Recommendation method and system for placement position of virtual article
By calculating the correlation between virtual items and elements in real scenes, the placement of virtual items is automatically recommended, which solves the problems of poor realism and heavy manual adjustment in the real environment, and achieves an efficient and realistic virtual item fusion effect.
Patent Information
- Application Number
- CN202411998269.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-05-06
AI Technical Summary
When the prior art integrates virtual items into a real environment, virtual items are mostly displayed in a suspended state, which has a poor sense of reality and requires manual preset or manual adjustment of the position of virtual items, which is relatively heavy.
A recommended method and system for placement of virtual items is proposed. By obtaining virtual items and their corresponding item information and each element in a real scene and their corresponding element information, the correlation between virtual items and each element in a real scene is calculated, and the appropriate placement position is automatically recommended.
It improves the efficiency and visual realism of implanting virtual items in real space, reduces the workload of manual adjustment, and improves the integration effect of virtual items and real environment.
Smart Images
Figure CN119937784A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and system for recommending a virtual object placement location. Background Art
[0002] With the development of dynamic video, animated images, 3D and AR technologies, providing users with immersive experience has gradually become the exploration and development direction of various service industries. For example, online trading platforms or architectural design systems integrate the objects of interest as virtual objects with the real environment, so that users can get a simulated real experience in advance.
[0003] Currently, when objects are integrated into the real environment as virtual objects, virtual objects are mostly displayed in a suspended state, which lacks realism; or the position of virtual objects superimposed in the real world is manually preset or adjusted, which is a heavy workload. Summary of the invention
[0004] The main purpose of the embodiments of the present application is to propose a method and system for recommending a virtual object placement location, aiming to automatically recommend a placement location for a virtual object, thereby improving the efficiency and visual realism of implanting virtual objects in a real space.
[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a method for recommending a virtual item placement location, the method comprising:
[0006] Acquire virtual items and their corresponding item information and various elements in a real scene and their corresponding element information, wherein the item information includes classification information of the virtual items and basic information of the virtual items, and the element information includes classification information of the elements and entity information of the elements;
[0007] Calculating the association between the virtual item and each element in the real scene according to the item information corresponding to the virtual item and the element information corresponding to each element in the real scene;
[0008] According to the association between the virtual item and each element, a target element in the real scene where the virtual item can be placed is determined and recommended.
[0009] In one embodiment of the present application, after determining the target element in the real scene where the virtual item can be placed, the method further includes:
[0010] According to the target element, the relevant parameter value of the virtual item is adjusted.
[0011] In one embodiment of the present application, before obtaining the virtual item and its corresponding item information, the method further includes:
[0012] Generate virtual items and their corresponding basic information;
[0013] Identifying and classifying the category to which the virtual item belongs according to the basic information corresponding to the virtual item to determine the classification information of the virtual item;
[0014] The virtual items and their corresponding item information are associated and mapped.
[0015] In one embodiment of the present application, obtaining each element in a real scene and its corresponding element information includes:
[0016] Real scene information is obtained, and each element in the real scene and its corresponding element information are obtained through a spatial ontology knowledge base, wherein the spatial ontology knowledge base includes ontology knowledge of all elements in the real scene.
[0017] In one embodiment of the present application, the calculating, according to the item information of the virtual item and the element information corresponding to each element in the real scene, the association between the virtual item and each element in the real scene comprises:
[0018] Extracting key features of items from item information corresponding to the virtual item, and extracting key features of elements from element information corresponding to each element;
[0019] Converting the item key feature into an item key feature vector, and converting the element key feature into an element key feature vector;
[0020] Based on the object key feature vector and the element key feature vector, a matching algorithm is used to calculate the association between the virtual object and each element in the real scene.
[0021] In one embodiment of the present application, the calculating, according to the item information of the virtual item and the element information corresponding to each element in the real scene, the association between the virtual item and each element in the real scene comprises:
[0022] Extracting different item features from the item information corresponding to the virtual item, and extracting different element features from the element information corresponding to the target element, wherein the target element is any element in the real scene;
[0023] Constructing an associated feature pair, wherein the associated feature pair includes an item feature and a corresponding element feature;
[0024] Calculate the matching degree between the item features and the corresponding element features in each associated feature pair;
[0025] Different weights are assigned to different pairs of correlation features according to their influence on the correlation;
[0026] The matching degrees of each associated feature pair are integrated according to the corresponding assigned weights to obtain a comprehensive score, and the comprehensive score is used to represent the association between the virtual object and the target element in the real scene.
