An artificial intelligence-based furniture layout space optimization design method and system

Abstract

The application provides a furniture layout space optimization design method and system based on artificial intelligence. In the application, light distribution data and furniture surface reflectivity data of a home environment are collected, dynamic light maps are generated by monitoring light changes, and the light maps are segmented into time blocks to match the position coordinates of corresponding sensors; the light attenuation rate is calculated based on the reflectivity, and the window installation position is determined in combination with the light distribution; space superposition is performed by fusing the time blocks, coordinates and attenuation rate to construct a daylight interaction table; the light coverage boundary is divided according to the light data and the window position, a light gradient map is constructed and implanted into a grid unit, daylight data is mapped into the grid, units with light intensity lower than the visual visible threshold are detected as shadow areas, and a shadow distribution map is generated; the overlapping area of the shadow area and the preset furniture size is identified, and the furniture coordinates are iteratively adjusted to generate a space optimization scheme. The application effectively improves the space utilization and visual comfort of a room.

Description

Technical Field

[0001] This application relates to the field of smart home space optimization technology, and in particular to a furniture layout space optimization design method and system based on artificial intelligence. Background Technology

[0002] In the design of furniture layout in the home environment, it is necessary to be able to dynamically capture the fluctuations in light intensity distribution caused by changes in the sun's position and weather; to set comfort standards to avoid glare and shadow areas and quantify their spatial range; therefore, a method is needed that can automatically generate a solution based on window position, furniture size and its surface properties, so as to intelligently avoid undesirable light and shadow areas and effectively reduce the cost of relying on repeated trial and error based on human experience.

[0003] Currently, one existing targeted solution is a semi-automatic planning technology that combines a static BIM model with light sensor linkage. This solution constructs the three-dimensional structure of the building using a building information model, and performs static lighting simulation on this model at specific time points. By collecting actual illuminance data, a greedy algorithm is used to prioritize placing large furniture in non-avoidance areas, and then a collision detection algorithm is used to adjust the position of small furniture, ultimately outputting a preliminary furniture layout plan.

[0004] However, the existing solution has significant drawbacks. Because it relies on a static BIM lighting model, it cannot effectively capture the dynamic changes in lighting throughout the day, resulting in a mismatch with the actual dynamic light and shadow environment. The solution ignores key environmental coupling factors and only analyzes based on raw illuminance data, which leads to excessive prediction errors in shadow areas. The greedy strategy simply arranges furniture mechanically in descending order of size without fully considering the spatial topological relationship between light and shadow distribution and window geometry. Summary of the Invention

[0005] This application provides a furniture layout space optimization design method and system based on artificial intelligence to solve the problem of excessive prediction error in the prior art.

[0006] Firstly, this application provides a furniture layout space optimization design method based on artificial intelligence, including:

[0007] Data on light distribution and furniture surface reflectivity in a home environment are collected to monitor changes in light and generate a dynamic light map. The dynamic light map is divided into equally spaced time blocks, and the position coordinates of the corresponding sensor are matched to each time block.

[0008] The light attenuation rate is calculated based on the surface reflectivity data of the furniture, and the window installation position is determined based on the solar orientation of the light distribution data. The time blocks, position coordinates and light attenuation rate are integrated, and a lighting interaction table is constructed by spatial overlay.

[0009] Based on the light distribution data and the window installation location, the light coverage boundary is divided, a light gradient map is constructed, grid cells are embedded in the light gradient map, the light data of the light interaction table is mapped to each grid cell, the light intensity value of each grid cell is detected, and when the light intensity value drops below the visually visible threshold, it is marked as a shadow area. The spatial coordinates of all shadow areas are summarized to generate a shadow distribution map.

[0010] Based on the coordinates of the shadow area in the shadow distribution map and the spatial dimensions of the pre-set furniture, overlapping areas are identified. By iteratively adjusting the furniture coordinates to offset the overlapping areas, a furniture layout space optimization scheme is generated.

[0011] Optionally, the light attenuation rate is calculated based on the furniture surface reflectivity data, and the window installation position is determined based on the solar azimuth of the light distribution data. The time blocks, location coordinates, and light attenuation rate are integrated, and a lighting interaction table is constructed through spatial overlay, including:

[0012] The reflectance value is extracted from the reflectance data of the furniture surface, and the complement of the reflectance value is calculated as the light attenuation rate;

[0013] Identify the direction of the maximum solar azimuth angle in the illumination distribution data, extend along the direction of the maximum value to the plane of the building's exterior wall, and determine the intersection point as the window installation location;

[0014] An independent storage area is allocated for the location coordinates corresponding to each time block, and the light attenuation rate is written into the independent storage area;

[0015] In three-dimensional space, all coordinates with the same coordinate value are grouped into the same group. The light attenuation rate of all independent storage areas in the same group is extracted to form a dataset of the same group. The values ​​in the dataset of the same group are continuously superimposed to obtain the superimposed result value.

[0016] Based on the superposition result value and the corresponding position coordinates, a light-gathering interaction table containing the mapping relationship between coordinate points and light attenuation rate is constructed.

[0017] Optionally, in three-dimensional space, all coordinates with the same coordinate value are grouped into the same group, and the light attenuation rate of all independent storage areas within the same group is extracted to form a dataset of the same group. The values ​​in the dataset of the same group are then continuously superimposed to obtain the superimposed result value, including:

[0018] By comparing the three-dimensional values ​​of the location coordinates, all location coordinates with identical three-dimensional values ​​are grouped into the same physical group;

[0019] Starting from each location coordinate within the physical group, locate the independent storage area access channel corresponding to the location coordinate, and read the light attenuation rate of all independent storage areas within the physical group in sequence through the access channel;

[0020] All the light attenuation rate values ​​read are stored in a contiguous memory block in the order they were read, and the value at the first address of the memory block is taken as the base accumulation value.

[0021] The basic accumulated value is added to the value at the next adjacent address. The result is updated to the basic accumulated value. The addition is repeated in address order until the end address of the storage block is reached. The final basic accumulated value is recorded as the superposition result value.

[0022] Optionally, a light coverage boundary is defined based on the light distribution data and the window installation location, a light gradient map is constructed, grid cells are embedded in the light gradient map, the light data from the light-gathering interaction table is mapped to each grid cell, the light intensity value of each grid cell is detected, and when the light intensity value drops below the visually visible threshold, it is marked as a shadow area. The spatial coordinates of all shadow areas are summarized to generate a shadow distribution map, including:

[0023] Using the window installation location as the center point, a radial coverage boundary is divided at preset equal intervals. A light gradient map is constructed within the radial coverage boundary, and different distance regions of the light gradient map correspond to layers of different depth levels.

[0024] Within the illumination gradient map, grid cells of equal area are set. Based on the coordinates of the center point of the grid cell, data records with the same spatial coordinates in the lighting interaction table are located, and the lighting parameters of the data records are written into the data area of ​​the corresponding grid cell.

[0025] Read the illumination intensity value of each grid cell, compare the illumination intensity value with a preset visually visible threshold, and when the illumination intensity value is lower than the visually visible threshold, mark the grid cell as a shadow area;

[0026] Extract the spatial coordinates of all grid cells identified as shaded areas, and connect the spatial coordinates in order of adjacent positions to form a closed polygonal region, which serves as the shaded area distribution map.

[0027] Optionally, based on the coordinates of the shaded areas in the shadow distribution map and the spatial dimensions of the pre-set furniture, overlapping areas are identified. By iteratively adjusting the furniture coordinates to offset these overlapping areas, a furniture layout space optimization scheme is generated, including:

[0028] Collect spatial dimension data of the pre-installed furniture, and construct the geometric boundaries of the furniture based on the spatial dimension data;

[0029] Spatially compare the geometric boundaries of the furniture with the coordinates of the shadow area in the shadow distribution map to identify the overlapping areas between them;

[0030] When the overlapping area exists, the furniture coordinates are changed by a fixed value in the preset coordinate system. After each change of the furniture coordinates, the spatial comparison is re-executed and the updated overlapping part is calculated.

[0031] When the overlapping area disappears, the current furniture coordinates are recorded as the final position. The furniture coordinates, orientation angle data, and spatial size data of the final position are integrated and reorganized into a layout structure data package. The layout structure data package is then integrated according to the room coordinate system to form a furniture layout space optimization scheme.

