Festival AR model generation method based on AI assistance

Abstract

The invention discloses a festival AR model generation method based on AI assistance, and the method comprises the steps: inputting a query about a festival AR model through an artificial intelligence robot, and outputting a query analysis result through the artificial intelligence robot; the artificial intelligence robot converts the query analysis result output by the artificial intelligence robot into instructions and parameters generated by the AR model; inputting the instruction and parameters generated by the AR model into an AI design editing tool platform to render and generate a rendering graph of a 3D model; and uploading the rendered image to a 3D model generation platform so as to generate a 3D model from the rendered image. The problem that a traditional 3D model creating process is tedious and time-consuming is solved. Through fusion of the AIGC technology, rapid, efficient and high-quality 3D model generation is realized so as to support development of AR application.

Description

Technical Field

[0001] The present invention relates to virtual technology, and in particular to a method for generating a festival AR model based on AI assistance. Background Art

[0002] Festival AR models are becoming more and more popular, but generating high-quality AR models usually requires complex design and rendering work. Existing methods have problems such as low efficiency, high cost, and limited creativity in the generation process. Therefore, an AI-assisted method is needed to generate festival AR models more efficiently and creatively. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies of the above-mentioned prior art and provide an AI-assisted festival AR model generation method to solve the cumbersome and time-consuming problems of the traditional 3D model creation process.

[0004] To achieve the above object, the technical solution of the present invention is:

[0005] A method for generating a festival AR model based on AI assistance, comprising:

[0006] Use the AI ​​robot to input queries about the festival AR model, and the AI ​​robot outputs the query analysis results;

[0007] The AI ​​robot converts the query analysis results it outputs into instructions and parameters generated by the AR model;

[0008] Inputting the instructions and parameters generated by the AR model into the AI ​​design editing tool platform to render and generate a rendering of the 3D model;

[0009] The rendering is uploaded to a 3D model generation platform to generate a 3D model from the rendering.

[0010] Furthermore, the AI-assisted festival AR model generation method further includes:

[0011] The 3D model is exported to the AR model management background, and the 3D model is adjusted to be suitable for the AR scene.

[0012] Furthermore, the artificial intelligence robot outputs the query analysis results as user preferences, including the color, shape, and movement of the model.

[0013] Furthermore, the artificial intelligence robot is ChatGPT.

[0014] Furthermore, the AI ​​design editing tool platform is clipdrop.co.

[0015] Furthermore, the 3D model generation platform is csm.ai.

[0016] The AR model management backend includes an AR environment module, an AR interaction module, a data storage module, a data analysis module, and a data interaction module; wherein,

[0017] The AR environment module is used to provide a 3D model for display in the form of a three-dimensional model;

[0018] The AR interaction module is used to realize the interaction operation between the user and the 3D model;

[0019] The data storage module is used to store user information and 3D model information;

[0020] The data analysis module is used to perform real-time analysis on user behavior and 3D model sales data;

[0021] The data interaction module is used to update the 3D model information in real time to ensure that the 3D model purchased by the user in the AR environment module is consistent with the 3D model information stored in the storage module.

[0022] The AR model management background also includes a user management module for verifying user identities and managing permissions.

[0023] Furthermore, the user information includes user purchase, user usage, AR interaction and error data during AR experience.

[0024] Furthermore, the error data in the AR experience process is obtained by: tracking points in the overall process, recording the errors captured in each link, storing the error log, and obtaining the error data in the AR experience process;

[0025] When error data is obtained during the AR experience, it is processed according to the severity, including:

[0026] Emergency level, the handling method is: send information to designated technicians for timely resolution;

[0027] For more serious cases, the following methods are used to handle the situation: Send the information to the designated operation and maintenance group for queue processing;

[0028] For the general level, the processing method is: according to the statistics of the error reports on the day, the processing is scheduled according to the frequency and time;

[0029] After the graded processing, error statistics are generated, including daily, weekly, and monthly reports, and regular review;

