Method and system for item background presentation for smart window displays and smart window displays

Abstract

The application relates to the technical field of artificial intelligence, and discloses an article background display method and system for an intelligent showcase, a computer storage medium, a computer program product and an intelligent showcase, which are used to solve the technical problem that the background effect displayed by an existing intelligent showcase system cannot be adjusted according to displayed articles and watched audiences, resulting in a poor article background display effect. The method comprises the following steps: acquiring an article image of a target article to be displayed, and acquiring a portrait image of an audience currently watching the showcase; identifying image information of the collected article to be displayed, so as to obtain first text description information of an appearance of the displayed article; identifying image information of the collected audience watching the showcase, so as to obtain second text description information of characteristics of the audience; inputting the first text description information and the second text description information into an image generation model to generate a showcase background image; and displaying the background image of the showcase.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, system, computer storage medium, computer program product, and smart window for displaying item backgrounds in a smart window. Background Art

[0002] In recent years, AI-generated content (AIGC) technology has continued to mature in the field of image generation and processing, and its application in multimedia and advertising has become increasingly widespread. Using AI-generated content can make the generation and customization of image content more efficient and intelligent. Specifically, traditional window displays usually rely on manual design and layout, which is not only time-consuming but also difficult to change in real time. With the development of AI technology, smart windows use computer vision and deep learning algorithms to achieve intelligent generation and adjustment of display content, improving the display effect and viewer experience.

[0003] However, existing AI-generated content for background displays in smart window displays often involves taking photos of the items and then generating promotional images. This image generation process requires professionals to input prompts for the items and the corresponding scene requirements. The images are then generated in the cloud, captured, and transmitted to the display terminal via a network system for display. This requires personnel experienced with prompts, and since everyone's environmental perception varies, achieving a consistent generation effect is difficult. Furthermore, this generation method leaves the background effects generated by the merchant user to their own discretion. Not only is it inaccurate in matching the characteristics of the displayed items, but it also cannot be adjusted based on the audience, failing to account for individual preferences. Summary of the Invention

[0004] The main purpose of the present invention is to solve the technical problem in the prior art that the background effect of the existing smart window display system cannot be adjusted according to the displayed items and the viewing audience, resulting in poor background display effect of the items.

[0005] A first aspect of the present invention provides a method for displaying an item background in a smart window, comprising: acquiring an object image of a target item to be displayed, and acquiring a person image of a person currently viewing the window; identifying the collected image information of the item to be displayed, and obtaining first text description information of the appearance of the displayed item; identifying the collected image information of a person viewing the window, and obtaining second text description information of the person's characteristics; generating a window background image based on the first text description information and the second text description information, and displaying the window background image.

[0006] Optionally, in a first implementation manner of the first aspect of the present invention, the identifying the collected image information of the item to be displayed to obtain the first text description information of the appearance of the item to be displayed includes: preprocessing the image information of the item to be displayed and identifying the object body contained in the preprocessed image information of the item to be displayed; identifying the object body based on a multimodal language model, generating a natural language description corresponding to the appearance of the object body, and obtaining the first text description information.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the identifying of the collected image information of the person viewing the window display to obtain the second text description information of the person's characteristics includes: preprocessing the image information of the person viewing the window display, and identifying the person subject contained in the preprocessed person image information; identifying the person subject based on a multimodal language model, generating a natural language description corresponding to the person characteristics of the person subject, and obtaining the second text description information.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the display window includes a first screen and a second screen at an angle to the first screen; generating a display window background image based on the first text description information and the second text description information, and displaying the display window background image includes: calling an aesthetic design model, inferring the background design in combination with the first text description information and the second text description information, and obtaining background prompt words; inputting the background prompt words into an image generation model, and based on the positional relationship between the first screen and the second screen, generating and displaying background images suitable for the first screen and the second screen respectively.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, obtaining the object image of the target item on display includes: receiving first video information inside the smart window, and performing image sampling on the first video information at first preset time intervals; identifying whether there are any items placed in the current smart window based on the internal image of the window obtained by image sampling; and if there are any items placed, collecting the object image of the target item on display.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, obtaining the person image of the viewer currently viewing the window includes: receiving second video information in front of the smart window, and performing image sampling on the second video information every second preset time; identifying whether there is someone currently viewing the window based on the image obtained by the image sampling; and if there is someone viewing the window, collecting the person image of the viewer currently viewing the window.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the method for background display of items in a smart window further includes: determining whether the items displayed in the smart window have been replaced; if replaced, recording the replacement time of the items in the smart window; calculating the item replacement frequency based on the replacement time; and generating a first preset time based on the item replacement frequency.

