Virtual space design teaching auxiliary tool for intelligent evaluation and feedback

Abstract

The invention discloses a virtual space design teaching auxiliary tool for intelligent evaluation and feedback, and belongs to the field of teaching. The virtual space design teaching auxiliary tool comprises a virtual space design module, an intelligent evaluation module, a real-time feedback and interaction module and a learning recording and growth analysis module. The intelligent evaluation module is based on industrial standards of spatial design, AI can analyze spatial layout, color matching and light arrangement, quantitative scores and quality evaluation are provided for students, and the integrating degree of design styles and project requirements can be detected. According to the scheme, a comprehensive intelligent evaluation module is provided by integrating an AI technology, data analysis and virtual space design. The module not only can quantify scores, but also can generate targeted design improvement suggestions, thereby helping students to improve the design ability and optimize the learning experience, and finally promoting the innovation and development of space design education.

Description

Technical Field

[0001] The present invention relates to the field of teaching, and more specifically, to a virtual space design teaching auxiliary tool with intelligent evaluation and feedback. Background Art

[0002] In current spatial design education, students usually rely on traditional design evaluation methods, such as subjective scoring by teachers and peer evaluation. This method has many limitations, including inconsistency in evaluation criteria, bias caused by subjectivity, and difficulty in providing systematic feedback. In addition, with the advancement of design technology, virtual reality (VR) and augmented reality (AR) technologies are increasingly used in spatial design, but most existing evaluation tools have failed to fully integrate with these emerging technologies, resulting in the inability to optimize the design using real-time data analysis. Although current intelligent design evaluation technologies have emerged, they mostly focus on specific aspects of analysis, such as color matching or lighting simulation, and lack comprehensive, multi-dimensional comprehensive evaluation capabilities. These technologies are usually unable to automatically identify and analyze multiple factors in the design, such as spatial layout, functional area division, color matching, and style fit, which limits the evaluation results to surface data and makes it impossible to deeply understand the overall quality of the design. Summary of the invention

[0003] To address this problem, this solution integrates AI technology, data analysis and virtual space design to provide a comprehensive intelligent evaluation module. This module can not only quantify the score, but also generate targeted design improvement suggestions, thereby helping students improve their design capabilities, optimize their learning experience, and ultimately promote the innovation and development of space design education.

[0004] Technical solution: A virtual space design teaching auxiliary tool with intelligent evaluation and feedback, including a virtual space design module, an intelligent evaluation module, a real-time feedback and interaction module, and a learning record and growth analysis module;

[0005] The virtual space design module supports students to create and edit 3D models in virtual space. They can add common elements of space design, including walls, furniture, and lighting, to simulate the real design process. It allows users to view the design results from different perspectives and experience the design effects immersively through VR devices to feel the layout and atmosphere of the space.

[0006] The intelligent evaluation module is based on the industry standards of space design. AI can analyze space layout, color matching, and light arrangement to provide students with quantitative scores and quality evaluations. It can also detect the fit between design styles and project requirements, including industrial style and Nordic style, and point out the highlights and shortcomings of the design. Based on the evaluation results, AI can automatically propose design improvement suggestions, including color matching adjustments, furniture position changes, and optimized light distribution.

[0007] The real-time feedback and interaction module provides instant feedback during the student design process, including reminding the user of functional problems in the space or places that do not match the style. The teacher can directly view the student's design work through the virtual space, provide real-time or delayed voice and text feedback, and discuss and guide the students with modifications;

[0008] The learning record and growth analysis module automatically saves the students' design process and the results of each stage for review and improvement. It also generates a learning report for each student, analyzes their growth curve in various skills, and helps teachers accurately grasp the students' progress.

[0009] Preferably, the working steps of the intelligent evaluation module are as follows:

[0010] S1. Data collection and analysis: Prepare to collect industry standards related to space design, including space layout, color matching, light arrangement, and furniture arrangement, and collect design sample data that conform to different styles. Perform feature extraction on the sample data and analyze the common features of excellent designs that conform to industry standards, including layout proportions, lighting parameters, color saturation, and element spacing, to provide training data for the AI ​​model.

