Hotspot adding verification method, device, electronic device and storage medium

Abstract

The present application provides a hotspot adding verification method, device, electronic device and computer-readable storage medium. The hotspot adding verification method comprises: obtaining the currently added hotspot of the target scene element; obtaining the hotspot category of the currently added hotspot; verifying the currently added hotspot of the target scene element according to the hotspot category and the preset verification strategy, and outputting the verification result. It can be seen that the present application uses the preset verification strategy to verify the target scene element and outputs the verification result. It can be verified whether the added hotspot is correct by judging whether the hotspot category conforms to the preset verification strategy.

Description

Technical Field

[0001] The present application relates to the field of panoramic roaming, and in particular to a hotspot adding verification method, device, electronic device and computer-readable storage medium. Background Art

[0002] With the development of virtual reality technology, virtual reality technology has been widely used in real-life display based on panoramas. In order to interact with users, hot spots will be set for one or several scene elements in the panorama. Users can jump to external links and other functions by clicking on the hot spots. The setting of hot spots increases the user's immersion in the scene. In the current panorama production process, hot spots can be automatically added to the panorama by matching the scene elements in the panorama with the preset hot spots. After adding the hot spots, the panorama needs to be verified to verify whether the hot spots are added correctly.

[0003] In the prior art, manual review is mainly used to click on each automatically added hotspot to confirm whether the ideal function can be achieved. This verification method is time-consuming and labor-intensive. Summary of the invention

[0004] The present application provides a hotspot adding verification method, device, electronic device and storage medium, aiming to solve the problem that the method of manually reviewing whether the automatically added hotspots are correct requires clicking on each hotspot, which is time-consuming and labor-intensive.

[0005] In a first aspect, the present application provides a hotspot adding verification method, the method comprising:

[0006] Get the currently added hotspot of the target scene element;

[0007] Get the hotspot category of the currently added hotspot;

[0008] According to the hotspot category and a preset verification strategy, the currently added hotspot of the target scene element is verified, and a verification result is output, where the verification result is used to indicate whether the currently added hotspot of the target scene element is incorrect.

[0009] In a possible implementation of the present application, obtaining the hotspot category of the currently added hotspot includes:

[0010] Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located;

[0011] Acquire a hotspot region image according to the scene image; perform feature extraction processing on the hotspot region image to obtain a style feature map of the hotspot region image;

[0012] Prediction processing is performed according to the style feature map to obtain the hotspot category of the currently added hotspot.

[0013] In a possible implementation of the present application, the verification strategy includes determining whether the hotspot category is associated with the scene category, and verifying the currently added hotspot of the target scene element according to the hotspot category and the preset verification strategy, and outputting the verification result, including:

[0014] Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located;

[0015] Performing feature extraction processing on the scene image to obtain a scene feature map of the scene image;

[0016] Perform prediction processing according to the scene feature map to obtain the scene category;

[0017] Determine whether the hotspot category is associated with the scene category, and if the hotspot category is not associated with the scene category, output a verification result.

[0018] In a second aspect, the present application provides a hotspot adding verification device, the hotspot adding verification device comprising:

[0019] A hotspot acquisition unit, used to acquire the currently added hotspot of the target scene element;

[0020] A category acquisition unit, used to acquire the hotspot category of the currently added hotspot;

[0021] The verification unit is used to verify the currently added hotspot of the target scene element according to the hotspot category and the verification strategy, and output the verification result.

[0022] In a possible implementation of the present application, the category acquisition unit is specifically used to:

[0023] Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located;

[0024] Acquire a hotspot region image according to the scene image; perform feature extraction processing on the hotspot region image to obtain a style feature map of the hotspot region image;

[0025] Prediction processing is performed according to the style feature map to obtain the hotspot category of the currently added hotspot.

[0026] In a possible implementation of the present application, the verification method includes determining whether the hotspot category is associated with the scene category, and the verification unit is specifically used to:

[0027] Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located;

[0028] Performing feature extraction processing on the scene image to obtain a scene feature map of the scene image;

[0029] Perform prediction processing according to the scene feature map to obtain the scene category;

[0030] Determine whether the hotspot category is associated with the scene category, and if the hotspot category is not associated with the scene category, output a verification result.

[0031] In a possible implementation of the present application, the currently added hotspot includes multiple hotspots, the verification strategy includes detecting whether the hotspot categories of the multiple currently added hotspots are the same, and verifying the currently added hotspot of the target scene element according to the hotspot category and the verification strategy, and outputting the verification result, including:

[0032] It is detected whether the hotspot categories of the multiple currently added hotspots are the same. If the hotspot categories of the multiple currently added hotspots are not the same, the verification fails and the verification result is output.

[0033] In a possible implementation of the present application, the hotspot adding verification device is specifically used to:

[0034] Obtaining the similarity between the target scene element and each preset scene element in a preset database, wherein the preset database includes each preset scene element, each preset hotspot of each preset scene element, and a hotspot category of each preset hotspot;

[0035] According to the similarity, acquiring the currently added hotspot from each preset hotspot of each preset scene element;

[0036] Add the currently added hotspot to the target scene element.

[0037] In a possible implementation of the present application, the hotspot adding verification device is specifically used to:

[0038] Acquire the three-dimensional element features of the sub-scene element in the target scene element;

[0039] Comparing the three-dimensional element features with the three-dimensional model features of the sub-model library to which each of the preset scene elements belongs, to obtain the geometric similarity between the three-dimensional element features and the three-dimensional model features;

[0040] Determine a target sub-model library to which a target three-dimensional model feature belongs, wherein a geometric similarity between the target three-dimensional model feature and the three-dimensional element feature is greater than a preset threshold;

[0041] A target preset hotspot of a target preset scene element is obtained from the target sub-model library, and the target preset hotspot is used as the currently added hotspot.

[0042] In a possible implementation of the present application, the hotspot adding verification device is specifically used to:

[0043] receiving a hotspot adjustment instruction, wherein the hotspot adjustment instruction includes information of a target component, and the target component includes at least one of a text component, a background component, and a line component;

[0044] Receive a component selection instruction, wherein the component selection instruction includes information of the component to be adjusted in the currently added hotspot and information of the target component;

[0045] Updating the component to be adjusted with the target component to obtain a new style hotspot of the target scene element;

[0046] The new style hotspot and the target scene element are recorded in the preset database.