[0032] Optionally, data on light distribution and furniture surface reflectivity in the home environment are collected, light changes are monitored and a dynamic light map is generated, the dynamic light map is divided into equally spaced time blocks, and the position coordinates of a corresponding sensor are matched to each time block, including:

[0033] Multiple light sensors are discretely deployed in the indoor space. Visible light energy values ​​are collected by the light sensors at fixed time intervals. The visible light energy values ​​are combined to generate light distribution data, and the reflectivity data of the furniture surface is measured simultaneously.

[0034] Extract the illumination distribution data during the continuous monitoring period, calculate the change in the visible light energy value at adjacent acquisition times, and generate a time-stamped dynamic illumination map;

[0035] The dynamic illumination map is divided into multiple time blocks of equal length using a preset time slice length. The position coordinates of each light sensor are analyzed, and a one-to-one binding relationship is established between the position coordinates and the corresponding time block.

[0036] Optionally, grid cells of equal area are set inside the illumination gradient map. Based on the center point coordinates of the grid cells, data records with the same spatial coordinates in the daylighting interaction table are located, and the daylighting parameters of the data records are written into the data area corresponding to the grid cell, including:

[0037] The boundary range of the illumination gradient map is determined, a preset grid cell size parameter is set, and grid lines are divided within the boundary range according to the grid cell size parameter to form multiple grid cells of equal area.

[0038] Calculate the three-dimensional coordinates of the geometric center point of each grid cell, and use the three-dimensional coordinates of the geometric center point as the search key to traverse all data records in the light-collecting interaction table and match data record entries that are exactly the same as the three-dimensional coordinates.

[0039] Lighting parameters are extracted from the matched data record entries and written to the dedicated storage location of the corresponding grid cell.

[0040] Secondly, this application provides an artificial intelligence-based furniture layout space optimization design system, including:

[0041] The matching module is used to collect light distribution data and furniture surface reflectivity data in the home environment, monitor light changes and generate a dynamic light map, divide the dynamic light map into equally spaced time blocks, and match the position coordinates of the corresponding sensor for each time block;

[0042] The fusion module is used to calculate the light attenuation rate based on the surface reflectivity data of the furniture, and to determine the window installation position based on the solar orientation of the light distribution data. It integrates the time blocks, position coordinates and light attenuation rate, and constructs a lighting interaction table through spatial overlay.

[0043] The detection module is used to divide the light coverage boundary according to the light distribution data and the window installation position, construct a light gradient map, embed grid cells in the light gradient map, map the light data of the light interaction table to each grid cell, detect the light intensity value of each grid cell, and mark the light intensity value as a shadow area when it drops below the visually visible threshold. The module also summarizes the spatial coordinates of all shadow areas to generate a shadow distribution map.

[0044] The generation module is used to identify overlapping areas based on the coordinates of the shadow area in the shadow distribution map and the spatial dimensions of the pre-set furniture, and generate a furniture layout space optimization scheme by iteratively adjusting the furniture coordinates to offset the overlapping areas.

[0045] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement an artificial intelligence-based furniture layout space optimization design method as described in the first aspect above.

[0046] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements an artificial intelligence-based furniture layout space optimization design method as described in the first aspect.

[0047] This application, by collecting and monitoring changes in light distribution data and furniture surface reflectivity data, can construct dynamic illumination maps in real time, accurately capturing the spatiotemporal fluctuation characteristics of natural light. By dividing the dynamic illumination map into equally spaced time blocks and matching them with sensor location coordinates, it can correlate the mapping relationship between changes in the light environment and spatial coordinates, providing a basis for time-segmented analysis. Based on reflectivity data, it calculates the light attenuation rate and, combined with the sun's position, determines the window location, quantifying light propagation loss and locating the main light sources, enhancing the physical rationality of environmental modeling. Finally, it spatially overlays the time blocks, coordinates, and attenuation rate. By constructing a lighting interaction table, a dynamic interactive model of the three-dimensional lighting environment can be established, enabling the collaborative expression of multi-dimensional lighting parameters. Boundaries are defined based on illumination data and window positions, and an illumination gradient map is constructed. By embedding grid cells to map the lighting data, spatial illumination distribution can be discretized and quantified. By detecting the illumination intensity of grid cells and marking shadow areas below the visual threshold, undesirable light areas that need to be avoided can be accurately identified. Finally, based on the shadow distribution map and furniture size data, overlapping areas are identified, and furniture coordinates are iteratively adjusted to dynamically avoid shadow areas, generating a layout scheme that maximizes both space utilization and visual comfort.

[0048] Furthermore, by extracting the reflectivity values ​​of furniture surfaces and using their complement as the light attenuation rate, the actual impact of material absorption characteristics on light propagation is quantified. The direction of the maximum solar azimuth angle in the illumination data is identified and extended to the building's exterior wall plane to determine the window installation location, achieving scientific positioning of the main light source. Independent storage areas are allocated to the position coordinates of each time block, and the attenuation rate is written to ensure isolated storage and traceability of spatiotemporal data. All position points with the same coordinates in three-dimensional space are collected, and the attenuation rates of the same group of storage areas are continuously superimposed to construct a multi-time period light attenuation accumulation model. A light-gathering interaction table with mapping relationships is generated based on the superimposed values ​​and their coordinates, forming a dynamic database. The final generated light-gathering interaction table contains both the cumulative light attenuation value of spatial coordinates and is associated with the dynamic time dimension, providing high-precision data support for shadow area identification. This completely solves the prediction error problem caused by ignoring the coupling of material properties and environment in existing technologies, significantly improving the reliability of light and shadow avoidance.

[0049] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1A flowchart of a furniture layout space optimization design method based on artificial intelligence provided in this application is shown;

[0052] Figure 2 The illustration shows a scenario diagram of a furniture layout space optimization design method based on artificial intelligence provided in this application;

[0053] Figure 3 A schematic diagram of the structure of a furniture layout space optimization design system based on artificial intelligence provided in this application is shown;

[0054] Figure 4 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0055] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0056] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0057] Research has revealed significant flaws in current furniture layout spatial optimization methods. Because they rely on static building information model (BIM) lighting models, they fail to effectively capture the dynamic characteristics of all-weather lighting changes, leading to a misalignment with the actual dynamic light and shadow environment. The methods neglect key environmental coupling factors, such as the influence of furniture surface reflectivity, relying solely on raw illuminance data for analysis, resulting in excessively large prediction errors for shadow areas. Furthermore, greedy strategies mechanically arrange furniture in descending order of size, failing to fully consider the spatial topological relationship between light and shadow distribution and window geometry, causing a mismatch between the layout and actual lighting requirements. Therefore, there is an urgent need for an intelligent furniture layout spatial optimization design method that can integrate dynamic lighting data in real time and incorporate environmental factors.

[0058] To address the aforementioned issues, this invention proposes an artificial intelligence-based method for optimizing furniture layout space. Its core lies in the fusion and spatial mapping optimization of dynamic lighting data. Intelligent adjustments are achieved by constructing a lighting interaction table and a shadow distribution map using AI algorithms. Specifically, firstly, data on the light distribution and furniture surface reflectivity of the home environment are collected. Light changes are monitored to generate a dynamic lighting map, which is then divided into equally spaced time blocks and matched with position coordinates. Based on reflectivity, the light attenuation rate is calculated, and the window installation positions are determined by combining the sun's orientation. The time blocks, position coordinates, and attenuation rate are then fused to construct a lighting interaction table. Next, lighting coverage boundaries are defined to construct a lighting gradient map. Grid units are embedded to map lighting data, and the light intensity of each unit is detected and shadow areas are marked, generating a shadow distribution map. Finally, based on the shadow distribution map, overlapping areas with furniture dimensions are identified. An iterative algorithm is used to optimize and adjust the furniture coordinates to avoid shadow areas, generating a layout scheme. This method addresses significant shortcomings in the prior art: by processing dynamic illumination maps, it effectively captures dynamic changes in illumination throughout the day, avoiding misalignment with the actual environment; by fusing environmental coupling factors using reflectivity data, it significantly reduces shadow prediction errors; and by using intelligent iterative optimization rather than greedy size sorting, it fully considers the spatial topological relationship between light and shadow distribution and window positions, thereby ensuring the accuracy and rationality of furniture layout.