[0011] S2. Use the convolutional neural network (CNN) training model to identify the proportion and partition of the space layout in the design. Based on color theory, use a multimodal model that combines natural language processing (NLP) with the CNN model to analyze the color matching in the design. Use the lighting rendering model or physical simulation model to analyze the light source layout and brightness distribution. Based on the trained classification model, analyze the material, color, and element matching characteristics of the space design to automatically classify the design style into industrial style and Nordic style to determine whether it meets the project requirements.

[0012] S3. The model scores the design in terms of layout, color, light, style fit, etc. Each score is converted into a quantitative score based on the confidence of the model output. The area, proportion and flow of the functional area are calculated to give a rationality score for space utilization. Based on color matching theory, the contrast, hue and saturation of the color are scored. The light distribution is analyzed to score the uniformity of the lighting, the suitability of the brightness and the coordination between natural light and artificial light. Based on the results of the style feature matching, a fit score is given to determine whether the design style meets the project requirements. The scores of each sub-item are weighted to obtain a comprehensive score for the design so that students can understand the quality level of the overall design.

[0013] S4. The model can detect the highlights in the design, automatically mark and display them, encourage students' strengths, and point out specific deficiencies in the design by comparing them with industry standards and excellent design samples, including:

[0014] The layout is unreasonable, the area of ​​a certain area is insufficient or the traffic flow is not smooth;

[0015] The color matching deviates from the style and there are discordant colors;

[0016] Inadequately or excessively lit areas;

[0017] S5. Based on the analyzed style and color matching issues, AI can recommend color schemes that match the style, including more suitable background colors and accessory colors. If the model detects that the furniture layout is unreasonable, it can make adjustment suggestions and indicate the ideal position. Based on the light analysis, AI can recommend adding or reducing light sources, or adjusting the position of light sources to improve the uniformity and comfort of space lighting.

[0018] S6. Automatically generate feedback reports, display scores, pros and cons analysis, and optimization suggestions by item, and directly mark problem areas in the designed 3D model to help students understand and optimize the design more intuitively.

[0019] Preferably, the layout scoring method is as follows:

[0020] Functional area identification: Identify the location and area of ​​different functional areas in the design through AI models;

[0021] Area and proportion calculation: The model calculates the area proportion of each functional area and checks whether it meets industry standards and design goals;

[0022] Analysis of the smoothness of moving lines: Use the path planning algorithm to analyze the moving lines in the space and check whether there are problems such as the moving lines being too long or blocked;

[0023] Layout score: score is given based on indicators such as the proportion of functional area and smoothness of traffic flow.

[0024] Preferably, the color matching scoring method is as follows:

[0025] Color extraction and classification: Use K-Means clustering algorithm to extract the main colors in the design scheme, and judge the color combination through color theory;

[0026] Contrast and hue analysis: calculate the contrast and hue deviation of colors, and evaluate whether the colors are harmonious based on color matching theory;

[0027] Saturation and style analysis: Analyze the saturation and brightness of the main colors to check whether they meet the style requirements;

[0028] Color scoring: The color matching score is generated by comprehensively considering contrast, hue and saturation. Reasonable contrast, harmonious hue and saturation that match the style will get high scores, while those with poor contrast will get low scores.

[0029] Preferably, the light arrangement scoring method is as follows:

[0030] Light source positioning: Use image segmentation and analysis technology to identify the number and distribution of light sources in the design and distinguish between natural and artificial light sources;

[0031] Brightness distribution calculation: Calculate the brightness values ​​of different areas in the space by simulating the physical model of illumination to determine the uniformity of light distribution and the suitability of brightness;

[0032] Coordination of natural light and artificial light: Analyze the ratio of natural light to artificial light to ensure that natural light is dominant during the day and artificial light provides sufficient supplementary light at night. Analyze whether there are areas that are too dark or too bright;

[0033] Lighting score: score based on the number of light sources, brightness distribution, and coordination between natural light and artificial light.

[0034] Preferably, the style fit scoring method is as follows:

[0035] Design feature extraction: The convolutional neural network deep learning model is used to extract the style features of the design, including the main materials, colors, and furniture styles;

[0036] Style matching analysis: Compare the designed features with sample data of different styles and calculate the similarity with the target style;

[0037] Style matching score: Based on the similarity score, the design style and the project requirements are obtained. Designs that match the style get high scores, and designs that do not match the style get low scores.