[0047] In a third aspect, the present application also provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, it executes the steps of any hotspot adding verification method provided in the present application.

[0048] In a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program is loaded by a processor to execute the steps in the hotspot adding verification method.

[0049] The method provided by the present application includes: obtaining the hotspot of the target scene element; determining the hotspot category of the hotspot; verifying the currently added hotspot of the target scene element according to the hotspot category and the preset verification strategy, and outputting the verification result. It can be seen that the present application uses the preset verification strategy to verify the target scene element and outputs the verification result. It can be verified whether the added hotspot is correct by judging whether the hotspot category conforms to the preset verification strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1It is a schematic diagram of an application scenario of a hotspot adding verification device provided in an embodiment of the present application;

[0052] Figure 2 It is a flow chart of a hotspot adding verification method provided in an embodiment of the present application;

[0053] Figure 3 is a schematic diagram of an embodiment of step S22 provided in an embodiment of the present application;

[0054] Figure 4 is a schematic diagram of step S73 provided in an embodiment of the present application;

[0055] Figure 5 It is a flowchart of steps S71 to S74 provided in the embodiment of the present application;

[0056] Figure 6 is a schematic structural diagram of an embodiment of a package separation device provided in an embodiment of the present application;

[0057] Figure 7 It is a schematic diagram of the structure of an embodiment of an electronic device provided in the embodiments of the present application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0059] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0060] In order to enable any person skilled in the art to implement and use the present application, the following description is provided. In the following description, details are listed for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present application can also be implemented without using these specific details. In other examples, the known process will not be elaborated in detail to avoid unnecessary details that make the description of the present application embodiment obscure. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest range of principles and features disclosed in accordance with the embodiments of the present application.

[0061] The embodiments of the present application provide a hotspot adding verification method, device, electronic device and computer readable storage medium. The hotspot adding verification device can be integrated in an electronic device, which can be a server, a terminal or other device.

[0062] The executor of the hotspot adding verification method of the embodiment of the present application may be the hotspot adding verification device provided in the embodiment of the present application, or different types of electronic devices such as a server device, a physical host or a user equipment (UE) that integrates the hotspot adding verification device, wherein the hotspot adding verification device may be implemented in hardware or software, and the UE may specifically be a terminal device such as a smart phone, a tablet computer, a laptop computer, a PDA, a desktop computer or a personal digital assistant (PDA).

[0063] The electronic device can adopt a working mode of independent operation, or can also adopt a working mode of a device cluster. By applying the hotspot adding verification method provided in the embodiment of the present application, it can be verified whether the added hotspot is correct.

[0064] See also Figure 1 , Figure 1 1 is a schematic diagram of a scenario of a hotspot adding verification device provided in an embodiment of the present application. The package separation device may include an electronic device 100, in which the package separation device is integrated.

[0065] In addition, if Figure 1 As shown, the hotspot adding verification device may also include a memory 200 for storing data, such as image data and video data.

[0066] It should be noted that Figure 1 The scenario diagram of the hotspot adding verification device shown is merely an example. The hotspot adding verification device and the scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided by the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the hotspot adding verification device and the emergence of new business scenarios, the technical solution provided by the embodiment of the present application is equally applicable to similar technical problems.

[0067] Next, we will begin to introduce the hotspot adding verification method provided in the embodiment of the present application. In the embodiment of the present application, an electronic device is used as the execution subject. For the sake of simplicity and ease of description, the execution subject will be omitted in the subsequent method embodiments.

[0068] Reference Figure 2 , Figure 2It is a flow chart of a hotspot adding verification method provided by an embodiment of the present application. It should be noted that although the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than that here. The hotspot adding verification method includes steps 10 to 30, wherein:

[0069] 10. Get the current added hotspot of the target scene element.

[0070] The target scene element refers to the target scene that the user verifies.

[0071] The target scene element may be a scene that the user can see from the terminal, or a scene that the user cannot see from the terminal.

[0072] In some embodiments, the target scene element may be a scene that the user sees from the terminal, or may be a portion of the scene that the user sees from the terminal. For example, when the user roams in a 3D exhibition hall model made with 3DMAX, the target scene element may be Exhibition Hall 1 that the user sees on the computer screen. The target scene element may also be an area in Exhibition Hall 1 displayed on the computer screen that only contains handicraft models.

[0073] In some embodiments, the target scene element may be a scene that the user has not seen on the terminal but has selected through a scene operation instruction, or may be a part of a scene selected through a scene operation instruction. For example, when a user is roaming in a station panoramic scene formed by stitching together multiple station interior panoramic views, the target scene element may be a waiting room selected after clicking on a scene name list. The target scene element may also be an area in the waiting room panoramic view that only contains seats.

[0074] Specifically, the scene operation instruction can be a user click on the terminal touch screen. Taking the target scene element as the waiting room as an example: the user can first search the scene name list on the mobile phone screen, find the panoramic view named "Waiting Room", and then click "Waiting Room" in the scene name list to complete the scene selection.

[0075] In addition, the scene operation instruction can also be a code input by the user. For example, when the user is roaming in a station panoramic scene formed by stitching multiple station interior panoramic images, the user can enter a code that can realize the waiting room selection function in the compiler to complete the scene selection.

[0076] The hotspot currently added is the hotspot in the target scene element. The concept of hotspot is explained in detail below:

[0077] A hotspot can be a link in a scene that interacts with the user. The user can interact with the current scene by clicking on the hotspot. For example, the user can click on the hotspot to switch the current scene displayed on the terminal to another scene. For another example, the user can click on the hotspot to jump to the external network link associated with the hotspot.

[0078] A hotspot can also be a label in a scene that has no interactive function. For example, a hotspot can be a text label that displays "No Passing" in a street navigation scene.

