Intelligent data processing system and method for interior design

Abstract

The application relates to the technical field of intelligent data processing, and discloses an intelligent data processing system and method for indoor design. The application obtains a preliminary design scheme based on space conditions and user demands, collects historical light data of corresponding time periods based on user work demands, analyzes health abnormalities of users in different space environments under the influence of light and the sensitivity of the users to light, screens the preliminary design scheme based on the health abnormalities of the users in the different space environments under the influence of light and the sensitivity of the users to light, obtains a to-be-tested design scheme, matches materials of the to-be-tested design scheme, calculates the cost, screens a design scheme meeting the user budget, fundamentally avoids health hazards caused by improper environmental design while ensuring that the design scheme meets functional and aesthetic demands, finally outputs an optimized scheme meeting health standards and satisfying the user budget, and improves the service quality of indoor design.

Description

Technical Field

[0001] This invention relates to the field of intelligent data processing technology, and in particular to an intelligent data processing system and method for interior design. Background Technology

[0002] Intelligent data processing in interior design is a process of optimizing design processes and decisions through artificial intelligence and big data analytics, encompassing data collection, model building, scheme generation, and iterative optimization.

[0003] In existing interior design methods, the process usually relies on the designer's experience and subjective judgment. The design scheme is mostly based on static spatial dimensions and the functional and aesthetic needs proposed by users. There is a lack of scientific quantitative analysis of dynamic environmental factors and their long-term impact on users' health. This may lead to potential health risks in the final design scheme, and compromises are often forced at the implementation stage due to budget constraints. For example, current technology rarely considers the impact of lighting environment on human physiological rhythms, visual health and psychological state. Designers usually design daylighting and lighting based on standard illuminance values ​​or artistic effects, and cannot make personalized plans based on users' specific working hours, historical lighting habits and personal physiological sensitivities.

[0004] To address the aforementioned problems, this invention provides an intelligent data processing system and method for interior design. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent data processing system and method for interior design. While ensuring that the design scheme meets functional and aesthetic requirements, this invention fundamentally avoids health hazards caused by improper environmental design, and ultimately outputs an optimal solution that meets both health standards and user budget, thereby improving the quality of interior design services.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] The intelligent data processing method for interior design includes the following specific steps:

[0008] Step 1: Collect indoor space parameters and obtain a preliminary design scheme based on space conditions and user needs;

[0009] Step 2: Collect historical light data for the corresponding time period based on user work needs, obtain physiological data of users in different spatial environments, and analyze the health abnormalities of users in different spatial environments under the influence of light and the sensitivity of users to light.

[0010] Step 3: Based on the health abnormalities of users in different spatial environments under the influence of light and the users' sensitivity to light, the preliminary design schemes are screened to obtain the design schemes to be tested;

[0011] Step 4: Perform material matching and cost calculation for the design scheme to be tested, and select a design scheme that meets the user's budget.

[0012] Preferably, step one includes the following specific steps:

[0013] A 3D laser scanner is used to perform a panoramic scan of the interior space, generating raw 3D point cloud data and identifying the structural elements of the interior space.

[0014] We collect basic user information through online forms and mine natural dialogues using sentiment analysis and keyword extraction models to obtain users' emotional needs and potential demands.

[0015] Collect user lifestyle data and analyze their activity paths, frequency of area use, and daily routines in the existing space;

[0016] User profiles are generated based on users' emotional needs, potential needs, activity paths, regional usage frequency, and daily routines.

[0017] Using spatial parameters and user profiles as input conditions, the interior design model generates preliminary design schemes with different styles and layouts in batches based on the input conditions.

[0018] Preferably, step two includes the following specific steps:

[0019] Based on the historical ambient illuminance collected during the user's core working time period, the light illuminance is obtained using the light illuminance fluctuation calculation formula, which is: ,in, For light fluctuation rate, The duration of historical ambient light intensity data collection. Let be the historical ambient illuminance at time t. The historical ambient illuminance at time t-1 This represents a safe value for ambient light fluctuations. Integral over time;

[0020] Acquire physiological data of users in different spatial environments, including HRV, GSR, body temperature and heart rate, and simultaneously collect spatial environmental data, including illuminance of lighting equipment, color temperature of lighting equipment, noise, VOC concentration, temperature and humidity;

[0021] HRV abnormalities are obtained based on the ratio of standard HRV to average HRV, GSR abnormalities are obtained based on the ratio of average GSR to standard GSR, body temperature abnormalities are obtained based on the ratio of average body temperature to standard body temperature, and heart rate abnormalities are obtained based on the ratio of average heart rate to standard heart rate. The HRV abnormalities, GSR abnormalities, body temperature abnormalities, and heart rate abnormalities are weighted and summed to obtain the user's health abnormalities under different environments.