[0038] Preferably, the comprehensive score is calculated as follows:

[0039] Weight setting: According to teaching needs and project focus, assign weights to each scoring item: layout: 30%; color: 25%; light: 25%; style fit: 20%

[0040] Weighted average: Add up the scores of each item according to their weights to calculate the comprehensive score. The formula is as follows:

[0041] Comprehensive score = layout score × 0.3 + color score × 0.25 + light score × 0.25 + style score × 0.2 comprehensive score;

[0042] Grading feedback generation: Generate feedback reports and provide students with scores, weighted comprehensive scores, problem areas, and optimization suggestions to help them fully understand the quality level of their designs.

[0043] Compared with the prior art, the advantages of the present invention are:

[0044] (1) Improve the objectivity of evaluation: Use AI technology to quantify and score designs, reduce subjective bias, ensure more consistent and accurate evaluation results, and help students obtain real design feedback.

[0045] (2) Provide comprehensive feedback: Combined with multi-dimensional analysis such as layout, color, light, and style fit, the feedback systematically points out the highlights and shortcomings of the design, helping students to fully understand and improve their design works.

[0046] (3) Promote learning and innovation: Through automatically generated design improvement suggestions, students are encouraged to explore new ideas and improve their design capabilities. At the same time, the immersive experience of virtual space enhances the interactivity and fun of learning, and promotes students' active learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a schematic diagram of the overall system of a virtual space design teaching auxiliary tool with intelligent evaluation and feedback according to the present invention. DETAILED DESCRIPTION

[0048] For examples, see Figure 1 , a virtual space design teaching auxiliary tool with intelligent evaluation and feedback, including a virtual space design module, an intelligent evaluation module, a real-time feedback and interaction module, and a learning record and growth analysis module;

[0049] The virtual space design module supports students to create and edit 3D models in virtual space. They can add common elements of space design, including walls, furniture, and lighting, to simulate the real design process. It allows users to view the design results from different perspectives and experience the design effects immersively through VR devices to feel the layout and atmosphere of the space.

[0050] The intelligent evaluation module is based on the industry standards of space design. AI can analyze space layout, color matching, and light arrangement to provide students with quantitative scores and quality evaluations. It can also detect the fit between design styles and project requirements, including industrial style and Nordic style, and point out the highlights and shortcomings of the design. Based on the evaluation results, AI can automatically propose design improvement suggestions, including color matching adjustments, furniture position changes, and optimized light distribution.

[0051] The real-time feedback and interaction module provides instant feedback during the student design process, including reminding the user of functional problems in the space or places that do not match the style. The teacher can directly view the student's design work through the virtual space, provide real-time or delayed voice and text feedback, and discuss and guide the students with modifications;

[0052] The learning record and growth analysis module automatically saves the students' design process and the results of each stage for review and improvement. It also generates a learning report for each student, analyzes their growth curve in various skills, and helps teachers accurately grasp the students' progress.

[0053] The working steps of the intelligent evaluation module are as follows:

[0054] S1. Data collection and analysis: Prepare to collect industry standards related to space design, including space layout, color matching, light arrangement, and furniture arrangement, and collect design sample data that conform to different styles. Perform feature extraction on the sample data and analyze the common features of excellent designs that conform to industry standards, including layout proportions, lighting parameters, color saturation, and element spacing, to provide training data for the AI ​​model.

[0055] S2. Use the convolutional neural network (CNN) training model to identify the proportion and partition of the space layout in the design. Based on color theory, use a multimodal model that combines natural language processing (NLP) with the CNN model to analyze the color matching in the design. Use the lighting rendering model or physical simulation model to analyze the light source layout and brightness distribution. Based on the trained classification model, analyze the material, color, and element matching characteristics of the space design to automatically classify the design style into industrial style and Nordic style to determine whether it meets the project requirements.