[0012] Optionally, in a seventh implementation of the first aspect of the present invention, the method for displaying item backgrounds in a smart window further includes: determining whether the audience viewing the smart window has changed; if changed, recording the audience change time; calculating the audience change frequency based on the audience change time; and generating a second preset time based on the audience change frequency.

[0013] Optionally, in an eighth implementation manner of the first aspect of the present invention, generating a window background image based on the first text description information and the second text description information, and displaying the window background image also includes: determining a viewing position of the current audience based on a person image of the audience currently viewing the window; and stretching and adjusting the background images suitable for the first screen and the second screen according to the viewing position and the angle information between the first screen and the second screen, and then displaying them.

[0014] The second aspect of the present invention provides an item background display system for a smart window, comprising: an image acquisition module for acquiring an object image of a target item for display and an image of a person currently viewing the window; a first recognition module for identifying the acquired image information of the item to be displayed and obtaining first text description information of the appearance of the displayed item; a second recognition module for identifying the acquired image information of a person viewing the window and obtaining second text description information of the person's characteristics; and a background generation module for generating a window background image based on the first text description information and the second text description information, and displaying the window background image.

[0015] A third aspect of the present invention provides a smart display window, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory to enable the smart display window to execute the steps of the above-mentioned method for background display of items in the smart display window.

[0016] A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which, when executed on a computer, causes the computer to execute the steps of the above-mentioned method for background display of items in a smart window.

[0017] A fifth aspect of the present invention provides a computer program product, comprising a computer program / instruction, characterized in that when the computer program / instruction is executed by a processor, the steps of the method for background display of items in a smart window as described above are implemented.

[0018] In the technical solution provided by the present invention, an image of the target item to be displayed is obtained, and an image of the person currently viewing the window display is obtained; the collected image information of the item to be displayed is recognized to obtain first textual description information of the item's appearance; the collected image information of the person viewing the window display is recognized to obtain second textual description information of the person's characteristics; the first and second textual description information are input into an image generation model to generate a window display background image, and the window display background image is then displayed. This method enables a smart window display to intelligently adjust the display background based on the displayed items and the audience viewing the items, so that the generated display background is more closely aligned with the displayed items and can meet the preferences of different viewing groups. In addition, the system, computer-readable storage medium, computer program product, and smart window provided by the present invention also solve corresponding technical problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 Schematic diagram of the steps of a first embodiment of a method for displaying item backgrounds in a smart window according to an embodiment of the present invention;

[0021] Figure 2 Schematic diagram of the steps of a second embodiment of the method for displaying item backgrounds in a smart window according to an embodiment of the present invention;

[0022] Figure 3 This is a first working diagram of the smart window in an embodiment of the present invention;

[0023] Figure 4 This is a second working diagram of the smart window in an embodiment of the present invention;

[0024] Figure 5 This is a third working diagram of the smart window in an embodiment of the present invention;

[0025] Figure 6 Schematic diagram of the workflow of the smart window in an embodiment of the present invention;

[0026] Figure 7 Schematic diagram of an embodiment of an item background display system for a smart window according to an embodiment of the present invention;

[0027] Figure 8 Schematic diagram of another embodiment of the item background display system for a smart window in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, exemplary embodiments can be implemented in various forms, and it should not be understood that the present invention is limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more comprehensive and complete, making it easier to fully convey the inventive concept to those skilled in the art. In the figures, the same reference numerals represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0029] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0030] In the description of specific embodiments, the features, structures, characteristics, or other details of the present invention are described to enable those skilled in the art to fully understand the embodiments. However, this does not preclude those skilled in the art from practicing the technical solutions of the present invention without one or more of the specific features, structures, characteristics, or other details.

