pictures, the cost and time cycle are relatively large. Second, when merchants are promoting products, for those merchants lacking promotion experience or being non-professional, they often need to rely on their personal brains to conceive promotion forms and content, which is time-consuming and laborious.

[0100] Therefore, in the entire promotion link of traditional e-commerce products such as publications, discs, albums, etc., many steps require a large amount of manpower and material resources, resulting in high overall promotion costs and long cycles.

[0101] In view of this, how to accurately and efficiently obtain effective publicity information has become an urgent problem to be solved.

[0102] In view of one or more of the above problems, an exemplary embodiment of the present disclosure provides an information processing method. Through this method, the basic information of the object to be processed can be determined first, and then the initial picture of the object to be processed can be determined according to the basic information of the object to be processed. Then, the main picture can be determined from the initial picture, and finally, the target picture can be generated according to the main picture and the scene description information of the object to be processed. It can be seen that the present disclosure can directly expand and obtain the initial picture automatically according to the basic information of the object to be processed, then automatically process the initial picture, and finally automatically generate the target picture. The whole process of generating the target picture does not require manual participation, improving the efficiency of obtaining effective publicity information of the object to be processed and reducing the cost of obtaining effective publicity information of the object to be processed. Moreover, since the target picture is generated in combination with the scene description information of the object to be processed, on the basis of obtaining effective publicity information, publicity information more in line with the actual use scenario is also obtained, improving the content richness of the target picture and avoiding the situation where users need to perform additional optimization and adjustment on the picture, thereby enhancing the user experience.

[0103] Overview of Application Scenarios

[0104] To better understand the technical solutions provided by the embodiments of the present disclosure, the following briefly introduces the application scenarios applicable to the technical solutions provided by the embodiments of the present disclosure. It should be noted that the following introduced application scenarios are only used to illustrate the embodiments of the present disclosure rather than to limit them. In specific implementation, the technical solutions provided by the embodiments of the present disclosure can be flexibly applied according to actual needs.

[0105] To introduce the content of the embodiments of the present disclosure more clearly, the following introduces some key terms:

[0106] The large language model (LLM) refers to a deep learning model trained with a large amount of text data, which can generate natural language text or understand the meaning of language text. The large language model can handle various natural language tasks, such as text classification, question answering, dialogue, etc., and is an important way to artificial intelligence.

[0107] Mask: It is an important tool for compositing images, with the functions of protection and isolation. It is a kind of mask that protects the image areas that do not need to be edited in the image (the areas corresponding to black are protected), and can be used for the image restoration model to understand area division and identification.

[0108] Image restoration model: A plug-and-play model with decomposed double-branch diffusion, such as BrushNet. This model can input prompts to restore the missing areas (mask areas) of the image while maintaining overall coherence.

[0109] In the embodiments of the present disclosure, the information processing technology can be applied to business scenarios where various goods to be promoted through e-commerce are to be publicized, such as business scenarios for publicizing traditional publications (such as books, magazines, periodicals, etc.), or business scenarios for publicizing various agricultural products, or business scenarios for publicizing discs of operas or TV dramas, or business scenarios for publicizing music albums. The embodiments of the present disclosure do not limit this.

[0110] Please refer to Figure 1 as shown in Figure 1 which is an application scenario applicable to the technical solution of the embodiments of the present disclosure. In this scenario schematic diagram, it includes a terminal device 110 and an electronic device 120. Among them, the terminal device 110 can be one or more, and an information processing platform can be set on each terminal device 110, so that different users can log in to the information processing platform deployed on the corresponding terminal device 110. Figure 1 One is taken as an example for illustration. And, the terminal device 110 and the electronic device 120 communicate through one or more networks 130.

[0111] In the embodiments of the present disclosure, the user can log in to the information processing platform deployed on the corresponding terminal device 110 and trigger an information processing request. Thus, the electronic device 120 can receive the information processing request, and then determine the basic information of the object to be processed according to the basic information of the object to be processed carried in the information processing request. Then, according to the basic information of the object to be processed, determine the initial picture of the object to be processed; further, determine the main picture from the initial picture, and generate a target picture according to the main picture and the scene description information of the object to be processed, and send the target picture to the terminal device 110. Thus, the user can use the target picture for the promotion and publicity of the object to be processed, that is, the commodity. It can be seen that the present disclosure automatically generates a target picture through the basic information of the object to be processed, and the whole process is fully automated without manual participation, improving the efficiency of obtaining effective publicity information of the object to be processed.