[0079] Hotspots can be in various forms. For example, hotspots can be images or text. For example, when a user is roaming in a 3D exhibition hall model made with 3DMAX, the hotspot can be the text "Click to view exhibition information" associated with the exhibition cabinet model in the current scene. A hotspot can also be a chair picture that a user can click to jump to an external website, and the chair picture is also associated with the chair model.

[0080] In some embodiments, the number and location of hotspots can be set according to specific scene requirements. For example, when a user roams in a 3D exhibition hall model made with 3DMAX, since there are a large number of exhibits in the exhibition hall, such as handicrafts and furniture, in order to allow the user to interact with each exhibit and obtain specific information about the exhibits, a hotspot needs to be associated with each exhibit. For a 3D exhibition hall model, there are a large number of hotspots, and the hotspot locations are spread throughout the 3D exhibition hall model according to the distribution of the exhibits.

[0081] Among them, the target scene element can have only one currently added hotspot or multiple currently added hotspots. For example, the target scene element is an area that only contains seats in the waiting room panorama. When multiple seats are added with hotspots, there will be multiple currently added hotspots in the target scene element. When only one seat is added with a hotspot, there will be only one currently added hotspot in the target scene element.

[0082] The target scene element may also include a sub-scene element. Specifically, the sub-scene element refers to an object in the verified area.

[0083] In some embodiments, the sub-scene element may be an object in the image. For example, if the target scene element is an area in the waiting room panorama that only contains seats, then each seat is a scene sub-element.

[0084] In some embodiments, the sub-scene element may also be a three-dimensional model. For example, when roaming in a 3D exhibition hall model made with 3DMAX, the target scene element is Exhibition Hall 1 seen by the user on the computer screen, and each handicraft model in Exhibition Hall 1 is a scene sub-element.

[0085] 20. Obtain the hotspot category of the currently added hotspot.

[0086] Among them, the hotspot category is a category preset according to the characteristics of the currently added hotspot.

[0087] In some embodiments, the hotspot categories can be divided according to the different uses of the currently added hotspots. For example, when a user is roaming in a 3D exhibition hall model made with 3DMAX, the currently added hotspots associated with the goods in the roaming scene, which will jump to the mall after clicking, can be classified as "exhibits". The currently added hotspots that only display text can be classified as "non-exhibits".

[0088] In some embodiments, the hotspot categories can be divided according to different styles of the currently added hotspots. For example, when a user roams in a 3D exhibition hall model made with 3DMAX, for the currently added hotspots in the form of pictures, the currently added hotspots in the form of triangular pictures can be classified as "exhibits", and the currently added hotspots in the form of circular pictures can be classified as "non-exhibits". For another example, the currently added hotspots with blue pictures can be classified as "exhibits", and the currently added hotspots with red pictures can be classified as "non-exhibits".

[0089] It should be noted that the naming and classification of the currently added hotspots in this step are only examples and do not limit the situation in the actual scene.

[0090] In some embodiments, the hotspot category can be obtained by predicting image features. Specifically, the image containing the currently added hotspot can be first subjected to feature extraction processing to obtain a style feature map of the image. The style feature map is then subjected to prediction processing to obtain the category of the hotspot.

[0091] 30. According to the hotspot category and a preset verification strategy, verify the currently added hotspot of the target scene element, and output a verification result, wherein the verification result is used to indicate whether the currently added hotspot of the target scene element is incorrect.

[0092] The verification strategy is a strategy method for determining whether the currently added hotspot is added correctly according to the acquired hotspot category. There may be multiple verification strategies according to different requirements.

[0093] In some embodiments, the verification strategy can be to determine whether the multiple hotspot categories obtained are all the same category. If the multiple hotspot categories obtained are all the same category, the verification is successful, and the addition result of the currently added hotspot is correct. For example, when a user roams in a station panoramic scene formed by stitching multiple station interior panoramas, the target scene element is the seat area, then the currently added hotspot that needs to be verified is the hotspot added to the seat area. If the multiple hotspot categories of the seat area hotspot are all "seats", the currently added hotspot is added correctly.

[0094] Furthermore, the verification strategy can also be to determine whether the multiple hotspot categories obtained are included in the preset hotspot categories. For example, when a user roams in a station panoramic scene formed by stitching together multiple station interior panoramas, the target scene element is the seat area. Sometimes there are people waiting for the train sitting in the seat area. Therefore, in order to avoid detecting the hotspots added to the waiting people and causing the verification result to fail, the preset hotspot categories can be set to "seats" and "people". If the multiple hotspot categories of the seat area hotspot are at least one of "seats" and "people", the hotspot in the seat area is added correctly.

[0095] In some embodiments, the verification strategy may be to determine whether the multiple hotspot categories obtained are associated with the image category of the scene image. The scene image is an image containing target scene elements, and the image category is a pre-set category. The scene image can be classified to obtain the image category of the scene image, and then determine whether the hotspot category is associated with the image category for verification. Specifically, a specific hotspot category associated with a specific image category can be pre-set.

[0096] For example, if the target scene element is a seat area, the scene image may be a waiting room image containing the seat area, and the category of the image is the pre-set "waiting room" category. For the "waiting room" category, the pre-set hotspot categories associated with it are "seat" and "person", so if the hotspot category of the hotspot in the seat area is at least one of "seat" and "person", the hotspot in the seat area is added correctly.

[0097] Furthermore, there are multiple ways to output the verification result. For example, an error prompt box may pop up to prompt the user that the verification has failed and suggest the user to add the hotspot again. For another example, the currently added hotspots of all target scene elements may be deleted and steps 10 to 30 may be repeated.

[0098] In summary, the method provided by the embodiment of the present application includes: obtaining the currently added hotspot of the target scene element; obtaining the hotspot category of the currently added hotspot; verifying the currently added hotspot of the target scene element according to the hotspot category and the preset verification strategy, and outputting the verification result. It can be seen that the present application uses the preset verification strategy to verify the target scene element and outputs the verification result, and can verify whether the added hotspot is correct by judging whether the hotspot category conforms to the preset verification strategy.

[0099] In some practical scenarios, in order to obtain the hotspot category of the currently added hotspot, a method of predicting image features may be used. Specifically, steps 21-24 include:

[0100] 21. Obtain a scene image for displaying the target scene element.