[0027] In one embodiment of the present application, determining the target element in the real scene where the virtual item can be placed according to the association between the virtual item and each element includes:
[0028] Sorting all elements in the real scene according to the magnitude of the association, so as to select the first N elements with the highest association as target elements where the virtual item can be placed, wherein N is a positive integer;
[0029] Alternatively, a threshold is predetermined, and the element corresponding to the relevance greater than the threshold is used as the target element for placing the virtual item.
[0030] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a virtual item placement location recommendation system, the system comprising a location interaction module, the location interaction module comprising:
[0031] An acquisition unit, configured to acquire virtual items and their corresponding item information and various elements in a real scene and their corresponding element information, wherein the item information includes classification information of the virtual items and basic information of the virtual items, and the element information includes classification information of the elements and entity information of the elements;
[0032] A calculation unit, configured to calculate the correlation between the virtual item and each element in the real scene according to the item information corresponding to the virtual item and the element information corresponding to each element in the real scene;
[0033] The determination and recommendation unit is used to determine and recommend the target element in the real scene where the virtual item can be placed according to the association between the virtual item and each element.
[0034] In one embodiment of the present application, the system further includes:
[0035] A generation module, used to generate virtual items and their corresponding basic information;
[0036] A classification module, used to identify and classify the category to which the virtual item belongs according to the basic information corresponding to the virtual item, so as to determine the classification information of the virtual item;
[0037] The mapping module is used to associate and map the virtual items with their corresponding item information.
[0038] In one embodiment of the present application, the system further includes:
[0039] The scene module is used to obtain real scene information and obtain each element in the real scene and its corresponding element information through a spatial ontology knowledge base, wherein the spatial ontology knowledge base includes the ontology knowledge of all elements in the real scene.
[0040] In the technical solution provided in the embodiment of the present application, firstly obtain the virtual item and its corresponding item information and each element in the real scene and its corresponding element information, so that the correlation between the virtual item and each element in the real scene can be calculated based on the item information corresponding to the virtual item and the element information corresponding to each element in the real scene. Then, according to the correlation between the virtual item and each element, the target element in the real scene where the virtual item can be placed can be determined and recommended. That is, through the correlation analysis between the virtual item and each element in the real scene, a more suitable placement position can be automatically recommended for the virtual item, which can improve the efficiency and visual realism of implanting virtual items in the real scene. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 is a flow chart of a method for recommending a virtual item placement location provided by an embodiment of the present application;
[0042] Figure 2 is a flowchart of steps performed before obtaining a virtual item and its corresponding item information provided by an embodiment of the present application;
[0043] Figure 3 is a flowchart of steps for obtaining each element in a real scene and its corresponding element information provided by an embodiment of the present application;
[0044] Figure 4 This is a flowchart of the first step of calculating the association between the virtual item and each element in the real scene according to the item information of the virtual item and the element information corresponding to each element in the real scene provided by an embodiment of the present application;
[0045] Figure 5 is a flowchart of the second step of calculating the association between the virtual item and each element in the real scene according to the item information of the virtual item and the element information corresponding to each element in the real scene provided by an embodiment of the present application;
[0046] Figure 6 A flowchart of steps for determining and recommending target elements in a real scene where virtual items can be placed based on the association between virtual items and various elements provided by an embodiment of the present application;
[0047] Figure 7 2 is a schematic diagram of a virtual item placement location recommendation system provided by an embodiment of the present application. DETAILED DESCRIPTION
[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0049] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0051] See-Through technology, as the name suggests, means that users can see the real world outside the device. There are two common ways to implement See-Through: optical see-through and video see-through.