[0112] In the embodiments of the present disclosure, Figure 1The terminal device 110 in [description] can be a mobile phone, a tablet computer (PAD), a personal computer, a smart TV, a smart watch, a smart speaker, a smart vehicle-mounted device, a wearable device, etc., but is not limited thereto.

[0113] In the embodiments of the present disclosure, Figure 1 the electronic device 120 in [description] can also be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers. It can also be a cloud server or a cloud server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms, but is not limited thereto.

[0114] Of course, the method provided in the embodiments of the present disclosure is not limited to Figure 1 the application scenarios shown in [description]. It can also be used in other possible application scenarios. For example, only the electronic device 120 executes the information processing method, that is, the electronic device itself: determines the basic information of the object to be processed; determines the initial picture of the object to be processed according to the basic information of the object to be processed; determines the main picture from the initial picture; and generates the target picture according to the main picture and the scene description information of the object to be processed. The embodiments of the present disclosure do not limit this.

[0115] Exemplary Method

[0116] To further illustrate the technical solutions provided in the embodiments of the present disclosure, the following will be described in detail with reference to the accompanying drawings and specific implementation manners. Although the embodiments of the present disclosure provide the method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or non-creative labor. In steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiments of the present disclosure. When the method is actually processed or executed by the device, it can be executed in the order shown in the embodiments or drawings or executed in parallel.

[0117] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of an information processing method in the embodiments of the present disclosure. The process of the method can be executed by an electronic device, for example. The electronic device can be Figure 1 the electronic device 120 in [description]. The specific implementation process of this method is as follows:

[0118] Step 201: Determine the basic information of the object to be processed.

[0119] In the embodiments of the present disclosure, the electronic device can automatically determine the basic information of the object to be processed, or can determine the basic information of the object to be processed according to the information processing request triggered by the user. The embodiments of the present disclosure do not limit this.

[0120] In the embodiments of the present disclosure, the object to be processed can be understood as a product to be promoted by a merchant. Such a product can be, for example, a publication, an agricultural product, an album, etc. The embodiments of the present disclosure do not limit this.

[0121] In the embodiments of the present disclosure, the basic information of the object to be processed can be understood as the basic introduction information of the product. Optionally, assuming that the object to be processed is a publication, the basic information of the object to be processed is the basic introduction information such as the title, author, and version information of the publication. For example, if the object to be processed is a publication, the book "AAA" and its author is BBB, then the basic information of the object to be processed is "Alive" and "Yu Hua".

[0122] Step 202: Determine the initial image of the object to be processed according to the basic information of the object to be processed.

[0123] In the embodiments of the present disclosure, the electronic device can retrieve the initial image corresponding to the object to be processed from the network according to the basic information of the object to be processed.

[0124] For example, if the electronic device determines that the basic information of the object to be processed is "Alive" and "Yu Hua", it can retrieve the standard cover image corresponding to the publication from at least one data repository and / or database from the network, and use this standard cover image as the initial image of the object to be processed.

[0125] In the embodiments of the present disclosure, the electronic device can, based on the network retrieval ability of the LLM, retrieve the initial image of the object to be processed based on the basic information of the object to be processed.

[0126] Step 203: Determine the main image from the initial image.

[0127] In the embodiments of the present disclosure, the electronic device can determine the main image from the initial image. Among them, the main image can be understood as an image that only includes the object to be processed itself.

[0128] In the embodiments of the present disclosure, the electronic device can perform main body extraction based on edge detection on the initial image to obtain the main image.

[0129] Specifically, the electronic device can detect the boundary color of the initial picture, and then detect from the boundary of the initial picture to the inside according to the boundary color to detect non-edge pixel points. The main area is determined according to the positions of the non-edge pixel points, and thus the main picture is determined from the initial picture. Among them, the non-edge pixel points are pixel points whose color difference from the boundary color exceeds a first preset value, or pixel points whose color difference from adjacent edge pixel points exceeds a second preset value.