[0022] The abnormal health values ​​of indoor space users under light fluctuation are obtained by multiplying the light fluctuation rate, the health impact coefficient of light fluctuation, and the abnormal health value.

[0023] The sensitivity index is calculated by dividing the HRV difference in different spatial environments by the illuminance difference of lighting equipment in different spatial environments, and the sensitivity anomaly value is obtained by dividing the sensitivity index by the standard sensitivity.

[0024] The sensitivity anomalies of indoor space users under light fluctuations are obtained by multiplying the light fluctuation rate, the sensitivity influence coefficient of light fluctuations, and the sensitivity anomalies.

[0025] Preferably, step three includes the following specific steps:

[0026] Obtain the health anomaly values ​​and light sensitivity anomaly values ​​of indoor space users under light fluctuations corresponding to the preliminary design scheme, and screen the preliminary design schemes that simultaneously meet the preset health anomaly thresholds and light sensitivity anomaly thresholds, and set them as the design schemes to be tested.

[0027] Preferably, step four includes the following specific steps:

[0028] A target demand vector is generated based on the user profile. The target demand vector includes VOC emission rate, light reflectivity and market price. The attribute vector of each material is obtained. The similarity between the attribute vector of each material and the target demand vector in the direction is calculated based on the cosine similarity algorithm. The material with the highest similarity is obtained.

[0029] Cost calculations are performed by multiplying the bill of materials corresponding to the most similar materials by the corresponding market prices, and then selecting design solutions that fit the user's budget.

[0030] An intelligent data processing system for interior design, comprising methods for implementing intelligent data processing in interior design, including:

[0031] The preliminary scheme screening module is used to collect indoor space parameters and obtain preliminary design schemes based on space conditions and user needs;

[0032] The health anomaly analysis module is used to collect historical light data for corresponding time periods based on user work needs, obtain users' physiological data in different spatial environments, and analyze health anomalies of users in different spatial environments under the influence of light.

[0033] The light sensitivity analysis module is used to collect historical light data for a corresponding time period based on user work needs, and analyze the sensitivity of users to light in different spatial environments under the influence of light.

[0034] The test scheme screening module is used to screen preliminary design schemes based on the health abnormalities of users in different spatial environments under the influence of light and the users' sensitivity to light, and to obtain test design schemes.

[0035] The final solution selection module is used to match materials and calculate costs for the design schemes under test, and to select design schemes that meet the user's budget.

[0036] An electronic device includes a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-described intelligent data processing method for interior design by calling the computer program stored in the memory.

[0037] A computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the aforementioned intelligent data processing method for interior design.

[0038] Compared with the prior art, the beneficial effects of the present invention are:

[0039] This invention collects indoor space parameters, obtains preliminary design schemes based on spatial conditions and user needs, collects historical light data for corresponding time periods based on user work needs, acquires physiological data of users in different spatial environments, analyzes health abnormalities of users in different spatial environments under the influence of light, and assesses users' sensitivity to light. Based on the health abnormalities of users in different spatial environments under the influence of light and their sensitivity to light, the preliminary design schemes are screened to obtain test design schemes. Material matching and cost calculation are performed on the test design schemes, and design schemes that meet the user's budget are selected. This invention ensures that the design scheme meets functional and aesthetic requirements while fundamentally avoiding health hazards caused by improper environmental design, and finally outputs the optimal scheme that meets both health standards and user budget, thus improving the quality of interior design services. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a schematic diagram of the intelligent data processing method for interior design according to the present invention;

[0042] Figure 2 This is a flowchart illustrating step one of the intelligent data processing methods for interior design according to the present invention.

[0043] Figure 3 This is a flowchart illustrating step two of the intelligent data processing method for interior design according to the present invention.

[0044] Figure 4 This is a schematic diagram of the overall framework of the intelligent data processing system for interior design according to the present invention. Detailed Implementation

[0045] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0046] Example 1

[0047] Please see Figure 1 This invention provides an intelligent data processing method for interior design, which includes the following specific steps:

[0048] Step 1: Collect indoor space parameters and obtain a preliminary design scheme based on space conditions and user needs;

[0049] Please see Figure 2 In this embodiment, step one includes the following specific steps:

[0050] A 3D laser scanner is used to perform a panoramic scan of the interior space, generating raw 3D point cloud data and identifying the structural elements of the interior space.

[0051] In this embodiment, point cloud data is uploaded to a cloud server. The background uses a semantic segmentation algorithm based on deep learning to automatically process the point cloud and label each point, identifying and classifying structural elements such as walls, floors, ceilings, doors, windows, beams and columns. The system parameterizes the identified structural elements, such as the length, height, and position of walls, and the width and height of windows from the ground, to construct a lightweight BIM model with geometric information and topological relationships, forming an initial digital twin.

