Desktop background automatic generation method and system based on screen projection image recognition

Abstract

The invention discloses a desktop background automatic generation method and system based on projection screen image recognition, and the method comprises the steps: receiving a projection screen image transmitted by a transmitting end, and recognizing image elements in the projection screen image through an AI image recognition technology; replacing the same type of elements in the current wallpaper according to an identification result, or performing element creation according to the screen projection image; returning the image after the elements of the same type are replaced or a new image after element creation and element parameters to the sending end through a screen projection system, so as to carry out element adjustment or parameter adjustment at the sending end; and receiving the adjusted element or the adjusted parameter fed back by the sending end, and regenerating and displaying a corresponding image. According to the invention, content creation of desktop wallpaper and same-position material switching of similar elements are realized, and rich customizable desktop wallpaper materials are provided for users.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method and system for automatically generating a desktop background based on projection image recognition. Background Art

[0002] With the advancement of science and technology, desktop wallpaper applications for electronic devices such as smart TVs and smart phones have provided users with very rich materials. Users can select pictures from the theme mall or local storage according to the application scenario requirements, and then select and switch desktop wallpapers.

[0003] Although the demand for desktop wallpapers has been met in terms of diversity, there is still room for improvement in the customizability of desktop wallpapers (especially in terms of desktop wallpaper content creation and element switching for large-screen devices); for example, smart TVs cannot select pictures from local storage and replace wallpapers, and usually, the local storage of users' smart TVs does not store images such as photos; therefore, the desktop wallpapers of smart TVs are synchronized to the local storage of the TV through technical means such as network disk downloads and mobile phone transmissions, and then the desktop wallpapers that users want can be set; obviously, this way of setting desktop wallpapers for smart TVs can no longer meet the functional requirements of diversity and customization. How to create desktop wallpaper content and switch between materials of the same type of elements in the same location on the desktop that smart TV users have already set has become an urgently needed technology for smart TV desktop wallpapers.

[0004] Therefore, the prior art needs to be improved. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in view of the defects of the prior art, the present invention provides a method and system for automatically generating desktop backgrounds based on projection image recognition, so as to solve the problem that the existing desktop wallpaper setting method of smart devices cannot realize content creation and material switching.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows:

[0007] In a first aspect, the present invention provides a method for automatically generating a desktop background based on projection image recognition, comprising:

[0008] Receive the projection image sent by the sender, and identify the image elements in the projection image through AI image recognition technology;

[0009] Replace the same type of elements in the current wallpaper according to the recognition result, or create elements according to the projected image;

[0010] The image after the replacement of the same type of elements or the new image after the elements are created and the element parameters are returned to the sending end through the projection system, so as to adjust the elements or parameters at the sending end;

[0011] The adjusted elements or adjusted parameters fed back by the sending end are received, and the corresponding images are regenerated and displayed.

[0012] In one implementation, the receiving the projection image sent by the transmitting end and identifying the image elements in the projection image by using AI image recognition technology includes:

[0013] Receiving the projection image sent by the sending end;

[0014] The co-located elements and creative elements of the projected image are analyzed through the AI ​​image big model to obtain the recognition results of the co-located elements and the recognition results of the creative elements.

[0015] In one implementation, the co-located elements include: one or a combination of architectural elements, human elements, clothing elements, object elements, plant elements, animal elements, mountain elements, and water elements of the image;

[0016] The creative elements include: one or a combination of theme elements, style elements, color matching elements and concept elements.

[0017] In one implementation, replacing the same type of elements in the current wallpaper according to the recognition result includes:

[0018] According to the recognition result of the same-position elements, the same elements as the current wallpaper are obtained from the projection image;

[0019] The acquired elements are replaced to the corresponding positions in the current wallpaper, and an image containing the acquired elements is regenerated through the AI ​​image model in combination with other materials in the projected image to obtain an image after the elements of the same type are replaced.

[0020] In one implementation, the creating an element according to the projected image includes:

[0021] Determining comprehensive attributes of an image element set according to the recognition results of the creative elements of the projection image;

[0022] According to the comprehensive attributes, the AI ​​image model is used to generate images of different creative styles and AI elements, and the new image after the element creation and the corresponding element parameters are obtained.

[0023] In one implementation, the receiving the adjusted element or the adjusted parameter fed back by the sending end, and regenerating and displaying the corresponding image includes:

[0024] Regenerate an image with adjusted elements using the AI ​​image macro model according to the adjusted co-location elements fed back by the sending end;

[0025] The image after the elements are adjusted is displayed, and the image after the elements are adjusted is sent to the sending end through a screen projection data link so as to be synchronously presented at the sending end.