[0031] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0032] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0033] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0034] See also Figure 1 The first embodiment of the method for displaying item backgrounds in a smart window according to the present invention includes:

[0035] S101, obtaining an image of a target item on display and an image of a person currently viewing the window display;

[0036] It is understandable that the execution subject of the present invention can be an item background display device or a smart window terminal, and the specific details are not limited here. The embodiment of the present invention is described by taking the smart window as the execution subject as an example.

[0037] The smart display window described in this embodiment can be used to display a background image related to the target item currently displayed in the display window to viewers viewing the display window. In specific implementations, the smart display window can respond to an item display request and obtain an image of the target item currently displayed and an image of the person currently viewing the display window.

[0038] When obtaining the object image of the currently displayed target object and the person image of the current audience viewing the window, the image acquisition module in the smart window can respectively capture images of the target object placed in the window and the audience viewing the window.

[0039] In a specific embodiment, the smart window can automatically determine whether a background image for the window can be generated. For example, it can detect whether there are spectators in the current window and whether there are target items on display. If both are present, it is determined that background image generation is necessary, and an image of the target item on display and an image of the spectator currently viewing the window are obtained. The detection of whether there are spectators in the current window and whether there are target items on display can be performed through infrared sensing or other detection methods. In a preferred embodiment, an image acquisition module can be used to obtain image information within the window and in front of the window, perform recognition based on the image information, and determine whether there are spectators in the current window and whether there are items on display based on the content contained in the recognized image.

[0040] S102: Identify the collected image information of the object to be displayed to obtain first text description information of the appearance of the object to be displayed;

[0041] After obtaining the image information of the target object being displayed, the features of the object contained in the image information are identified, and the features are converted into a natural language description to obtain the first text description information, wherein the first text description information is mainly for the appearance shape, type information, color and other contents of the target object displayed in the current image information.

[0042] S103, recognizing the collected image information of the person viewing the window display to obtain second text description information of the person's characteristics;

[0043] After obtaining the image information of the person viewing the window display, the features of the person contained in the image information are identified, and the features are converted into a natural language description to obtain second text description information, wherein the second text description information mainly focuses on the gender, age, clothing style, etc. of the person viewing the window display contained in the current image information.

[0044] S104: Generate a window background image based on the first text description information and the second text description information, and display the window background image.

[0045] Combining the first text description information and the second text description information in the aforementioned steps, the self-trained aesthetic design model is called to infer the window background design based on the described items and the characteristics of the people viewing the window, and the prompt words required for generating the window background image are output. The window background image is generated according to the prompt words, and the window background image is displayed.

[0046] The method in the embodiment of the present invention enables the smart window to intelligently adjust the display background according to the displayed items and the audience viewing the items, so that the generated display background is more closely matched with the displayed items and can meet the preferences of different viewing groups.

[0047] Please see Figure 2-6 The second embodiment of the method for displaying item backgrounds in a smart window according to the present invention includes:

[0048] S201, obtaining an image of a target item on display and an image of a person currently viewing the window display;

[0049] The smart display window in this embodiment includes a first screen and a second screen, wherein the second screen forms a preset angle with the first screen. Figure 3 The first screen is located at the rear background position of the target item displayed in the smart window, the second screen is connected to the first screen and is arranged at a right angle below, and the displayed target item can be placed above the second screen.

[0050] The smart display window described in this embodiment also includes a processor and an image acquisition module. The processor can be used to control the image acquisition module and the display window screen, as well as process and generate images. The various models described below can be configured in the processor. There can be one or more image acquisition modules. In a preferred embodiment, there can be two image acquisition modules, including a first image acquisition module and a second image acquisition module. The first image acquisition module is used to capture images of displayed items, and the second image acquisition module is used to capture images of people viewing the display window.