[0101] The scene image refers to an image containing target scene elements. For example, when a user roams in a 3D exhibition hall model made with 3DMAX, the target scene element may be the handicraft model area in Exhibition Hall 1 displayed on the computer screen. The scene image refers to the scene image seen by the user on the computer screen, and the scene image contains information about the handicraft model area.

[0102] There are many ways to obtain scene images, and possible ways to obtain them are exemplarily described below.

[0103] In some embodiments, the scene image may be obtained by taking a screenshot of the image displayed on the computer screen. It may also include recording a background video of the user's roaming process to obtain a roaming video with the user's observation perspective as the first perspective, and then filtering the video frames of the video to obtain the scene image.

[0104] In some embodiments, the panoramic scene is formed by stitching together multiple scene images, in which case the scene image may be one of the multiple scene images. For example, when a user roams in a station panoramic scene formed by stitching together multiple station interior panoramic images, the scene image may be one of the multiple station interior panoramic images, such as a waiting hall panoramic image.

[0105] Furthermore, in this case, the scene image can be obtained by acquiring a plurality of image source files of the station interior panoramic images from the background, and filtering out the scene image therefrom.

[0106] 22. Obtain a hot spot area image based on the scene image.

[0107] The hotspot region image is an image obtained by cutting out a specific region from the scene image, and the specific region does not contain any hotspots other than the currently added hotspots (hotspots other than the currently added hotspots are referred to as irrelevant hotspots hereinafter). Furthermore, the image size of the hotspot region image can be changed as needed, as long as the condition of not containing irrelevant hotspots is met.

[0108] Below Figure 3 Explain the content in step S22. Assume that image A is a scene image, B, C, D are currently added hot spots, and E is an irrelevant hot spot. In the embodiment of the present application, all images are rectangular images, so the hot spot area image can be Figure 3 The image referred to by rectangle F that contains BCD but does not contain E.

[0109] There are many specific methods for obtaining the hotspot area image, for example, the scene image can be cropped to obtain the hotspot area image, which will not be described in detail.

[0110] 23. Perform feature extraction processing on the hot spot area image to obtain a style feature map of the hot spot area image.

[0111] 24. Perform prediction processing according to the style feature map to obtain a hotspot category of the hotspot.

[0112] The style feature map refers to a feature map obtained after performing feature extraction processing on the hotspot area image. Specifically, a feature extraction network can be used to extract features from the hotspot area image.

[0113] Among them, the trained hotspot prediction model can be used to implement steps 23 and 24.

[0114] The hotspot prediction model specifically includes the following structure:

[0115] The feature extraction layer uses the hotspot image as input and is used to perform feature extraction processing based on the hotspot image to obtain a style feature map. In some embodiments, a convolutional neural network (CNN) with the fully connected layer removed can be used to perform feature extraction operations such as convolution and pooling on the hotspot image to obtain a style feature map.

[0116] The prediction layer takes the style feature map as input and is used to perform regression classification prediction processing based on the style feature map to determine the hotspot category of the hotspot. Among them, the fully connected layer in the existing target classification network such as Alex-net can be used as the prediction layer.

[0117] For the preset hotspot prediction model, it is necessary to use the sample image set to train it before a trained hotspot prediction model can be obtained. The specific training steps are as follows:

[0118] A. Obtain a sample image set.

[0119] The sample image set includes a plurality of sample hotspot region images. Each sample hotspot region image contains a sample hotspot and carries label data, and the label data is used to indicate the hotspot category of the sample hotspot.

[0120] B. Call the preset hotspot prediction model, perform feature extraction processing based on the sample hotspot area image, and obtain the sample feature map.

[0121] C. Call the preset hotspot prediction model, perform prediction processing according to the sample feature map, and obtain the sample hotspot category of the sample hotspot.

[0122] D. According to the sample hotspot categories and the hotspot categories in the label data, adjust the model parameters of the preset hotspot prediction model until the preset hotspot prediction model converges to obtain a trained hotspot prediction model.

[0123] After the above steps A to D, a trained hotspot prediction model is obtained, and then steps 23-24 are performed to obtain the hotspot category of the hotspot.

[0124] When actually verifying the currently added hotspot, different verification strategies can be adopted according to the needs. The following introduces two different verification strategies.

[0125] Verification strategy 1:

[0126] In some actual scenarios, a verification strategy that can effectively determine whether the currently added hotspot of the target scene element is added correctly includes: determining whether the hotspot category of the currently added hotspot is associated with the scene category of the scene image. The association between the hotspot category and the scene category can refer to the hotspot category being a preset subcategory to which the scene category belongs. For example, for a station panoramic scene formed by stitching together multiple station interior panoramas, the subcategories to which the scene category "waiting room" belongs can be preset to include the hotspot category "seats" and the hotspot category "waiters", that is, the scene category "waiting room" is associated with the hotspot category "seats" and the hotspot category "waiters".

[0127] When the above verification strategy is adopted, the following steps 31-34 may be specifically included:

[0128] 31. Obtain a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located.

[0129] The meaning of the scene image can be referred to the explanation in step S21 and will not be repeated here.

[0130] 32. Perform feature extraction processing on the scene image to obtain a scene feature map of the scene image.

[0131] 33. Perform prediction processing based on the scene feature map to obtain the scene category.

[0132] Among them, a trained scene prediction model can be used to implement steps S32 and S33.

[0133] The scenario prediction model specifically includes the following structure:

[0134] The feature extraction layer takes the scene image as input and is used to perform feature extraction processing based on the scene image to obtain a scene feature map. In some embodiments, a common convolutional neural network (CNN) can be used to perform feature extraction operations such as convolution and pooling on the scene image to obtain a scene feature map.

[0135] The prediction layer takes the scene feature map as input and is used to perform regression classification prediction processing based on the scene feature map to determine the scene category of the scene image. Among them, the fully connected layer in the existing target classification network such as Alex-net can be used as the prediction layer.

[0136] For the preset scene prediction model, it is necessary to train it with a sample scene image set to obtain a trained scene prediction model. The specific training steps can refer to steps A to D above.