[0030] Analyze the root causes of the problems based on the error statistics and optimize them by category, including:

[0031] Caused by user operations, optimization measures: simplify user operations, add front-end page prompts, and set up a robot to automatically answer common questions;

[0032] The test is not covered. Optimization measures: Feed the error content back to the test case library to gradually expand the coverage;

[0033] Hardware device does not support, optimization measures: the market average device support rate is used as a benchmark. If it is lower than the benchmark, it means that the underlying AR capabilities need to be replaced.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] High degree of automation: Compared with traditional manual production, this method reduces manual operations and improves efficiency.

[0036] Innovative Diversity: The generated models are diverse and innovative, enriching the design of 3D models.

[0037] Rapid iteration: Rapidly generate and optimize models by adjusting parameters and details to meet different needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of a method for generating an AI-assisted festival AR model according to an embodiment of the present invention;

[0039] Figure 2 A flowchart of a method for generating an AI-assisted festival AR model provided in a preferred embodiment of the present invention;

[0040] Figure 3 Schematic diagram of the AR model for analyzing the most popular festivals among Generation Z using ChatGPT;

[0041] Figure 4 A diagram showing the text description of the model generated using ChatGPT;

[0042] Figure 5-6 Generate renderings of 3D models using clipdrop;

[0043] Figure 7-8 Generate 3D model schematics for csm.ai;

[0044] Fig. 9 This is a schematic diagram of the composition of the AR model management background;

[0045] Fig.10 It is the AR error monitoring flow chart;

[0046] Fig.11 Optimize the action map for problem classification. DETAILED DESCRIPTION

[0047] Example:

[0048] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0049] See also Figure 1 As shown, the AI-assisted festival AR model generation method provided in this embodiment mainly includes the following steps:

[0050] 101. Use the artificial intelligence robot to input a query about the festival AR model, and the artificial intelligence robot outputs the query analysis results;

[0051] In this step, an artificial intelligence robot is used to automatically analyze consumers' preferences for holiday AR models, and the types of holiday AR models preferred by consumers are analyzed.

[0052] 102. The artificial intelligence robot converts the query analysis results output by it into instructions and parameters generated by the AR model;

[0053] In this step, the type of holiday AR model preferred by the consumer is obtained and the instructions and parameters for making the model are automatically generated, thus eliminating the need for manual operation.

[0054] 103. Inputting the instructions and parameters generated by the AR model into the AI ​​design editing tool platform to render and generate a rendering of the 3D model;

[0055] In this step, you only need to enter the instructions and parameters for AR model generation to generate a rendering of the 3D model.

[0056] 104. Upload the rendering to a 3D model generation platform to generate a 3D model from the rendering.

[0057] It can be seen that this method solves the cumbersome and time-consuming problems of the traditional 3D model creation process, and can achieve fast, efficient, and high-quality 3D model generation to support the development of AR applications.

[0058] In a preferred embodiment, if Figure 2 As shown, the above-mentioned AI-assisted festival AR model generation method also includes the following steps:

[0059] 105. Export the 3D model to an AR model management background, and adjust the 3D model to be suitable for an AR scene.

[0060] In this step, the 3D model is exported to the AR model management background to adjust the light, add animation, etc. to make it more suitable for AR scenes. When the user uses the AR application to scan the adapted scene, the application automatically loads and displays the generated 3D model, and the user can interact.

[0061] In a specific embodiment, the artificial intelligence robot is ChatGPT, such as Figure 3 As shown in the figure, using ChatGPT, input relevant queries about holiday AR models, such as "the most popular Santa Claus AR model among Generation Z", ChatGPT analyzes relevant data on the Internet, hot topics on social media, and user comments to obtain the latest AR model trends and popular features, and ChatGPT outputs text descriptions including detailed information such as color, shape, and action, which reflect the preferences of Generation Z users. Based on the analysis results, Figure 4 As shown in the figure, ChatGPT generates text descriptions related to the most popular holiday AR models, such as "a cheerful Santa Claus wearing a red coat, holding a gift bag and smiling"; ChatGPT converts the generated text descriptions into instructions and parameters for model generation for the subsequent model generation process.