[0059] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] Figure 1 A flowchart of an artificial intelligence-based furniture layout space optimization design method is provided as an embodiment of this application, such as... Figure 1 As shown, the method includes:

[0061] 101. Collect light distribution data and furniture surface reflectivity data in the home environment, monitor light changes and generate dynamic light map, divide the dynamic light map into equally spaced time blocks, and match the position coordinates of the corresponding sensor for each time block;

[0062] Optionally, step 101 may specifically include the following steps:

[0063] 1011. Multiple light sensors are discretely deployed in the indoor space. Visible light energy values ​​are collected by the light sensors at fixed time intervals. The visible light energy values ​​are combined to generate light distribution data, and the reflectivity data of the furniture surface is measured simultaneously.

[0064] 1012. Extract the illumination distribution data during the continuous monitoring period, calculate the change in the visible light energy value at adjacent acquisition times, and generate a time-stamped dynamic illumination map;

[0065] 1013. Divide the dynamic illumination map into equal-distance segments using a preset time slice length to form multiple time blocks of equal length. Analyze the position coordinates of each light sensor and establish a one-to-one binding relationship between the position coordinates and the corresponding time block.

[0066] In the steps described above, a light sensor is a device placed in different locations within a home to measure light intensity. Visible light energy values ​​refer to the data on the intensity of light captured by these sensors at a specific moment. Light distribution data refers to the aggregated visible light energy values ​​measured by all light sensors at the same moment, depicting the distribution of light intensity throughout the space, including light intensity, light angle, and light duration. Furniture surface reflectivity data is the measured reflectivity of the furniture material surface, indicating how much incident light is reflected back. A continuous monitoring period refers to a range of time during which measurements are continuously performed. A dynamic illumination map is an image or data set that uses continuous illumination distribution data, calculates the change in light energy between adjacent measurement moments, and adds time stamps to show how illumination changes over time. A preset time slice length is a user-defined interval value used to divide time. Time segmentation refers to dividing the total monitoring time into equal-length short time segments at fixed intervals. The location coordinates of the light sensors refer to the information, in digital form, precisely recording the spatial location of each sensor in the home environment. A one-to-one binding relationship refers to establishing a precise correspondence between each time segment and the specific physical location of the sensor involved in the measurement within that time segment.

[0067] In this embodiment, firstly, in step 1011, multiple light sensors are installed at intervals in different areas of the room, such as the ceiling, walls, and near furniture surfaces. These sensors, like clocks, automatically measure the light intensity at their current location at set intervals, obtaining a numerical value, which is the visible light energy value. Simultaneously, a reflectance measuring instrument is used to measure the reflectivity of surfaces such as tables, sofas, and cabinets, acquiring their reflectance data. All sensors combine the light data measured at the same time, including light intensity, light angle, and light duration, to form a "snapshot" describing the light intensity in various corners of the room at that moment—this is the light distribution data. At the same time, the reflectance data of the furniture surfaces is also independently recorded and stored. For example, in a living room environment, three sensors are installed next to the sofa, above the coffee table, and in the corner of the TV cabinet. These sensors simultaneously measure the light brightness at their respective locations every 10 seconds, for example, measuring 200 lux, 150 lux, and 100 lux respectively. Meanwhile, staff used instruments to measure the reflectivity of the sofa surface as 0.4, the coffee table top as 0.6, and the TV cabinet door as 0.3. Every 10 seconds, these three brightness values ​​were grouped together to represent the current light distribution at these three points in the living room {beside the sofa: 200 lx, on the coffee table: 150 lx, corner of the TV cabinet: 100 lx}, and the reflectivity of the sofa, coffee table, and TV cabinet (0.4, 0.6, 0.3) was also recorded simultaneously.

[0068] Next, in step 1012, the system extracts multiple sets of continuously recorded illumination distribution data over a relatively long period, such as all illumination distribution data for a whole day. To understand how illumination changes over time, the system analyzes this continuous data, calculating the difference in light energy between each pair of adjacent measurement points—that is, between the previous moment and the current moment. The same calculation is performed for all sensor locations. Thus, at each new moment, a set of data is generated, labeled with the specific time and the amount of illumination change at all locations at that moment, such as {Sensor location 1: change +5lx, Sensor location 2: change -3lx, Sensor location 3: change 0lx}. Arranging these numerous sets with time stamps and corresponding location change information in chronological order creates a dynamic illumination map that visually shows how illumination fluctuates at different times and locations. For example, suppose monitoring of the living room begins at 8:00 AM, with data recorded every 10 seconds. For the time point 8:00:10, the system compares the illumination data at 8:00:10 with the data at the previous time point 8:00:00. If the sensor next to the sofa measures 200 lx at 8:00:00 and 205 lx at 8:00:10, the change at that point is ΔE = 205 - 200 = +5 lx. This process is repeated for other points at 8:00:10, such as +2 lx on the coffee table and -1 lx at the corner of the TV cabinet. These changes are then time-stamped with 8:00:10. This calculation and marking process is repeated for all consecutive moments throughout the day, and the resulting record, containing information on temporal and spatial changes, is the dynamic illumination map.

[0069] Finally, in step 1013, the system segments the generated dynamic illumination map by time period. The user pre-sets a segment length, such as 30 minutes. The total duration covered by the entire dynamic illumination map, such as 24 hours in a day or 3 hours in the morning, is divided into several equal 30-minute segments. Each segment is a time block. Simultaneously, the system knows the precise installation locations of all participating sensors, typically stored in three-dimensional coordinates (X,Y,Z). For example, with a corner of the living room as the origin (0,0,0), the sensor next to the sofa is located at (2.5,1.2,0.8) meters. The system identifies which sensors participated in generating the dynamic illumination map data within a specific time block, such as the first 30 minutes from 8:00 to 8:30. Then, the system establishes a unique one-to-one association between the unique identifier of this time block and the physical location coordinates of these sensors in the home space, ensuring that subsequent analysis can identify the specific physical locations from which the data for each time period originates. For example, suppose the entire dynamic lighting map covers the period from 8:00 AM to 11:00 AM, a total of 3 hours and 180 minutes. Using a preset slice length of 30 minutes, these 3 hours will be equally divided into 6 time blocks: Time Block 1 (8:00-8:30), Time Block 2 (8:30-9:00), ..., Time Block 6 (10:30-11:00). Within Time Block 1 (8:00-8:30), it is assumed that only three sensors are operating in the living room: S1 at position (1.0, 2.0, 0.5) meters, S2 at position (3.0, 1.5, 1.0) meters, and S3 at position (4.5, 0.5, 0.8) meters. The system will then clearly mark in the data records that the data source for time block 1 is limited to sensors S1, S2, and S3, whose positions are (1.0, 2.0, 0.5), (3.0, 1.5, 1.0), and (4.5, 0.5, 0.8), respectively. The same principle is applied to every other time block to ensure precise correspondence between time and position.

[0070] In practical applications, for example, in a home environment (A), researchers first placed 10 light sensors distributed throughout areas such as the living room and bedroom. These sensors were programmed to automatically record the room's light intensity every 5 minutes; for example, the first measurement yielded an energy value of 50 units, the second 53 units, and so on. Simultaneously, a portable instrument was used to scan the surface reflectivity of five common pieces of furniture, such as sofas and tables, recording values ​​of, for example, 0.4 and 0.6. Reflectivity is an index between 0 and 1, where 0 represents no light reflection and 1 represents complete reflection. All sensor energy values ​​and furniture reflectivity data were combined to form complete light distribution information. Next, continuous monitoring data for 24 hours was extracted, for example, a total time of 1440 minutes. Then, the light difference between adjacent measurement points was calculated; for example, comparing the second measurement value with the first measurement value, 53 minus 50 yielded a change of 3 units. All changes, combined with time stamps, generated a dynamic light map. The dynamic lighting map was then divided into equidistant segments with a preset time of 30 minutes: the total time of 1440 minutes divided by the segment length of 30 minutes yielded 48 time blocks of identical duration. Finally, the specific location coordinates of each sensor were confirmed using sensor tags, such as sensor 1 at coordinates (2.5, 3.0), and these coordinates were one-to-one bound to each corresponding time block, such as block 1 corresponding to 8:00 AM to 8:30 AM. This allowed dynamic changes in lighting to be correlated with specific locations in real time, optimizing the lighting tracking capabilities of the home environment.

[0071] In the overall scheme of step 101 above, multiple light sensors discretely deployed in the indoor space collect visible light energy values ​​at fixed time intervals and combine them to generate light distribution data. At the same time, the reflectivity data of furniture surfaces is measured to monitor light changes and generate a time-stamped dynamic light map. This map is divided into multiple time blocks of equal length by equal distances of preset time slice length. Each time block establishes a one-to-one binding relationship by analyzing the position coordinates of the light sensors, ultimately achieving the ability to accurately capture the distribution and dynamic changes of ambient light.