[0052] We collect basic user information through online forms and mine natural dialogues using sentiment analysis and keyword extraction models to obtain users' emotional needs and potential demands.

[0053] After user authorization, collect user lifestyle data and analyze their activity paths, frequency of area use, and daily routines in the existing space;

[0054] User profiles are generated based on users' emotional needs, potential needs, activity paths, regional usage frequency, and daily routines.

[0055] In this embodiment, basic information about target user A is collected to obtain the apartment type, permanent residents and occupation of target user A’s current residence. Based on the occupation, the user is dynamically asked whether they need to work from home. When the user chooses to work from home, the user is dynamically asked about the office area. The user’s initial style and budget settings are obtained. For example, the basic profile of user A is: a white-collar worker who needs to work from home, has a clear budget and likes simplicity and lives alone.

[0056] After the user completes the form, the AI ​​assistant initiates a natural conversation, using NLP techniques to delve deeper. Below are some examples of past conversations:

[0057] AI Assistant: "User A, thank you for filling out the form! We have learned about your basic information. Now, could you tell me your true feelings about 'your current home'? For example, is there anything you are dissatisfied with, or anything you would like to have in your new home?"

[0058] User A: "I want to be able to completely relax when I get home. This house is too oppressive, especially at night. The lights are dim and it feels messy. There's nowhere to put my things. I want a bright living room, and preferably a comfortable corner where I can curl up and read."

[0059] The background NLP model performs real-time analysis of the dialogue:

[0060] Sentiment analysis: Negative sentiment words are oppressive, dark, and chaotic, corresponding to the emotional need to get rid of oppression and chaos; positive sentiment words are relaxing, bright, and comfortable, corresponding to the emotional need to pursue relaxation, brightness, and comfort.

[0061] Keyword extraction: dim lighting, insufficient storage space; bright living room, comfortable corner for reading;

[0062] Intent recognition: Improve lighting, increase storage space, create a reading corner;

[0063] After obtaining authorization from user A, the system accessed existing smart home device data via API interface to perform behavioral analysis. The analysis revealed that the average brightness of the living room main light was 30%, with a color temperature of 4000K. Every night after 10 PM, user A entered relaxation mode, only turning on one floor lamp with a color temperature of 2700K. Therefore, it can be analyzed that user A has potential discomfort with high-brightness, cool white light environments and prefers a relaxing environment with low illumination and warm color temperatures. When working from home, the smart thermostat was set to 24°C during the day and 26°C at night. Therefore, it can be analyzed that user A has a clear preference for ambient temperature and needs a comfortable environment with time-based and zone-based temperature control. On weekday afternoons, the smart speaker was used for an average of 1 hour in the study and 2 hours in the living room, with content mainly consisting of podcasts and background music. Location tracking via a smartwatch showed the most frequent activity areas were: the sofa area, the kitchen countertop, and the bedside area in the bedroom.

[0064] The system integrates the data from the above three steps to generate a comprehensive user profile:

[0065] Basic Information: 27-year-old project manager, living alone, 85m tall 2 Two bedrooms and one living room, budget 150,000;

[0066] Core demand: To find a home that is completely relaxing, bright, and warm;

[0067] Potential demand:

[0068] To alleviate the feeling of oppression, a significant improvement in overall lighting is needed, especially in the evening environment.

[0069] Create a core area: The living room sofa area is the center of life and needs to be upgraded into a multifunctional and comfortable corner that integrates "work, reading, audio-visual entertainment, and relaxation";

[0070] Regular sleep schedule: Enters a relaxing mode after 10 PM, prefers warm light;

[0071] Light sensitivity: Positive physiological response to low-intensity warm light, negative response to cool white light and high-brightness environment;

[0072] Temperature preference: Prefers cool daytime environments (24°C) and warm nighttime environments (26°C);

[0073] Core Behavioral Principle: The living room sofa is the activity center;

[0074] Using the spatial parameters and user profiles of the digital twin as input conditions, the interior design model learns from a massive number of design cases and generates preliminary design schemes of different styles and layouts in batches based on the input conditions. Each scheme includes complete 3D model renderings and soft furnishing concepts.

