Voice room interface layout generation method and device, equipment and storage medium

Abstract

The invention provides a voice room interface layout generation method and device, equipment and a storage medium, and relates to the technical field of Internet. The method comprises the following steps: acquiring a target background picture of a target voice room; the target background picture is input into a preset image recognition model, an image recognition result is obtained, the image recognition result comprises article elements, and the preset image recognition model is obtained through training based on a machine learning model; matching the article elements with the layout elements of the target voice room to obtain a matching result; and determining the position of the layout element in the target voice room according to the matching result, and generating the interface layout of the target voice room. Therefore, the fusion degree of the layout elements and the room background is high, the layout elements and the room background are not stiff, the voice room interface layout presented in front of the user is thousands of people and thousands of faces, the playability is high, personalized customization of the voice room interface layout is achieved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method, device, equipment and storage medium for generating a voice room interface layout. Background Art

[0002] With the development of the Internet, real-time voice chat has become a popular form of entertainment, such as organizing live chats and singing interactions in voice rooms. In traditional voice room design, a replaceable room background and fixed layout elements are usually used. These layout elements include microphone positions, microphones, gift buttons, etc. They are set in specific locations in the room, and the layout is fixed and not easy to change. In specific scenarios, these layout elements will be moved to another fixed layout form. The room background of the voice room usually only serves as a decoration (similar to wallpaper).

[0003] This design makes the voice room only run in a specific form, and cannot flexibly adapt to different scenarios or activity requirements. At the same time, because the layout elements are relatively fixed and have no close connection with the room background, it is relatively rigid and the user experience is poor. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for generating a voice room interface layout, so as to solve the problem that the layout form of the voice room in the prior art is fixed, achieve a high degree of integration between the layout elements and the room background without being abrupt, and improve playability and user experience.

[0005] The present invention provides a method for generating a voice room interface layout, comprising:

[0006] Get the target background image of the target voice room;

[0007] Input the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes object elements, and the preset image recognition model is obtained by training based on a machine learning model;

[0008] Matching the object element with the layout element of the target voice room to obtain a matching result;

[0009] The position of the layout element in the target voice room is determined according to the matching result, and the interface layout of the target voice room is generated.

[0010] According to a method for generating a voice room interface layout provided by the present invention, matching the item element with the layout element of the target voice room to obtain a matching result includes:

[0011] Acquire a layout element set and an item element set of the target voice room, wherein the layout element set includes the layout element, and the item element set includes the item element;

[0012] Traversing the layout element set, determining whether each of the layout elements and the item element conform to a preset matching rule, and obtaining the matching result;

[0013] The determining the position of the layout element in the target voice room according to the matching result and generating the interface layout of the target voice room includes:

[0014] Based on the preset matching rule, placing the first layout element within a preset coordinate range of the location of the item element matching the first layout element; and / or, based on a preset layout scheme, placing the second layout element at preset coordinates;

[0015] Generate an interface layout of the target voice room; wherein the first layout element is a layout element that meets the preset matching rule, and the second layout element is a layout element that does not meet the preset matching rule.

[0016] According to a method for generating a voice room interface layout provided by the present invention, placing a second layout element at a preset coordinate based on a preset layout scheme includes:

[0017] Obtaining a target preset layout solution from multiple preset layout solutions according to a random algorithm;

[0018] Based on the target preset layout scheme, determining the preset coordinates of the second layout element;

[0019] The second layout element is placed according to the preset coordinates.

[0020] According to a method for generating a voice room interface layout provided by the present invention, before inputting the target background image into a preset image recognition model to obtain an image recognition result, the method further includes:

[0021] Determining whether the target background image is a monotonous image;

[0022] If not, execute the step of inputting the target background image into a preset image recognition model to obtain an image recognition result.

[0023] According to a method for generating a voice room interface layout provided by the present invention, after determining whether the target background image is a monotonous image, the method further includes:

[0024] If yes, the position of the layout element in the target voice room is determined based on a preset layout scheme, and the interface layout of the target voice room is generated.