[0137] 34. Determine whether the hotspot category is associated with the scene category. If the hotspot category is not associated with the scene category, output the verification result.

[0138] There are many ways to associate hotspot categories with scene categories.

[0139] For example, when the hotspot category of the preset scene category is used, a mapping table of scene categories and hotspot categories can be established. After the scene category of the scene image is obtained through steps S31 to S33 and the hotspot category is obtained through steps S21 to S24, it is determined whether the hotspot category is associated with the scene category according to the mapping table.

[0140] For example, after obtaining the scene category and hotspot category, the keywords of the scene category and hotspot category can be searched through the search engine, and then the association is determined based on the search results. Specifically, taking the station panoramic scene formed by stitching multiple station interior panoramic images as an example, the scene category "waiting hall", the hotspot category "seat" and the hotspot category "waiting person" are searched through the search engine, and then it is determined whether the number of searched entries is higher than the preset threshold. If so, the scene category is associated with the hotspot category.

[0141] Verification strategy 2:

[0142] In some actual scenarios, in order to simplify the verification process, the verification strategy may also include detecting whether the hotspot categories of the multiple currently added hotspots are the same. Specifically, after obtaining multiple hotspot categories through steps 21-24, it is possible to detect whether the multiple hotspot categories obtained are all the same hotspot categories. Taking the station panoramic scene formed by stitching together multiple station interior panoramas as an example, when the target scene element is the waiting room, if the multiple hotspot categories obtained are all "seats", the verification passes. If there are two hotspot categories of "seats" and "commodities" among the multiple hotspot categories obtained, the verification fails and the verification result is output.

[0143] In order to make the verification more accurate, it is also possible to detect whether the hotspot categories of the multiple currently added hotspots are the same. If not, it is further detected whether the hotspot categories of the multiple currently added hotspots are associated. If not, the verification fails and an error prompt is output.

[0144] When detecting whether the hotspot categories of multiple currently added hotspots are associated, the mapping table described in step 34 can also be referred to. If the mappings of the hotspot categories of multiple currently added hotspots in the mapping table are all the same scene category, then the hotspot categories of the multiple hotspots are associated. In addition, the hotspot categories of multiple currently added hotspots can also be searched through a search engine, and then it is determined whether the number of entries obtained by the search is higher than a preset threshold. If so, the hotspot categories of multiple currently added hotspots are associated.

[0145] Compared with the verification strategy in steps 31 to 34, the verification strategy in the embodiment of the present application omits the step of predicting the scene category, and the verification is simpler and time-saving.

[0146] In order to more easily obtain the hotspot category, the hotspot category of the currently added hotspot can also be preset when adding the currently added hotspot. Exemplarily, this hotspot adding method specifically includes steps 51 to 53:

[0147] 51. Obtain similarity between the target scene element and each preset scene element in a preset database, wherein the preset database contains each preset scene element and each preset hotspot of the preset scene element and a hotspot category of each preset hotspot.

[0148] There are different similarity acquisition methods for 2D and 3D roaming scenes. The following will explain the similarity acquisition methods for 2D and 3D cases separately.

[0149] In some embodiments, the roaming scene is a 2D scene, and the preset database contains images that contain elements of the preset scene. At this time, the similarity refers to the similarity between the target image and the preset image, the target image refers to an image that contains elements of the target scene, and the preset image refers to an image that contains elements of the preset scene in the preset database.

[0150] A specific method for obtaining the similarity between the target image and the preset image may be an existing histogram matching method, a method based on Euclidean distance calculation, etc., which will not be elaborated in detail here.

[0151] In some embodiments, the roaming scene is a 3D scene, and the similarity in this case refers to the similarity between three-dimensional features. In the case where the roaming scene is a 3D scene, the preset database refers to the three-dimensional model library that comes with the 3D modeling software. Usually, the three-dimensional model library will contain multiple sub-model libraries, each of which contains its unique three-dimensional model features. The three-dimensional model containing the feature belongs to the sub-model library, and the three-dimensional model that does not contain the feature does not belong to the sub-model library. For preset scene elements containing the same features (such as shape), they can generally be considered to belong to the same category, such as a round table and a square table that also have four cylindrical legs. Both belong to tables. Therefore, the hotspot categories of multiple preset hotspots in a sub-model library are also usually set to the same.

[0152] 52. According to the similarity, obtain the currently added hotspot from the preset hotspots of the preset scene elements.

[0153] Among them, the specific method for obtaining the currently added hotspot includes determining whether the similarity is greater than a preset similarity threshold. If it is greater than the preset similarity threshold, the preset hotspot of the preset scene element used in the determination is used as the currently added hotspot.

[0154] Taking the station panoramic scene (2D roaming) formed by stitching together multiple station interior panoramic images as an example, assuming that the target scene element is the waiting room, first obtain the similarity between the target image containing the waiting room and the preset image A in the preset database, and then determine whether the obtained similarity is greater than the preset similarity threshold. If the obtained similarity is 0.95 and the preset similarity threshold is 0.9, the preset hotspot of A is used as the hotspot.

[0155] In some embodiments, there may be a situation where the similarity between the target image and multiple preset images is greater than the preset similarity threshold. In order to correctly add a hotspot, the preset image with the greatest similarity can be selected from the multiple preset images, and then the preset hotspot of the preset image is used as the current hotspot to be added. For example, the similarity between the target image and preset images B, C, and D is 0.9, 0.91, and 0.92 respectively, and the preset similarity threshold is 0.9. At this time, the preset hotspot of preset image D is used as the current hotspot to be added.

[0156] 53. Add the currently added hotspot to the target scene element.

[0157] In some practical scenarios, in order to improve the efficiency of adding hotspots in 3D roaming scenarios, a hotspot adding method based on the 3D model features in the 3D model library may be adopted. In this case, the following steps 61-64 may be specifically included:

[0158] 61. Obtain three-dimensional element features of the sub-scene elements in the target scene element.

[0159] The scenes involved in step 61 to step 64 are all 3D roaming scenes, so the sub-scene element refers to the three-dimensional model in the target scene element.