[0051] Please continue reading Figure 4The first image acquisition module can acquire first video information inside the intelligent showcase in real time, and can acquire an image inside the showcase by image sampling based on the acquired first video information every first preset time; whether there is an article placed in the current intelligent showcase is identified based on the image inside the showcase acquired by image sampling; if there is an article placed, an article image of a target article displayed is acquired or the image inside the showcase is cut to obtain the article image of the target article displayed.

[0052] Please continue to refer to Figure 5 The second image acquisition module can acquire second video information in front of the intelligent showcase in real time, and can acquire an image in front of the showcase by image sampling based on the acquired second video information every second preset time; whether there is a person watching the showcase and the articles inside the showcase in front of the current intelligent showcase is identified based on the image in front of the showcase acquired by image sampling; if there is a person watching the showcase, a person image of a person watching the showcase is acquired or the image in front of the showcase is cut to obtain the person image of the person watching the showcase. The person image of the person watching the showcase further includes environmental information of the person watching the showcase in addition to the person image information.

[0053] S202, pre-processing the image information of the article to be displayed, and identifying the article main body contained in the pre-processed image information of the article to be displayed;

[0054] After obtaining the image information of the article to be displayed, the image information is first pre-processed. The image pre-processing steps include filtering and denoising, illumination correction, and image edge enhancement. The pre-processed image information of the article to be displayed is identified to obtain the article main body contained in the image information of the article to be displayed.

[0055] S203, identifying the article main body based on a multi-modal language model to generate a natural language description corresponding to the appearance of the article main body, and obtaining first text description information;

[0056] The article main body is identified based on a pre-trained multi-modal language model to obtain a natural language description corresponding to the appearance of the article main body. The multi-modal language model is trained to generate natural language description information of the article features, including appearance shape, article category, and article color, etc. according to the image of the article main body identified in the image. The first text description information obtained in this step is the appearance shape, article category, and article color, etc. information described in natural language form generated according to the article main body obtained in the foregoing step.

[0057] S204, pre-processing the image information of the person watching the showcase, and identifying the person main body contained in the pre-processed image information of the person;

[0058] S205: Identify the character subject based on the multimodal language model, generate a natural language description corresponding to the character characteristics of the character subject, and obtain second text description information;

[0059] In this embodiment, steps S204 and S205 are similar to steps S202 and S203 in the aforementioned embodiment, and similarly, the image information of the person viewing the window display is preprocessed to identify the subject of the person contained in the preprocessed image information of the person. The subject of the person is identified based on a pre-trained multimodal language model. In addition to the functions in S203, the multimodal language model is also configured to generate a natural language description of the characteristics of the person based on the image of the subject of the person, to generate a natural language description of the characteristics of the environment based on the environment in which the subject of the person is located, and other functions. In step S205, the second text description information of the characteristics of the subject of the person obtained by identifying the subject of the person based on the multimodal language model includes information such as the subject of the person's age, gender, and clothing style.

[0060] Furthermore, the second text description information described in this embodiment also includes a natural language description of the person's environment. When the second text description information also includes a natural language description of the person's environment, information about the environment currently viewing the window display is extracted simultaneously with the image information of the person viewing the window display, and a natural language description of the environment is generated based on this information.

[0061] S206: Invoke the aesthetic design model, combine the first text description information and the second text description information to perform background design reasoning, and obtain background prompt words;

[0062] After obtaining the first and second text description information, the first and second text description information are input into a pre-trained aesthetic design model. The aesthetic design model is constructed based on a deep learning algorithm and can specifically be a large unimodal or multimodal language model. The aesthetic design model is trained to perform design inference based on the first and second text description information of the text description, and is capable of inferring a more favorable window background design based on the characteristics of the items displayed in the window and the people viewing the window, and outputting background prompts for the window background design.

[0063] S207: Input the background prompt words into the image generation model, and based on the positional relationship between the first screen and the second screen, generate and display background images suitable for the first screen and the second screen respectively.

[0064] The image generation model may be a diffusion image generation model, which may generate a window background according to background prompt words, and display the window background on the first screen and the second screen.