[0130] For example, please refer to Figure 3 , Figure 3 which is a schematic diagram of a process for obtaining a main picture provided by the present disclosure. In Figure 3 , the standard cover picture of a publication with the book title "XX" and the author "Mn" can be determined. Since there will be a non-publication part of the same color around the publication in the standard cover picture, such as a white edge, it is necessary to calculate the color at the edge position.

[0131] In the embodiments of the present disclosure, the horizontal axis pixel points at the topmost, bottommost, leftmost, and rightmost can be traversed, and the RGB values of each pixel point are recorded. If the differences in the three colors of R, G, and B between two pixel points are all within 10, it is considered that they are of the same color. For example, if the difference between the RGB(255, 255, 255) of pixel point 1 and the RGB(252, 253, 252) of pixel point 2 is within 10, then it is considered that pixel point 1 and pixel point 2 are of the same color. Thus, the color with the most identical pixel points among the four edge axes is calculated. In the embodiments of the present disclosure, the color with the most identical pixel points among the four edge axes is called the majority color.

[0132] In the embodiments of the present disclosure, the electronic device can perform edge recursive detection based on the aforementioned majority color. Specifically, starting from the four directions of up, down, left, and right (for example, the four directions shown in Figure 3 ), each pixel point is traversed row by row / column by column inward. When a pixel point with a color different from the majority color is encountered in a certain row / column, it is determined that the traversal in that direction ends. When it is determined that the recursive detections in the four directions have all ended, the rectangular frame area at the end positions in the four directions can be determined, and thus it can be determined that this rectangular frame area is the complete main part of the publication. Further, according to the position information of the rectangular frame area, the original standard cover picture of the publication can be cropped to obtain the complete main picture of the publication cover, that is, the aforementioned main picture.

[0133] Step 204: Generate a target picture according to the main picture and the scene description information of the object to be processed.

[0134] In the embodiments of the present disclosure, after obtaining the main body picture, a target picture can be generated according to the main body picture and the scene description information of the object to be processed. It can be seen that the target picture in the embodiments of the present disclosure is a main body picture or a combined picture of the optimized main body picture and the background.

[0135] In the embodiments of the present disclosure, please refer to Figure 4 As shown, the electronic device can adopt but is not limited to the following steps to generate a target picture.

[0136] Step 401: Combine the main body picture with the first background to obtain a basic picture;

[0137] In the embodiments of the present disclosure, the electronic device can determine a white background canvas picture of the first preset size as the first background, and then use the main body picture as the upper layer and the first background as the lower layer for layer merging processing to obtain a basic picture.

[0138] Optionally, before performing the layer merging processing on the main body picture and the first background, a preset processing can also be performed on the main body picture to obtain a processed main body picture. Among them, the preset processing is, for example, rotation processing, scaling processing, etc., and the embodiments of the present disclosure do not limit this.

[0139] For example, for a random angle value from -30 degrees to 30 degrees, rotate the obtained main body picture to obtain a rotated publication main body picture.

[0140] It should be noted that the preset processing can be determined corresponding to the scene description information. That is to say, in order to determine a more beautiful and optimized target picture, a preset processing can be performed on the main body picture, so that the finally determined target picture better conforms to the target usage scenario, thereby improving the publicity effect on the basis of automatically generating publicity pictures and further improving the user experience.

[0141] For example, the electronic device can use the expected size of the scene picture to automatically draw a pure white background picture of this size as the lower layer, use the processed main body picture as the upper layer, calculate the center position, and then perform layer merging processing on the upper layer and the lower layer to obtain a rotated publication main body white background picture of the expected scene picture size, that is, the aforementioned basic picture. That is to say, the first preset size can be determined corresponding to the size of the expected scene picture, and the embodiments of the present disclosure do not limit the specific value of the first preset size.

[0142] Step 402: Generate a mask picture for representing the background area in the basic picture.

[0143] In an embodiment of the present disclosure, a transparent bottom canvas image with a second preset size can be determined first, and then the main image and the transparent bottom canvas image can be subjected to layer merging processing to obtain a first processed image, and the brightness and saturation of the first processed image can be adjusted to obtain a second processed image. Further, the second processed image and the first background can be subjected to layer merging processing to obtain a mask image.