[0160] 62. Compare the 3D element features with the 3D model features of the sub-model library to which each preset scene element belongs, and obtain geometric similarity between the 3D element features and the 3D model features.

[0161] 63. Determine a target sub-model library to which a target three-dimensional model feature belongs, wherein a geometric similarity between the target three-dimensional model feature and the three-dimensional element feature is greater than a preset threshold.

[0162] Among them, the 3D element feature refers to the 3D feature of the sub-scene element, which may specifically include contour features, texture features, and skeleton shape features, etc. For example, the target scene element is the No. 1 exhibition hall that the user sees on the computer screen in the 3D exhibition hall model made with 3DMAX, and the sub-scene element is the handicraft model in the No. 1 exhibition hall. The 3D element feature may be the contour feature of the handicraft model, or the texture feature of the handicraft model.

[0163] In some embodiments, the three-dimensional element features and the three-dimensional model features refer to the three-dimensional features contained in the shape distribution histogram. Next, the method for determining the target sub-model library in this case is used as an example for explanation.

[0164] (1) First, any two vertices of the sub-scene element can be sampled to obtain the distance between the two vertices, where the vertex refers to a point on the surface of the sub-scene element.

[0165] (2) After obtaining the distances of all vertex pairs on the sub-scene element, a first shape distribution histogram is constructed according to the distances of all vertex pairs. The obtained first shape distribution histogram contains the three-dimensional element features.

[0166] (3) Obtain a second shape distribution histogram that includes the characteristics of the three-dimensional model.

[0167] (4) Calculate the paradigm distance between the first shape distribution histogram and the second shape distribution histogram, and determine whether the obtained paradigm distance is less than a preset threshold. If it is less than the preset threshold, use the sub-model library corresponding to the second shape distribution histogram as the target sub-model library. The paradigm distance can be calculated according to an existing calculation method, which will not be described in detail here.

[0168] It should be noted that the above steps (1) to (4) are only a method for determining the target sub-model library. Different sub-model libraries have different three-dimensional features. Therefore, it is necessary to select the method for determining the target sub-model library according to the actual scene requirements.

[0169] 64. Obtain a target preset hotspot of a target preset scene element from the target sub-model library, and use the target preset hotspot as the currently added hotspot.

[0170] Among them, the target preset scene element refers to any three-dimensional model in the target sub-model library. As mentioned above, the hotspots of the preset scene elements in the same sub-model library usually have the same hotspot category. Therefore, the target preset hotspot of any three-dimensional model can be obtained from the target sub-model library, and then the target preset hotspot is used as the hotspot.

[0171] Through steps 61-64, when constructing a 3D roaming scene, the currently added hotspot can be correctly and automatically added to the scene based on the three-dimensional features, and the currently added hotspot already contains the hotspot category information in the preset database. During verification, it is only necessary to call the corresponding hotspot category from the preset database, without the need for feature extraction and other operations, thereby reducing the verification process time.

[0172] refer to Figure 5 In some actual scenarios, the user can also adjust the style of the automatically added hotspot, and record the adjusted hotspot and the corresponding scene element in the preset database to facilitate the automatic addition of hotspots to other scene elements next time. Specific steps 71-74 include:

[0173] 71. Receive a hotspot adjustment instruction, wherein the hotspot adjustment instruction includes information of a target component, and the target component includes at least one of a text component, a background component, and a line component.

[0174] 72. Receive a component selection instruction, wherein the component selection instruction includes information about the component to be adjusted in the currently added hotspot and information about the target component.

[0175] 73. Update the component to be adjusted with the target component to obtain a new style hotspot of the target scene element.

[0176] The hotspot adjustment instruction may be an instruction input by the user through a mouse or keyboard, or may be an instruction generated when the user touches the touch screen.

[0177] The component selection instruction may also be an instruction generated by a user clicking with a mouse, or an instruction generated by a user touching a touch screen.

[0178] The following is a specific example to illustrate the process of step 71 to step 73:

[0179] (1) The user inputs instructions through the mouse or keyboard and selects the target component. The target component can be a background image selected by the user from the local database (i.e., background component). It can also be text entered by the user through the keyboard (i.e., text component). It can also be a line component generated by the user through the preset interface in the panorama making software according to the background code file when making a panorama.

[0180] Furthermore, the currently added hotspot is composed of a text component, a background component and a line component. Before the currently added hotspot is automatically added, the preset text component, the preset background component and the preset line component can also be assembled into the currently added hotspot through the preset interface in the panoramic image making software. The preset text component, the preset background component and the preset line component can change the style according to different needs, and at least one of the components can be reduced according to different needs. For example, the user can adjust the height of the line, the size of the picture or the font size of the text, etc. For another example, the user can only assemble the background component and the text component to form the currently added hotspot, or only assemble the text component and the line component to form the currently added hotspot.

[0181] (2) The user selects the target component, and then selects the component to be adjusted in the currently added hotspot added to the target scene element. If the user wants to change the background component of the currently added hotspot, select the background component of the currently added hotspot; if the user wants to change the text component of the currently added hotspot, select the text component of the currently added hotspot.

[0182] (3) Replace the component to be adjusted in the currently added hotspot with the target component to obtain a new style hotspot. The replacement method may include: deleting the component to be adjusted and pasting the target component to the position where the component to be adjusted originally existed. It should be noted that the target component and the component to be adjusted should belong to the same type of component, that is, when the target component is a text component, the component to be adjusted should also be a component to be adjusted, and the same applies to line components and background components.

[0183] After the replacement, multiple components can also be assembled together through the preset interface in the panoramic image making software to obtain a new style hotspot.

[0184] Furthermore, if the target component is a text component, the background component of the hotspot may be resized according to the size of the text component after replacement.