[0072] 102. Calculate the light attenuation rate based on the surface reflectivity data of the furniture, and determine the window installation position based on the solar orientation of the light distribution data. Combine the time blocks, position coordinates and light attenuation rate, and construct a lighting interaction table through spatial overlay.

[0073] Optionally, step 102 may specifically include the following steps:

[0074] 1021. Extract the reflectance value from the reflectance data of the furniture surface, and calculate the complement of the reflectance value as the light attenuation rate;

[0075] 1022. Identify the direction of the maximum value of the solar azimuth angle in the illumination distribution data, extend along the direction of the maximum value to the plane of the building's exterior wall, and determine the intersection point as the window installation position;

[0076] 1023. Allocate an independent storage area for the location coordinates corresponding to each time block, and write the light attenuation rate into the independent storage area;

[0077] 1024. In three-dimensional space, all coordinates with the same coordinate value are grouped into the same group, the light attenuation rate of all independent storage areas in the same group is extracted to form a dataset of the same group, and the values ​​in the dataset of the same group are continuously superimposed to obtain the superimposed result value.

[0078] Step 1024 may specifically include the following process: comparing the three-dimensional values ​​of the position coordinates, classifying all position coordinates with identical three-dimensional values ​​into the same physical group; starting from each position coordinate within the physical group, locating the access channel of the independent storage area corresponding to the position coordinate, and reading the light attenuation rate of all independent storage areas within the physical group in sequence through the access channel; storing all the read light attenuation rate values ​​into a contiguous storage block in memory in the order of reading, and taking the value at the first address of the storage block as the basic accumulated value; performing an addition calculation on the basic accumulated value and the value at the next adjacent address, updating the basic accumulated value with the calculation result, and repeating the addition calculation in address order until the end address of the storage block, and recording the final basic accumulated value as the superposition result value.

[0079] 1025. Based on the superposition result value and the corresponding position coordinates, construct a light-collecting interaction table containing the mapping relationship between coordinate points and light attenuation rate.

[0080] In the above steps, the light attenuation rate is obtained by calculating the complement of the reflectance value, representing the proportion of light lost after hitting the furniture surface, typically 1 minus the reflectance value. The solar azimuth is the direction of the sun in the sky analyzed from illumination distribution data; the solar azimuth angle is the specific angular measurement of that azimuth in a three-dimensional coordinate system. The direction of the maximum value indicates the solar azimuth angle with the strongest light intensity, identified from data analysis. The building exterior wall plane is the location of the external wall of the building where the home is located, defined as a boundary area in the three-dimensional coordinate system. The intersection point is the specific coordinate point calculated by extending the maximum value direction line until it intersects with the building exterior wall plane; the window installation location is this intersection point, representing the optimal installation location for the home's windows. An independent storage area is a computational region allocated for each time block and corresponding location coordinates, used to store related data separately. Three-dimensional space is a three-dimensional environment system that uses a coordinate system to define location; all location coordinates with the same value represent three-dimensional values ​​and are grouped into the same physical group, representing units created based on these same coordinates. An access channel is a path identifier for entering the storage area to read data. The dataset for the same group consists of attenuation rate values ​​for all locations within the physical group. The superposition result is the final sum obtained after accumulation. The daylighting interaction table is a data table constructed after analysis, containing a one-to-one mapping relationship between coordinate points (location coordinates) and their corresponding superposition result values.

[0081] In this embodiment, firstly, step 1021 extracts the specific reflectance value of each piece of furniture from the previously measured surface reflectance data. These values ​​are directly obtained reflectance ratio data. Then, these reflectance values ​​are calculated to obtain the light attenuation rate. The calculation process involves subtracting the complement of 1 from each reflectance value, i.e., 1 minus the reflectance value, to obtain the proportion of light loss caused by that furniture, which is the light attenuation rate. For example, in a living room environment, if the reflectance of the sofa surface is measured to be 0.4, it indicates 40% reflection, and the attenuation rate is calculated as 1 minus 0.4 equals 0.6, which is 60% light loss. Similarly, if the reflectance of the coffee table surface is 0.6, the attenuation rate is calculated as 1 minus 0.6 equals 0.4. These calculations use a simple subtraction formula: attenuation rate = 1 - reflectance, and the result reflects how light is attenuated by the furniture surface.

[0082] Secondly, in step 1022, based on the previously collected light distribution data, the solar azimuth information is identified: the system scans all solar azimuth angle measurements in the data and finds the direction with the largest value as the point of strongest light, for example, an azimuth angle of 240 degrees represents the southwest direction. Then, a straight line vector is extended from this maximum value direction, usually the sensor origin. The coordinates of the intersection point of this line with the exterior wall plane of the building are calculated in three-dimensional space. The exterior wall plane is a boundary defined in the coordinate system, and this intersection point is the window installation location. For example, in a bedroom environment, the light distribution data analysis shows that the maximum solar azimuth angle is 120 degrees due east. The extended line starts from the starting point coordinates (0,0,0), and the vector calculation intersects with the exterior wall plane where X equals 10, resulting in the intersection point coordinates (10,2,1). This point is determined as the location where the window should be installed to improve lighting efficiency.

[0083] Next, in step 1023, the system allocates a dedicated independent storage area for each time block and corresponding location coordinates defined in step 101: a unique storage area is allocated for each time period, such as the time block from 8:00 to 8:30, and a link is established with the sensor location coordinates recorded within this time period, such as (1.5 m, 2.0 m, 1.0 m). Then, the light attenuation rate value calculated in step 1021 is written into the corresponding independent storage area. For example, if the time block is set to 9:00 to 9:30 AM, a total length of 30 minutes, and the location coordinates (3.0 m, 1.5 m, 0.5 m) are matched with an independent storage area, and the attenuation rate at this location is calculated to be 0.5, then 0.5 is directly written into this storage area; similarly, the attenuation rate of 0.6 at the location (4.0 m, 0.5 m, 0.8 m) is also written into its matched storage area, ensuring that the data for each location and time period is saved independently.

[0084] Then, through step 1024, all location coordinates with identical coordinate values ​​in three-dimensional space are grouped into the same physical group: the system compares whether the three-dimensional values ​​of the location coordinates, such as the X, Y, and Z axes, are consistent, and points that match perfectly, such as (1.0 meter, 2.0 meter, 1.5 meter), are grouped into one physical group. Next, the system traverses each location coordinate within the physical group, locates its corresponding independent storage area access path, such as a memory address, and sequentially reads the list of light attenuation rate values ​​for all locations within the group through this access channel; these values ​​are stored in contiguous memory blocks, with addresses arranged in order from start to end; the value at the first address of the block is taken as the base accumulated value, and then addition is performed with the value at the next adjacent address, such as adding the new value to the base value to update the accumulated value, and the addition is repeated in address order until the last address, and the final accumulated result is recorded as the superposition result value. For example, three sensors with location coordinates (2.0 meters, 3.0 meters, 1.0 meters) are in the same physical group, with attenuation rates of 0.3, 0.4, and 0.5, respectively. The data is stored in a contiguous memory block from address A1000 to A1002. The first address value of 0.3 is taken as the base accumulation value, and the next address value of 0.4 is added to get 0.7. Then, the value of 0.5 at address A1002 is added to get 1.2 as the superposition result. This process is implemented in the background calculator.

[0085] Finally, in step 1025, based on the superposition result values ​​and corresponding location coordinates obtained in step 1024, a daylighting interaction table is constructed. The system associates the superposition result value of each physical group with its location coordinates, creating a structured data table where the coordinate points serve as index keys and the superposition result values ​​serve as mapping values, forming a clear key-value pair relationship. For example, for a family living room environment, the superposition result value for location coordinates (1.5 meters, 2.0 meters, 1.0 meters) is 1.2. The daylighting interaction table will generate a record such as "coordinates (1.5, 2.0, 1.0) mapped to value 1.2"; and so on, all location points are entered into the table for subsequent daylighting optimization decisions.