[0144] In an embodiment of the present disclosure, the electronic device can use the expected scene image size to automatically draw a pure transparent bottom image of this size as the lower layer, and use the main image (or the main image processed by the foregoing solution) as the upper layer. After calculating the center position, the pure transparent bottom image and the main image are subjected to layer merging processing, so as to obtain a rotated transparent bottom image of the publication main body under the expected scene image size, that is, the foregoing first processed image.

[0145] Further, the electronic device can adjust the brightness and saturation of the rotated transparent bottom image of the publication main body. For example, the brightness and saturation of the image are both adjusted to -100, so that the main body part of the publication can be directly changed to pure black, and then a pure black rotated transparent bottom image of the publication main body can be obtained, that is, the foregoing second processed image.

[0146] Further, the electronic device can use the pure white bottom image drawn again with the expected scene image size, that is, the foregoing first background, as the lower layer, and use the pure black rotated transparent bottom image of the publication main body as the upper layer, and perform layer merging processing on these two layers, so as to obtain a pure black rotated white bottom image of the publication main body, that is, the foregoing mask image.

[0147] Step 403: Generate a target image according to the base image, the mask image, and the scene description information of the object to be processed.

[0148] In an embodiment of the present disclosure, the electronic device can perform expansion processing on the basic information of the object to be processed according to the preset information expansion model to determine the scene description information of the object to be processed. Among them, the preset information expansion model can be constructed according to the LLM model, or can be constructed based on other neural network models or deep learning models, which are not limited in the embodiments of the present disclosure.

[0149] For example, use the LLM to automatically generate a description word for the publication scene image, and this description word is the prompt word for generating the image.

[0150] In an embodiment of the present disclosure, the electronic device can extract potential feature information from the base image, perform downsampling processing on the mask image to obtain downsampled feature information, and perform image feature extraction processing on the mask image to obtain image feature information. Then, the target image can be generated according to the potential feature information, the downsampled feature information, the image feature information, and the scene description information.

[0151] Optionally, the electronic device may process the base picture, the mask picture, and the scene description information of the object to be processed based on an image restoration model to generate a target picture. Among them, the image restoration model may be constructed based on models such as a neural network model and a deep learning model, which is not limited in the embodiments of the present disclosure.

[0152] For example, assuming that the image restoration model is the BrushNet model, the rotated white-background picture of the publication main body can be used as the original picture input of the BrushNet model, the rotated white-background picture of the pure black publication main body can be used as the mask picture input of the BrushNet model, and the publication scene description words can be used as the prompt word input of the BrushNet. Then, through the local redrawing technology of the BrushNet model, a publication scene picture with the expected size can be obtained, that is, the aforementioned target picture.

[0153] In the embodiments of the present disclosure, a specific example is used below to introduce the process schematic diagram of obtaining the target picture in the present disclosure. For example, please refer to Figure 5 as shown.

[0154] In the embodiments of the present disclosure, the electronic device may obtain a standard cover picture of the publication (such as Figure 5 Picture 1 in), and then perform main body extraction processing based on edge detection on the standard cover picture of the publication to obtain a main body picture (such as Figure 5 Picture 2 in). Further, the electronic device may rotate the main body picture by a certain angle to obtain a rotated main body picture (such as Figure 5 Picture 3 in).

[0155] In the embodiments of the present disclosure, the electronic device may use a white-background canvas with a specified size (such as Figure 5 Picture 4 in) as the lower layer, and use the rotated main body picture as the upper layer for layer merging processing to obtain a base picture (such as Figure 5 Picture 5 in).

[0156] In the embodiments of the present disclosure, the electronic device may use a transparent-background canvas with a specified size (such as Figure 5 Picture 6 in) as the lower layer, and use the rotated main body picture as the upper layer for layer merging processing to obtain a first processed picture (such as Figure 5 Picture 7 in).

[0157] In the embodiments of the present disclosure, the electronic device may adjust the brightness and saturation of the first processed picture to obtain a second processed picture (such as Figure 5The picture in (8). Further, the electronic device may use a white background canvas of a specified size as the lower layer, and perform layer merging processing on the second processed picture as the upper layer to obtain a mask picture (for example Figure 5 the picture in (9).