[0065] In this embodiment, due to the positional relationship between the first screen and the second screen, the background displayed in the first screen and the second screen needs to be adjusted accordingly to show relevant but not identical images. Specifically, a pre-trained image generation model can be called to generate specific images. The image generation model can be based on a diffusion model and a low-rank adaptation (LoRA) model.

[0066] The image generation model is pre-trained, which can adjust the window background image generated by the image generation model based on the size ratio and the included angle information between the first screen and the second screen, and generate two background images of the first screen and the second screen that match each other.

[0067] In a preferred embodiment, the second screen can also be multiple, which can be located above and on the left and right sides of the target object, and each second screen and the first screen form a cuboid or a cubic storage space. In this embodiment, the low-rank adaptation model can adjust the brightness and stretching of the generated background image according to the positional relationship between each second screen and the first screen to obtain a better background image, and display the adjusted background image.

[0068] In a preferred embodiment, when the image information of the person viewing the window is obtained in step S204 and step S205, the position of the person in the image information is also identified to obtain the relative position of the person viewing the window and the window, including the relative distance and the line of sight height. Specifically, the position and area of the task in the image information can be identified to obtain the relative position. Then, when the image is adjusted in step S207, the image adjustment parameters of the first screen and each second screen image can be calculated according to the relative distance and the line of sight height, and the background image is adjusted and displayed based on the image adjustment parameters.

[0069] In a specific embodiment, please continue to refer to Figure 6In a specific workflow of a smart window, after the smart window begins operation, it receives a video signal through the image acquisition module and samples the video every 1 second. Based on the sampled image, it determines whether a person is lingering in front of the smart window. If a person is lingering, semantic recognition of the person and the environment is performed. If no one is lingering, the video signal continues to be sampled and processed. Simultaneously, the smart window can display items. In this embodiment, the sampling interval can be set based on the frequency of item replacement. Image acquisition is performed based on the set interval for sampling the item images, and semantic recognition of the items is performed. Based on the semantic recognition results of the person and the environment and the item, a program is called to generate a background image and transmit it to the screen for display. For specific steps, please refer to the contents of steps S201-S207 in this embodiment.

[0070] The method provided in the embodiments of the present invention enables a smart display window to intelligently adjust the display background based on the items on display and the audience viewing the items. This provides different backgrounds for displaying merchandise in different scenarios for different audiences, allowing the generated background to meet the preferences of different viewing groups. Overall, the display window can be more targeted to display the appearance styles that the current audience is most likely to be interested in, thereby increasing audience appeal. Furthermore, the generated display background can be adjusted based on the displayed items, ensuring a more balanced display effect. Furthermore, the background can be adjusted based on the positional relationship between the screens used to display the background and the audience's position, resulting in a more aesthetically pleasing display effect.

[0071] The above describes the method for displaying the background of items in a smart window according to an embodiment of the present invention. The following describes the system for displaying the background of items in a smart window according to an embodiment of the present invention. Figure 7 In one embodiment of the present invention, an item background display system for a smart window includes:

[0072] The image acquisition module 701 is used to acquire an image of the target item on display and an image of the person currently viewing the window display;

[0073] A first recognition module 702 is configured to recognize the collected image information of the object to be displayed and obtain first text description information of the appearance of the object to be displayed;

[0074] The second recognition module 703 is used to recognize the collected image information of the person viewing the window display and obtain second text description information of the person's characteristics;

[0075] The background generation module 704 is configured to generate a window background image based on the first text description information and the second text description information, and display the window background image.

[0076] The method provided in the embodiment of the present invention enables the smart window to intelligently adjust the display background according to the displayed items and the audience viewing the items. The generated display background is more closely matched with the displayed items and can meet the preferences of different viewing groups.

[0077] See also Figure 8 In another embodiment of the present application, the first recognition module 702 is specifically used to: preprocess the image information of the item to be displayed, and identify the object body contained in the preprocessed image information of the item to be displayed; identify the object body based on the multimodal language model, generate a natural language description corresponding to the appearance of the object body, and obtain first text description information.