[0026] In one implementation, the receiving the adjusted element or the adjusted parameter fed back by the sending end, and regenerating and displaying the corresponding image, further includes:

[0027] Regenerate an image with adjusted element parameters using the AI ​​image large model according to the adjusted element parameters fed back by the sending end;

[0028] The image after adjusting the element parameters is displayed, and the image after adjusting the element parameters is sent to the sending end through the screen projection data link so as to be synchronously presented at the sending end.

[0029] In a second aspect, the present invention provides a system for automatically generating a desktop background based on projection image recognition, comprising:

[0030] An AI image recognition module is used to receive the projection image sent by the sending end, and identify the image elements in the projection image through AI image recognition technology;

[0031] An element replacement and creation module, used to replace the same type of elements in the current wallpaper according to the recognition results, or to create elements according to the projection image;

[0032] An image return module, used to return the image after the same type of element is replaced or the new image after the element is created and the element parameters to the sending end through the projection system, so as to adjust the elements or parameters at the sending end;

[0033] The image display module is used to receive the adjusted elements or adjusted parameters fed back by the sending end, and regenerate and display the corresponding image.

[0034] In a third aspect, the present invention provides a terminal, comprising: a processor and a memory, wherein the memory stores a program for automatically generating a desktop background based on projection image recognition, and when the program for automatically generating a desktop background based on projection image recognition is executed by the processor, it is used to implement the operation of the method for automatically generating a desktop background based on projection image recognition as described in the first aspect.

[0035] In a fourth aspect, the present invention further provides a medium, which is a computer-readable storage medium, and which stores a program for automatically generating a desktop background based on projection image recognition. When the program for automatically generating a desktop background based on projection image recognition is executed by a processor, it is used to implement the operation of the method for automatically generating a desktop background based on projection image recognition as described in the first aspect.

[0036] The present invention adopts the above technical solution to achieve the following effects:

[0037] The present invention uses AI image recognition technology to identify image elements in the projection image, and can replace the same type of elements in the current wallpaper according to the recognition results, or create elements according to the projection image; thereby returning the image after the replacement of the same type of elements or the new image and element parameters after the element creation to the sending end through the projection system, so as to adjust the elements or parameters at the sending end; and, by receiving the adjusted elements or adjusted parameters fed back by the sending end, the corresponding image can be regenerated and displayed. The present invention realizes the content creation of desktop wallpapers and the switching of the same type of elements in the same position, providing users with rich and customizable desktop wallpaper materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0039] Figure 1 It is a flow chart of the method for automatically generating desktop background based on projection image recognition in the present invention.

[0040] Figure 2 It is an interactive diagram of the method for automatically generating desktop background based on projection image recognition in the present invention.

[0041] Figure 3 It is an overall flow chart of the method for automatically generating desktop background based on projection image recognition in the present invention.

[0042] Figure 4 It is a functional principle diagram of a terminal in one implementation of the present invention.

[0043] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0045] Exemplary Methods

[0046] The existing desktop wallpapers of smart TVs are synchronized to the local storage of the TV through technical means such as network disk downloading and mobile phone transmission, and then the desktop wallpaper that the user wants can be set; obviously, this way of setting the desktop wallpaper of smart TVs can no longer meet the diverse and customizable functional requirements. How to create desktop wallpaper content and switch the same-position materials of similar elements on the desktop that the smart TV user has set has become an urgently needed technology for the current smart TV desktop wallpaper.

[0047] In response to the above technical problems, an embodiment of the present invention provides a method for automatically generating a desktop background based on projection image recognition. The method uses AI image recognition technology to identify image elements in the projection image, and can replace the same type of elements in the current wallpaper according to the recognition results, or create elements according to the projection image; thereby returning the image after the replacement of the same type of elements or the new image and element parameters after the element creation to the sending end through the projection system, so as to adjust the elements or parameters at the sending end; and, by receiving the adjusted elements or adjusted parameters fed back by the sending end, the corresponding image can be regenerated and displayed. The embodiment of the present invention realizes the content creation of desktop wallpapers and the switching of the same type of elements in the same position, providing users with rich and customizable desktop wallpaper materials.

[0048] like Figure 1 As shown, an embodiment of the present invention provides a method for automatically generating a desktop background based on projection image recognition, comprising the following steps:

[0049] Step S100, receiving the projection image sent by the sending end, and identifying the image elements in the projection image through AI image recognition technology.

[0050] In this embodiment, the method for automatically generating a desktop background based on projection image recognition is implemented based on a system for automatically generating a desktop background based on projection image recognition provided in this embodiment; Figure 2 As shown, the system in this embodiment includes at least one smart TV and one smart phone; wherein, the smart TV and the smart phone project screens through a projection data link, the smart TV can serve as a receiving end of the projection data (i.e., the projection image selected by the user), and the smart phone serves as a sending end of the projection data (i.e., the projection image selected by the user).