[0056] S3. The model scores the design in terms of layout, color, light, style fit, etc. Each score is converted into a quantitative score based on the confidence of the model output. The area, proportion and flow of the functional area are calculated to give a rationality score for space utilization. Based on color matching theory, the contrast, hue and saturation of the color are scored. The light distribution is analyzed to score the uniformity of the lighting, the suitability of the brightness and the coordination between natural light and artificial light. Based on the results of the style feature matching, a fit score is given to determine whether the design style meets the project requirements. The scores of each sub-item are weighted to obtain a comprehensive score for the design so that students can understand the quality level of the overall design.

[0057] S4. The model can detect the highlights in the design, automatically mark and display them, encourage students' strengths, and point out specific deficiencies in the design by comparing them with industry standards and excellent design samples, including:

[0058] The layout is unreasonable, the area of ​​a certain area is insufficient or the traffic flow is not smooth;

[0059] The color matching deviates from the style and there are discordant colors;

[0060] Inadequately or excessively lit areas;

[0061] S5. Based on the analyzed style and color matching issues, AI can recommend color schemes that match the style, including more suitable background colors and accessory colors. If the model detects that the furniture layout is unreasonable, it can make adjustment suggestions and indicate the ideal position. Based on the light analysis, AI can recommend adding or reducing light sources, or adjusting the position of light sources to improve the uniformity and comfort of space lighting.

[0062] S6. Automatically generate feedback reports, display scores, pros and cons analysis, and optimization suggestions by item, and directly mark problem areas in the designed 3D model to help students understand and optimize the design more intuitively.

[0063] The layout scoring method is as follows:

[0064] Functional area recognition: The location and area of ​​different functional areas in the design are identified through AI models. Different areas of the space can be segmented through image segmentation technology (such as Mask R-CNN).

[0065] Area and proportion calculation: The model calculates the area proportion of each functional area and checks whether it meets industry standards and design goals. For example, whether the area occupied by the living room and kitchen is reasonable and meets the standards of the space type.

[0066] Traffic flow analysis: Use path planning algorithms (such as A* algorithm) to analyze the traffic flow in the space and check whether there are problems such as too long traffic flow, obstruction, etc. For example, the model can measure the walking distance from the living room to the kitchen to determine the convenience of the traffic flow.

[0067] Layout score: Scoring is based on indicators such as the proportion of functional areas and the smoothness of moving lines. For example, a reasonable proportion and smooth moving lines will get high scores, while the opposite will get low scores.

[0068] Color matching score

[0069] Color extraction and classification: Use K-Means clustering algorithm to extract the main colors in the design scheme, and judge the color combination through color theory (such as triadic colors, complementary colors, etc.).

[0070] Contrast and hue analysis: Calculate the contrast and hue deviation of colors, and evaluate whether the colors are harmonious based on color matching theory (such as color wheel theory, color psychology). For example, color matching with similar hues is considered harmonious, and too sharp contrast may get a low score.

[0071] Saturation and style analysis: Analyze the saturation and brightness of the main colors to check whether they meet the style requirements. For example, the color saturation of industrial style is usually low, while the Nordic style tends to have high brightness colors.

[0072] Color score: The color matching score is generated by combining contrast, hue and saturation. Reasonable contrast, harmonious hue and saturation that match the style will get high scores, while those that are not will get low scores.

[0073] Lighting arrangement scoring (lighting scoring)

[0074] Light source localization: Use image segmentation and analysis techniques (such as YOLO object detection) to identify the number and distribution of light sources in the design, and distinguish between natural light sources (such as windows) and artificial light sources (such as lamps).

[0075] Brightness distribution calculation: The brightness values ​​of different areas in the space are calculated by simulating the physical model of illumination to determine the uniformity of light distribution and the suitability of brightness.

[0076] Coordination of natural light and artificial light: Analyze the ratio of natural light to artificial light to ensure that natural light is dominant during the day and artificial light provides sufficient supplementary light at night. Analyze whether there are areas that are too dark or too bright.

[0077] Lighting score: The score is given based on the number of light sources, brightness distribution, and the coordination between natural light and artificial light. For example, even lighting and no dead spots will get high scores, while areas that are too dark or too bright will get low scores.

