An artificial intelligence-based scenario generation system

Abstract

The present invention provides an artificial intelligence-based scene generation system, which includes a scene understanding module, a scene construction module, a rendering optimization module, and a scene adjustment module; the scene understanding module is used to parse out key elements, layout information, and rendering information for scene generation from user input information; the scene construction module is used to construct a three-dimensional scene according to the information provided by the scene understanding unit; the rendering optimization module is used to perform rendering processing on the three-dimensional scene constructed by the scene construction module to generate a final three-dimensional scene; the scene adjustment module is used to perform change and adjustment processing on the finally generated three-dimensional scene according to user requirements; the present invention realizes an automated process from user input to high-quality three-dimensional scene generation, greatly improving the efficiency and quality of scene design, and at the same time enhancing the ability of user personalized customization and interactive experience.

Description

Technical Field

[0001] The present invention relates to the field of scene generation systems, and particularly to a scene generation system based on artificial intelligence. Background Art

[0002] In the rapid development of the digital age, three-dimensional scene generation technology has become a key driving force in fields such as virtual reality, game development, film and television production, and even urban planning. With the progress of technology, the demand for more realistic, efficient, and highly personalized three-dimensional scenes is increasing day by day. Traditional manual scene design methods have gradually been unable to meet the requirements of modern society for three-dimensional scene generation due to their long time consumption, high cost, and difficulty in adapting to rapidly changing demands. Therefore, exploring a new method that can automatically generate accurate and realistic three-dimensional scenes while allowing users to customize and adjust according to their personal preferences has become an important goal of current technological development.

[0003] Referring to relevant publicly disclosed technical solutions, the technology with the publication number CN117273006A proposes an artificial intelligence content generation method and system. By performing semantic analysis and inspection before content generation, multiple expandable items are obtained, providing multiple versions for subsequent content generation. After content generation, security inspection is carried out to ensure that the content generated by artificial intelligence meets the requirements of grammar and logic. At the same time, it will also predict the possible directions of the generated content to see if they contain expandable items, and select the direction with the most expandable items to continue generating content, and finally output the content, overcoming the problems of low quality and lack of diversification of the content generated by the existing technology. However, this solution may be insufficient in understanding users' generation requirements and personalized adjustment capabilities, especially in precisely capturing users' specific element layouts, style preferences, and dynamic adjustment requirements for three-dimensional scenes, and cannot provide a high level of depth and flexibility. Summary of the Invention

[0004] The purpose of the present invention is to propose a scene generation system based on artificial intelligence for the current deficiencies.

[0005] The present invention adopts the following technical solutions:

[0006] A scene generation system based on artificial intelligence, the system includes a scene understanding module, a scene construction module, a rendering optimization module, and a scene adjustment module;

[0007] The scene understanding module is used to parse key elements, layout information, and rendering information for scene generation from user input information; the scene construction module is used to construct a three-dimensional scene according to the information provided by the scene understanding unit; the rendering optimization module is used to perform rendering processing on the three-dimensional scene constructed by the scene construction module to generate the final three-dimensional scene; the scene adjustment module is used to perform change and adjustment processing on the finally generated three-dimensional scene according to user requirements.

[0008] The scene understanding module includes a data receiving unit, a key element extraction unit, and a layout understanding unit; the data receiving unit is used to receive various forms of input information provided by the user; the key element extraction unit is used to analyze and process the received input information, and extract key elements, layout information, and rendering information for scene generation therefrom; the layout understanding unit is used to establish the spatial relationships of the key elements, providing a blueprint for subsequent scene construction;

[0009] The scene construction module includes a three-dimensional object generation unit and a scene layout adjustment unit; the three-dimensional object generation unit is used to generate three-dimensional object models corresponding to the key elements provided by the scene understanding module; the scene layout adjustment unit is used to complete the spatial position adjustment and fusion between the three-dimensional object models;

[0010] Further, the key elements extracted by the key element extraction unit further include the description clarity of each key element, and the description clarity of each key element is obtained by obtaining the attribute integrity and semantic clarity of each key element;

[0011] Further, the layout understanding unit includes an element layout subunit, an element connection thesaurus, and a conflict element adjustment subunit. The element layout subunit is used to generate a preliminary layout of each key element according to each key element and its layout information; the element connection thesaurus is a preset database containing the connection degrees quantitatively represented between different key elements; the conflict element adjustment subunit is used to identify and resolve the layout conflicts in the preliminary layout of each key element by combining the description clarity and connection degree of each key element, and generate the adjusted key elements and their final layout;