[0051] In this embodiment, after the smart TV is turned on, the desktop system of the smart TV and the screen projection protocol will be loaded; thereafter, the user can enter the theme application store of the smart TV to download online wallpapers or built-in wallpapers of the theme and set them as the desktop wallpaper of the smart TV; or select images stored locally on the smart TV and set them as the desktop wallpaper of the smart TV. After setting the desktop wallpaper of the smart TV, if the user does not like these desktop wallpapers, the user can select the AI ​​wallpaper setting module through the system setting option of the smart TV to turn on the screen projection wallpaper generation function.

[0052] As an example, in this embodiment, when the switch of the AI ​​wallpaper setting module is on, the screen projection system of the smart TV is automatically started. At this time, the AI ​​image big model running in the smart TV is in working state. The AI ​​image big model can be used to perform AI image analysis on the current smart TV desktop wallpaper, and generate an image based on the results of the AI ​​image analysis. Of course, in another implementation method of this embodiment, the AI ​​image big model can also run in the cloud, and the AI ​​image big model in the cloud can be used to perform AI image analysis on the current smart TV desktop wallpaper, and generate an image based on the results of the AI ​​image analysis, and send the generated image to the smart TV.

[0053] As an example, in this embodiment, when the switch of the AI ​​wallpaper setting module is on, the image elements of the current smart TV desktop wallpaper can be analyzed by the AI ​​image recognition function of the AI ​​image large model to obtain the analysis results of the image elements corresponding to the current smart TV desktop wallpaper; wherein, the image elements corresponding to the current smart TV desktop wallpaper include co-location elements and creative elements, and the co-location elements are the content data of the image, including the image's architecture, characters, clothing, objects, plants, animals, mountains, water and other elements; the creative elements are the creation information of the image, including: themes, styles, colors, concepts and other elements.

[0054] When analyzing the image elements of the current smart TV desktop wallpaper, if the current desktop wallpaper is a theme wallpaper from the theme mall and the image elements have been analyzed, the image elements can be directly obtained from the database corresponding to the theme mall. If the image element database of the image wallpaper does not have relevant data, when the switch is turned on, the AI ​​image recognition function is called for automatic analysis, and the analysis results (i.e., image elements) are stored in the database of the AI ​​wallpaper setting module.

[0055] In this embodiment, after the user enters the setting interface of the AI ​​wallpaper setting module of the smart TV, the user can set the on / off state of the AI ​​wallpaper setting function. At the same time, the corresponding opening prompt information is presented in the setting interface of the AI ​​wallpaper setting module, and the connection and data transmission QR code of the corresponding projection system is displayed; for example, the user is reminded to "Scan the QR code below to create AI wallpapers!" and the corresponding QR code is displayed; thereafter, the user scans the QR code through the mobile phone to establish a connection with the TV projection system (i.e., AI wallpaper creation on the mobile phone), and can obtain the operation instructions for AI wallpaper settings on the mobile phone.

[0056] Specifically, in an implementation of this embodiment, step S100 includes the following steps:

[0057] Step S101, receiving the projection image sent by the sending end;

[0058] Step S102, analyzing the co-located elements and creative elements of the projection image through the AI ​​image macro model to obtain recognition results of the co-located elements and recognition results of the creative elements.

[0059] In this embodiment, after setting the desktop wallpaper of the smart TV and completing the corresponding operations of the AI ​​wallpaper setting interface of the smart TV, the user can use the screen projection function of the smart phone to select one or more images (for example, landscape images, architectural images, character images, animal images) as replacement elements or creative materials of the current smart TV desktop wallpaper and project them to the smart TV system; for example, the user can select one or more images and project them to the TV at one time or multiple times through the projection interface of the AI ​​wallpaper setting on the mobile phone. Moreover, the user can add, delete, replace, and other operations on the projected images in the projection interface of the AI ​​wallpaper setting on the mobile phone.

[0060] As an example, the user selects an image on the screen projection interface of the mobile phone, for example, the user selects two user photos (image person 1, image person 2), and two landscape photos (image 3-landscape painting, image 4-architectural painting); then, the user selects the screen projection function on the mobile phone, and the image can be transmitted to the screen projection system of the smart TV through the screen projection protocol; the TV screen projection system obtains the image, and performs the same-position element analysis on the transmitted image through the AI ​​image recognition function of the AI ​​image large model: for example, analyzing the wallpaper name-element group:

[0061] 1) Element 1 (person 1) - element tag; for example, person attributes (such as face tag data, used for face recognition), male, age, element position (coordinate area on the image), etc.;

[0062] 2) Element 2 (mountain) - element marker; for example, steep, tall and graceful, surrounded by clouds and mist, etc.;

[0063] 3) Element 3 - element tag;

[0064] 4) Analysis of creative elements; for example, creative elements, creative style (such as realistic style), color matching (such as bright colors), conception (such as leisurely and comfortable), etc.