[0062] In a specific embodiment, the AI ​​design editing tool platform is clipdrop.co; Figure 5-6 As shown, using clipdrop.co, users upload text descriptions generated by ChatGPT and set relevant parameters, such as the scale of the model, lighting effects, etc.; clipdrop.co renders and generates images of 3D models based on the user's input; users can adjust the rendered images by dragging, rotating, scaling, etc. to meet their personalized needs; clipdrop.co provides commands and operations, such as "adjust lighting direction" and "change model size", for users to optimize rendered images.

[0063] In a specific embodiment, the 3D model generation platform is csm.ai; Figure 7-8 As shown, the user's optimized rendering is uploaded to the csm.ai platform; csm.ai analyzes the rendering and generates a corresponding 3D model, considering the model's appearance, material, texture, etc. The user can further optimize the generated 3D model through commands, operations, parameters, etc. to adapt to AR scenarios and meet the preferences of Generation Z users.

[0064] It can be seen that this AI-assisted holiday AR model generation method, by combining tools such as ChatGPT, Midjourney and csm.ai, has achieved efficient, innovative and user-friendly AR model generation. This method can effectively reduce the difficulty and cost of model generation, while meeting the needs of Generation Z users, and provides new ideas and solutions for the development of the AR field.

[0065] In a specific embodiment, if Fig. 9As shown, the AR model management background mainly includes an AR environment module, an AR interaction module, a data storage module, a data analysis module and a data interaction module.

[0066] Among them, the AR environment module is used to provide 3D models in the form of three-dimensional models, from which users can select and purchase 3D models; the AR interaction module is used to realize interactive operations between users and 3D models, such as dragging or enlarging 3D models, taking photos, and recording videos; the data storage module is used to store user information, 3D model information, and operation records. The 3D model information includes the specifications, styles, prices and other information of the 3D model, so as to facilitate the management and query of gifts, and to classify, display, manage inventory and analyze sales data of 3D models.

[0067] The data analysis module is used to perform real-time analysis on user behavior and 3D model sales data, so as to analyze the user's gift purchasing habits, provide more targeted services to operators, improve operational efficiency, provide data support, and help operators make scientific decisions; the data interaction module is used to update 3D model information in real time to ensure that the gifts purchased by users in the AR environment are consistent with the information in the gift database; preferably, the AR model management background also includes a user management module for user identity verification and authority management;

[0068] In addition, in order to solve the problem that operators cannot know the actual user usage, and thus cannot optimize gift styles and recommendations in a timely manner, nor can they optimize model adaptation and AR functions, in the gift-giving interaction process, user information is recorded in real time, including user purchase, user usage, AR interaction and other data, including error data during the AR experience, and the analysis results are fed back to operators so that they can optimize gift styles, model adaptation, AR functions, etc. in a timely manner. Specifically, Figure 10-11 The error data during the AR experience is obtained in the following way:

[0069] Track errors in the overall process, record the errors captured in each link, store error logs, and obtain error data during the AR experience.

[0070] When error data is obtained during the AR experience, it is processed according to the severity, including:

[0071] Emergency level, the handling method is: send information to designated technicians for timely resolution;

[0072] For more serious cases, the following methods are used to handle the situation: Send the information to the designated operation and maintenance group for queue processing;

[0073] For the general level, the processing method is: according to the statistics of the error reports on the day, the processing is scheduled according to the frequency and time;

[0074] After the graded processing, error statistics are generated, including daily, weekly, and monthly reports, and regular review;

[0075] Analyze the root causes of the problems based on the error statistics and optimize them by category, including:

[0076] Caused by user operations, optimization measures: simplify user operations, add front-end page prompts, and set up a robot to automatically answer common questions;

[0077] The test is not covered. Optimization measures: Feed the error content back to the test case library to gradually expand the coverage;

[0078] The hardware device is not supported. Optimization measures: The market average device support rate is used as the benchmark. If it is lower than the benchmark, it means that the underlying AR capabilities need to be replaced.