[0075] In this embodiment, the input conditions are spatial parameters and user profile. The system converts the parameters of the digital twin into a black and white wireframe diagram, depicting the layout, walls, and door and window locations of the interior space. The system converts the user profile into a detailed, structured prompt using a large language model (LLM). The system calls a specially trained and fine-tuned text-based graph model (a customized model based on Stable Diffusion). The system inputs the black and white wireframe diagram into the ControlNet module, applies the LoRA model for style and concept fine-tuning, and inputs the encoded instruction set into the interior design AI model, setting different random seeds to generate multiple preliminary schemes in batches. Some preliminary design schemes are listed below:

[0076] Option 1:

[0077] 3D model rendering description: Under the south-facing window in the living room, a large bay window cushion is designed, next to a floor-to-ceiling open bookshelf, forming a bright reading corner. The sofa and coffee table are in the center, and a long desk is placed against the wall behind it, cleverly dividing the office area. It is both transparent and functional. The overall color scheme is natural wood color and beige, decorated with green plants, and the light is plentiful.

[0078] Interior design concept: linen curtains, light gray fabric sofa, round coffee table set, rattan storage basket.

[0079] Option 2:

[0080] 3D model rendering description: A curved sofa is used to create a warm communication area. The background wall uses a soft curved shape and warm-colored wall paint, paired with hidden light strips. The office area is integrated into a curved niche, which is both a feature and a way to divide the space. Herringbone wood flooring is used on the floor, which adds dynamism and warmth to the space.

[0081] Interior design concept: wool rug, mushroom-shaped floor lamp, cream-colored cushions, and built-in storage cabinets.

[0082] Option 3:

[0083] 3D model rendering description: In the center of the living room is a large multi-functional island, with a desk on one side and a bar and storage cabinet on the other. Sofas and movable side tables replace the traditional coffee tables, making the space more flexible.

[0084] Interior design concepts: industrial-style island countertop, modular sofa, foldable yoga mat, metal shelving unit.

[0085] Option 4:

[0086] 3D model rendering description: The ceiling is equipped with magnetic track lights without a main light, there are wall washer light strips in the corners, and the reading area has adjustable spotlights with daytime mode (high color temperature, high brightness), cinema mode (local lighting), and reading mode (4000K focused light). The furniture is selected with a combination of light and dark colors to highlight the sense of light and shadow.

[0087] Interior design concepts: intelligent light strip system, track lighting, intelligent curtains, and a dark blue velvet armchair.

[0088] Step 2: Collect historical light data for the corresponding time period based on user work needs, obtain physiological data of users in different spatial environments, and analyze the health abnormalities of users in different spatial environments under the influence of light and the sensitivity of users to light.

[0089] Please see Figure 3 In this embodiment, step two includes the following specific steps:

[0090] Based on the historical ambient illuminance collected during the user's core working time period, the light illuminance is obtained using the light illuminance fluctuation calculation formula, which is: ,in, For light fluctuation rate, The duration of historical ambient light intensity data collection. Let be the historical ambient illuminance at time t. The historical ambient illuminance at time t-1 As a safe value for ambient light fluctuations, this implementation can use 200 lux. Integral over time;

[0091] In this embodiment, the user's work habits are confirmed through a form to obtain information on user A's core work hours from 14:00 to 18:00 on weekdays;

[0092] A smart light sensor connected to Wi-Fi is deployed in User A's actual work area (next to the sofa in the living room). The sensor automatically measures the current ambient light level every 5 minutes and uploads the data (timestamp and illuminance value) to the cloud. All data points within the weekday time window of 14:00-18:00 are filtered out. The following is a partial list of ambient light levels:

[0093] 14:00:910lux;

[0094] 14:05:920lux;

[0095] 14:10:900lux;

[0096] 14:15:1300 lux (The sun suddenly emerged from the clouds);

[0097] 14:20:1350lux;

[0098] The greater the fluctuation rate of light, the more unstable the natural light environment. User A's work environment has the problem of frequent light fluctuations. The south-facing window is frequently exposed to direct sunlight in the afternoon, which forces User A's pupils to adjust frequently, greatly consuming energy and causing User A to feel tired and unable to concentrate.

[0099] Acquire physiological data of users in different spatial environments, including HRV, GSR, body temperature and heart rate, and simultaneously collect spatial environmental data, including illuminance of lighting equipment, color temperature of lighting equipment, noise, VOC concentration, temperature and humidity;

[0100] HRV abnormalities are obtained based on the ratio of standard HRV to average HRV, GSR abnormalities are obtained based on the ratio of average GSR to standard GSR, body temperature abnormalities are obtained based on the ratio of average body temperature to standard body temperature, and heart rate abnormalities are obtained based on the ratio of average heart rate to standard heart rate. The HRV abnormalities, GSR abnormalities, body temperature abnormalities, and heart rate abnormalities are weighted and summed to obtain the user's health abnormalities under different environments.

[0101] The abnormal health values ​​of indoor space users under light fluctuation are obtained by multiplying the light fluctuation rate, the health impact coefficient of light fluctuation, and the abnormal health value.