[0158] In the embodiments of the present disclosure, the electronic device may generate a target picture according to the base picture, the mask picture, and the scene prompt words of the publication (for example Figure 5 the picture in (10).

[0159] It can be seen that the information processing method provided by the embodiments of the present disclosure can quickly and efficiently obtain effective promotional information of the object to be processed, thereby improving the efficiency of obtaining effective promotional information. Moreover, the entire process does not require manual participation, reducing the cost of obtaining effective promotional information and enhancing the user experience.

[0160] In the embodiments of the present disclosure, considering that after the user obtains the target picture of the product, the product still needs to be promoted on e-commerce platforms. Therefore, the target picture can be further optimized to meet the release requirements of different e-commerce promotion platforms, etc., enhancing the user experience.

[0161] In the embodiments of the present disclosure, the electronic device may determine the recommended text information of the object to be processed according to the basic information of the object to be processed, and then generate target recommended information according to the recommended text information and the target picture.

[0162] For example, the electronic device may use the Internet retrieval ability of the LLM to retrieve additional information such as the standard cover picture of the publication (if the merchant lacks the standard cover picture), the creation background of the publication, the author's experience, online book reviews, award-winning situations, etc. based on the basic information of the publication. Moreover, the electronic device may use the LLM to generate recommended text information for e-commerce scenarios according to the basic information and the additional information obtained above. The recommended text information includes: copy title, copy text, copy tags / topics, etc. Further, the electronic device may generate target recommended information according to the recommended text information and the target picture.

[0163] In the embodiments of the present disclosure, the electronic device may also determine the display channel of the target recommended information, and then adjust the target recommended information according to the display form corresponding to the display channel. The display channel can be understood as different promotion channels, such as various promotion platforms or applications, etc.

[0164] For example, if the display channel of the target recommended information is Application 1, and the display form corresponding to Application 1 is a graphic form and allows shopping links, the sales information of the publication can be obtained, and then the target recommended information can be generated according to the sales information, the recommended text information, and the target picture.

[0165] It can be seen that in the embodiments of the present disclosure, the determination of the entire publicity content of a commodity in an e-commerce scenario does not require manual participation throughout the process. That is, based on the basic information of the object to be processed, high-quality graphic publicity content can be quickly and accurately generated and directly automated for listing, greatly reducing labor costs and production cycles, not only improving the efficiency of information processing, but also enhancing the user experience.

[0166] In the embodiments of the present disclosure, the following uses a specific example to introduce the process schematic diagram of obtaining the target recommendation information of the present disclosure. For example, please refer to Figure 6 as shown.

[0167] In the embodiments of the present disclosure, the electronic device can retrieve the initial picture and additional information of the object to be processed based on the basic information of the object to be processed, such as Figure 6 the title and author of the publication in, and retrieve the initial picture and additional information of the object to be processed through networking. Then, the electronic device automatically generates a personalized scene picture based on the initial picture of the object to be processed, that is, the aforementioned target picture, such as Figure 5 or Picture 10 in 6. The specific process of obtaining the target picture can refer to the corresponding implementation process described above Figure 5 and will not be elaborated here.

[0168] In the embodiments of the present disclosure, the electronic device can automatically generate recommended text information based on the additional information. Specifically, the electronic device can first determine each piece of information in the additional information of the object to be processed, such as Figure 6 the creation background of the publication, the author's journey of the publication, and the online book reviews of the publication in, and then the electronic device processes the creation background of the publication, the author's journey of the publication, and the online book reviews based on the LLM to generate recommended text information, and the recommended text information includes a copywriting title, a copywriting body, and copywriting tags / topics.

[0169] In the embodiments of the present disclosure, after obtaining the target picture and the recommended text information, the electronic device generates target recommendation information based on the target picture and the recommended text information, and then performs processing such as posting, commodity listing, note posting, and video posting based on different display channels.

[0170] It can be seen that in the embodiments of the present disclosure, the target picture and the target recommendation information can be automatically obtained based on the basic information of the object to be processed, greatly improving the efficiency of obtaining effective publicity information of the object to be processed.