[0025] According to a method for generating a voice room interface layout provided by the present invention, after inputting the target background image into a preset image recognition model and obtaining the image recognition result, the method further includes:

[0026] If the image recognition result includes a human element, generating a binary mask image according to the human element;

[0027] Synthesizing the binary mask image into the target background image;

[0028] The determining the position of the layout element in the target voice room according to the matching result and generating the interface layout of the target voice room includes:

[0029] The position of the layout element in the target voice room is determined according to the matching result and the synthesized target background image, and the interface layout of the target voice room is generated.

[0030] According to a method for generating a voice room interface layout provided by the present invention, before generating the interface layout of the target voice room, the method further includes:

[0031] The size information of the layout element is adjusted according to the size information of the item element, wherein the size information includes at least one of a size and a rotation angle.

[0032] The present invention also provides a device for generating a voice room interface layout, comprising:

[0033] A first acquisition module is used to acquire a target background image of a target voice room;

[0034] A second acquisition module is used to input the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes an object element, and the preset image recognition model is obtained by training based on a machine learning model;

[0035] A matching module, used for matching the object element with the layout element of the target voice room to obtain a matching result;

[0036] A generation module is used to determine the position of the layout element in the target voice room according to the matching result, and generate the interface layout of the target voice room.

[0037] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for generating a voice room interface layout as described in any one of the above is implemented.

[0038] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating a voice room interface layout as described in any one of the above is implemented.

[0039] The method, device, equipment and storage medium for generating the interface layout of the voice room provided by the present invention perform image recognition on the target background picture of the target voice room through a preset image recognition model, and if an object element is recognized, match the object element with the layout element of the target voice room, and determine the position of the layout element in the target voice room according to the matching result, thereby generating the interface layout of the target voice room. In this way, the layout elements and the room background are highly integrated and not stiff, and the voice room interface layout presented to the user is different for each person and has high playability, realizing personalized customization of the voice room interface layout and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is one of the flow charts of the method for generating the voice room interface layout provided by the present invention;

[0042] Figure 2 This is the second flow chart of the method for generating the voice room interface layout provided by the present invention;

[0043] Figure 3 is one of the interface schematic diagrams of the voice room interface layout using an exemplary embodiment of the present invention;

[0044] Figure 4 This is a second interface schematic diagram of a voice room interface layout using an exemplary embodiment of the present invention;

[0045] Figure 5 It is a structural schematic diagram of a device for generating a voice room interface layout provided by the present invention;

[0046] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] It should be noted that, in the description of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0049] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0050] Combine the following Figure 1-Figure 6 The invention describes a method, device, equipment and storage medium for generating a voice room interface layout.

[0051] like Figure 1 As shown, the present invention provides a method for generating a voice room interface layout, which may specifically include the following steps:

[0052] Step 110, obtaining a target background image of a target voice room.

[0053] Specifically, the target background image may be a background image selected by the user from an online gallery, or may be a background image uploaded by the user.

[0054] Step 120, input the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes object elements, and the preset image recognition model is obtained by training based on a machine learning model.

[0055] Specifically, the target background image is input into the trained image recognition model, and image recognition is performed on the target background image to identify the elements contained in the target background image. The elements may include object elements (such as tables, chairs, sofas, stages, doors, windows, televisions, etc.), human elements (such as full-length portraits, half-length portraits, two-dimensional images, three-dimensional virtual images, etc.), and environmental elements (such as the sky, grass, sea, etc.).

[0056] The preset image recognition model can be obtained by training based on a machine learning model. The model used can be any one or more of image recognition models such as TensorFlow, PyTorch, ONNX, Keras, Caffe, etc., and the present invention does not make specific limitations.

[0057] In order to further filter the pictures, in some embodiments, before step 120, the following steps may also be included:

[0058] Determining whether the target background image is a monotonous image;

[0059] If not, step 120 is executed.