[0078] In another embodiment of the present application, the second recognition module 703 is specifically used to: preprocess the image information of the person viewing the window display, and identify the character subject contained in the preprocessed character image information; identify the character subject based on the multimodal language model, generate a natural language description corresponding to the character characteristics of the character subject, and obtain second text description information.

[0079] In another embodiment of the present application, the display window includes a first screen and a second screen at an angle to the first screen; the background generation module 704 includes:

[0080] The image design unit 7041 is specifically configured to call an aesthetic design model, combine the first text description information and the second text description information to perform background design reasoning, and obtain background prompt words;

[0081] The image generation unit 7042 inputs the background prompt words into the image generation model, and based on the positional relationship between the first screen and the second screen, generates and displays background images suitable for the first screen and the second screen respectively.

[0082] In another embodiment of the present application, the image acquisition module 701 includes a first acquisition unit 7011, which is specifically used to: receive first video information inside the smart window, and perform image sampling on the first video information every first preset time; identify whether there are items placed in the current smart window based on the internal image of the window obtained by image sampling; if there are items placed, collect the item image of the target item on display.

[0083] In another embodiment of the present application, the image acquisition module 701 includes a second acquisition unit 7012, which is specifically used to: receive second video information in front of the smart window, and perform image sampling on the second video information every second preset time; identify whether there is someone currently viewing the window based on the image obtained by image sampling; if there is someone viewing the window, collect the image of the audience currently viewing the window.

[0084] In another embodiment of the present application, the image acquisition module 701 also includes a preset time adjustment unit, and the preset time adjustment unit 7013 is specifically used to: determine whether the items displayed in the smart window have been replaced; if replaced, record the replacement time of the items in the smart window; calculate the item replacement frequency based on the replacement time; and generate a first preset time based on the item replacement frequency.

[0085] In another embodiment of the present application, the image acquisition module 701 also includes a preset time adjustment unit, and the preset time adjustment unit 7013 is specifically used to: determine whether the audience viewing the smart window has changed; if changed, record the audience change time; calculate the audience change frequency based on the audience change time; and generate a second preset time based on the audience change frequency.

[0086] In another embodiment of the present application, the background generation module 704 also includes: an image adjustment unit 7043, which is specifically used to determine the viewing position of the current audience based on the character image of the audience currently viewing the window display; according to the viewing position and the angle information between the first screen and the second screen, the background images suitable for the first screen and the second screen are stretched and adjusted and then displayed.

[0087] For a detailed description of the item background display system for a smart window described in this embodiment, reference may be made to the contents of the aforementioned embodiment of the item background display method for a smart window.

[0088] The item background display system for smart display windows provided in embodiments of the present invention enables the smart display window to intelligently adjust the display background based on the items on display and the audience viewing the items. This provides different backgrounds for displaying merchandise in different scenarios for different audiences, allowing the generated background to meet the preferences of different viewing groups. Overall, the display window is more targeted at displaying the appearance styles that the current audience is most likely to be interested in, thereby increasing audience appeal. Furthermore, the generated display background can be adjusted based on the displayed items, ensuring a more consistent display effect with the displayed items. Furthermore, the background can be adjusted based on the positional relationship between the screens used to display the background and the audience's position, resulting in a more aesthetically pleasing display effect.

[0089] Based on the same inventive concept, an embodiment of this specification also provides a smart display window, which includes: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory to enable the smart display window to execute the steps of the object background display method for the smart display window described in the aforementioned embodiment.

[0090] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium is enabled to implement the above method of the present invention, that is: Figure 1 、 2 Or the method shown in 6.

[0091] accomplish Figure 1 、 2 The computer program of the method shown in or 6 can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable 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 thereof.

[0092] The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. The data signal propagated may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0093] The program code may be implemented in any of one or more programming languages, including object-oriented programming languages such as Java, C++, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0094] In light of the above, the present application can be implemented in hardware, or software run on one or more processors, or a combination thereof. Those skilled in the art should appreciate that the functions of some or all of the elements in the above-described embodiments can be carried out by one or more general-purpose data processors or a special-purpose computer, or by any other computing device capable of executing program code. The present application can also be implemented as a program product stored on a computer-readable medium, which can be read by a computer or other machine. Such a program product can be stored on a computer-readable medium, which can be any medium readable by a computer or other machine, including magnetic, semiconductor, optical, or other types of storage mediums.