[0012] Further, the three-dimensional object generation unit dynamically generates three-dimensional object models corresponding to the key elements provided by the conflict element adjustment subunit by using a generative adversarial network; during the generation process of the three-dimensional object models corresponding to each key element, it includes adjusting the detail level of the three-dimensional object models according to the description clarity of each key element, so as to ensure that the generated three-dimensional object models conform to the user input description;

[0013] Further, the scene layout adjustment unit performs spatial position adjustment and fusion on the generated three-dimensional object models according to the final layout provided by the conflict element adjustment subunit; this includes adjusting the relative positions and angles between the three-dimensional object models by combining geometric constraints and simulated physical rules, so as to complete the construction of the three-dimensional scene;

[0014] Further, based on the rendering information provided by the scene understanding module, the rendering optimization module renders the three-dimensional scene constructed by the scene layout adjustment unit through ray tracing and physically based rendering techniques, thereby generating the final three-dimensional scene;

[0015] Further, the scene adjustment module includes a scene feedback update unit and a rendering feedback update unit; the scene feedback update unit is used to receive the feedback information of the user on the generated scene and perform modification operations on the generated scene; the rendering update unit is used to receive the rendering feedback information of the user and perform rendering operations on the modified scene to generate the modified three-dimensional scene.

[0016] The beneficial effects achieved by the present invention are:

[0017] The present invention accurately analyzes the input information of the user, thereby capturing the key elements, layout information, and rendering information for scene generation, ensuring a seamless conversion from user requirements to scene design; by combining the description clarity and connection degree of each key element to finely adjust and resolve the layout conflicts of each key element in the scene, the generation of the three-dimensional scene can be more finely completed according to the user's understanding; by receiving the feedback of the user and adjusting the scene in combination with the user feedback information, the user's sense of participation and satisfaction in scene design are enhanced, thereby ensuring that the finally produced three-dimensional scene fully meets the user's expectations. Description of the Drawings

[0018] The present invention can be further understood from the following description in conjunction with the drawings. The components in the drawings are not necessarily drawn to scale, but the emphasis is placed on showing the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0019] Figure 1 It is a schematic diagram of the overall module of the present invention.

[0020] Figure 2 It is a schematic flow diagram of the method for obtaining the description clarity of the key elements of the present invention.

[0021] Figure 3 It is a schematic work flow diagram of the conflict element adjustment subunit of the present invention.

[0022] Figure 4 It is a schematic work flow diagram of the layout update unit of the present invention. Detailed Embodiments

[0023] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention; for those skilled in the art, after consulting the following detailed description, other systems, methods and / or features of this embodiment will become obvious; it is intended that all such additional systems, methods, features and advantages are included in this specification; included within the scope of the present invention and protected by the appended claims; additional features of the disclosed embodiments are described in the following detailed description and will be obvious in accordance with the following detailed description.

[0024] In the drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right", etc. indicating the orientation or positional relationship, they are based on the orientation or positional relationship shown in the drawings. This is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, the terms describing the positional relationship in the drawings are only for illustrative purposes and cannot be understood as a limitation of this patent. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances.

[0025] Embodiment 1:

[0026] As Figure 1 shown, this embodiment provides a scenario generation system based on artificial intelligence. The system includes a scenario understanding module, a scenario construction module, a rendering optimization module, and a scenario adjustment module;

[0027] The scenario understanding module is used to parse out key elements, layout information, and rendering information for scenario generation from the user input information; the scenario construction module is used to construct a three-dimensional scenario based on the information provided by the scenario understanding unit; the rendering optimization module is used to perform rendering processing on the three-dimensional scenario constructed by the scenario construction module to generate the final three-dimensional scenario; the scenario adjustment module is used to perform change and adjustment processing on the finally generated three-dimensional scenario according to user requirements.

[0028] The scenario understanding module includes a data receiving unit, a key element extraction unit, and a layout understanding unit; the data receiving unit is used to receive various forms of input information provided by the user; the key element extraction unit is used to analyze and process the received input information, and extract key elements, layout information, and rendering information for scenario generation from it; the layout understanding unit is used to establish the spatial relationship of each key element to provide a blueprint for subsequent scenario construction.