[0086] In practical applications, such as in a residential lighting optimization project, researchers calculated light attenuation based on previously collected furniture reflectivity data. Taking a fabric sofa in the living room as an example, its measured surface reflectivity is 0.4. By calculating the complement, the light attenuation rate at this location is: 1 - 0.4 = 0.6. Simultaneously, analysis of three consecutive days of illumination distribution data revealed that the sensor records in the northwest direction consistently showed the highest values ​​between 9:00 AM and 10:00 AM, with peak values ​​reaching 95 units. Based on this, the direction of maximum solar azimuth was extended to the building's exterior wall, and the intersection of coordinates (5.2, 7.8) on the floor plan was determined as the optimal window installation location. Next, the 48 previously divided time blocks, each 30 minutes long, were processed: an independent data area was created for the sensor coordinates within each block, such as the coordinates (3.1, 2.4) corresponding to the breakfast period of 8:30-9:00 AM, and the light attenuation rate of 0.6 at that location was written into this storage area. During 3D spatial modeling, when the system detects that the coordinate values ​​of three sensors are exactly the same, for example, all labeled (3.1, 2.4, 1.0), they are grouped into the same physical group. At this point, the system performs a crucial accumulation operation: it reads the value 5 from the first memory address A001 of the group, then reads the value 3 from the adjacent address A002, accumulating for the first time to get 5 + 3 = 8; it continues reading the value 4 from address A003, accumulating for the second time to get 8 + 4 = 12; finally, the superimposed value of the coordinate point is 12. By traversing all 48 time blocks, a mapping table between coordinate points and accumulated values ​​is established. For example, the coordinates (3.1, 2.4) ultimately correspond to the value 12, forming a visually intuitive table showing the spatial location and the degree of light attenuation.

[0087] In the overall scheme of step 102 above, the complement of the reflectivity value of the furniture surface reflectivity data is calculated as the light attenuation rate. The window installation position is determined by extending the direction of the maximum solar azimuth angle in the illumination distribution data to the building interface. Then, an independent storage area is allocated to the position coordinates corresponding to each time block and the light attenuation rate is written into it. Subsequently, all position coordinates are classified into physical groups according to the same coordinate values ​​in three-dimensional space. The light attenuation rate values ​​of each independent storage area in the group are read sequentially and stored into a continuous memory block. The cumulative value based on the first address value is added to the subsequent address values ​​in turn to obtain the superimposed result value. Thus, a light interaction table containing the dynamic mapping relationship between coordinate points and light attenuation rate is constructed to realize the fusion and quantitative analysis of ambient light attenuation characteristics and spatial coordinates.

[0088] 103. Divide the light coverage boundary according to the light distribution data and the window installation position, construct a light gradient map, embed grid cells in the light gradient map, map the light data of the light interaction table to each grid cell, detect the light intensity value of each grid cell, when the light intensity value drops below the visually visible threshold, it is marked as a shadow area, summarize the spatial coordinates of all shadow areas, and generate a shadow distribution map;

[0089] Optionally, step 103 may specifically include the following steps:

[0090] 1031. Using the window installation location as the center point, divide the radial coverage boundary at preset equal intervals, and construct a light gradient map within the radial coverage boundary. Different distance regions of the light gradient map correspond to layers of different depth levels.

[0091] 1032. Set up grid cells of equal area inside the illumination gradient map, locate data records with the same spatial coordinates in the lighting interaction table according to the center point coordinates of the grid cells, and write the lighting parameters of the data records into the data area of ​​the corresponding grid cells.

[0092] Step 1032 may specifically include the following processes: determining the boundary range of the illumination gradient map, setting preset grid cell size parameters, dividing grid lines within the boundary range according to the grid cell size parameters to form multiple grid cells of equal area; calculating the three-dimensional coordinate value of the geometric center point of each grid cell, using the three-dimensional coordinate value of the geometric center point as the search key, traversing all data records in the lighting interaction table, and matching data record entries that are exactly the same as the three-dimensional coordinate values; extracting lighting parameters from the matched data record entries, and writing the lighting parameters into the dedicated storage location of the corresponding grid cell.

[0093] 1033. Read the illumination intensity value of each grid cell, compare the illumination intensity value with a preset visually visible threshold, and when the illumination intensity value is lower than the visually visible threshold, mark the grid cell as a shadow area;

[0094] 1034. Extract the spatial coordinates of all grid cells identified as shaded areas, and connect the spatial coordinates in order of adjacent positions to form a closed polygonal region as the shaded distribution map.

[0095] In the above steps, the illumination gradient map is a graphical result constructed within the coverage boundary, showing the trend of light intensity gradually decreasing from the window position outwards. Different distance areas correspond to different intensity levels in the layered map effect. Grid cells are small, equal-area squares divided within the illumination gradient map, used to refine spatial analysis units. Daylight data refers to the overlay results in the daylight interaction table, used to describe the light performance at a location point. Illumination intensity values ​​are numerical values ​​extracted from the daylight data, representing the light intensity level within the grid cell. The visually visible threshold is a preset value; areas below this value are considered areas with insufficient light affecting vision. Shadow areas are identified areas of insufficient light, marked when the illumination intensity value is below the visually visible threshold. Spatial coordinates are the location data of the geometric center point of the grid cell, expressed in three-dimensional coordinates. The shadow distribution map is a graphical representation formed by summarizing the coordinates of shadow areas, displaying a panoramic view of areas with concentrated shadows in the home environment. The preset equidistant interval is a user-defined value, representing the fixed spacing of the boundary division from the center outwards. The radial coverage boundary is a concentric ring-shaped area divided radially outwards from the center. The distance region is a sub-part of the lighting gradient map, representing different distance intervals. The depth level is the intensity classification level of the layer at different distances. The grid cell size parameter is the user-defined length and width values ​​of the grid cell. The geometric center point is the location of the center point of the grid cell. The 3D coordinate value is information that precisely represents the spatial location of the center point using numerical values. The search key is an identifier that matches data using coordinate values. The data record entry is the specific record in the lighting interaction table. The lighting parameter is the superimposed result value of the corresponding position in the lighting interaction table. The dedicated storage location is the data storage area allocated to the grid cell. The closed polygon region is the enclosed area formed by connecting adjacent spatial coordinates.

[0096] In this embodiment, step 1031 first uses the window installation location as the starting point center and divides radial coverage boundaries outward using preset equidistant intervals. Concentric ring boundaries increasing at fixed intervals from the center point are calculated, with each ring corresponding to a distance region and assigned a depth level number, from high to low indicating decreasing intensity. This constructs a light gradient map, which is internally organized into layers, each layer representing the light intensity variation trend at different distances. For example, in a living room environment, the window installation location coordinates are set to (0,0,0), and the preset equidistant interval is 1 meter. The system divides 10 concentric ring boundaries to form 10 ring regions, such as 0-1 meter, 1-2 meters, etc. Each distance region is assigned a depth level; 0-1 meter is Level 1, representing the strongest light. The constructed light gradient map shows the effect of light decreasing in intensity from the window outwards, facilitating subsequent analysis of the light attenuation path.

[0097] Secondly, through step 1032, based on the boundary range of the illumination gradient map, the system first sets the grid cell size parameter, and draws grid lines horizontally and vertically within the boundary range according to the parameter, dividing the area into multiple grid cells of equal area. Then, it calculates the three-dimensional coordinate value of the geometric center point of each grid cell, such as the center point position of each small square. Next, using the center point coordinate value as the search key, it traverses all data record entries in the lighting interaction table, precisely matching records with completely identical three-dimensional coordinate values. The lighting parameter, i.e., the superposition result value, is extracted from the matched record and written to the dedicated storage location of the corresponding grid cell as the light intensity reference data. For example, in the illumination gradient map of a 15-square-meter living room, the grid cell size is set to 0.5 meters, dividing the area into 60 grid cells. The center point coordinates of a certain grid cell are (1.2, 1.0, 0.5). The system matches the record entry with the same coordinates in the lighting interaction table, extracts the superposition result value such as 1.3, and writes it to the storage area of ​​that grid cell, realizing the accurate loading of illumination data into the spatial grid.

[0098] Next, in step 1033, the system sequentially reads the illumination intensity value of each grid cell's storage location, i.e., the written superposition result value, and compares it with a preset visually visible threshold, such as 300 lux. When the read illumination intensity value is less than or equal to this threshold, the system marks the grid cell as a shadow area. The comparison process is implemented using a simple numerical magnitude judgment algorithm, and after detecting all grid cells, a list of shadow area identifiers is output. For example, in the living room grid diagram, if the read illumination intensity value of a grid cell is 250 lux, and 250 is less than 300 when compared with the threshold of 300 lux, the system marks the cell as a shadow area; otherwise, if the cell value is 350 lux, it is not marked, ensuring accurate identification of areas with insufficient light.