[0052] In the display scene of combining virtual and real under the optical perspective mode, since users can see the real scene and virtual scene at the same time, the scene superposition and information processing required are more complicated. In order to improve the realism of the virtual objects generated by the system, the virtual objects need to be better integrated into the real environment. The placement of virtual objects is the first problem that should be solved. In the current scheme, virtual objects are mostly displayed in a suspended state, which is not very realistic; or they rely on manual presetting or manual adjustment of the position of virtual objects superimposed in the real world, which is a heavy workload.
[0053] Based on this, the embodiments of the present application propose a method and system for recommending a virtual item placement location, aiming to automatically recommend a placement location for a virtual item, thereby improving the efficiency and visual realism of implanting virtual items in a real space.
[0054] Reference Figure 1 , Figure 1 It is a flowchart of a method for recommending a virtual item placement location provided in an embodiment of the present application, including but not limited to steps S110 to S130.
[0055] Step S110, obtaining virtual items and their corresponding item information and various elements in the real scene and their corresponding element information, the item information includes classification information of the virtual items and basic information of the virtual items, and the element information includes classification information of the elements and entity information of the elements.
[0056] In the embodiment of the present application, in order to automatically determine the placement position for placing virtual items, it is necessary to first obtain the virtual items and their corresponding item information and the elements in the real scene and their corresponding element information. Among them, the item information of the virtual items includes the virtual items and their corresponding item information and the elements in the real scene and their corresponding element information. The classification information of the virtual items refers to the information used to describe the category to which the virtual items belong, such as the virtual items can belong to the fruit category, the furniture category, the food category, the animal category, the clothing category, etc. The basic information of the virtual items refers to the information used to describe the basic attributes, basic characteristics, basic conditions, etc. of the virtual items. This information is usually necessary for a preliminary understanding of the virtual items, which can help people understand and recognize the virtual items more quickly. The elements in the real scene refer to the material entities that can be directly perceived by the senses in the real scene. If the exhibition hall is taken as the real scene, the material entities that can be directly perceived by the senses in the exhibition hall, such as the tables, chairs, walls, floors, exhibition frames, etc. in the exhibition hall, are all elements in the real scene. The classification information of the elements refers to the information used to describe the category to which the elements belong, such as the elements can belong to the building category, the furniture category, the decoration category, etc. The entity information of an element refers to the specific attributes and descriptions of the element in the corresponding real-world scenario, such as the element's name, location, type, form, status, etc.
[0057] Reference Figure 2 , Figure 2 It is a flowchart of steps performed before obtaining virtual items and their corresponding item information provided by an embodiment of the present application, including but not limited to steps S210 to S230.
[0058] Step S210, generating virtual items and their corresponding basic information;
[0059] Step S220, identifying and classifying the category to which the virtual item belongs according to the basic information corresponding to the virtual item, so as to determine the classification information of the virtual item;
[0060] Step S230: associate and map the virtual items and their corresponding item information.
[0061] In an embodiment of the present application, the system needs to first generate virtual items that need to be implanted in real scenes, and provide basic information corresponding to the virtual items. For example, the various attributes of virtual items can be defined first, such as name, type, function, appearance, etc. After determining the attributes of the virtual item, a model can be created to represent the virtual item. This may involve technologies such as 3D modeling and texture mapping to present the appearance and behavior of virtual items in a virtual environment. Next, code needs to be written to implement the generation logic of virtual items. This may include different methods such as random generation, generation based on specific rules, or generation based on user input. Finally, the logic of generating virtual items is integrated into the entire system, so that the system can generate virtual items and provide basic information corresponding to the virtual items.
[0062] Next, the attribute information of the virtual item can be extracted from the basic information corresponding to the virtual item. The attribute information is an important factor in determining the category to which the virtual item belongs. The category to which the virtual item belongs can be identified based on the attribute information of the virtual item. Based on the identified category to which the virtual item belongs, the virtual item is classified to determine the classification information of the virtual item. In the embodiment of the present application, the classification standard can be obtained through the spatial ontology knowledge base, and the classification of virtual items needs to be included in the existing classification of the spatial ontology knowledge base. For example, the existing classification of the spatial ontology knowledge base includes 5 categories, namely Class A, Class B, Class C, Class D and Class F. Based on the attribute information of the virtual item, the virtual item needs to be classified into one of the 5 existing categories.