[0065] It can be understood that in this embodiment, the AI ​​image recognition function of the smart TV system performs composition recognition, scene recognition, style recognition and face recognition (AI image recognition elements) on the received image (i.e., the projected image) to obtain the recognition result corresponding to the projected image, that is, the analysis result of the image element corresponding to the projected image is obtained; wherein, the image elements corresponding to the projected image include co-location elements and creative elements, and the co-location elements are the content data of the image, including the image's architecture, characters, clothing, objects, plants, animals, mountains, water and other elements; the creative elements are the creation information of the image, including: themes, styles, colors, concepts and other elements.

[0066] like Figure 1 As shown, an embodiment of the present invention provides a method for automatically generating a desktop background based on projection image recognition, comprising the following steps:

[0067] Step S200, replacing the same type of elements in the current wallpaper according to the recognition result, or creating elements according to the projected image.

[0068] In this embodiment, after obtaining the analysis results of the image elements corresponding to the current smart TV desktop wallpaper and the analysis results of the image elements corresponding to the projected image respectively, according to the user's selection on the smart phone, the same-type element generation scheme is executed (that is, replacing the same type of elements of the current smart TV desktop wallpaper) to generate the wallpaper after the elements are replaced; or the AI ​​image creation scheme is executed (that is, the creation element, generating a new desktop wallpaper according to the projected image) to directly generate the wallpaper.

[0069] Specifically, in an implementation of this embodiment, in step S200, replacing the same type of elements in the current wallpaper according to the recognition result (i.e., a scheme for generating the same type of elements) includes the following steps:

[0070] Step S201, according to the recognition result of the same-position elements, obtaining the same elements as the current wallpaper from the projection image;

[0071] Step S202, replace the acquired element to the corresponding position in the current wallpaper, and regenerate an image containing the acquired element by combining the AI ​​image model with other materials in the projected image to obtain the image after the same type of element is replaced.

[0072] In this embodiment, the user can select the AI ​​same-position element replacement scheme in the AI ​​wallpaper creation interface on the mobile phone, that is, according to the image selected by the user, after AI image recognition, the same type of elements are replaced with the same type of elements of the current smart TV desktop wallpaper, and then AI image generation is performed. That is, a set of wallpapers is generated by the AI ​​image of the specified image element, and the same type of elements replace the elements of the current smart TV desktop wallpaper; or select the AI ​​wallpaper generation scheme, that is, according to the comprehensive attributes of the element set after the element analysis corresponding to the image projected to the TV (that is, a set of wallpapers is generated based on the creative elements of multiple images), the creative style + AI element is used to generate AI images, without considering the image element attributes of the current wallpaper.

[0073] As an example, in the AI ​​same-place element replacement scheme of this embodiment, by analyzing the image elements projected by the user and the image elements of the current smart TV desktop wallpaper, the same-place elements of the two are determined, and the same-place element replacement can be performed; for example, the intersection of the element set of the current wallpaper and the element set of the image projected to the TV end is obtained. If the character attribute of element 1 of the current wallpaper and the person of the image character 1 projected to the TV end are the same person, but the creative style is different, it is regarded as a same-place element. Therefore, the image element of the projected screen is used as a replacement element to replace the element material of the current wallpaper. Simply put, if the current wallpaper has three people A, B, and C, if the user projects photos of A, B, and C to the TV, the photos of A, B, and C projected on the screen are used as materials to replace the images of the image areas of A, B, and C of the current wallpaper. In addition, a wallpaper containing the photos of A, B, and C projected on the screen as materials is regenerated through the AI ​​image large model combined with other material elements of the projected screen, that is, the image after the replacement of the same type of elements is obtained.

[0074] Specifically, in an implementation of this embodiment, in step S200, element creation (i.e., AI image creation solution) is performed according to the projection image, including the following steps:

[0075] Step S203, determining the comprehensive attributes of the image element set according to the recognition result of the creative elements of the projection image;

[0076] Step S204, based on the comprehensive attributes, use the AI ​​image model to generate images of different creative styles and AI elements, and obtain new images after the element creation and corresponding element parameters.

[0077] In this embodiment, if the user does not need to replace the same-position elements of the current wallpaper, AI wallpaper creation is performed based on the creative elements of the projection wallpaper, and the wallpaper generated by the AI ​​image and the element parameter options generated by the AI ​​image are returned to the mobile phone through the projection link.