[0185] refer to Figure 4 For explanation. For example, when the component to be adjusted is the text component "Hello", the length of side a and side b of the background component referred to by square A is the same as the length of side c and side d of the square text box B containing the text component "Hello". It should be noted that text box B is the smallest square that can contain the text "Hello", and the font size of the text "Hello" is not limited. Side length a is parallel to side length c, and side length b is parallel to side length d. When the target component is the text component "Hello everyone", text box C is the smallest rectangle containing the text "Hello everyone", a is parallel to e, and b is parallel to f. It is assumed here that the font size of the target component and the component to be adjusted are the same, so the side length a of A is the same as the height e of C, and the side length b of A is smaller than the width f of C. For hotspots that are not replaced, it is assumed that the background component is a square of the same size as A (reference Figure 4 (a)), after replacement, the background component will automatically adjust to a rectangle with the same size as C (refer to Figure 4 (b)). It should be noted that the description of the background component size here is only an exemplary description and does not constitute a limitation on the background component size.

[0186] Here is a method for automatically adjusting the background component. First, according to the number of characters in the text component, the corresponding size of the background component is preset. For example, for a text component containing 3 characters, the length of the background component is preset to 3cm; for a text component containing 4 characters, the length of the background component is preset to 4cm. Then, the number of characters in the text component is detected, and the length of the background component is adjusted to the preset length according to the number of detected characters.

[0187] Furthermore, the user can directly copy and paste the new style hotspot to generate a template hotspot with the same style as the new style hotspot, so as to change the style of other hotspots after obtaining the new style hotspot. For the template hotspot obtained after pasting, at least one of the background component, text component and line component can be replaced as required.

[0188] 74. Record the new style hotspot and the target scene element in the preset database.

[0189] In order to better implement the hotspot adding verification method in the embodiment of the present application, based on the hotspot adding verification method, the embodiment of the present application also provides a hotspot adding verification device, such as Figure 6 As shown, it is a schematic diagram of the structure of an embodiment of a hotspot adding verification device in an embodiment of the present application, and the hotspot adding verification device 600 includes:

[0190] A hotspot acquisition unit 601 is used to acquire the currently added hotspot of the target scene element;

[0191] A category acquisition unit 602 is used to acquire the hotspot category of the currently added hotspot;

[0192] The verification unit 603 is used to verify the currently added hotspot of the target scene element according to the hotspot category and a preset verification strategy, and output the verification result.

[0193] In a possible implementation of the present application, the category acquisition unit 602 is specifically used to:

[0194] Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located;

[0195] Acquire a hotspot region image according to the scene image; perform feature extraction processing on the hotspot region image to obtain a style feature map of the hotspot region image;

[0196] Prediction processing is performed according to the style feature map to obtain the hotspot category of the currently added hotspot.

[0197] In a possible implementation of the present application, the verification strategy includes determining whether the hotspot category is associated with the scene category, and the verification unit 603 is specifically used to:

[0198] Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located;

[0199] Performing feature extraction processing on the scene image to obtain a scene feature map of the scene image;

[0200] Perform prediction processing according to the scene feature map to obtain the scene category;

[0201] Determine whether the hotspot category is associated with the scene category, and if the hotspot category is not associated with the scene category, output a verification result.

[0202] In a possible implementation of the present application, the currently added hotspot includes multiple hotspots, and the verification method includes detecting whether the hotspot categories of the multiple currently added hotspots are the same, and the verification unit 603 is specifically used to:

[0203] It is detected whether the hotspot categories of the multiple currently added hotspots are the same. If the hotspot categories of the multiple currently added hotspots are not the same, the verification fails and the verification result is output.

[0204] In a possible implementation of the present application, the hotspot adding verification device is specifically used to:

[0205] Obtaining the similarity between the target scene element and each preset scene element in a preset database, wherein the preset database includes each preset scene element and each preset hotspot of the preset scene element and a hotspot category of each preset hotspot;

[0206] According to the similarity, acquiring the currently added hotspot from each preset hotspot of each preset scene element;

[0207] Add the currently added hotspot to the target scene element.

[0208] In a possible implementation of the present application, the hotspot adding verification device is specifically used to:

[0209] Acquire the three-dimensional element features of the sub-scene element in the target scene element;

[0210] Comparing the three-dimensional element features with the three-dimensional model features of the sub-model library to which each of the preset scene elements belongs, to obtain the geometric similarity between the three-dimensional element features and the three-dimensional model features;

[0211] Determine a target sub-model library to which a target three-dimensional model feature belongs, wherein a geometric similarity between the target three-dimensional model feature and the three-dimensional element feature is greater than a preset threshold;

[0212] A target preset hotspot of a target preset scene element is obtained from the target sub-model library, and the target preset hotspot is used as the currently added hotspot.

[0213] In a possible implementation of the present application, the hotspot adding verification device is specifically used to:

[0214] receiving a hotspot adjustment instruction, wherein the hotspot adjustment instruction includes information of a target component, and the target component includes at least one of a text component, a background component, and a line component;

[0215] Receive a component selection instruction, wherein the component selection instruction includes information of the component to be adjusted in the currently added hotspot and information of the target component;

[0216] Updating the component to be adjusted with the target component to obtain a new style hotspot of the target scene element;

[0217] The new style hotspot and the target scene element are recorded in the preset database.

[0218] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0219] Since the hotspot adds a verification device, the application can be executed as follows Figures 1 to 5 Corresponding to the steps in the hotspot adding verification method in any embodiment, therefore, the present application can be implemented as follows Figures 1 to 5 The beneficial effects that can be achieved by the hotspot adding verification method in any embodiment are detailed in the previous description and will not be repeated here.

[0220] In addition, in order to better implement the hotspot adding verification method in the embodiment of the present application, on the basis of the hotspot adding verification method, the embodiment of the present application also provides an electronic device, referring to Figure 7 , Figure 7 A schematic diagram of the structure of an electronic device according to an embodiment of the present application is shown. Specifically, the electronic device provided by the embodiment of the present application includes a processor 701, and the processor 701 is used to execute a computer program stored in a memory 702 to implement the following Figures 1 to 5 Corresponding to each step of the hotspot adding verification method in any embodiment; or, the processor 701 is used to execute the computer program stored in the memory 702 to implement the following Figure 7 The functions of each unit in the corresponding embodiment.