[0060] If yes, the position of the layout element in the target voice room is determined based on a preset layout scheme, and the interface layout of the target voice room is generated.

[0061] In this embodiment, monotonous images such as single solid color and gradient color can be filtered first. If the image is monotonous, it does not need to be input into the preset image recognition model for image recognition. The layout elements of the voice room with the monotonous image as the background image are positioned according to the preset layout scheme to generate the interface layout.

[0062] Specifically, the color histogram of the target background image can be analyzed to check the color distribution. If a certain color occupies the vast majority of pixels (for example, more than 90%), then the area can be considered as a pure color or monotonous background, and the target background image can be judged as a monotonous image.

[0063] Step 130, matching the object element with the layout element of the target voice room to obtain a matching result.

[0064] Specifically, the layout elements of the voice room may include: microphone position, microphone button, gift button, public screen, exit room button, etc. The recognized object elements are matched with the layout elements of the voice room. Preset matching rules may be stored locally. According to the preset matching rules, it is determined whether the object elements of the target background image can match the layout elements to obtain a matching result.

[0065] In some embodiments, after step 120, the following steps may also be included:

[0066] If the image recognition result includes a human element, generating a binary mask image according to the human element;

[0067] Synthesizing the binary mask image into the target background image;

[0068] Accordingly, step 130 may include:

[0069] The position of the layout element in the target voice room is determined according to the matching result and the synthesized target background image, and the interface layout of the target voice room is generated.

[0070] In this embodiment, for the human element identified in the target background image, the image of the human element is segmented from the target background image, a binary mask image is generated according to the image of the human element, and the binary mask image is synthesized into the target background image. In this way, the human element in the target background image can be shielded, and the area of ​​the human element will be avoided when the layout elements are subsequently placed. In this way, the layout elements can be prevented from blocking the human element in the background image, so that the human element has a better display effect, further improving the user experience.

[0071] If the image recognition result does not include human elements, there is no need to perform the above processing on the target background image.

[0072] In one embodiment, an image segmentation model can be used to separate the human element from the target background image and generate a binary mask of the human element. The image segmentation model can be a model such as DeepLab, Mask R-CNN, etc., and the present invention does not make specific limitations. The image segmentation model can be a separate model or a model combined with the above-mentioned preset image recognition model.

[0073] Step 140: determine the position of the layout element in the target voice room according to the matching result, and generate the interface layout of the target voice room.

[0074] In this step, the position of each layout element in the target voice room interface is determined according to the matching degree between the object element and the layout element, so that the interface layout of the voice room generated has a high degree of integration with the target background image.

[0075] In some embodiments, step 130 specifically includes:

[0076] Acquire a layout element set and an item element set of the target voice room, wherein the layout element set includes the layout element, and the item element set includes the item element;

[0077] The layout element set is traversed to determine whether each of the layout elements and the item element conforms to a preset matching rule, thereby obtaining the matching result.

[0078] Accordingly, step 140 specifically includes:

[0079] Based on the preset matching rule, placing the first layout element within a preset coordinate range of the location of the item element matching the first layout element; and / or, based on a preset layout scheme, placing the second layout element at preset coordinates;

[0080] Generate an interface layout of the target voice room; wherein the first layout element is a layout element that meets the preset matching rule, and the second layout element is a layout element that does not meet the preset matching rule.

[0081] In this embodiment, the image recognition result output by the preset image recognition model contains an item element, and then an item element set is obtained. All layout elements of the target voice room generate a layout element set. All layout elements in the layout element set are traversed to find the item elements that can be placed by each layout element in the item element set, that is, the two match.

[0082] The preset matching rules may include the item elements that can be matched with various layout elements, and the positional relationship between the layout elements and the item elements. Thus, for the layout elements that meet the preset matching rules, the coordinate range of the location of the layout elements is determined according to the preset matching rules, and the layout elements are placed.

[0083] Specifically, the positional relationship may be that the layout element is placed within the area of ​​the item element, the layout element is placed around the item element, and so on.