[0078] Style fit score

[0079] Design feature extraction: The style features of the design are extracted through deep learning models such as convolutional neural networks (CNN), including the main materials (such as metal, wood), colors, furniture styles, etc.

[0080] Style matching analysis: Compare the design features with sample data of different styles and calculate the similarity with the target style. For example, the Nordic style usually includes bright colors and simple furniture, while the industrial style may be more inclined to metal materials and dark colors.

[0081] Style matching score: Based on the similarity score, the design style and the project requirements are obtained. Designs that match the style get high scores, and designs that do not match the style get low scores.

[0082] The comprehensive score is calculated as follows:

[0083] Weight setting: According to teaching needs and project focus, assign weights to each scoring item: layout: 30%; color: 25%; light: 25%; style fit: 20%

[0084] Weighted average: Add up the scores of each item according to their weights to calculate the comprehensive score. The formula is as follows:

[0085] Comprehensive score = layout score × 0.3 + color score × 0.25 + light score × 0.25 + style score × 0.2 comprehensive score;

[0086] Grading feedback generation: Generate feedback reports and provide students with scores, weighted comprehensive scores, problem areas, and optimization suggestions to help them fully understand the quality level of their designs.

[0087] The basic principles, main features and advantages of the present invention are shown and described above; those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected; the scope of protection claimed by the present invention is determined by the attached claims and their effects.

Claims

1. A virtual space design teaching aid tool with intelligent evaluation and feedback, characterized in that: It includes virtual space design module, intelligent evaluation module, real-time feedback and interaction module, and learning record and growth analysis module; The virtual space design module supports students to create and edit 3D models in virtual space. They can add common elements of space design, including walls, furniture, and lighting, to simulate the real design process. It allows users to view the design results from different perspectives and experience the design effects immersively through VR devices to feel the layout and atmosphere of the space. The intelligent evaluation module is based on the industry standards of space design. AI can analyze space layout, color matching, and light arrangement to provide students with quantitative scores and quality evaluations. It can also detect the fit between design styles and project requirements, including industrial style and Nordic style, and point out the highlights and shortcomings of the design. Based on the evaluation results, AI can automatically propose design improvement suggestions, including color matching adjustments, furniture position changes, and optimized light distribution. The real-time feedback and interaction module provides instant feedback during the student design process, including reminding the user of functional problems in the space or places that do not match the style. The teacher can directly view the student's design work through the virtual space, provide real-time or delayed voice and text feedback, and discuss and guide the students with modifications; The learning record and growth analysis module automatically saves the students' design process and the results of each stage for review and improvement. It also generates a learning report for each student, analyzes their growth curve in various skills, and helps teachers accurately grasp the students' progress.

2. According to claim 1, a virtual space design teaching auxiliary tool with intelligent evaluation and feedback, characterized in that: The working steps of the intelligent evaluation module are as follows: S1. Data collection and analysis: Prepare to collect industry standards related to space design, including space layout, color matching, light arrangement, and furniture arrangement, and collect design sample data that conform to different styles. Perform feature extraction on the sample data and analyze the common features of excellent designs that conform to industry standards, including layout proportions, lighting parameters, color saturation, and element spacing, to provide training data for the AI ​​model. S2. Use the convolutional neural network (CNN) training model to identify the proportion and partition of the space layout in the design. Based on color theory, use a multimodal model that combines natural language processing (NLP) with the CNN model to analyze the color matching in the design. Use the lighting rendering model or physical simulation model to analyze the light source layout and brightness distribution. Based on the trained classification model, analyze the material, color, and element matching characteristics of the space design to automatically classify the design style into industrial style and Nordic style to determine whether it meets the project requirements. S3. The model scores the design in terms of layout, color, light, style fit, etc. Each score is converted into a quantitative score based on the confidence of the model output. The area, proportion and flow of the functional area are calculated to give a rationality score for space utilization. Based on color matching theory, the contrast, hue and saturation of the color are scored. The light distribution is analyzed to score the uniformity of the lighting, the suitability of the brightness and the coordination between natural light and artificial light. Based on the results of the style feature matching, a fit score is given to determine whether the design style meets the project requirements. The scores of each sub-item are weighted to obtain a comprehensive score for the design so that students can understand the quality level of the overall design. S4. The model can detect the highlights in the design, automatically mark and display them, encourage students' strengths, and point out specific deficiencies in the design by comparing them with industry standards and excellent design samples, including: The layout is unreasonable, the area of ​​a certain area is insufficient or the traffic flow is not smooth; The color matching deviates from the style and there are discordant colors; Inadequately or excessively lit areas; S5. Based on the analyzed style and color matching issues, AI can recommend color schemes that match the style, including more suitable background colors and accessory colors. If the model detects that the furniture layout is unreasonable, it can make adjustment suggestions and indicate the ideal position. Based on the light analysis, AI can recommend adding or reducing light sources, or adjusting the position of light sources to improve the uniformity and comfort of space lighting. S6. Automatically generate feedback reports, display scores, pros and cons analysis, and optimization suggestions by item, and directly mark problem areas in the designed 3D model to help students understand and optimize the design more intuitively.