[0029] The scene construction module includes a three-dimensional object generation unit and a scene layout adjustment unit; the three-dimensional object generation unit is used to generate three-dimensional object models corresponding to each key element provided by the scene understanding module; the scene layout adjustment unit is used to complete the spatial position adjustment and fusion between the three-dimensional object models;

[0030] The scene adjustment module includes a user feedback receiving unit, a scene fine-tuning unit, and a rendering update unit; the user feedback receiving unit is used to receive feedback information of the user on the generated scene, and the scene fine-tuning unit is used to perform specific scene fine-tuning operations in combination with the feedback information; the rendering update unit is used to complete the rendering operation on the fine-tuned scene;

[0031] Further, as Figure 2 shown, the key elements extracted by the key element extraction unit further include the description clarity of each key element; the description clarity of each key element is obtained through the following method:

[0032] S11: Obtain the attribute information of each key element, and the attribute information includes, but is not limited to, attribute descriptions such as the size, color, and shape of the key element;

[0033] S12: Calculate the attribute integrity score of each key element:

[0034]

[0035]

[0036] Among them, P i is the attribute integrity score of the i-th key element, a ik is the existence judgment coefficient of the attribute k in the i-th key element, and m is the number of attributes of the i-th key element, which can be preset according to the type of the key element;

[0037] S13: Obtain the semantic description information of each key element; the semantic description information is all vocabulary descriptions of the corresponding key element;

[0038] S14: Calculate the semantic clarity score of each key element:

[0039]

[0040] Among them, S i is the semantic clarity score of the i-th key element, M i is the number of words with unclear or polysemous descriptions in the semantic description information of the i-th key element, and W i is the total number of words in the semantic description information of the i-th key element;

[0041] S15: Evaluate the description clarity of each key element:

[0042] D i = ω1·P i + ω2·S i ;

[0043] where D i is the description clarity of the i-th key element, ω1 and ω2 are respectively the pre-set weight coefficients of attribute integrity and semantic clarity, satisfying ω1 + ω2 = 1;

[0044] Furthermore, the layout understanding unit includes an element layout sub-unit, an element connection thesaurus, and a conflict element adjustment sub-unit. The element layout sub-unit is used to generate a preliminary layout of each key element according to each key element and its layout information; the element connection thesaurus is a pre-set database containing the connection degrees quantitatively represented between different key elements; the conflict element adjustment sub-unit is used to identify and resolve layout conflicts in the preliminary layout of each key element, and generate each adjusted key element and its final layout;

[0045] Furthermore, as Figure 3 shown, the specific working process of the conflict element adjustment sub-unit is as follows:

[0046] S21: Identify the layout conflict situation of each key element in the scene through spatial analysis technology; the conflict situation includes but is not limited to the position overlap between key elements and the layout that does not conform to physical laws; the spatial analysis technology includes but is not limited to collision detection and physical rule verification;

[0047] S22: For key elements that have layout conflicts with each other, evaluate their priorities:

[0048]

[0049] where F i is the priority coefficient of the i-th key element with layout conflicts, E i,j is the connection degree between the i-th key element with layout conflicts and the j-th key element in the scene that does not have layout conflicts, satisfying 0 ≤ E i,j ≤ 1; n is the number of key elements in the scene that do not have layout conflicts;

[0050] S23: Compare the priorities of each key element that has layout conflicts with each other, and select the key element with the highest priority to keep its current attributes and position unchanged as the basic point for layout adjustment;

[0051] S24: For other key elements with lower priorities, perform operations of attribute reduction or position adjustment on these key elements;

[0052] S25: Repeat the previous step until there is no layout conflict in the scene, and use the finally adjusted key elements and their final layout as the blueprint for subsequent scene construction;

[0053] Further, the 3D object generation unit dynamically generates 3D object models corresponding to each key element provided by the conflict element adjustment subunit using a generative adversarial network; during the generation process of the 3D object models corresponding to each key element, it includes adjusting the level of detail of the 3D object models according to the description clarity of each key element, so as to ensure that the generated 3D object models conform to the user input description;

[0054] Further, the scene layout adjustment unit adjusts the spatial positions and fuses the generated 3D object models according to the final layout provided by the conflict element adjustment subunit; this includes adjusting the relative positions and angles between the 3D object models in combination with geometric constraints and simulated physical rules, so as to complete the construction of the 3D scene;

[0055] Further, the scene adjustment module includes a scene feedback update unit and a rendering feedback update unit; the scene feedback update unit is used to receive the feedback information of the user on the generated scene and perform modification operations on the generated scene; the rendering update unit is used to receive the rendering feedback information of the user and perform rendering operations on the modified scene to generate a modified 3D scene.