[0099] Finally, in step 1034, the system extracts the spatial coordinate data of all grid cells marked as shaded areas. Following adjacent positions, and using a triangular mesh generation algorithm (for example), it connects the nearest coordinate points to form closed polygonal regions. This ultimately forms a shadow distribution map, which visually displays the spatial set of shaded areas in a home environment in the form of polygonal enclosed areas. For example, in a living room environment, the coordinates of three shaded grid cells are (1.0, 1.0, 0), (1.5, 1.0, 0), and (1.5, 1.5, 0). The system connects them in adjacent order to form a triangular closed region, generating a shadow distribution map that shows the corners of the living room as densely shaded areas, which is used for subsequent layout optimization decisions.

[0100] In practical applications, such as in a residential lighting optimization project, researchers first used the location of the newly installed window (coordinates (5.2, 7.8)) as the center point, and divided concentric circles outward at 0.5-meter intervals. For example, the first circle had a radius of 0.5 meters, and the second circle had a radius of 1.0 meter, forming a stepped lighting gradient map. Square grid cells with sides of 0.4 meters were then laid out within this gradient map. For example, in a 3m × 4m room area, 7 columns were divided horizontally (calculation: 3m ÷ 0.4m = 7.5, rounded to 7 columns), and 10 rows were divided vertically (4m ÷ 0.4m = 10 rows), generating a total of 70 equal-area grid cells. By calculating the geometric center coordinates of the grid cells, such as the center point of cell G05 (1.2, 0.8), the lighting interaction table record was matched: using coordinates (1.2, 0.8) as an index, the corresponding light attenuation rate of 12 was found in the interaction table, and this value was written to the dedicated storage area of ​​cell G05. The system continuously monitors the light intensity values ​​of all units. When it detects that the light intensity of unit G05 gradually decreases from the initial value of 58 units to 30 units, falling below the preset visual threshold of 35 units, the unit is immediately marked as a shadow area. Finally, the center coordinates of the 37 marked units are extracted, such as the coordinates (1.2, 0.8) of unit G05. Adjacent coordinate points are connected in spatial order to form closed polygons. For example, connecting the six points (1.2, 0.8), (1.2, 1.2), (1.6, 1.2), etc., forms the shadow area, thus constructing a visual shadow distribution map that clearly shows the weakly lit area of ​​the sofa by the window in the afternoon.

[0101] In the overall scheme of step 103 above, a radial coverage boundary is divided at preset equal intervals with the window installation position as the center, and a light gradient map containing layers of different depth levels is constructed. After setting equal-area grid units inside the gradient map, data records with the same spatial coordinates in the daylighting interaction table are located according to the coordinates of the grid center point. The corresponding daylighting parameters are written into the dedicated storage location of the grid unit. Then, the light intensity value of each grid unit is read and compared with a preset visually visible threshold. When the light intensity is detected to be lower than the threshold, the grid unit is marked as a shadow area. Finally, the spatial coordinates of all shadow area grid units are extracted and connected in order of adjacent positions to form a closed polygon area, thereby generating an accurate spatial distribution map of indoor shadows in the building, realizing the overall visualization analysis of potential shadow areas in the building.

[0102] 104. Based on the coordinates of the shadow area in the shadow distribution map and the spatial dimensions of the pre-set furniture, identify overlapping areas, and generate a furniture layout space optimization scheme by iteratively adjusting the furniture coordinates to offset the overlapping areas.

[0103] Optionally, step 104 may specifically include the following steps:

[0104] 1041. Collect the spatial dimension data of the pre-installed furniture, and construct the geometric boundary of the furniture based on the spatial dimension data;

[0105] 1042. Spatial comparison of the geometric boundaries of the furniture with the coordinates of the shadow area in the shadow distribution map to identify the overlapping area between the two;

[0106] 1043. When the overlapping area exists, the furniture coordinates are changed by a fixed value in the preset coordinate system. After each change of the furniture coordinates, the spatial comparison is re-executed and the updated overlapping part is calculated.

[0107] 1044. When the overlapping area disappears, record the current furniture coordinates as the final position, integrate the furniture coordinate values, direction angle data and spatial size data of the final position, and reorganize them into a layout structure data package. Integrate the layout structure data package according to the room coordinate system to form a furniture layout space optimization scheme.

[0108] In the above steps, pre-set furniture refers to items such as sofas and tables planned for placement in the home environment. Spatial dimension data refers to the length, width, and height values ​​of the furniture. Furniture geometric boundaries are the furniture outline defined by rectangular or cubic modeling based on the spatial dimension data. The coordinates of the shaded area in the shadow distribution map are the boundary points of the insufficiently lit areas, obtained by marking grid cells. Overlapping areas refer to the parts where the furniture geometric boundaries and shadow area coordinates coincide in space. Furniture coordinates are numerical representations of the furniture's center point position in the room. Fixed values ​​are the unit distances set by the user for each adjustment or movement. Direction angle data indicates the rotation direction of the furniture placement, such as 0 degrees north or 90 degrees east. The layout structure data package contains structured records of position, angle, and dimension information. The room coordinate system refers to a two-dimensional or three-dimensional position reference system established based on the walls. The furniture layout space optimization scheme is a layout plan formed by integrating the adjusted positions of all furniture.

[0109] In this embodiment, step 1041 first collects the spatial dimension data of the pre-set furniture, and constructs a three-dimensional geometric boundary based on the length, width, and height values: taking the center point of the furniture as a reference, a rectangular boundary (two-dimensional plane) or a cubic boundary (three-dimensional space) is defined according to the dimension data. For example, if the sofa dimensions are 2 meters long, 0.8 meters wide, and 0.7 meters high, its geometric boundary is represented as a 2×0.8×0.7 cubic outline frame centered on the coordinate point, which is used for subsequent position detection.

[0110] Secondly, in step 1042, the geometric boundaries of the furniture are spatially compared with the coordinates of the shadow area in the shadow distribution map: it is detected whether the furniture boundary cube covers any grid cell coordinate point in the shadow area. If the boundary contains a shadow point, it is determined that there is an overlapping area. For example, if the shadow area coordinate point is (1.5, 1.0, 0), and the sofa's initial coordinates are (1.6, 1.1, 0), its 2×0.8 meter boundary contains this point, which is marked as an overlapping area by the system, triggering the subsequent adjustment process.

[0111] Next, in step 1043, if an overlapping area exists, the furniture position is iteratively adjusted: the X or Y coordinates of the furniture are changed by a fixed value of ±0.1 meters, and after each movement, the furniture boundary is re-checked to see if it still contains the shadow point. For example, if the initial position of the sofa (1.6,1.1,0) overlaps with the shadow point (1.5,1.0,0), after the first reduction of the X value by 0.1 meters to (1.5,1.1,0), it is found that the shadow point is still included. After further reduction by 0.1 meters to (1.4,1.1,0), the boundary no longer covers any shadow point, and the overlap disappears, so the movement stops.

[0112] Finally, in step 1044, when the overlapping area disappears, an optimization plan is generated: First, the coordinate values ​​of the adjusted furniture are directly extracted, and combined with the original orientation angle and spatial dimensions of the furniture, they are packaged into a structured record. After all furniture is optimized independently, all structured records are integrated according to the coordinate system of the room to which they belong to, generating a complete furniture layout space optimization plan. The output is a room floor plan and a table of location parameters to guide the actual placement. For example, the final position of the sofa is (1.4, 1.1, 0), with a rotation angle of 0 degrees and dimensions of 2 × 0.8 × 0.7 meters, packaged into a data entry; other furniture is adjusted synchronously to form a complete plan, and a layout mapping table of the living room coordinate system is output for actual placement reference.