[0084] In some embodiments, when multiple layout elements match the same item element and their positional relationship is that the layout elements are placed within the area of ​​the item element, the area value of the item element can be calculated; if the area value of the item element is not less than the sum of the original area values ​​of the multiple layout elements, the multiple layout elements are placed within the area of ​​the item element; if the area value of the item element is less than the sum of the original area values ​​of the multiple layout elements, the size of the layout elements is adjusted so that the multiple layout elements can be placed within the area of ​​the item element.

[0085] In other embodiments, when multiple layout elements match the same type of item elements, there are multiple item elements of this type, and the positional relationship is that the layout elements are placed in the area of ​​the item elements, the area value of each item element is calculated in a similar manner, and the number of layout elements that can be placed in each item element is calculated in combination with the original area value of the layout element, and each layout element is placed in the area of ​​the corresponding item element according to the number that can be placed.

[0086] For layout elements that cannot be matched successfully, their coordinate positions in the voice room interface are determined according to the set layout scheme. In some embodiments, placing the second layout element at the preset coordinates based on the preset layout scheme may include:

[0087] Obtaining a target preset layout solution from multiple preset layout solutions according to a random algorithm;

[0088] Based on the target preset layout scheme, determining the preset coordinates of the second layout element;

[0089] The second layout element is placed according to the preset coordinates.

[0090] In this embodiment, a plurality of layout schemes are set in advance, and a random algorithm may be used to select one of the layout schemes to determine the coordinate positions of the layout elements, thereby generating an interface layout.

[0091] In some embodiments, before generating the interface layout of the target voice room, the method further includes: adjusting the size information of the layout element according to the size information of the object element, wherein the size information includes at least one of size and rotation angle.

[0092] Specifically, in addition to adjusting the position of the layout elements in the interface to match and blend with the object elements of the target background image, the size and rotation angle of the layout elements can also be adjusted according to the size and presentation angle of the object elements. The style of the layout elements (such as the shape of the elements, display patterns), dynamic effects, etc. can also be adjusted.

[0093] It should be understood that the preset layout scheme adopted by the above-mentioned layout elements that cannot be successfully matched includes the position, size, rotation angle, style, dynamic effect, etc. of the layout elements.

[0094] In some embodiments, the method further includes: adjusting the position of the layout element in the target voice room based on a drag operation instruction of the layout element.

[0095] In this embodiment, after the interface layout is generated according to the matching results, the user can also customize and drag the layout elements to further improve the user experience.

[0096] Figure 2 FIG. 1 is a flow chart of a method for generating a voice room interface layout according to an exemplary embodiment of the present invention. Figure 2 As shown, after obtaining the target background image of the target voice room, first determine whether the target background image is a monotonous image. If it is a monotonous image, randomly select a preset layout scheme, determine the position, size, rotation angle, style, dynamic effect, etc. of the layout elements, and generate the interface layout of the target voice room. If it is not a monotonous image, input the image into the preset image recognition model to obtain the image recognition result. If the image recognition result contains a person element, it is also necessary to shield the area of ​​the person element in the target background image. Traverse the layout elements and match them with the object elements in the image recognition result. If the layout element cannot match all the object elements, the layout element of this type randomly selects a preset layout scheme to determine the position, size, rotation angle, style, dynamic effect, etc. of the layout element; if the layout element can match one of the object elements, the position, size, rotation angle, style, and whether it has a dynamic effect are determined according to the preset matching rules. When all the layout elements have determined the position, size, rotation angle, style, dynamic effect, etc., the interface layout of the target voice room is finally generated. Thus, the interface layout of the target voice room is generated according to the target background image, and the personalized customization of the interface layout of the voice room is realized.