3. According to claim 2, a virtual space design teaching auxiliary tool with intelligent evaluation and feedback, characterized in that: The layout scoring method is as follows: Functional area identification: Identify the location and area of ​​different functional areas in the design through AI models; Area and proportion calculation: The model calculates the area proportion of each functional area and checks whether it meets industry standards and design goals; Analysis of the smoothness of moving lines: Use the path planning algorithm to analyze the moving lines in the space and check whether there are problems such as the moving lines being too long or blocked; Layout score: score is given based on indicators such as the proportion of functional area and smoothness of traffic flow.

4. According to claim 3, a virtual space design teaching auxiliary tool with intelligent evaluation and feedback is characterized in that: The color matching scoring method is as follows: Color extraction and classification: Use K-Means clustering algorithm to extract the main colors in the design scheme, and judge the color combination through color theory; Contrast and hue analysis: calculate the contrast and hue deviation of colors, and evaluate whether the colors are harmonious based on color matching theory; Saturation and style analysis: Analyze the saturation and brightness of the main colors to check whether they meet the style requirements; Color scoring: The color matching score is generated by comprehensively considering contrast, hue and saturation. Reasonable contrast, harmonious hue and saturation that match the style will get high scores, while those with poor contrast will get low scores.

5. According to claim 4, a virtual space design teaching auxiliary tool with intelligent evaluation and feedback is characterized in that: The light arrangement scoring method is as follows: Light source positioning: Use image segmentation and analysis technology to identify the number and distribution of light sources in the design and distinguish between natural and artificial light sources; Brightness distribution calculation: Calculate the brightness values ​​of different areas in the space by simulating the physical model of illumination to determine the uniformity of light distribution and the suitability of brightness; Coordination of natural light and artificial light: Analyze the ratio of natural light to artificial light to ensure that natural light is dominant during the day and artificial light provides sufficient supplementary light at night. Analyze whether there are areas that are too dark or too bright; Lighting score: score based on the number of light sources, brightness distribution, and coordination between natural light and artificial light.

6. According to claim 5, a virtual space design teaching auxiliary tool with intelligent evaluation and feedback is characterized in that: The style fit scoring method is as follows: Design feature extraction: The convolutional neural network deep learning model is used to extract the style features of the design, including the main materials, colors, and furniture styles; Style matching analysis: Compare the designed features with sample data of different styles and calculate the similarity with the target style; Style matching score: Based on the similarity score, the design style and the project requirements are obtained. Designs that match the style get high scores, and designs that do not match the style get low scores.

7. The virtual space design teaching auxiliary tool with intelligent evaluation and feedback according to claim 6, characterized in that: The comprehensive score is calculated as follows: Weight setting: Assign weights to each scoring item based on teaching needs and project focus, layout: 30%; Color: 25%; Light: 25%; Style fit: 20% Weighted average: Add up the scores of each item according to their weights to calculate the comprehensive score. The formula is as follows: Comprehensive score = layout score × 0.3 + color score × 0.25 + light score × 0.25 + style score × 0.2 comprehensive score; Grading feedback generation: Generate feedback reports and provide students with scores, weighted comprehensive scores, problem areas, and optimization suggestions to help them fully understand the quality level of their designs.

Images