[0063] After the virtual items are classified, the virtual items and their corresponding item information need to be associated and mapped, that is, the virtual items and their corresponding item information are bound so that after the virtual item is selected, the item information corresponding to the virtual item can be displayed accordingly. In the embodiment of the present application, the information corresponding to the virtual item can be entered one by one according to the preset information items of the classification to which the virtual item belongs. For example, the preset information items may include name, category, purpose, function, size, color, etc.
[0064] Reference Figure 3 , Figure 3 It is a flowchart of the steps for obtaining each element in a real scene and its corresponding element information provided by an embodiment of the present application, including but not limited to steps S310 to S320.
[0065] Step S310, obtaining real scene information;
[0066] Step S320, obtaining each element in the real scene and its corresponding element information through the spatial ontology knowledge base, the spatial ontology knowledge base includes the ontology knowledge of all elements in the real scene.
[0067] In the embodiment of the present application, the system first obtains the real scene information, and then interacts with the spatial ontology knowledge base to obtain each element in the real scene and its corresponding element information. Among them, the spatial ontology knowledge base includes the ontology knowledge of all elements in the real scene. The spatial ontology knowledge base is a knowledge base specifically used to represent and manage geographic spatial information. It defines the attributes, relationships and behaviors of objects in the geographic space to establish a conceptual model to help users understand and find geographic information. In the embodiment of the present application, the real scene information can be obtained through on-site sensors or cameras, etc., or the real scene can be manually entered into the system in advance.
[0068] Step S120, calculating the correlation between the virtual object and each element in the real scene according to the object information corresponding to the virtual object and the element information corresponding to each element in the real scene.
[0069] In the embodiment of the present application, after obtaining the virtual item and its corresponding item information and each element in the real scene and its corresponding element information, the association between the virtual item and each element in the real scene can be further calculated based on the item information corresponding to the virtual item and the element information corresponding to each element in the real scene. Specifically, the association between the virtual item and each element in the real scene can be determined by matching the item information corresponding to the virtual item with the element information corresponding to each element in the real scene.
[0070] Reference Figure 4 , Figure 4 It is a first step flowchart provided by an embodiment of the present application for calculating the association between a virtual item and each element in a real scene based on the item information of the virtual item and the element information corresponding to each element in the real scene, including but not limited to steps S410 to S430.
[0071] Step S410, extracting the key features of the item from the item information corresponding to the virtual item, and extracting the key features of the element from the element information corresponding to each element;
[0072] Step S420, converting the item key features into an item key feature vector, and converting the element key features into an element key feature vector;
[0073] Step S430, based on the object key feature vector and the element key feature vector, a matching algorithm is used to calculate the correlation between the virtual object and each element in the real scene.
[0074] In an embodiment of the present application, the key features of the item can be first extracted from the item information corresponding to the virtual item, and the key features of the element can be extracted from the element information corresponding to each element. For example, the category of the virtual item can be extracted from the item information corresponding to the virtual item as the key feature of the item, and the category of the element can be extracted from the element information corresponding to the element as the key feature of the element. The key features of the item are then converted into an item key feature vector, and the key features of the element are converted into an element key feature vector, so that the correlation between the virtual item and each element in the real scene can be calculated based on the item key feature vector and the element key feature vector, using a matching algorithm. The matching algorithm can use Euclidean distance, cosine similarity convolutional neural network (CNN), etc. The embodiment of the present application can effectively calculate the correlation between the virtual item and each element in the real scene by extracting key features for correlation calculation.
[0075] Reference Figure 5 , Figure 5 It is a second step flowchart provided by an embodiment of the present application for calculating the correlation between the virtual item and each element in the real scene based on the item information of the virtual item and the element information corresponding to each element in the real scene, including but not limited to steps S510 to S550.
[0076] Step S510, extracting different item features from the item information corresponding to the virtual item, and extracting different element features from the element information corresponding to the target element, where the target element is any element in the real scene;
[0077] Step S520, constructing an associated feature pair, the associated feature pair including an item feature and a corresponding element feature;
[0078] Step S530, calculating the matching degree between the item feature and the corresponding element feature in each associated feature pair;
[0079] Step S540, assigning different weights to different association feature pairs according to the degree of influence of different association feature pairs on the association;
[0080] Step S550, the matching degrees of each associated feature pair are integrated according to the corresponding assigned weights to obtain a comprehensive score, which is used to represent the correlation between the virtual object and the target element in the real scene.