[0102] The sensitivity index is calculated by dividing the HRV difference in different spatial environments by the illuminance difference of lighting equipment in different spatial environments. The sensitivity anomaly value is obtained by dividing the sensitivity index by the standard sensitivity. In this embodiment, the standard sensitivity can be 0.01.

[0103] The sensitivity anomalies of indoor space users under light fluctuations are obtained by multiplying the light fluctuation rate, the sensitivity influence coefficient of light fluctuations, and the sensitivity anomalies.

[0104] In this embodiment, the user wears a VR headset and a smartwatch to enter a virtual space rendered in real time by the system. This space is consistent with the digital twin in step one. Each experimental scenario precisely controls one or more environmental variables, for example:

[0105] Scene 1:

[0106] Visual description: A VR space simulating a living room, but the light is very glaring. There is a 6000K cool white LED panel light on the ceiling, shining directly down, with an illuminance of up to 800 lux (similar to an office). The walls are pure white with a high reflectivity.

[0107] Environmental parameter settings: Illumination 800 lux, color temperature 6000K, noise 35dB, temperature 25°C, humidity 50%;

[0108] Scene 2:

[0109] Visual description: A VR space simulating a living room, with the main light off and only a 2700K warm yellow floor lamp emitting a soft light in the corner, with an illuminance of about 150 lux. The wall simulates the flickering flames of a fireplace.

[0110] Environmental parameter settings: Illumination 150 lux, color temperature 2700K, noise 35dB, temperature 25°C, humidity 50%;

[0111] User A puts on the device and enters a neutral gray space in VR to relax, allowing physiological indicators to return to baseline levels. Physiological data from this relaxed state is collected as standard physiological data. Based on this standard physiological data, user A's standard HRV, standard GSR, standard heart rate, and standard body temperature are obtained. The system switches to Scene 1, where user A can move around or sit freely, and the system records data throughout. Then, the user returns to the neutral gray space to remove the influence of the previous scene, and the system switches to Scene 2 again, recording data throughout. During each user experience scene, the physiological data streams (HRV, GSR, heart rate, body temperature, etc.) collected by the smartwatch are synchronized with environmental data streams (light, color temperature, noise, VOC concentration, temperature, humidity, etc.) recorded by environmental sensors via Bluetooth and Wi-Fi, using millisecond-level timestamps. The average and standard deviation of each physiological indicator for user A in Scene 1 and Scene 2 are calculated separately. The following are some examples of physiological data:

[0112] Heart rate: The average heart rate in scenario 1 was 82 bpm, and the average heart rate in scenario 2 was 68 bpm;

[0113] HRV (Heart Rate Variability, the higher the value, the more relaxed the person): The average HRV in Scenario 1 was 28ms, and the average HRV in Scenario 2 was 45ms.

[0114] GSR (Genre Response, the higher the level, the more stressed the person): The average GSR in scenario 1 was 1.8µS, and the average GSR in scenario 2 was 0.9µS.

[0115] Body temperature: The average body temperature in scenario one is 36.7°C, and the average body temperature in scenario two is 37.2°C;

[0116] The Pearson correlation coefficient between illuminance and HRV was calculated, and the result was -0.85, indicating that the higher the illuminance, the lower the HRV of user A, meaning that user A was more stressed. The sensitivity index was calculated as follows: the difference between the HRV of scene two and the HRV of scene one divided by the difference between the illuminance of scene one and the illuminance of scene two. In this example, it is: (45-28) / (800-150)≈0.026ms / lux, meaning that user A's light sensitivity index is 0.026, which is a highly sensitive type, reflecting that user A's physiological state is easily affected by artificial lighting. When the light sensitivity index is less than 0.01, it is an insensitive type, and the physiological indicators are very stable. A sensitivity index of 0.01–0.02 indicates moderate sensitivity with a moderate physiological response. A sensitivity index of 0.02–0.035 indicates high sensitivity with a significant physiological response. A sensitivity index greater than 0.035 indicates extreme sensitivity, where even slight changes in illuminance can cause severe physiological fluctuations, potentially accompanied by symptoms such as headaches and nausea. Therefore, high color temperature and high illuminance environments significantly reduce user A's HRV, increase heart rate and stress levels, and are not conducive to relaxation and recovery. Conversely, low color temperature, low illuminance, and indirect lighting environments can increase user A's HRV, allowing them to enter a state of deep relaxation, which is extremely beneficial for user A's evening rest and stress relief.