[0095] In addition, the present application also provides a computer program product, comprising computer programs / instructions, which, when executed by a processor, implement the steps of the method for displaying an item background of an intelligent window as described in the foregoing embodiments.

[0096] The above-described embodiments are merely specific implementations of the present application, and are not intended to limit the purpose, technical solutions, and beneficial effects of the present application. It should be understood that the present application is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can implement the present application. The above-described embodiments are merely specific implementations of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0097] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0098] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for displaying item background in a smart window, characterized in that: include: Obtain an object image of the target object on display and obtain a person image of the audience currently viewing the window display; Identify the collected image information of the object to be displayed to obtain first text description information of the appearance of the object to be displayed; Recognizing the collected image information of the person viewing the window display to obtain second text description information of the person's characteristics; A window background image is generated based on the first text description information and the second text description information, and the window background image is displayed.

2. The method for displaying item background in a smart window according to claim 1, characterized in that: The step of identifying the collected image information of the object to be displayed to obtain first text description information of the appearance of the object to be displayed includes: Preprocessing the image information of the object to be displayed and identifying the object body contained in the preprocessed image information of the object to be displayed; The object body is identified based on a multimodal language model, and a natural language description corresponding to the appearance of the object body is generated to obtain first text description information.

3. The method for displaying item background in a smart window according to claim 1, characterized in that: The step of identifying the collected image information of the person viewing the window display to obtain the second text description information of the person's characteristics includes: Preprocessing image information of a person viewing a shop window, and identifying a person subject contained in the preprocessed image information of the person; The character subject is identified based on a multimodal language model, and a natural language description corresponding to the character characteristics of the character subject is generated to obtain second text description information.

4. The method for displaying item backgrounds in a smart window according to claim 1, wherein: The display window includes a first screen and a second screen that is at an angle to the first screen; Generating a window background image based on the first text description information and the second text description information, and displaying the window background image includes: Invoking an aesthetic design model, combining the first text description information and the second text description information to perform background design reasoning, and obtaining background prompt words; The background prompt words are input into an image generation model, and based on the positional relationship between the first screen and the second screen, background images suitable for the first screen and the second screen are generated and displayed respectively.

5. The method for displaying item background in a smart window according to claim 1, characterized in that: The acquiring of the displayed target item image includes: receiving first video information inside the smart window, and sampling images of the first video information at first preset time intervals; Based on the internal image of the window obtained by image sampling, it is determined whether there are items placed in the current smart window; If there are objects placed, an object image of the displayed target object is collected.

6. The method for displaying item backgrounds in a smart window according to claim 1, characterized in that: The step of obtaining the image of the person currently viewing the window display comprises: receiving second video information in front of the smart window, and sampling the second video information at a second preset time interval; Based on the image sampling, it is recognized whether there is someone viewing the window display at present; If someone is viewing the window display, an image of the person viewing the window display is collected.

7. An item background display system for a smart window, characterized in that: The item background display system for the smart window includes: An image acquisition module is used to acquire an image of the target item on display and an image of the person currently viewing the window display; a first recognition module, configured to recognize the collected image information of the object to be displayed and obtain first text description information of the appearance of the object to be displayed; A second recognition module is used to recognize the collected image information of the person viewing the window display and obtain second text description information of the person's characteristics; The background generation module is used to input the first text description information and the second text description information into the image generation model to generate a window background image, and display the window background image.

8. A smart display window for displaying objects in the background, characterized in that: The smart window includes: a memory and at least one processor, wherein the memory stores instructions; The at least one processor calls the instructions in the memory to enable the smart window device to execute the steps of the method for displaying item backgrounds in a smart window according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the program / instruction is executed by a processor, the steps of the method for displaying item backgrounds in a smart window as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method for displaying item backgrounds in a smart window according to any one of claims 1 to 6 are implemented.

Images