[0056] Embodiment 2:

[0057] This embodiment should be understood as including at least all the features of any one of the foregoing embodiments and being further improved on this basis;

[0058] Although the automatic generation technology can greatly improve the efficiency and creativity of scene design, it is still a challenge to ensure that the generated scene fully meets the specific needs and detailed expectations of the user; to make up for the possible gaps in the automatic generation process, this embodiment provides a flexible post-adjustment mechanism for the user in combination with the scene adjustment module; the scene adjustment module includes a scene feedback update unit and a rendering feedback update unit; the scene feedback update unit is used to receive the feedback information of the user on the generated scene and perform modification operations on the generated scene; the rendering update unit is used to receive the rendering feedback information of the user and perform rendering operations on the modified scene to generate a modified final 3D scene;

[0059] Further, the scenario feedback and update unit includes a key element adjustment subunit, a key element replacement unit, and a layout update unit; the key element adjustment subunit is configured to receive the adjustment information of the existing key elements in the generated scenario feedback by the user, and the key element replacement unit is configured to receive the information of adding new key elements and deleting the existing key elements in the generated scenario feedback by the user; the layout update unit is configured to receive the layout adjustment information feedback by the user, generate the adjusted key elements and their final layouts after the user feedback adjustment as the blueprints modified by the user, and send the modified blueprints to the scenario construction module to construct the modified 3D scenario;

[0060] Further, as Figure 4 shown, the specific working process of the layout update unit is as follows:

[0061] S31: Obtain the layout adjustment information feedback by the user, the adjustment information of the existing key elements in the generated scenario, the information of adding new key elements and deleting the existing key elements in the generated scenario, and generate the preliminary layouts of the adjusted key elements according to all the above information;

[0062] S32: Combine the spatial analysis technology to identify the layout conflict situations of the adjusted key elements in the preliminary layout scenario;

[0063] S33: For the key elements with layout conflicts with each other in the adjusted preliminary layout scenario, evaluate their modification priorities:

[0064]

[0065] Among them, G k is the priority coefficient of the kth key element with layout conflicts after adjustment, D k is the description clarity of the kth key element with layout conflicts after adjustment, α k is the adjustment weight of the kth key element with layout conflicts after adjustment, E k,m is the degree of connection between the kth key element with layout conflicts after adjustment and the mth key element without layout conflicts in the adjusted scenario, satisfying 0 ≤ E k,m ≤ 1; l is the number of key elements without layout conflicts in the adjusted scenario, and max(E k,m ) is the maximum value of all E k,m ;

[0066] For the adjustment weight α k satisfies:

[0067]

[0068] S34: Compare the priorities of the key elements with layout conflicts after adjustment, and select the key element with the highest priority to keep its current attributes and position unchanged as the basic point for layout adjustment;

[0069] S35: For other key elements with lower priorities, perform operations to reduce the attributes or adjust the positions of these key elements;

[0070] S36: Repeat the previous step until there is no layout conflict in the modified scenario, and use the finally adjusted key elements and their final layout as the blueprint modified by the user;

[0071] S37: Send the modified blueprint to the scene construction module to construct the modified 3D scene;

[0072] In this embodiment, the scene adjustment module executes the feedback modification of the user on the generated scene, improving the functionality and flexibility of the scene generation system; it allows the user to make detailed customization of the automatically generated scene according to personal preferences, and the personalized customization ability greatly enhances the user experience; the user can directly give feedback and adjust the generated scene, greatly improving the overall scene design and development efficiency.

[0073] The content disclosed above is only the preferred and feasible embodiment of the present invention, and does not limit the protection scope of the present invention. Therefore, all equivalent technical changes made by using the content of the specification and drawings of the present invention are included in the protection scope of the present invention. In addition, the elements therein can be updated with the development of technology.