[0079] In this way, by analyzing the data of the gift-giving interaction process, on the one hand, we can provide data support for subsequent gift customization, and on the other hand, we can optimize according to the AR operation situation of the user's device, reduce operational errors, facilitate user operation, meet the special needs of 3D models in the AR environment, and improve the actual user value of AR gifts.

[0080] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable ordinary technicians in the field to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent changes or modifications made based on the essence of the content of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating a festival AR model based on AI assistance, characterized in that: include: Use the AI ​​robot to input queries about the festival AR model, and the AI ​​robot outputs the query analysis results; The AI ​​robot converts the query analysis results it outputs into instructions and parameters generated by the AR model; Inputting the instructions and parameters generated by the AR model into the AI ​​design editing tool platform to render and generate a rendering of the 3D model; The rendering is uploaded to a 3D model generation platform to generate a 3D model from the rendering.

2. The AI-assisted festival AR model generation method according to claim 1, characterized in that: Also includes: The 3D model is exported to the AR model management background, and the 3D model is adjusted to be suitable for the AR scene.

3. The AI-assisted festival AR model generation method according to claim 1, characterized in that: The artificial intelligence robot outputs the query analysis results as the user's preferences, including the color, shape, and movement of the model.

4. The AI-assisted festival AR model generation method according to claim 1 or 3, characterized in that: The artificial intelligence robot is ChatGPT.

5. The AI-assisted festival AR model generation method according to claim 1, characterized in that: The AI ​​design editing tool platform is clipdrop.co.

6. The AI-assisted festival AR model generation method according to claim 1, characterized in that: The 3D model generation platform is csm.ai.

7. The AI-assisted festival AR model generation method according to claim 2, characterized in that: The AR model management backend includes an AR environment module, an AR interaction module, a data storage module, a data analysis module, and a data interaction module; wherein, The AR environment module is used to provide a 3D model for display in the form of a three-dimensional model; The AR interaction module is used to realize the interaction operation between the user and the 3D model; The data storage module is used to store user information and 3D model information; The data analysis module is used to perform real-time analysis on user behavior and 3D model sales data; The data interaction module is used to update the 3D model information in real time to ensure that the 3D model purchased by the user in the AR environment module is consistent with the 3D model information stored in the storage module.

8. The AI-assisted festival AR model generation method according to claim 7, characterized in that: The AR model management background also includes a user management module for verifying user identities and managing permissions.

9. The AI-assisted festival AR model generation method according to claim 7, characterized in that: The user information includes user purchase, user usage, AR interaction and error data during the AR experience.

10. The AI-assisted festival AR model generation method according to claim 9, characterized in that: The error data in the AR experience process is obtained by: tracking points in the overall process, recording the errors captured in each link, storing the error log, and obtaining the error data in the AR experience process; When error data is obtained during the AR experience, it is processed according to the severity, including: Emergency level, the handling method is: send information to designated technicians for timely resolution; For more serious cases, the following methods are used to handle the situation: Send the information to the designated operation and maintenance group for queue processing; For the general level, the processing method is: according to the statistics of the error reports on the day, the processing is scheduled according to the frequency and time; After the graded processing, error statistics are generated, including daily, weekly, and monthly reports, and regular review; Analyze the root causes of the problems based on the error statistics and optimize them by category, including: Caused by user operations, optimization measures: simplify user operations, add front-end page prompts, and set up a robot to automatically answer common questions; The test is not covered. Optimization measures: Feed the error content back to the test case library to gradually expand the coverage; The hardware device is not supported. Optimization measures: The market average device support rate is used as the benchmark. If it is lower than the benchmark, it means that the underlying AR capabilities need to be replaced.

Images