[0117] Step 3: Based on the health abnormalities of users in different spatial environments under the influence of light and the users' sensitivity to light, the preliminary design schemes are screened to obtain the design schemes to be tested;

[0118] In this embodiment, step three includes the following specific steps:

[0119] Obtain the health anomaly values ​​and light sensitivity anomaly values ​​of indoor space users under light fluctuations corresponding to the preliminary design scheme, and screen the preliminary design schemes that simultaneously meet the preset health anomaly thresholds and light sensitivity anomaly thresholds, and set them as the design schemes to be tested.

[0120] In practical implementation, this embodiment can also set the following screening conditions for the design scheme under test based on the health abnormality threshold and the light sensitivity abnormality threshold:

[0121] Lighting restrictions for core relaxation areas: In core relaxation areas such as the living room sofa area and bedroom, the simulated ambient illuminance in evening relaxation mode shall not exceed 300 lux and the color temperature shall not exceed 3000K;

[0122] Task area lighting isolation: High-intensity lighting (greater than 500 lux) in task areas such as office areas and reading corners must use localized, independently controllable luminaires, and their light must not significantly interfere with the ambient light of the core relaxation area;

[0123] Material reflectivity restrictions: The light reflectivity of the main surfaces in the core relaxation area (such as walls, floors, and ceilings) should not be too high. Matte materials with a reflectivity of less than 70% are recommended for walls, and less than 40% for floors.

[0124] Simulation results for Scheme 1:

[0125] The core area (sofa) meets the following requirements: average illuminance of 180 lux and color temperature of 2800K in night mode;

[0126] The reading corner (under the window) meets the following requirements: the local illuminance of the reading lamp at night is 450 lux, but the light has a light-blocking design, so it has little impact on the sofa area;

[0127] The wall material conforms to the design: light beige matte latex paint with a reflectivity of 65%;

[0128] Simulations show that during the day, when the south-facing window receives direct sunlight, the peak illuminance in the sofa area can exceed 2000 lux. Although it is not nighttime, this may cause discomfort. Therefore, this solution is feasible, but smart curtains need to be added.

[0129] Simulation results for Scheme 2:

[0130] The core area (sofa) meets the following requirements: average illuminance of 220 lux and color temperature of 3000K in night mode; the office area (niche) meets the following requirements: task light of 4000K, but the niche design effectively isolates the light.

[0131] Wall material requirements: Warm-toned artistic paint, matte finish, 60% reflectivity;

[0132] Therefore, Option 2 is approved;

[0133] Simulation results for Scheme 3:

[0134] The core area (sofa) meets the following requirements: average illuminance of 150 lux and color temperature of 2700K in night mode;

[0135] The island office area meets the following requirements: The integrated pendant light is 4000K, but the hanging position and lampshade design ensure that the light is concentrated downwards and has no impact on the sofa area;

[0136] The wall material does not meet the requirements: white matte finish with a reflectivity of 75%. The wall reflectivity is too high, which may increase the amount of diffuse reflection of ambient light. The system predicts that this will cause the overall HRV to drop by 3-5ms, which is a potential risk.

[0137] Therefore, Option 3 was not approved;

[0138] Simulation results for Scheme 4:

[0139] The core area (sofa) does not meet the requirements of "Cinema Mode": illuminance 80 lux, color temperature 2500K;

[0140] "Daytime Mode": Illuminance 500 lux, color temperature 4500K;

[0141] Therefore, Option 4 was not approved;

[0142] This step eliminates unhealthy design elements (such as high-reflectivity walls), corrects designs with potential risks (such as adding smart curtains), and retains the solutions that best meet users' health needs, forming a high-quality pool of design solutions to be tested.

[0143] Step 4: Perform material matching and cost calculation on the design scheme to be tested, and select the design scheme that meets the user's budget;

[0144] In this embodiment, step four includes the following specific steps:

[0145] A target demand vector is generated based on the user profile. The target demand vector includes VOC emission rate, light reflectivity and market price. The attribute vector of each material is obtained. The similarity between the attribute vector of each material and the target demand vector in the direction is calculated based on the cosine similarity algorithm. The material with the highest similarity is obtained.

[0146] Cost calculations are performed by multiplying the bill of materials corresponding to the most similar materials by the corresponding market prices, and then selecting design solutions that fit the user's budget.