[0113] In a practical application, in a home lighting optimization project, researchers first collected the pre-defined spatial dimensions of a sofa in the living room. The sofa was 2.0 meters long and 1.5 meters wide. Based on these dimensions, the geometric boundaries of the sofa were constructed. For example, if the initial coordinates were (3.0, 4.0), the right boundary point was calculated to be 3.0 + 2.0 = 5.0 meters in the x-direction, and the lower boundary point was 4.0 + 1.5 = 5.5 meters in the y-direction, forming a rectangular bounding box. Next, the coordinates of the shaded areas in the shadow distribution map were extracted, including points (3.5, 4.5), (3.5, 4.8), and (4.0, 4.8). These points were then spatially compared with the sofa bounding box to identify overlaps. If a point was within the boundary, it was considered an overlap. For example, point (3.5, 4.5) was located within the x-value range of 3.0 to 5.0 and the y-value range of 4.0 to 5.5 of the sofa bounding box, confirming the existence of an overlapping area. Due to the overlap, the system performs iterative adjustments: In the preset coordinate system, the sofa coordinates are changed by a fixed amount of 0.1 meters along the x-direction. Initially, the x-value is 3.0 and the y-value is 4.0. After the first change, the x-value becomes 3.0 plus 0.1, equaling 3.1, while the y-value remains unchanged. Then, the new sofa boundary is recalculated, with x changing from 3.1 to 5.1 and y from 4.0 to 5.5. The coordinates of the shaded area are then compared. If point (3.5, 4.5) is within the new boundary, it indicates that there is still overlap. Therefore, the sofa coordinates are changed a second time, with the x-value changing from 3.1 plus 0.1 to 3.2. This process is repeated five times until the x-value reaches 3.5. The shaded area points are then re-compared, and the calculation shows that point (3.5, 4.5) is within the new boundary's x-value range of 3.5 to 5.5, but the shaded area point (4.0, 4.8) has been moved out of the boundary range, and there is no longer any overlap. When the overlap completely disappears, the system records the final sofa coordinates as (3.5, 4.0), including the 0-degree orientation angle data and size data, and reassembles them into a layout structure data package, which includes information blocks such as coordinates, orientation, and size. Subsequently, the data package is integrated with the room coordinate system to finally generate a furniture layout space optimization scheme, achieving a more reasonable distribution of light in the home environment.

[0114] In the overall scheme of step 104 above, after constructing the geometric boundary of the furniture based on the spatial dimension data of the pre-set furniture, it is spatially compared with the coordinates of the shadow area of ​​the shadow distribution map to identify the existence of overlapping areas. When an overlapping area is detected, the furniture coordinate position is cyclically changed in the preset coordinate system with a fixed value. After each change, the spatial comparison is re-performed and the area of ​​the overlapping part is dynamically calculated. When the overlapping area is detected to be eliminated, the current furniture coordinates are recorded as the final position. The coordinate value, direction angle and spatial dimension parameters of this position are integrated and reorganized into a layout structure data package. Finally, all optimized furniture position data are integrated and arranged in the room coordinate system to generate a furniture layout space optimization scheme that avoids the shadow area of ​​natural light.

[0115] The following is a complete embodiment for steps 101 to 104:

[0116] like Figure 2 As shown, in a home environment optimization project, technicians first deployed 15 sensors in areas such as the living room and dining room, including points A (2.0, 3.5) and B (4.5, 1.8). Light intensity values ​​were collected every 10 minutes; for example, at 8:00 AM, point A measured 50 units, and at 8:10 AM, it increased to 52 units. Simultaneously, the reflectivity of the sofa surface was measured at 0.35, and the light attenuation rate of 0.65 was calculated using "1 - reflectivity". After 72 hours of continuous monitoring data to form a dynamic illumination map, it was divided into 36 time blocks in 2-hour intervals. The calculation process was: 72 hours × 3 blocks / hour = 216 blocks, which were then merged into 36 long time periods. Subsequent analysis of the illumination distribution data revealed that the maximum solar azimuth angle at 10:00 AM pointed northwest, extending to the exterior wall coordinates (7.2, 0.0), which was determined to be the window location.

[0117] Next, a radiating circle with 0.5-meter intervals was drawn around the window, with the innermost circle having a radius of 0.5 meters and the outer circles increasing in size sequentially, constructing a layered illumination gradient map. A 0.3m × 0.3m grid unit was then embedded in this map. For a 5m × 6m area in the room, the grid was divided into 16 horizontal columns (5 ÷ 0.3 ≈ 16.6, rounded down) and 20 vertical rows (6 ÷ 0.3 = 20), for a total of 320 units. By matching the grid center coordinates, such as the center of unit G07 (1.5, 2.1), the corresponding light attenuation rate of 0.65 from the daylighting interaction table was written into that unit. When monitoring showed that the illumination value of unit G07 dropped from a peak of 60 units to 28 units, below the visual threshold of 35 units, it was marked as a shadow area. Finally, the coordinates of 45 shadow units were extracted and connected to form a polygonal shadow distribution map.

[0118] Based on the sofa's dimensions of 2.2 meters long and 0.9 meters wide, a geometric boundary was constructed with initial coordinates (3.0, 4.0). The right boundary was set to 3.0 + 2.2 = 5.2, and the lower boundary to 4.0 + 0.9 = 4.9. Comparison revealed that the shadow coordinates (3.8, 4.5) were within the sofa's boundary. Therefore, coordinate adjustments were made: the sofa moved in 0.1-meter increments along the Y-axis. The first move to (3.0, 4.1) resulted in overlap, but by the fifth move to (3.0, 4.5), the sofa boundary (3.0-5.2, 4.5-5.4) completely avoided the shadow area (3.8, 4.5). The final optimized solution was generated: a structure package integrating sofa coordinates (3.0, 4.5), orientation 0 degrees, and dimension data, achieving coordinated layout of furniture and lighting.

[0119] Figure 3 This application provides a schematic diagram of the structure of an artificial intelligence-based furniture layout space optimization design system, as shown in the embodiment. Figure 3 As shown, the system includes:

[0120] The matching module 31 is used to collect light distribution data and furniture surface reflectivity data in the home environment, monitor light changes and generate a dynamic light map, divide the dynamic light map into equally spaced time blocks, and match the position coordinates of the corresponding sensor for each time block.

[0121] The fusion module 32 is used to calculate the light attenuation rate based on the surface reflectivity data of the furniture, and to determine the window installation position based on the solar orientation of the light distribution data. It integrates the time blocks, position coordinates and light attenuation rate, and constructs a lighting interaction table through spatial overlay.

[0122] The detection module 33 is used to divide the light coverage boundary according to the light distribution data and the window installation position, construct a light gradient map, embed grid cells in the light gradient map, map the light data of the light interaction table to each grid cell, detect the light intensity value of each grid cell, and mark the light intensity value as a shadow area when it drops below the visually visible threshold. The spatial coordinates of all shadow areas are summarized to generate a shadow distribution map.

[0123] The generation module 34 is used to identify overlapping areas based on the coordinates of the shadow area in the shadow distribution map and the spatial dimensions of the pre-set furniture, and generate a furniture layout space optimization scheme by iteratively adjusting the furniture coordinates to offset the overlapping areas.

[0124] Figure 3 The aforementioned AI-based furniture layout space optimization design system can execute... Figure 1 The implementation principle and technical effects of the AI-based furniture layout space optimization design method described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit of the AI-based furniture layout space optimization design system in the above embodiments are performed have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0125] In one possible design, Figure 3 The furniture layout space optimization design system based on artificial intelligence, as shown in the embodiment, can be implemented as a computing device, such as... Figure 4 As shown, the computing device may include a storage component 41 and a processing component 42;

[0126] The storage component 41 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 42.

[0127] The processing component 42 is used for the above Figure 1 The embodiment describes an AI-based furniture layout space optimization design method.

[0128] The processing component 42 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0129] Storage component 41 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0130] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0131] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0132] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0133] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0134] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown is an artificial intelligence-based furniture layout space optimization design method.

[0135] 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.

[0136] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0137] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A furniture layout space optimization design method based on artificial intelligence, characterized in that, include: Data on light distribution and furniture surface reflectivity in a home environment are collected to monitor changes in light and generate a dynamic light map. The dynamic light map is divided into equally spaced time blocks, and the position coordinates of the corresponding sensor are matched to each time block. The light attenuation rate is calculated based on the surface reflectivity data of the furniture, and the window installation position is determined based on the solar orientation of the light distribution data. The time blocks, position coordinates and light attenuation rate are integrated, and a lighting interaction table is constructed by spatial overlay. The process involves integrating time blocks, location coordinates, and light attenuation rates to construct a lighting interaction table through spatial overlay. This includes: allocating an independent storage area for the location coordinates corresponding to each time block; writing the light attenuation rate into the independent storage area; grouping all location coordinates with the same coordinate value into a single group in three-dimensional space; extracting the light attenuation rate from all independent storage areas within the same group to form a dataset; continuously overlaying the values ​​in the dataset to obtain an overlay result value; and constructing a lighting interaction table containing the mapping relationship between coordinate points and light attenuation rates based on the overlay result value and the corresponding location coordinates. Based on the light distribution data and the window installation location, the light coverage boundary is divided, a light gradient map is constructed, grid cells are embedded in the light gradient map, the light data of the light interaction table is mapped to each grid cell, the light intensity value of each grid cell is detected, and when the light intensity value drops below the visually visible threshold, it is marked as a shadow area. The spatial coordinates of all shadow areas are summarized to generate a shadow distribution map. Collect spatial dimension data of pre-set furniture, construct the geometric boundary of furniture based on the spatial dimension data, identify the overlapping area between the geometric boundary of furniture and the coordinates of the shadow area of ​​the shadow distribution map; generate a furniture layout space optimization scheme by iteratively adjusting the furniture coordinates to offset the overlapping area.