[0078] like Figure 1 As shown, an embodiment of the present invention provides a method for automatically generating a desktop background based on projection image recognition, comprising the following steps:

[0079] Step S300, returning the image after the same type of element is replaced or the new image after the element is created and the element parameters to the sending end through the screen projection system, so as to adjust the elements or parameters at the sending end;

[0080] Step S400: receiving the adjusted elements or adjusted parameters fed back by the sending end, and regenerating and displaying the corresponding image.

[0081] Specifically, in an implementation of this embodiment, step S400 includes the following steps:

[0082] Step S401, regenerating an image after adjusting the elements using an AI image macro model according to the adjusted co-location elements fed back by the sending end;

[0083] Step S402, displaying the image after adjusting the elements, and sending the image after adjusting the elements to the sending end through the screen projection data link, so as to be synchronously presented at the sending end.

[0084] In this embodiment, after executing the isotope generation scheme, the AI ​​image large model can generate multiple sets of creative wallpapers with isotope replacement according to the data parameters of AI image recognition. At the same time, the AI ​​image recognition parameters and the corresponding wallpapers are returned to the smart TV and mobile phone AI wallpaper creation interface for users to adjust parameters and select wallpapers. The wallpaper corresponding to the image large model generation scheme is used, and the isotope replacement scheme and the generated wallpaper are returned to the mobile phone through the screen projection system.

[0085] Furthermore, after the same-type element replacement plan and the generated wallpaper are returned to the mobile phone through the screen projection system, the user can judge whether it meets the user's needs in the AI ​​wallpaper creation interface on the mobile phone. If it meets the user's needs, an image replaced with a certain element of the same type is selected as the desktop wallpaper, and it is set to the desktop wallpaper through the TV system, and the AI ​​image recognition data is saved in the database of the AI ​​wallpaper setting module.

[0086] Furthermore, after the co-location element replacement scheme and the generated wallpaper are returned to the mobile phone through the screen projection system, if there is no image that meets the user's needs in the wallpapers created by the AI ​​large model in this batch of returned images, the user can adjust the co-location replacement element or reselect the image for screen projection. After that, according to the co-location replacement element adjusted by the user or the reselected image, the TV end sends it to the image large model to regenerate the wallpaper of the corresponding scheme, and presents it on the mobile phone through the screen projection data link for the user to reselect.

[0087] In this embodiment, the AI ​​wallpaper setting module adjusts the same-position replacement elements according to the user's selection, and sends the image elements or images to the TV end, which sends them to the image model to regenerate the wallpaper of the corresponding scheme, and presents it on the mobile phone end through the screen projection data link.

[0088] Specifically, in an implementation of this embodiment, step S400 includes the following steps:

[0089] Step S403, regenerating an image with adjusted element parameters using the AI ​​image large model according to the adjusted element parameters fed back by the sending end;

[0090] Step S404, displaying the image after adjusting the element parameters, and sending the image after adjusting the element parameters to the sending end through the screen projection data link, so as to be synchronously presented at the sending end.

[0091] In this embodiment, in the AI ​​image creation scheme, after the wallpaper generated by the AI ​​image and the element parameter options generated by the AI ​​image are returned to the mobile phone through the projection link. If the returned wallpaper meets the user's needs, a certain wallpaper is selected to be set as the desktop wallpaper. If the wallpaper generated by the AI ​​image does not meet the user's needs, the user can adjust the creation elements or reselect the image projection. The AI ​​wallpaper setting module sends the image element parameters or the new projection image to the TV end according to the element creation parameters adjusted by the user, and the TV end sends it to the image model to regenerate the wallpaper of the corresponding scheme, and presents it on the mobile phone through the projection data link for the user to reselect.

[0092] like Figure 3 As shown, as an example, in this embodiment, the overall process of the method for automatically generating a desktop background based on projection image recognition includes the following steps:

[0093] S11, the smart TV is turned on, the desktop system is loaded, and the screen projection protocol is added;

[0094] S12, the user sets the desktop wallpaper of the smart TV;

[0095] S13, entering the AI ​​wallpaper setting module of the smart TV and turning on the screen projection wallpaper generation function; when the screen projection wallpaper generation function is turned on, the screen projection system is started, the AI ​​image recognition is started, and the AI ​​image generation is started; and through the AI ​​image recognition, the element information of the current wallpaper is obtained;

[0096] S14, the user starts the screen projection protocol on the mobile phone, connects to the smart TV, and selects a picture for screen projection;

[0097] S15, the smart TV obtains the picture transmitted by the screen projection system and analyzes the elements of the picture through AI image recognition;

[0098] In this embodiment, after the smart TV has completed setting the desktop wallpaper, the user can use the mobile phone to project the screen to send one or more selected pictures as replacement elements of the current desktop wallpaper to the smart TV system; the AI ​​image recognition of the smart TV system recognizes the received image, and executes the same-type element generation scheme according to the recognized image elements (that is, replaces the same type of elements of the current wallpaper) to generate the wallpaper after the elements are replaced; or executes the AI ​​image creation scheme (that is, the creation element, generates a new desktop wallpaper according to the projected image) to directly generate the wallpaper.