[0147] In this embodiment, the system calls a holographic material database, where each material is accompanied by a multi-dimensional attribute vector: [VOC emission rate, antibacterial grade, tactile comfort (assigned by experts), light reflectivity, warm / cool value, market price]. For each element in the design scheme to be tested, the system generates a target demand vector based on its health goals and aesthetic style, i.e., health goals: VOC emission rate must be undetectable (normalized to 0.0), antibacterial grade should be as high as possible (target 1.0), light reflectivity must be less than 70% (normalized to 0.7), warm / cool value must be positive (target +0.8), budget 150,000, corresponding to a price index target of 0.4 (mid-range). T = [0.0, 1.0, 0.6, +0.8, 0.4], where the reflectivity target is set to 0.6, leaving some optimization space based on a value less than 0.7. The cosine similarity algorithm is used to calculate the similarity between two vectors in direction; the closer the result is to 1, the better the match. For example, the vector for material A is A = [0.0, 0.95, 0.60, +0.80, 0.40], and its similarity to the target requirement vector is approximately 0.99. The vector for material B is B = [0.1, 0...]. The vector for material C, C=[0.70,0.55,+1.0,0.70], has a similarity of approximately 0.92 with the target demand vector. The vector for material D, D=[0.4,0.50,0.90,-0.5,0.30], has a similarity of approximately 0.65 with the target demand vector. The database quickly retrieves the Top [values] that best match the target demand vector. Material N represents Material A. The system defaults to selecting Material A for each design element, generating a detailed bill of materials. The system connects in real-time via API to the inventory and pricing systems of major building material suppliers and home furnishing e-commerce platforms to obtain the latest prices of matching materials, enabling dynamic and accurate cost calculations. For each complete scheme, the system calculates its total cost and comprehensive health score. This score, ranging from 0 to 100, is based on the health attributes of the materials used and the lighting environment of the design itself. For example, Scheme 1 has a comprehensive health score of 92 and a cost of 137,000, indicating excellent materials and perfect lighting design. Scheme 2 has a comprehensive health score of 90 and a cost of 143,000, indicating excellent materials but a slight risk of glare due to complex lighting. A Pareto front plot is generated, with the horizontal axis representing "total cost" and the vertical axis representing "comprehensive health score." Each point on the plot represents a design scheme. The Pareto front plot clearly shows that Scheme 1 is located to the upper left of all other points, indicating that Scheme 1 is cheaper and healthier. Therefore, Scheme 1 should be selected as the final design scheme.

[0148] The method for determining the weights, coefficients, and thresholds in this embodiment is as follows: obtain historical indoor space design data, including historical indoor space parameters, historical preliminary design schemes, light data corresponding to the user's historical working time period, physiological data under historical spatial environment, and the user's historical light sensitivity. Import the above data into each step of this embodiment to obtain the final design scheme. Compare the final design scheme obtained in this embodiment with the design scheme finally selected by the user, and select the set of weights, coefficients, and thresholds with the highest selection accuracy.

[0149] Example 2

[0150] Please see Figure 4 The present invention also provides an intelligent data processing system for interior design, implemented based on the above-described intelligent data processing method for interior design, including:

[0151] The preliminary scheme screening module is used to collect indoor space parameters and obtain preliminary design schemes based on space conditions and user needs;

[0152] The health anomaly analysis module is used to collect historical light data for corresponding time periods based on user work needs, obtain users' physiological data in different spatial environments, and analyze health anomalies of users in different spatial environments under the influence of light.

[0153] The light sensitivity analysis module is used to collect historical light data for a corresponding time period based on user work needs, and analyze the sensitivity of users to light in different spatial environments under the influence of light.

[0154] The test scheme screening module is used to screen preliminary design schemes based on the health abnormalities of users in different spatial environments under the influence of light and the users' sensitivity to light, and to obtain test design schemes.

[0155] The final solution selection module is used to match materials and calculate costs for the design schemes under test, and to select design schemes that meet the user's budget.

[0156] Example 3

[0157] This invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-described intelligent data processing method for interior design by calling the computer program stored in the memory.

[0158] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memories store at least one computer program that is loaded and executed by the processor to implement the intelligent data processing method for interior design provided in the above-described method embodiments. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted in this embodiment.

[0159] Example 4

[0160] This invention also provides a computer-readable storage medium storing instructions that, when a computer program is run on a computer device, cause the computer device to execute the aforementioned intelligent data processing method for interior design.

[0161] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices.