[0221] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 702, and executed by the processor 701 to complete the embodiment of the present application. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0222] The electronic device may include, but is not limited to, a processor 701 and a memory 702. Those skilled in the art will appreciate that the illustration is merely an example of an electronic device and does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the illustration, or a combination of certain components, or different components, for example, the electronic device may also include input and output devices, network access devices, buses, etc., and the processor 701, memory 702, input and output devices, and network access devices, etc. are connected via a bus.

[0223] The processor 701 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0224] The memory 702 can be used to store computer programs and / or modules. The processor 701 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 702 and calling the data stored in the memory 702. The memory 702 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device (such as audio data, video data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0225] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the hotspot adding verification device, the electronic device and its corresponding units described above can refer to the following. Figures 1 to 5 The description of the hotspot adding verification method in any embodiment will not be repeated here.

[0226] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0227] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the present application as follows: Figures 1 to 5 For the steps in the hotspot adding verification method in any embodiment, the specific operations can be referred to as follows Figures 1 to 5 The description of the hotspot adding verification method in any embodiment will not be repeated here.

[0228] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0229] Due to the instructions stored in the computer-readable storage medium, the present application can be executed. Figures 1 to 5 Corresponding to the steps in the hotspot adding verification method in any embodiment, therefore, the present application can be implemented as follows Figures 1 to 5 The beneficial effects that can be achieved by the hotspot adding verification method in any embodiment are detailed in the previous description and will not be repeated here.

[0230] The above is a detailed introduction to a hotspot adding verification method, device, electronic device and computer-readable storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A hotspot adding verification method, characterized in that: The method comprises: Get the currently added hotspot of the target scene element; Get the hotspot category of the currently added hotspot; According to the hotspot category and a preset verification strategy, verify the currently added hotspot of the target scene element, and output a verification result, wherein the verification result is used to indicate whether the currently added hotspot of the target scene element is incorrect; The verification strategy includes determining whether the hotspot category is associated with the scene category, verifying the currently added hotspot of the target scene element according to the hotspot category and the preset verification strategy, and outputting the verification result, including: Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located; Performing feature extraction processing on the scene image to obtain a scene feature map of the scene image; Perform prediction processing according to the scene feature map to obtain the scene category; Determine whether the hotspot category is associated with the scene category, and if the hotspot category is not associated with the scene category, output a verification result.

2. The hotspot adding verification method according to claim 1, characterized in that: The step of obtaining the hotspot category of the currently added hotspot includes: Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located; Acquire a hotspot region image according to the scene image, perform feature extraction processing on the hotspot region image, and obtain a style feature map of the hotspot region image; Prediction processing is performed according to the style feature map to obtain the hotspot category of the currently added hotspot.

3. The hotspot adding verification method according to claim 1, characterized in that: The currently added hotspots include multiple ones, the verification strategy includes detecting whether the hotspot categories of the multiple currently added hotspots are the same, and verifying the currently added hotspots of the target scene element according to the hotspot categories and the preset verification strategy, and outputting the verification result, including: It is detected whether the hotspot categories of the multiple currently added hotspots are the same. If the hotspot categories of the multiple currently added hotspots are not the same, the verification fails and the verification result is output.

4. The hotspot adding verification method according to claim 1, characterized in that: The method further comprises: Obtaining the similarity between the target scene element and each preset scene element in a preset database, wherein the preset database includes each preset scene element, each preset hotspot of each preset scene element, and a hotspot category of each preset hotspot; According to the similarity, acquiring the currently added hotspot from each preset hotspot of each preset scene element; Add the currently added hotspot to the target scene element.

5. The hotspot adding verification method according to claim 4, characterized in that: The preset database is a three-dimensional model library, the three-dimensional model library includes multiple sub-model libraries, each of the multiple sub-model libraries includes a unique three-dimensional model feature, the similarity includes geometric similarity, and the obtaining of the similarity between the target scene element and each preset scene element in the preset database includes: Acquire the three-dimensional element features of the sub-scene element in the target scene element; Comparing the three-dimensional element features with the three-dimensional model features of the sub-model library to which each of the preset scene elements belongs, to obtain the geometric similarity between the three-dimensional element features and the three-dimensional model features; The acquiring the currently added hotspot from each preset hotspot of each preset scene element according to the similarity includes: Determine a target sub-model library to which a target three-dimensional model feature belongs, wherein a geometric similarity between the target three-dimensional model feature and the three-dimensional element feature is greater than a preset threshold; A target preset hotspot of a target preset scene element is obtained from the target sub-model library, and the target preset hotspot is used as the currently added hotspot.

6. The hotspot adding verification method according to claim 4, characterized in that: The currently added hotspot includes at least one of a text component, a background component and a line component. After the currently added hotspot is added to the target scene element, the method further includes: receiving a hotspot adjustment instruction, wherein the hotspot adjustment instruction includes information of a target component, and the target component includes at least one of a text component, a background component, and a line component; Receive a component selection instruction, wherein the component selection instruction includes information of the component to be adjusted in the currently added hotspot and information of the target component; Updating the component to be adjusted with the target component to obtain a new style hotspot of the target scene element; The new style hotspot and the target scene element are recorded in the preset database.

7. A hotspot adding verification device, characterized in that: The device comprises: A hotspot acquisition unit, used to acquire the currently added hotspot of the target scene element; A category acquisition unit, used to acquire the hotspot category of the currently added hotspot; A verification unit, configured to verify the currently added hotspot of the target scene element according to the hotspot category and a preset verification strategy, and output a verification result; The verification strategy includes determining whether the hotspot category is associated with the scene category, verifying the currently added hotspot of the target scene element according to the hotspot category and the preset verification strategy, and outputting the verification result, including: Acquire a scene image for displaying the target scene element, wherein the scene image is an image of the scene where the currently added hotspot is located; Performing feature extraction processing on the scene image to obtain a scene feature map of the scene image; Perform prediction processing according to the scene feature map to obtain the scene category; Determine whether the hotspot category is associated with the scene category, and if the hotspot category is not associated with the scene category, output a verification result.

8. An electronic device, characterized in that: It comprises a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the hotspot adding verification method as described in any one of claims 1 to 6 is executed.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the hotspot adding verification method described in any one of claims 1 to 6.

Images