[0097] The above-mentioned method for generating the interface layout of the voice room can be applied to the client side of the voice social platform or to the server side. In the application scenario of the client side, each user of the voice room (including the room owner and the audience) can choose to upload a picture to set as the background picture of the voice room. After the client obtains the background picture, it calls the preset image recognition model to perform image recognition on the background picture uploaded by the user, identifies the object elements contained in the picture, and matches them with the layout elements. According to the matching results, the placement of each layout element is determined to generate the interface layout of the voice room. In this way, each user can set the background of the voice room according to his or her own preferences, and the layout elements of the voice room can be integrated with the background picture.

[0098] In the application scenario on the server side, the permission to change the background image of the voice room can be set as the permission of the room owner. When the room owner uploads the background image, the server side receives the image. Similarly, the server side calls the preset image recognition model to perform image recognition on the background image uploaded by the room owner, identifies the object elements contained in the image, and matches them with the layout elements. According to the matching results, the placement of each layout element is determined, and the interface layout of the voice room is generated. The configuration file of the interface layout is sent to all users of the voice room. The client receives the configuration file and updates the background image and interface layout of the voice room. Similarly, when a new listener enters the voice room, the server side will also send the configuration file to the corresponding client, so that the new listener can also use the background image and interface layout customized by the room owner.

[0099] In order to better understand the method for generating the voice room interface layout of the present invention, Figure 3 , Figure 4 The following is the layout of the voice room interface generated by the method of the present invention. Figure 3 As shown, by performing image recognition on the background image, the object elements included in the image can be identified: table, brush, carpet, door, etc. Figure 3 The layout elements shown include a microphone position 310 and an exit room button 320. The layout elements and the object elements are matched. The matching result is that the microphone position matches the table, and the microphone position 310 is placed around the table; the exit room button matches the door, and the exit room button 320 is placed in the door area, thereby generating Figure 3 The interface layout shown.

[0100] like Figure 4 As shown, by performing image recognition on the background image, the object elements included in the image can be identified: the stage. Figure 4 The layout elements shown include a microphone position 410 and an exit room button 420. The layout elements and the item elements are matched. The matching result is that the microphone position matches the stage, and the microphone position 410 is placed in the stage area. There is no item element to match the exit room button 420, and the layout is performed according to a random algorithm, thereby generating Figure 4 The interface layout shown.

[0101] The method for generating the interface layout of the voice room provided by the present invention performs image recognition on the target background picture of the target voice room through a preset image recognition model, and if an object element is recognized, matches the object element with the layout element of the target voice room, and determines the position of the layout element in the target voice room according to the matching result, thereby generating the interface layout of the target voice room. In this way, the layout elements and the room background are highly integrated and not rigid, and the voice room interface layout presented to the user is different for each person and has high playability, realizing personalized customization of the voice room interface layout and improving the user experience.

[0102] The following is a description of a device for generating a voice room interface layout provided by the present invention. The device for generating a voice room interface layout described below and the method for generating a voice room interface layout described above can be referred to each other in correspondence.

[0103] like Figure 5 As shown, the present invention also provides a device for generating a voice room interface layout, specifically comprising:

[0104] A first acquisition module 510 is used to acquire a target background image of a target voice room;

[0105] A second acquisition module 520, configured to input the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes an object element, and the preset image recognition model is obtained by training based on a machine learning model;

[0106] A matching module 530, used to match the object element with the layout element of the target voice room to obtain a matching result;

[0107] The generation module 540 is used to determine the position of the layout element in the target voice room according to the matching result, and generate the interface layout of the target voice room.

[0108] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute a method for generating a voice room interface layout, the method comprising: obtaining a target background image of a target voice room; inputting the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes an object element, and the preset image recognition model is obtained based on training of a machine learning model; matching the object element with the layout element of the target voice room to obtain a matching result; determining the position of the layout element in the target voice room according to the matching result, and generating the interface layout of the target voice room.

[0109] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0110] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for generating the voice room interface layout provided by the above methods, and the method includes: obtaining a target background image of a target voice room; inputting the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes object elements, and the preset image recognition model is obtained based on training of a machine learning model; matching the object elements with the layout elements of the target voice room to obtain a matching result; determining the position of the layout elements in the target voice room according to the matching result, and generating the interface layout of the target voice room.