[0162] It should be understood that, in various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0163] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, they generate in whole or in part the flow or function according to the embodiments of the present invention. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0164] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0165] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example, and the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0166] The preferred embodiments of the present invention disclosed above are only for the purpose of illustrating the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to specific implementation methods. Obviously, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for intelligent data processing for interior design, characterized in that, The method comprises the following specific steps: Step 1: Collecting indoor space parameters, obtaining a preliminary design scheme based on space conditions and user needs; Step 2: Collecting historical light data of the corresponding time period based on user work requirements, obtaining physiological data of users in different space environments, analyzing health abnormalities of users in different space environments under the influence of light and the sensitivity of users to light; Step 3: Screening the preliminary design scheme based on the health abnormalities of users in different space environments under the influence of light and the sensitivity of users to light, obtaining a design scheme to be tested; Step 4: Material matching and cost estimation of the design scheme to be tested, screening the design scheme meeting the user's budget; The step 2 comprises the following specific steps: Based on the user core work time period, the historical ambient light intensity of the corresponding time period is collected, and the light fluctuation rate is obtained based on a light fluctuation rate calculation formula, the light fluctuation rate calculation formula is: Wherein, The light fluctuation rate is The collection duration of the historical ambient light intensity is The historical ambient light intensity at t time is The historical ambient light intensity at t-1 time is The ambient light fluctuation safety value is The time integral is Obtaining physiological data of users in different space environments, the physiological data comprising HRV, GSR, body temperature and heart rate, synchronously collecting space environment data, the environment data comprising lighting device illuminance, lighting device color temperature, noise, VOC concentration, temperature and humidity; Obtaining HRV abnormal values based on the ratio of standard HRV to average HRV, obtaining GSR abnormal values based on the ratio of average GSR to standard GSR, obtaining body temperature abnormal values based on the ratio of average body temperature to standard body temperature, and obtaining heart rate abnormal values based on the ratio of average heart rate to standard heart rate, and obtaining health abnormal values of users in different environments by weighted sum of HRV abnormal values, GSR abnormal values, body temperature abnormal values and heart rate abnormal values; Obtaining health abnormal values of indoor space users under light fluctuation based on the product of light fluctuation rate, light fluctuation health influence coefficient and health abnormal value; Obtaining sensitivity abnormal values based on the ratio of sensitivity index to standard sensitivity; Obtaining sensitivity abnormal values of indoor space users under light fluctuation based on the product of light fluctuation rate, light fluctuation sensitivity influence coefficient and sensitivity abnormal value. 2.The intelligent data processing method for interior design according to claim 1, wherein, The step 1 comprises the following specific steps: Using a three-dimensional laser scanner to panoramic scan the indoor space, generating original three-dimensional point cloud data, and identifying structural elements of the indoor space; Collecting user basic information through an online form, mining natural dialogue through emotional analysis and keyword extraction model, and obtaining emotional appeal and potential needs of the user; Collecting user lifestyle data, analyzing activity path, regional use frequency and work and rest regularity of the user in the existing space; Generating a user portrait based on emotional appeal, potential needs, activity path, regional use frequency and work and rest regularity of the user; Taking the space parameters and the user portrait as input conditions, the indoor design model generates preliminary design schemes of different styles and layouts according to the input conditions. 3.The intelligent data processing method for interior design according to claim 1, wherein, The step 3 comprises the following specific steps: Obtaining health abnormal values of indoor space users under light fluctuation corresponding to the preliminary design scheme and sensitivity abnormal values of indoor space users under light fluctuation, screening the preliminary design scheme meeting the preset health abnormal threshold and light sensitivity abnormal threshold, and setting the preliminary design scheme as the design scheme to be tested. 4.The intelligent data processing method for interior design according to claim 1, wherein, The step 4 comprises the following specific steps: A target demand vector is generated based on the user portrait, the target demand vector including VOC release rate, light reflectivity and market price, an attribute vector of each material is obtained, the similarity of the attribute vector of each material and the target demand vector in the direction is calculated based on a cosine similarity algorithm, and the material with the highest similarity is obtained; Based on the bill of materials corresponding to the material with the highest similarity, the cost is calculated by multiplying the corresponding market price, and the design scheme meeting the user's budget is screened.

5. An intelligent data processing system for interior design for implementing the intelligent data processing method for interior design according to any one of claims 1 to 4, characterized in that It includes: A preliminary scheme screening module is configured to collect indoor space parameters, and obtain a preliminary design scheme based on space conditions and user needs; A health anomaly analysis module is configured to collect historical light data of a corresponding time period based on user work requirements, obtain physiological data of a user in different space environments, and analyze health anomalies of the user in different space environments under the influence of light; A light sensitivity analysis module is configured to collect historical light data of a corresponding time period based on user work requirements, and analyze the sensitivity of the user to light in different space environments under the influence of light; A to-be-tested scheme screening module is configured to screen the preliminary design scheme based on the health anomalies of the user in different space environments under the influence of light and the sensitivity of the user to light, and obtain a to-be-tested design scheme; A final scheme screening module is configured to perform material matching and cost calculation on the to-be-tested design scheme, and screen a design scheme meeting the user's budget.

6. An electronic device, comprising: It includes: A memory and a processor, wherein the memory stores a computer program that can be called by the processor, and the processor executes the intelligent data processing method for interior design of any one of claims 1-4 by calling the computer program stored in the memory.

7. A computer-readable storage medium, characterized in that, The instructions are stored in the memory, and when the instructions are run on the computer, the computer executes the intelligent data processing method for interior design of any one of claims 1-4.

Images