[0099] As an example, in this embodiment, the AI ​​image generation homonymous element replacement scheme includes the following steps:

[0100] S21, the smart TV executes the AI ​​image generation same-position element replacement algorithm;

[0101] S22, analyzing the co-located elements of the image elements projected by the user and the current wallpaper elements through the AI ​​image generation module;

[0102] S23, generating a replacement scheme for the same element, and generating a wallpaper corresponding to the scheme through the AI ​​image large model;

[0103] S24, AI image generation;

[0104] S25, returning the isotope element replacement scheme and the generated wallpaper to the mobile phone through the screen projection system;

[0105] S26, determine whether it meets the user's needs; if yes, execute step S27; if no, execute step S28;

[0106] S27, select a wallpaper and set it as the desktop wallpaper of the smart TV;

[0107] S28, the user adjusts the co-located replacement element or reselects the picture to be projected;

[0108] S29, according to the same-position replacement elements adjusted by the user, the image elements or images are sent to the smart TV end, and the smart TV end sends them to the AI ​​image model to regenerate the wallpaper of the corresponding solution, and presents it on the mobile phone end through the screen projection data link.

[0109] In the AI ​​image generation isotope replacement scheme of steps S21 to S29 above, after the isotope replacement scheme and the generated wallpaper are returned to the mobile phone through the screen projection system, the user can adjust the desktop wallpaper generation elements (for example, only replace the face, only replace the background, replace the face and background at the same time, re-create the background image based on the face and the scene, etc.).

[0110] While returning the image to the mobile phone through the screen projection system, the corresponding image result can also be generated in the smart TV system (for example, the AI ​​image generation module), and the AI ​​image recognition element of the co-location element generation scheme can be marked on the image result; thereafter, the user can adjust the AI ​​image recognition element on the mobile phone and return the adjusted AI image recognition element to the TV AI image generation module, which recomposes and presents the image based on the received AI image recognition element; during this process, the user can replace or reselect the picture on the mobile phone for re-screen projection and replace local element materials.

[0111] As an example, in this embodiment, the AI ​​image creation solution includes the following steps:

[0112] S31, the smart TV analyzes image elements according to the AI ​​image recognition result of the projection image, and generates an AI image;

[0113] S32, AI image generation;

[0114] S33, returning the wallpaper generated by the AI ​​image and the element parameter options generated by the AI ​​image to the mobile phone through the screen projection link;

[0115] S34, determine whether it meets the user's needs; if yes, execute step S35; if no, execute step S36;

[0116] S35, select a wallpaper and set it as the desktop wallpaper of the smart TV;

[0117] S36, the user adjusts the image generation element parameter options or reselects the picture to be projected;

[0118] S37, according to the element parameters adjusted by the user, the image element parameters or the projection screen image are sent to the TV end, and the TV end sends it to the image model to regenerate the wallpaper of the corresponding solution, and presents it on the mobile phone end through the projection screen data link.

[0119] In the AI ​​image creation scheme of steps S31 to S37 above, if there is no wallpaper that meets the user's needs among the wallpapers created by the returned AI large model, the user can adjust the element parameters or reselect the picture for screen projection. Then, the smart TV sends the wallpaper to the image large model to regenerate the wallpaper of the corresponding scheme, and presents it on the mobile phone through the screen projection data link for the user to reselect.

[0120] This embodiment achieves the following technical effects through the above technical solution:

[0121] This embodiment uses AI image recognition technology to identify image elements in the projection image, and can replace the same type of elements in the current wallpaper according to the recognition results, or create elements according to the projection image; thereby returning the image after the replacement of the same type of elements or the new image and element parameters after the element creation to the sending end through the projection system, so that the element adjustment or parameter adjustment can be performed at the sending end; and by receiving the adjusted elements or adjusted parameters fed back by the sending end, the corresponding image can be regenerated and displayed. This embodiment realizes the content creation of desktop wallpapers and the switching of the same type of elements in the same position, providing users with rich and customizable desktop wallpaper materials.