Claims

1. An artificial intelligence-based scenario generation system, characterized in that, The system includes a scene understanding module, a scene construction module, a rendering optimization module, and a scene adjustment module; The scene understanding module is used to parse out key elements, layout information, and rendering information for scene generation from the user input information; the scene construction module is used to construct a three-dimensional scene according to the information provided by the scene understanding unit; The rendering optimization module is used to perform rendering processing on the three-dimensional scene constructed by the scene construction module to generate the final three-dimensional scene; The scene adjustment module is used to perform change and adjustment processing on the finally generated three-dimensional scene according to user requirements; The scene understanding module includes a data receiving unit, a key element extraction unit, and a layout understanding unit; the data receiving unit is used to receive various forms of input information provided by the user; the key element extraction unit is used to analyze and process the received input information, and extract key elements, layout information, and rendering information for scene generation therefrom; the layout understanding unit is used to establish the spatial relationship of each key element, providing a blueprint for subsequent scene construction; The scene construction module includes a three-dimensional object generation unit and a scene layout adjustment unit; the three-dimensional object generation unit is used to generate three-dimensional object models corresponding to each key element provided by the scene understanding module; The scene layout adjustment unit is used to complete the spatial position adjustment and fusion between the three-dimensional object models; The working process of the layout understanding unit includes: S21: Identify the layout conflict situation of each key element in the scene through spatial analysis technology; S22: For the key elements that have layout conflicts with each other, evaluate their priorities: ； Among them, is the priority coefficient of the th key element with layout conflict, is the degree of connection between the th key element with layout conflict and the th key element without layout conflict in the scenario, satisfying ; is the number of key elements without layout conflict in the scenario; is the description clarity of the th key element. S23: Compare the priorities of each key element that has layout conflicts with each other, and select the key element with the highest priority to keep its current attributes and position unchanged as the basic point for layout adjustment; S24: For other key elements with lower priorities, perform attribute reduction or position adjustment operations on these key elements; S25: Repeat the above steps until there is no layout conflict situation in the scene, and use the finally adjusted key elements and their final layout as the blueprint for subsequent scene construction.

2. The scene generation system based on artificial intelligence according to claim 1, wherein, The key elements extracted by the key element extraction unit also include the description clarity of each key element, and the description clarity of each key element is obtained by obtaining the attribute integrity and semantic clarity of each key element.

3. The scenario generation system based on artificial intelligence according to claim 1, characterized in that, The layout understanding unit includes an element layout subunit, an element connection thesaurus, and a conflict element adjustment subunit. The element layout subunit is used to generate the preliminary layout of each key element according to each key element and its layout information; the element connection thesaurus is a preset database, containing the connection degree represented quantitatively between different key elements; the conflict element adjustment subunit is used to identify and resolve the layout conflicts in the preliminary layout of each key element by combining the description clarity and connection degree of each key element, and generate the adjusted key elements and their final layout.

4. The scenario generation system based on artificial intelligence according to claim 1, wherein, The three-dimensional object generation unit dynamically generates three-dimensional object models corresponding to each key element provided by the conflict element adjustment subunit using a generative adversarial network; during the generation process of the three-dimensional object models corresponding to each key element, it includes adjusting the level of detail of the three-dimensional object models according to the description clarity of each key element, so as to ensure that the generated three-dimensional object models conform to the user input description.

5. An artificial intelligence-based scenario generation system according to claim 1, characterized in that, The scene layout adjustment unit adjusts the spatial positions and fuses the generated three-dimensional object models according to the final layout provided by the conflict element adjustment subunit; this includes adjusting the relative positions and angles between the three-dimensional object models in combination with geometric constraints and simulated physical rules, thereby completing the construction of the three-dimensional scene.

6. An artificial intelligence-based scenario generation system according to claim 1, wherein The rendering optimization module renders the three-dimensional scene constructed by the scene layout adjustment unit through ray tracing and physically based rendering techniques based on the rendering information provided by the scene understanding module, thereby generating the final three-dimensional scene.

7. An artificial intelligence-based scenario generation system according to claim 1, wherein The scene adjustment module includes a scene feedback update unit and a rendering feedback update unit; The scene feedback update unit is used to receive the feedback information of the user on the generated scene and perform modification operations on the generated scene; the rendering update unit is used to receive the rendering feedback information of the user and perform rendering operations on the modified scene to generate the modified three-dimensional scene.

Images