[0111] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for generating the interface layout of a voice room provided by the above-mentioned methods, the method comprising: obtaining a target background image of a target voice room; inputting the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes object elements, and the preset image recognition model is obtained based on training of a machine learning model; matching the object elements with the layout elements of the target voice room to obtain a matching result; determining the position of the layout elements in the target voice room according to the matching result, and generating the interface layout of the target voice room.

[0112] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a voice room interface layout, characterized in that: include: Get the target background image of the target voice room; Input the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes object elements, and the preset image recognition model is obtained by training based on a machine learning model; Matching the object element with the layout element of the target voice room to obtain a matching result; The position of the layout element in the target voice room is determined according to the matching result, and the interface layout of the target voice room is generated.

2. The method for generating a voice room interface layout according to claim 1, characterized in that: The matching of the item element with the layout element of the target voice room to obtain a matching result includes: Acquire a layout element set and an item element set of the target voice room, wherein the layout element set includes the layout element, and the item element set includes the item element; Traversing the layout element set, determining whether each of the layout elements and the item element conform to a preset matching rule, and obtaining the matching result; The determining the position of the layout element in the target voice room according to the matching result and generating the interface layout of the target voice room includes: Based on the preset matching rule, placing the first layout element within a preset coordinate range of the location of the item element matching the first layout element; and / or, based on a preset layout scheme, placing the second layout element at preset coordinates; Generate an interface layout of the target voice room; wherein the first layout element is a layout element that meets the preset matching rule, and the second layout element is a layout element that does not meet the preset matching rule.

3. The method for generating a voice room interface layout according to claim 2, characterized in that: Placing the second layout element at a preset coordinate based on the preset layout scheme includes: Obtaining a target preset layout solution from multiple preset layout solutions according to a random algorithm; Based on the target preset layout scheme, determining the preset coordinates of the second layout element; The second layout element is placed according to the preset coordinates.

4. The method for generating a voice room interface layout according to claim 1, characterized in that: Before inputting the target background image into a preset image recognition model to obtain an image recognition result, the method further includes: Determining whether the target background image is a monotonous image; If not, execute the step of inputting the target background image into a preset image recognition model to obtain an image recognition result.

5. The method for generating a voice room interface layout according to claim 4, characterized in that: After determining whether the target background image is a monotonous image, the method further includes: If yes, the position of the layout element in the target voice room is determined based on a preset layout scheme, and the interface layout of the target voice room is generated.

6. The method for generating a voice room interface layout according to claim 1, characterized in that: After inputting the target background image into a preset image recognition model and obtaining an image recognition result, the method further includes: If the image recognition result includes a human element, generating a binary mask image according to the human element; Synthesizing the binary mask image into the target background image; The determining the position of the layout element in the target voice room according to the matching result and generating the interface layout of the target voice room includes: The position of the layout element in the target voice room is determined according to the matching result and the synthesized target background image, and the interface layout of the target voice room is generated.

7. The method for generating a voice room interface layout according to claim 1, characterized in that: Before generating the interface layout of the target voice room, the method further includes: The size information of the layout element is adjusted according to the size information of the item element, wherein the size information includes at least one of a size and a rotation angle.

8. A device for generating a voice room interface layout, characterized in that: include: A first acquisition module is used to acquire a target background image of a target voice room; A second acquisition module is used to input the target background image into a preset image recognition model to obtain an image recognition result, wherein the image recognition result includes an object element, and the preset image recognition model is obtained by training based on a machine learning model; A matching module, used for matching the object element with the layout element of the target voice room to obtain a matching result; A generation module is used to determine the position of the layout element in the target voice room according to the matching result, and generate the interface layout of the target voice room.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for generating the voice room interface layout as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating a voice room interface layout as described in any one of claims 1 to 7 is implemented.

Images