2. The method according to claim 1, characterized in that, The light attenuation rate is calculated based on the furniture surface reflectivity data, and the window installation position is determined based on the solar azimuth of the light distribution data, including: The reflectance value is extracted from the reflectance data of the furniture surface, and the complement of the reflectance value is calculated as the light attenuation rate; Identify the direction of the maximum solar azimuth angle in the illumination distribution data, extend along the direction of the maximum value to the plane of the building's exterior wall, and determine the intersection point as the window installation location.

3. The method according to claim 1, characterized in that, In three-dimensional space, all coordinates with the same coordinate value are grouped together. The light attenuation rate of all independent storage areas within the same group is extracted to form a dataset of the same group. The values ​​in the dataset of the same group are continuously superimposed to obtain the superimposed result value, including: By comparing the three-dimensional values ​​of the location coordinates, all location coordinates with identical three-dimensional values ​​are grouped into the same physical group; Starting from each location coordinate within the physical group, locate the independent storage area access channel corresponding to the location coordinate, and read the light attenuation rate of all independent storage areas within the physical group in sequence through the access channel; All the light attenuation rate values ​​read are stored in a contiguous memory block in the order they were read, and the value at the first address of the memory block is taken as the base accumulation value. The basic accumulated value is added to the value at the next adjacent address. The result is updated to the basic accumulated value. The addition is repeated in address order until the end address of the storage block is reached. The final basic accumulated value is recorded as the superposition result value.

4. The method according to claim 1, characterized in that, Based on the light distribution data and the window installation location, a light coverage boundary is defined, and a light gradient map is constructed. Grid cells are embedded in the light gradient map, and the light data from the daylighting interaction table is mapped to each grid cell. The light intensity value of each grid cell is detected, and when the light intensity value drops below the visually visible threshold, it is marked as a shadow area. The spatial coordinates of all shadow areas are summarized to generate a shadow distribution map, including: Using the window installation location as the center point, a radial coverage boundary is divided at preset equal intervals. A light gradient map is constructed within the radial coverage boundary, and different distance regions of the light gradient map correspond to layers of different depth levels. Within the illumination gradient map, grid cells of equal area are set. Based on the coordinates of the center point of the grid cell, data records with the same spatial coordinates in the lighting interaction table are located, and the lighting parameters of the data records are written into the data area of ​​the corresponding grid cell. Read the illumination intensity value of each grid cell, compare the illumination intensity value with a preset visually visible threshold, and when the illumination intensity value is lower than the visually visible threshold, mark the grid cell as a shadow area; Extract the spatial coordinates of all grid cells identified as shaded areas, and connect the spatial coordinates in order of adjacent positions to form a closed polygonal region, which serves as the shaded area distribution map.

5. The method according to claim 1, characterized in that, Collect spatial dimension data of the pre-set furniture, construct the geometric boundary of the furniture based on the spatial dimension data, and identify the overlapping area between the geometric boundary of the furniture and the coordinates of the shadow area of ​​the shadow distribution map; By iteratively adjusting the furniture coordinates to offset the overlapping areas, a furniture layout space optimization scheme is generated, including: Collect spatial dimension data of the pre-installed furniture, and construct the geometric boundaries of the furniture based on the spatial dimension data; Spatially compare the geometric boundaries of the furniture with the coordinates of the shadow area in the shadow distribution map to identify the overlapping areas between them; When the overlapping area exists, the furniture coordinates are changed by a fixed value in the preset coordinate system. After each change of the furniture coordinates, the spatial comparison is re-executed and the updated overlapping part is calculated. When the overlapping area disappears, the current furniture coordinates are recorded as the final position. The furniture coordinates, orientation angle data, and spatial size data of the final position are integrated and reorganized into a layout structure data package. The layout structure data package is then integrated according to the room coordinate system to form a furniture layout space optimization scheme.

6. The method according to claim 1, characterized in that, Data on light distribution and furniture surface reflectivity in a home environment are collected. Light changes are monitored and a dynamic light map is generated. This dynamic light map is divided into equally spaced time blocks, and the location coordinates of a corresponding sensor are matched to each time block. Multiple light sensors are discretely deployed in the indoor space. Visible light energy values ​​are collected by the light sensors at fixed time intervals. The visible light energy values ​​are combined to generate light distribution data, and the reflectivity data of the furniture surface is measured simultaneously. Extract the illumination distribution data during the continuous monitoring period, calculate the change in the visible light energy value at adjacent acquisition times, and generate a time-stamped dynamic illumination map; The dynamic illumination map is divided into multiple time blocks of equal length using a preset time slice length. The position coordinates of each light sensor are analyzed, and a one-to-one binding relationship is established between the position coordinates and the corresponding time block.

7. The method according to claim 4, characterized in that, Within the illumination gradient map, grid cells of equal area are set. Based on the center point coordinates of the grid cells, data records with the same spatial coordinates in the daylighting interaction table are located. The daylighting parameters of these data records are written into the data area corresponding to the grid cell, including: The boundary range of the illumination gradient map is determined, a preset grid cell size parameter is set, and grid lines are divided within the boundary range according to the grid cell size parameter to form multiple grid cells of equal area. Calculate the three-dimensional coordinates of the geometric center point of each grid cell, and use the three-dimensional coordinates of the geometric center point as the search key to traverse all data records in the light-collecting interaction table and match data record entries that are exactly the same as the three-dimensional coordinates. Lighting parameters are extracted from the matched data record entries and written to the dedicated storage location of the corresponding grid cell.

8. A furniture layout space optimization design system based on artificial intelligence, characterized in that, include: The matching module is used to collect light distribution data and furniture surface reflectivity data in the home environment, monitor light changes and generate a dynamic light map, divide the dynamic light map into equally spaced time blocks, and match the position coordinates of the corresponding sensor for each time block; The fusion module is used to calculate the light attenuation rate based on the surface reflectivity data of the furniture, and to determine the window installation position based on the solar orientation of the light distribution data. It integrates the time blocks, position coordinates and light attenuation rate, and constructs a lighting interaction table through spatial overlay. The process involves integrating time blocks, location coordinates, and light attenuation rates to construct a lighting interaction table through spatial overlay. This includes: allocating an independent storage area for the location coordinates corresponding to each time block; writing the light attenuation rate into the independent storage area; grouping all location coordinates with the same coordinate value into a single group in three-dimensional space; extracting the light attenuation rate from all independent storage areas within the same group to form a dataset; continuously overlaying the values ​​in the dataset to obtain an overlay result value; and constructing a lighting interaction table containing the mapping relationship between coordinate points and light attenuation rates based on the overlay result value and the corresponding location coordinates. The detection module is used to divide the light coverage boundary according to the light distribution data and the window installation position, construct a light gradient map, embed grid cells in the light gradient map, map the light data of the light interaction table to each grid cell, detect the light intensity value of each grid cell, and mark the light intensity value as a shadow area when it drops below the visually visible threshold. The module also summarizes the spatial coordinates of all shadow areas to generate a shadow distribution map. The generation module is used to collect spatial dimension data of preset furniture, construct the geometric boundary of the furniture based on the spatial dimension data, identify the overlapping area between the geometric boundary of the furniture and the coordinates of the shadow area of ​​the shadow distribution map, and generate a furniture layout space optimization scheme by iteratively adjusting the furniture coordinates to offset the overlapping area.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement an artificial intelligence-based furniture layout space optimization design method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements an artificial intelligence-based furniture layout space optimization design method as described in any one of claims 1 to 7.

Images