[0081] In the embodiment of the present application, as another way to calculate the correlation between the virtual item and each element in the real scene, it is necessary to first extract different item features from the item information corresponding to the virtual item, such as the color feature, shape feature, size feature, category feature, etc. of the virtual item. Then extract different element features from the element information corresponding to the target element, such as the geometric shape feature, category feature, position feature, color feature, etc. of the element. Among them, the target element is any element in the real scene. Then, construct an associated feature pair, wherein the associated feature pair includes item features and corresponding element features. For example, the category feature of the virtual item and the category feature of the element can be used as an associated feature pair, and the shape feature of the virtual item and the position feature of the element can be used as an associated feature pair. Then, according to the degree of influence of different associated feature pairs on the correlation, different weights are assigned to different associated feature pairs. For example, the position feature may be more important than the color feature, so a higher weight can be assigned to the position feature. Finally, the matching degree of each associated feature pair is integrated according to the corresponding assigned weight to obtain a comprehensive score. Among them, the comprehensive score can be used to represent the correlation between the virtual item and the target element in the real scene. The higher the comprehensive score, the greater the correlation between the virtual item and the target element in the real scene. The embodiment of the present application calculates the correlation based on the weights of each feature pair, which can improve the accuracy of matching between the virtual item and each element in the real scene.
[0082] Step S130, according to the association between the virtual object and each element, the target element in the real scene where the virtual object can be placed is determined and recommended.
[0083] In the embodiment of the present application, after calculating the correlation between the virtual item and each element in the real scene, the target element in the real scene where the virtual item can be placed can be determined and recommended according to the correlation between the virtual item and each element. For example, the element corresponding to the maximum correlation can be used as the target element where the virtual item can be placed and recommended.
[0084] Reference Figure 6 , Figure 6 It is a flowchart of steps provided by an embodiment of the present application for determining and recommending target elements in a real scene where virtual items can be placed based on the association between virtual items and various elements, including but not limited to steps S610 to S620.
[0085] Step S610, sorting all elements in the real scene according to the relevance, so as to select the first N elements with the highest relevance as target elements for placing virtual items, where N is a positive integer;
[0086] Step S620, alternatively, a threshold is predetermined, and elements corresponding to the elements having a correlation greater than the threshold are used as target elements for placing virtual items.
[0087] In an embodiment of the present application, each element in the real scene can be sorted from large to small according to the relevance, or sorted from small to large, to obtain a sorted list corresponding to each element. Based on the sorted list, the first N elements with the highest relevance are selected as the target elements where virtual items can be placed. If the value of N is 1, the element with the highest relevance is selected as the target element where the virtual item can be placed. If the value of N is 3, the first 3 elements with the highest relevance are selected as the target elements where the virtual item can be placed.
[0088] In the embodiment of the present application, a threshold value may be predetermined, and elements corresponding to the correlation greater than the threshold value may be used as target elements for placing virtual items. For example, if there are three elements with a correlation greater than the threshold value, the three elements may be used as target elements for placing virtual items.
[0089] In the embodiment of the present application, when multiple target elements are determined to be capable of placing virtual items, multiple target elements may be displayed on the display interface to allow the user to select one. Alternatively, one target element may be randomly selected from the multiple target elements capable of placing virtual items as the final target element for placing the virtual item, i.e., the final placement position.
[0090] In some embodiments, after determining the target element in the real scene where the virtual item can be placed, the relevant parameter value of the virtual item can also be adjusted according to the target element. The relevant parameter value may include the size parameter value, shape parameter value, color parameter value, etc. of the virtual item. For example, if the exhibition hall is used as the real scene, the virtual item is a virtual painting, and the target element in the real scene (i.e., the exhibition hall) where the virtual item (i.e., the virtual painting) can be placed is determined to be each picture frame, then the shape of the virtual painting can be adjusted according to the shape of the picture frame, and the size of the virtual painting can also be adjusted according to the size of the picture frame. In this way, the virtual item can be perfectly fitted with the placement position (target element).