[0122] Exemplary Devices

[0123] Based on the above embodiments, the present invention further provides a system for automatically generating a desktop background based on projection image recognition, comprising:

[0124] An AI image recognition module is used to receive the projection image sent by the sending end, and identify the image elements in the projection image through AI image recognition technology;

[0125] An element replacement and creation module, used to replace the same type of elements in the current wallpaper according to the recognition results, or to create elements according to the projection image;

[0126] An image return module, used to return the image after the same type of element is replaced or the new image after the element is created and the element parameters to the sending end through the projection system, so as to adjust the elements or parameters at the sending end;

[0127] The image display module is used to receive the adjusted elements or adjusted parameters fed back by the sending end, and regenerate and display the corresponding image.

[0128] In one implementation, the AI ​​image recognition module includes:

[0129] A screen projection image receiving unit, used to receive the screen projection image sent by the sending end;

[0130] The image element recognition unit is used to analyze the co-located elements and creative elements of the projected image through the AI ​​image big model to obtain the recognition results of the co-located elements and the recognition results of the creative elements.

[0131] In one implementation, the element replacement and creation module includes:

[0132] The same element acquisition unit is used to acquire the same element as the current wallpaper from the projection image according to the recognition result of the same-position element;

[0133] An image element replacement unit, used to replace the acquired element to a corresponding position in the current wallpaper, and regenerate an image containing the acquired element by combining the AI ​​image large model with other materials in the projection image to obtain the image after the same type of element is replaced;

[0134] A comprehensive attribute determination unit, configured to determine the comprehensive attributes of the image element set according to the recognition result of the creative elements of the projection image;

[0135] The image element creation unit is used to generate images of different creative styles and AI elements using the AI ​​image model according to the comprehensive attributes, and obtain the new image after the element creation and the corresponding element parameters.

[0136] In one implementation, the image display module includes:

[0137] A first image regeneration unit, configured to regenerate an image with adjusted elements by using an AI image macro model according to the adjusted co-location elements fed back by the sending end;

[0138] A first display and synchronization unit, configured to display the image after the elements are adjusted, and send the image after the elements are adjusted to the sending end through a screen projection data link, so as to be synchronously presented at the sending end;

[0139] A second image regeneration unit, configured to regenerate an image with adjusted element parameters by using an AI image macro model according to the adjusted element parameters fed back by the sending end;

[0140] The second display and synchronization unit is used to display the image after adjusting the element parameters, and send the image after adjusting the element parameters to the sending end through the screen projection data link so as to be synchronously presented at the sending end.

[0141] This embodiment achieves the following technical effects through the above technical solution:

[0142] This embodiment uses AI image recognition technology to identify image elements in the projection image, and can replace the same type of elements in the current wallpaper according to the recognition results, or create elements according to the projection image; thereby returning the image after the replacement of the same type of elements or the new image and element parameters after the element creation to the sending end through the projection system, so that the element adjustment or parameter adjustment can be performed at the sending end; and by receiving the adjusted elements or adjusted parameters fed back by the sending end, the corresponding image can be regenerated and displayed. This embodiment realizes the content creation of desktop wallpapers and the switching of the same type of elements in the same position, providing users with rich and customizable desktop wallpaper materials.

[0143] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be as follows: Figure 4shown.

[0144] The terminal includes: a processor, a memory, an interface, a display screen and a communication module connected through a system bus; wherein the processor of the terminal is used to provide computing and control capabilities; the memory of the terminal includes a storage medium and an internal memory; the storage medium stores an operating system and a computer program; the internal memory provides an environment for the operation of the operating system and the computer program in the storage medium; the interface is used to connect to external devices; the display screen is used to display corresponding information; and the communication module is used to communicate with a cloud server or other devices.

[0145] When the computer program is executed by a processor, it is used to implement the operation of a method for automatically generating a desktop background based on projection image recognition.

[0146] It can be understood by those skilled in the art that Figure 4 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0147] In one embodiment, a terminal is provided, which includes: a processor and a memory, the memory storing a program for automatically generating a desktop background based on projection image recognition, and the program for automatically generating a desktop background based on projection image recognition is used to implement the operation of the above-mentioned method for automatically generating a desktop background based on projection image recognition when the program is executed by the processor.

[0148] In one embodiment, a storage medium is provided, wherein the storage medium stores a program for automatically generating a desktop background based on projection image recognition, and when the program for automatically generating a desktop background based on projection image recognition is executed by a processor, it is used to implement the operation of the method for automatically generating a desktop background based on projection image recognition as described above.

[0149] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and volatile memory.