[0171] Exemplary Apparatus

[0172] An exemplary embodiment of the present disclosure also provides an information processing device. Refer to Figure 7 as shown. The information processing device 700 includes the following program units:

[0173] The first determination unit 701 is configured to determine the basic information of the object to be processed;

[0174] The second determination unit 702 is configured to determine the initial picture of the object to be processed according to the basic information of the object to be processed;

[0175] The processing unit 703 is configured to determine the main picture from the initial picture;

[0176] The generation unit 704 is configured to generate a target picture according to the main picture and the scene description information of the object to be processed.

[0177] In a possible implementation manner, the generation unit 704 is configured to:

[0178] Combine the main picture with a first background to obtain a basic picture;

[0179] Generate a mask picture for representing the background area in the basic picture;

[0180] Generate the target picture according to the basic picture, the mask picture, and the scene description information of the object to be processed.

[0181] In a possible implementation manner, the processing unit 703 is configured to:

[0182] Perform main body extraction based on edge detection on the initial picture to obtain the main picture.

[0183] In a possible implementation manner, the processing unit 703 is configured to:

[0184] Detect the boundary color of the initial picture;

[0185] Detect from the boundary of the initial picture to the inside according to the boundary color to detect non-edge pixel points, and determine the main body area according to the positions of the non-edge pixel points;

[0186] Determine the main picture from the initial picture according to the main body area.

[0187] In a possible implementation manner, the non-edge pixel points are pixel points whose color difference from the boundary color exceeds a first preset value, or pixel points whose color difference from adjacent edge pixel points exceeds a second preset value.

[0188] In a possible implementation manner, the generation unit 704 is configured to:

[0189] Determine a white background canvas picture with a first preset size as the first background;

[0190] Merge the subject image and the first background in a layer to obtain the base image.

[0191] In a possible implementation, the generating unit 704 is configured to:

[0192] Determine a transparent background canvas image of a second preset size;

[0193] Merge the subject image and the transparent background canvas image in a layer to obtain a first processed image;

[0194] Perform bright saturation adjustment processing on the first processed image to obtain a second processed image;

[0195] Merge the second processed image and the first background in a layer to obtain a mask image.

[0196] In a possible implementation, the generating unit 704 is configured to:

[0197] Extract potential feature information from the base image;

[0198] Perform downsampling processing on the mask image to obtain downsampled feature information; and perform image feature extraction processing on the mask image to obtain image feature information;

[0199] Generate a target image according to the potential feature information, downsampled feature information, image feature information, and scene description information.

[0200] In a possible implementation, the device further includes an expansion unit, configured to:

[0201] Expand the basic information of the object to be processed according to a preset information expansion model, and determine the scene description information of the object to be processed.

[0202] In a possible implementation, the generating unit 704 is further configured to:

[0203] Determine the recommended text information of the object to be processed according to the basic information of the object to be processed;

[0204] Generate target recommendation information according to the recommended text information and the target image.

[0205] In a possible implementation, the device further includes an adjustment unit, configured to:

[0206] Determine the display channel of the target recommendation information;

[0207] Adjust the target recommendation information according to the display form corresponding to the display channel.

[0208] The specific details of each part in the above device have been described in detail in the embodiments of the method part. For the details not disclosed, reference can be made to the content of the embodiments in the method part, and thus will not be elaborated here.

[0209] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the exemplary embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0210] Exemplary Program Product

[0211] The exemplary embodiments of the present disclosure also provide a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the above information processing method is implemented.

[0212] In one embodiment, the computer program product may be a tangible product containing the computer program, such as a computer-readable storage medium storing the computer program. The readable storage medium may be a storage medium based on signals such as electricity, magnetism, light, electromagnetic, infrared, etc., including but not limited to: random access memory (RAM), read-only memory (ROM), magnetic tape, floppy disk, flash memory (Flash), hard disk drive (HDD), solid state drive (SSD), etc. Exemplarily, the computer program product may be implemented as a non-volatile storage medium storing the computer program, such as read-only memory, Nand Flash, etc.

[0213] In one embodiment, the computer program product may be an intangible product containing the computer program. Exemplarily, the computer program product may be implemented as a virtual digital product, such as an executable file storing the computer program, digital files such as installation packages.