[0091] Reference Figure 7 , Figure 7 is a schematic diagram of a virtual item placement location recommendation system provided by an embodiment of the present application, comprising Figure 7 As shown, the recommendation system includes a location interaction module 710. The location interaction module 710 includes:
[0092] The acquisition unit 711 is used to acquire virtual items and their corresponding item information and various elements in the real scene and their corresponding element information, wherein the item information includes classification information of the virtual items and basic information of the virtual items, and the element information includes classification information of the elements and entity information of the elements;
[0093] A calculation unit 712, configured to calculate the correlation between the virtual item and each element in the real scene according to the item information corresponding to the virtual item and the element information corresponding to each element in the real scene;
[0094] The determination and recommendation unit 713 is used to determine and recommend target elements in the real scene where the virtual objects can be placed according to the associations between the virtual objects and various elements.
[0095] In the embodiment of the present application, the acquisition unit 711 of the position interaction module first acquires the virtual item and its corresponding item information and each element in the real scene and its corresponding element information, so that the calculation unit 712 can calculate the correlation between the virtual item and each element in the real scene based on the item information corresponding to the virtual item and the element information corresponding to each element in the real scene. Then, the determination and recommendation unit 713 can determine the target element in the real scene where the virtual item can be placed and recommend it based on the correlation between the virtual item and each element. That is, through the correlation analysis between the virtual item and each element in the real scene, a more suitable placement position can be automatically recommended for the virtual item, which can improve the efficiency and visual realism of implanting virtual items in the real scene.
[0096] Reference Figure 7 , the recommendation system also includes a generation module 720, a classification module 730, a mapping module 740 and a space ontology knowledge base 750. The generation module 720 is used to generate virtual items and their corresponding basic information. The classification module 730 is used to identify and classify the categories to which the virtual items belong according to the basic information corresponding to the virtual items, so as to determine the classification information of the virtual items. The mapping module 740 is used to associate and map the virtual items and their corresponding item information. The classification module 730 can interact with the space ontology knowledge base 750 to obtain the classification information items of the virtual items, that is, the information items required for classification, such as the name, the category, the function, etc. The classification module 730 can send the item information of the virtual items and the classification information items of the virtual items to the mapping module 740, and the mapping module 740 enters the information corresponding to the classification information items of the virtual items respectively, so as to complete the mapping association between the virtual items and their item information. If the information corresponding to the classification information item cannot be found from the item information of the virtual items, the mapping module 740 can interact with the generation module 720 to obtain more item information of the virtual items. After completing the information mapping, the mapping module 740 may transmit the virtual item and its corresponding item information to the position interaction module 710, so that the acquisition unit 711 of the position interaction module 710 may acquire the virtual item and its corresponding item information.
[0097] Reference Figure 7, the recommendation system also includes a scene module 760. The scene module 760 is used to obtain real scene information, and obtain each element in the real scene and its corresponding element information through the spatial ontology knowledge base 750, and the spatial ontology knowledge base includes the ontology knowledge of all elements in the real scene. The scene module 760 can interact with the spatial ontology knowledge base 750 to obtain each element in the real scene and its corresponding element information. After obtaining each element in the real scene and its corresponding element information, the scene module 760 can pass each element in the real scene and its corresponding element information to the position interaction module 710, so that the acquisition unit 711 of the position interaction module 710 can obtain each element in the real scene and its corresponding element information.
[0098] Reference Figure 7 The recommendation system further includes an output module 770. After determining a target element in the real scene where the virtual item can be placed, the location interaction module 710 can transmit the target element to the output module 770, and the output module 770 outputs the target element. After adjusting the relevant parameter value of the virtual item according to the target element, the output module 770 can also be used to output the relevant parameter value of the virtual item.
[0099] It should be noted that once the element used to place the virtual object is determined, the virtual object will be bound to the element, and the position of the virtual object will no longer change with the change of the user's field of view.
[0100] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0101] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0102] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, 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 solution of this embodiment.
[0103] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0104] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0105] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0106] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0107] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0108] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0109] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0110] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and substance of the present invention should be within the scope of the rights of the present invention.