[0150] In summary, the present invention provides a method and system for automatically generating a desktop background based on projection image recognition, including: receiving a projection image sent by a sending end, and identifying image elements in the projection image through AI image recognition technology; replacing the same type of elements in the current wallpaper according to the recognition result, or creating elements according to the projection image; returning the image after the replacement of the same type of elements or the new image and element parameters after the element creation to the sending end through the projection system, so as to adjust the elements or parameters at the sending end; receiving the adjusted elements or adjusted parameters fed back by the sending end, and regenerating and displaying the corresponding image. The present invention realizes the content creation of desktop wallpapers and the switching of the same type of elements in the same position, providing users with rich and customizable desktop wallpaper materials.

[0151] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for automatically generating a desktop background based on projection image recognition, characterized in that: include: Receive the projection image sent by the sender, and identify the image elements in the projection image through AI image recognition technology; Replace the same type of elements in the current wallpaper according to the recognition result, or create elements according to the projected image; The image after the replacement of the same type of elements or the new image after the elements are created and the element parameters are returned to the sending end through the projection system, so as to adjust the elements or parameters at the sending end; The adjusted elements or adjusted parameters fed back by the sending end are received, and the corresponding images are regenerated and displayed.

2. The method for automatically generating a desktop background based on projection image recognition according to claim 1, characterized in that: The receiving the projection image sent by the transmitting end and identifying the image elements in the projection image by using the AI ​​image recognition technology includes: Receiving the projection image sent by the sending end; The co-located elements and creative elements of the projected image are analyzed through the AI ​​image big model to obtain the recognition results of the co-located elements and the recognition results of the creative elements.

3. The method for automatically generating a desktop background based on projection image recognition according to claim 2, characterized in that: The homonymous elements include: one or a combination of architectural elements, human elements, clothing elements, object elements, plant elements, animal elements, mountain elements and water elements of the image; The creative elements include: one or a combination of theme elements, style elements, color matching elements and concept elements.

4. The method for automatically generating a desktop background based on projection image recognition according to claim 1, characterized in that: The replacing the same type of elements in the current wallpaper according to the recognition result includes: According to the recognition result of the same-position elements, the same elements as the current wallpaper are obtained from the projection image; The acquired elements are replaced to the corresponding positions in the current wallpaper, and an image containing the acquired elements is regenerated through the AI ​​image model in combination with other materials in the projected image to obtain an image after the elements of the same type are replaced.

5. The method for automatically generating desktop background based on projection image recognition according to claim 1, characterized in that: The creating of elements according to the projected image includes: Determining comprehensive attributes of an image element set according to the recognition results of the creative elements of the projection image; According to the comprehensive attributes, the AI ​​image model is used to generate images of different creative styles and AI elements, and the new image after the element creation and the corresponding element parameters are obtained.

6. The method for automatically generating a desktop background based on projection image recognition according to claim 1, characterized in that: The receiving the adjusted element or the adjusted parameter fed back by the sending end, and regenerating and displaying the corresponding image, includes: Regenerate an image with adjusted elements using the AI ​​image macro model according to the adjusted co-location elements fed back by the sending end; The image after the elements are adjusted is displayed, and the image after the elements are adjusted is sent to the sending end through a screen projection data link so as to be synchronously presented at the sending end.

7. The method for automatically generating a desktop background based on projection image recognition according to claim 1, characterized in that: The receiving the adjusted elements or adjusted parameters fed back by the sending end, and regenerating and displaying the corresponding image, further includes: Regenerate an image with adjusted element parameters using the AI ​​image large model according to the adjusted element parameters fed back by the sending end; The image after adjusting the element parameters is displayed, and the image after adjusting the element parameters is sent to the sending end through the screen projection data link so as to be synchronously presented at the sending end.

8. A desktop background automatic generation system based on projection image recognition, characterized in that: include: An AI image recognition module is used to receive the projection image sent by the sending end, and identify the image elements in the projection image through AI image recognition technology; An element replacement and creation module, used to replace the same type of elements in the current wallpaper according to the recognition results, or to create elements according to the projection image; An image return module, used to return the image after the same type of element is replaced or the new image after the element is created and the element parameters to the sending end through the projection system, so as to adjust the elements or parameters at the sending end; The image display module is used to receive the adjusted elements or adjusted parameters fed back by the sending end, and regenerate and display the corresponding image.

9. A terminal, characterized in that: include: A processor and a memory, wherein the memory stores a program for automatically generating a desktop background based on projection image recognition, and when the program for automatically generating a desktop background based on projection image recognition is executed by the processor, it is used to implement the operation of the method for automatically generating a desktop background based on projection image recognition as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program for automatically generating a desktop background based on projection image recognition. When the program for automatically generating a desktop background based on projection image recognition is executed by a processor, it is used to implement the operation of the method for automatically generating a desktop background based on projection image recognition as described in any one of claims 1-7.

Images