[0214] The code of the computer program can be written in one or more programming languages. Programming languages such as C language, Java, C++, etc. The program code can be executed entirely on the user's computing device, or partially on the user's computing device, or executed as an independent software package, or partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, such as a local area network (LAN), a wide area network (WAN), etc., or can be connected to an external computing device (for example, through the Internet connection provided by an operator).

[0215] Computer programs can be carried or transmitted by electrical, magnetic, optical, electromagnetic, infrared, etc. signals. An electronic device can convert the signal carrying the computer program into a digital signal and then run the computer program. When the computer program runs on the electronic device, its code is used to cause the electronic device to execute (more specifically, to cause the processor of the electronic device to execute) the method steps of various exemplary embodiments of the present disclosure. For example, the above information processing method can be executed, which includes the following steps: Step 201: Determine the basic information of the object to be processed; Step 202: Determine the initial picture of the object to be processed according to the basic information of the object to be processed; Step 203: Determine the main picture from the initial picture; Step 204: Generate a target picture according to the main picture and the scene description information of the object to be processed.

[0216] By implementing the above method steps through a computer program, the basic information of the object to be processed can be determined first, then the initial picture of the object to be processed can be determined according to the basic information of the object to be processed, then the main picture can be determined from the initial picture, and finally the target picture can be generated according to the main picture and the scene description information of the object to be processed. It can be seen that the present disclosure can directly automatically expand and obtain the initial picture according to the basic information of the object to be processed, then automatically process the initial picture, and finally automatically generate the target picture. The whole process of generating the target picture does not require manual participation, improving the efficiency of obtaining the effective publicity information of the object to be processed and reducing the cost of obtaining the effective publicity information of the object to be processed. And, since the target picture is generated in combination with the scene description information of the object to be processed, on the basis of obtaining the effective publicity information, publicity information more in line with the actual use scenario is also obtained, improving the content richness of the target picture and avoiding the situation where users need to perform additional optimization and adjustment on the picture, thereby improving the user experience.

[0217] Exemplary Electronic Device

[0218] Exemplary embodiments of the present disclosure also provide an electronic device. The electronic device may include a processor and a memory. The memory stores executable instructions of the processor, such as a computer program. The processor executes the executable instructions to execute the method steps of various exemplary embodiments of the present disclosure.

[0219] Next, with reference to Figure 8 , the electronic device will be exemplarily described in the form of a general computing device. It should be understood that Figure 8 the shown electronic device 800 is only an example and should not impose limitations on the functions and usage scope of the embodiments of the present disclosure.

[0220] Such as Figure 8As shown, the electronic device 800 may include: a processor 810, a memory 820, a bus 830, an I / O (input / output) interface 840, and a network adapter 850.

[0221] The memory 820 may include volatile memory, such as RAM 821 and a cache unit 822, and may also include non-volatile memory, such as ROM 823. The memory 820 may further include one or more program modules 824. Such program modules 828 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. For example, the program module 824 may include each unit in the above device.

[0222] The processor 810 may include one or more processing units. For example, the processor 810 may include an AP (Application Processor), a modem processor, a GPU (Graphics Processing Unit), an ISP (Image Signal Processor), a controller, an encoder, a decoder, a DSP (Digital Signal Processor), a baseband processor, and / or an NPU (Neural-Network Processing Unit), etc.

[0223] The processor 810 can be used to execute the executable instructions stored in the memory 820. For example, it can execute the above information processing method, which includes the following steps: Step 201: Determine the basic information of the object to be processed; Step 202: Determine the initial picture of the object to be processed according to the basic information of the object to be processed; Step 203: Determine the main picture from the initial picture; Step 204: Generate a target picture according to the main picture and the scene description information of the object to be processed.

[0224] By executing the above method steps through the processor 810, the basic information of the object to be processed can be determined first. Then, based on the basic information of the object to be processed, the initial picture of the object to be processed can be determined. Next, the main picture can be determined from the initial picture. Finally, based on the main picture and the scene description information of the object to be processed, the target picture is generated. It can be seen that the present disclosure can directly automatically expand and obtain the initial picture according to the basic information of the object to be processed, then automatically process the initial picture, and finally automatically generate the target picture. The entire process of generating the target picture does not require manual participation, improving the efficiency of obtaining the effective promotional information of the object to be processed and reducing the cost of obtaining the effective promotional information of the object to be processed. Moreover, since the target picture is generated in combination with the scene description information of the object to be processed, on the basis of obtaining the effective promotional information, promotional information that is more in line with the actual usage scenario is also obtained, improving the content richness of the target picture and avoiding the situation where users need to perform additional optimization and adjustment on the picture, thereby enhancing the user experience.