Claims
1. A method for recommending a virtual item placement location, characterized in that: The method comprises: Acquire virtual items and their corresponding item information and various elements in a real scene and their corresponding element information, wherein the item information includes classification information of the virtual items and basic information of the virtual items, and the element information includes classification information of the elements and entity information of the elements; Calculating the association between the virtual item and each element in the real scene according to the item information corresponding to the virtual item and the element information corresponding to each element in the real scene; According to the association between the virtual item and each element, a target element in the real scene where the virtual item can be placed is determined and recommended.
2. The method according to claim 1, characterized in that: After determining the target element in the real scene where the virtual object can be placed, the method further includes: According to the target element, the relevant parameter value of the virtual item is adjusted.
3. The method according to claim 1, characterized in that: Before obtaining the virtual item and its corresponding item information, the method further includes: Generate virtual items and their corresponding basic information; Identifying and classifying the category to which the virtual item belongs according to the basic information corresponding to the virtual item to determine the classification information of the virtual item; The virtual items and their corresponding item information are associated and mapped.
4. The method according to claim 1, characterized in that: Get each element in the real scene and its corresponding element information, including: Real scene information is obtained, and each element in the real scene and its corresponding element information are obtained through a spatial ontology knowledge base, wherein the spatial ontology knowledge base includes ontology knowledge of all elements in the real scene.
5. The method according to claim 1, characterized in that The calculating the correlation between the virtual item and each element in the real scene according to the item information of the virtual item and the element information corresponding to each element in the real scene includes: Extracting key features of items from item information corresponding to the virtual item, and extracting key features of elements from element information corresponding to each element; Converting the item key feature into an item key feature vector, and converting the element key feature into an element key feature vector; Based on the object key feature vector and the element key feature vector, a matching algorithm is used to calculate the association between the virtual object and each element in the real scene.
6. The method according to claim 1, characterized in that The calculating, according to the item information of the virtual item and the element information corresponding to each element in the real scene, the association between the virtual item and each element in the real scene comprises: Extracting different item features from the item information corresponding to the virtual item, and extracting different element features from the element information corresponding to the target element, wherein the target element is any element in the real scene; Constructing an associated feature pair, wherein the associated feature pair includes an item feature and a corresponding element feature; Calculate the matching degree between the item features and the corresponding element features in each associated feature pair; Different weights are assigned to different pairs of correlation features according to their influence on the correlation; The matching degrees of each associated feature pair are integrated according to the corresponding assigned weights to obtain a comprehensive score, and the comprehensive score is used to represent the association between the virtual object and the target element in the real scene.
7. The method according to claim 1, characterized in that The step of determining, according to the association between the virtual item and each element, a target element in the real scene where the virtual item can be placed comprises: Sorting all elements in the real scene according to the magnitude of the association, so as to select the first N elements with the highest association as target elements where the virtual item can be placed, wherein N is a positive integer; Alternatively, a threshold is predetermined, and the element corresponding to the relevance greater than the threshold is used as the target element for placing the virtual item.
8. A virtual item placement recommendation system, characterized in that: The system includes a location interaction module, and the location interaction module includes: An acquisition unit, configured to acquire virtual items and their corresponding item information and various elements in a real scene and their corresponding element information, wherein the item information includes classification information of the virtual items and basic information of the virtual items, and the element information includes classification information of the elements and entity information of the elements; A calculation unit, configured to calculate the correlation between the virtual item and each element in the real scene according to the item information corresponding to the virtual item and the element information corresponding to each element in the real scene; The determination and recommendation unit is used to determine and recommend the target element in the real scene where the virtual item can be placed according to the association between the virtual item and each element.
9. The system according to claim 8, characterized in that The system further comprises: A generation module, used to generate virtual items and their corresponding basic information; A classification module, used to identify and classify the category to which the virtual item belongs according to the basic information corresponding to the virtual item, so as to determine the classification information of the virtual item; The mapping module is used to associate and map the virtual items with their corresponding item information.
10. The system according to claim 8, characterized in that The system further comprises: The scene module is used to obtain real scene information and obtain each element in the real scene and its corresponding element information through a spatial ontology knowledge base, wherein the spatial ontology knowledge base includes the ontology knowledge of all elements in the real scene.