[0225] The bus 830 is used to implement the connection between different components of the electronic device 800 and may include a data bus, an address bus, and a control bus.

[0226] The electronic device 800 can communicate with one or more external devices 900 (such as a keyboard, a mouse, an external controller, etc.) through the I / O interface 840.

[0227] The electronic device 800 can communicate with one or more networks through the network adapter 850. For example, the network adapter 850 can provide mobile communication solutions such as 3G / 4G / 5G, or provide wireless communication solutions such as wireless local area network, Bluetooth, and near field communication. The network adapter 850 can communicate with other modules of the electronic device 800 through the bus 830.

[0228] Although Figure 8 not shown in the figure, other hardware and / or software modules can also be provided in the electronic device 800, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0229] As can be seen from the above, the technical solution of the present disclosure can be implemented as a method, a device, a system, a computer program product, a storage medium, an electronic device, etc. Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, such as can be respectively referred to as "circuit", "module", or "system".

[0230] It should be understood that the present disclosure is not limited to the specific method steps or structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. Those skilled in the art will readily think of other embodiments based on the specific embodiments provided by the present disclosure. Therefore, the specific embodiments provided by the present disclosure are only exemplary, and the scope and spirit of the present disclosure are pointed out by the claims, which should cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include well-known common general knowledge or conventional technical means in the technical field not disclosed by the present disclosure.

Claims

1. An information processing method, characterized in that, The method includes: Determine the basic information of the object to be processed; Determine the initial picture of the object to be processed according to the basic information of the object to be processed; Determine the main picture from the initial picture; Generate a target picture according to the main picture and the scene description information of the object to be processed.

2. The method according to claim 1, wherein The generating the target picture according to the main picture and the scene description information of the object to be processed includes: Combine the main picture with a first background to obtain a basic picture; Generate a mask picture for representing the background area in the basic picture; Generate the target picture according to the basic picture, the mask picture and the scene description information of the object to be processed.

3. The method according to claim 2, characterized in that, The determining the main picture from the initial picture includes: Perform main body extraction based on edge detection on the initial picture to obtain the main picture.

4. The method according to claim 3, characterized in that, The performing main body extraction based on edge detection on the initial picture to obtain the main picture includes: Detect the boundary color of the initial picture; Detect from the boundary of the initial picture to the inside according to the boundary color to detect non-edge pixel points, and determine the main body area according to the positions of the non-edge pixel points; Determine the main picture from the initial picture according to the main body area.

5. The method according to claim 4, wherein The non-edge pixel points are pixel points whose color difference from the boundary color exceeds a first preset value, or pixel points whose color difference from adjacent edge pixel points exceeds a second preset value.

6. The method according to any one of claims 2-5, characterized in that, The combining the main picture with a first background to obtain a basic picture includes: Determine a white background canvas picture with a first preset size as the first background; Perform layer merging processing on the main picture and the first background to obtain the basic picture.

7. The method according to any one of claims 2-5, characterized in that, The generating a mask picture for representing the background area in the basic picture includes: Determine a transparent background canvas picture with a second preset size; Perform layer merging processing on the main picture and the transparent background canvas picture to obtain a first processed picture; Perform bright saturation adjustment processing on the first processed picture to obtain a second processed picture; Perform layer merging processing on the second processed picture and the first background to obtain the mask picture.

8. An information processing method, characterized in that, The method includes: A first determination unit for determining the basic information of the object to be processed; A second determination unit for determining the initial picture of the object to be processed according to the basic information of the object to be processed; A processing unit for determining the main picture from the initial picture; A generating unit for generating a target picture according to the main picture and the scene description information of the object to be processed.

9. An electronic device, characterized in that, Includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the method according to any one of claims 1-7 by executing the executable instructions.

10. A computer program product, on which a computer program is stored, characterized in that, The computer program, when executed by a processor, implements the method according to any one of claims 1-7.

Images