Modeling system based on digital display

Abstract

The invention discloses a modeling system based on digital display, and relates to the technical field of automatic lamp control, and the modeling system comprises the steps: collecting data of lamps and sensors of different floors; calculating a preferred use scene of a user of each floor through the light use modes of different floors; constructing a user application preference model, and calculating application user preferences according to the user application preference model; matching sequence of floor light modes is carried out by combining the preference use scene of each floor user, the floor lamp use condition and the preference of the application user; and the visualization module is used for providing a visualization interface, providing all floor light mode matching sequences for the user when the user provides the current scene setting, and providing the current scene score for the user to autonomously select. According to the invention, the light requirements of different users on floors can be met, and meanwhile, the comfort and the energy-saving effect are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic lighting control, in particular to a modeling system based on digital display. Background Art

[0002] Traditional floor lighting control systems mostly rely on manual operation and are unable to achieve intelligent management and personalized settings of lighting. This not only fails to meet users' dual needs for comfort and energy saving, but also limits the improvement of the building's intelligence level.

[0003] In the current building environment, floor lighting is an important element in creating indoor atmosphere and providing necessary lighting. The intelligent and personalized control methods of floor lighting have become the focus of users. Users expect floor lighting to be automatically adjusted according to various factors such as time, weather, and personnel activities to meet the needs of different scenarios. At the same time, users also hope that the lighting system can learn and remember personal preferences so that they can be quickly called when needed.

[0004] However, most of the existing floor lighting control systems have problems such as insufficient intelligence, low user participation, and serious energy waste. These systems can often only achieve simple switching and brightness adjustment, and cannot perform intelligent management and personalized settings based on the actual needs and preferences of users on the floor. This not only reduces user comfort, but also leads to unnecessary energy waste.

[0005] To this end, the present invention provides a modeling system based on digital display. Summary of the invention

[0006] The purpose of the present invention is to provide a modeling system based on digital display to solve the existing problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: a modeling system based on digital display, comprising:

[0008] User behavior data collection module, used to collect data from lamps and sensors on different floors;

[0009] Intelligent scenario learning module, which calculates the preferred usage scenarios of users on each floor through the lighting usage patterns of different floors;

[0010] A user preference model building module, used to build a user application preference model and calculate the application user preference according to the user application preference model;

[0011] The resource sequence building module is used to match the floor lighting mode sequence according to the preferred usage scenarios of the users on each floor and the usage of the floor lamps and the preferences of the applicant users;

[0012] The visualization module is used to provide a visualization interface. When the user provides the current scene settings, it provides the user with the matching sequence of all lighting modes on the floor and provides the current scene score for the user to choose.

[0013] A further improvement of the present invention is that the user behavior data collection module is used to establish a floor lighting scene data set, including corresponding lighting scenes and expected lighting data ranges, including collecting lighting usage data on the user's floor when the system is running, and the lighting usage data includes light brightness, duration and adjustment frequency; and collecting light color temperature by installing color temperature sensors near floor lighting equipment; the lamps equipped on each floor record the usage of lights through Internet of Things devices, including the number of switches, brightness adjustment frequency, dimming duration, and adjusted brightness value.

[0014] The present invention is further improved in that the intelligent scenario learning module includes a scene fitness calculation unit and a scene preference matching unit; the scene fitness calculation unit is used to calculate the floor lighting scene fitness, including a lighting fitness calculation strategy, the lighting fitness calculation strategy obtains the lighting fitness by weighted summation of the bulb color temperature fitness, brightness fitness, duration fitness and adjustment frequency fitness; the bulb color temperature fitness calculation formula is: Where α represents the adjustment parameter, ΔT represents the average of the difference between the color temperature change reference value Rt set within the preset time and the actual color temperature change, T represents the set color temperature reference value, T max Indicates the maximum color temperature within the preset time, T min Indicates the minimum color temperature within the preset time; the brightness adaptability f1, duration adaptability f2 and adjustment frequency adaptability f3 are expressed by functions as follows: χ∈(1,2,3),F χ Indicates the current measured value. Indicates the preset value, δ χ Indicates the adjustment parameter.

[0015] The present invention is further improved in that the scene fitness calculation unit also includes a personnel comfort calculation strategy, which obtains the personnel comfort by collecting the weighted average of the floor color temperature comfort and the air quality comfort; the color temperature comfort is obtained based on the deviation between the current color temperature of the floor and the most comfortable color temperature; the air quality comfort is calculated based on the carbon dioxide concentration, and the air quality comfort calculation formula is: Among them, Q current Indicates the current floor air carbon dioxide concentration, Q ideal Indicates the carbon dioxide concentration under ideal air quality, Q max Indicates the set maximum carbon dioxide concentration.

[0016] A further improvement of the present invention is that the floor lighting scene adaptability is obtained by weighted summation of personnel comfort and lighting adaptability.

[0017] A further improvement of the present invention is that the floor lighting scene adaptability is used to obtain a range set of recommended lighting data for each floor through a lighting parameter search algorithm; the lighting parameter search algorithm specifically comprises the following steps:

[0018] Step 1: Collect historical floor user operation behaviors and corresponding fitness, store them in the operation behavior fitness database, and associate them with specific floor numbers;

[0019] Step 2: Set a lighting comfort threshold as a baseline for the system's recommended lighting settings, and extract lighting data from the operation behavior fitness database whose lighting scene fitness is greater than the lighting comfort threshold on any floor as a candidate lighting parameter set;

[0020] Step 3: extract the maximum and minimum values ​​of light brightness, the maximum and minimum values ​​of duration, and the maximum and minimum values ​​of adjustment frequency in the set of candidate light parameters, form a brightness recommendation range, a duration recommendation range, and an adjustment frequency recommendation range, and obtain a rough recommendation range set of light parameters;

[0021] Step 4: randomly generate K groups of lighting parameter combinations within the rough recommended range of the lighting parameters by using a genetic algorithm, calculate the lighting scene adaptability of each lighting parameter combination, and extract all lighting parameter combinations that are greater than the lighting comfort threshold;

[0022] Step 5: Extract the maximum and minimum values ​​of each parameter in the lighting parameter combination obtained in step 4 to form a set of detailed recommended ranges of lighting parameters.

[0023] The present invention is further improved in that the user preference model building module includes: when the user logs in to the lighting mode adjustment system, the system allows the user to select the lighting setting preference, associates the user's historical lighting setting preference with the lighting scene adaptability, and the system analyzes the lighting mode and range corresponding to each lighting scene adaptability according to the user's historical lighting setting preference, including collecting the mean value of the lighting data corresponding to the user's historical lighting setting preference as the main input variable of the user's lighting mode and range for the floor; extracting the lighting mode and range of all historical users for the floor as the secondary input variable; calculating the lighting feature vector corresponding to each lighting mode of the floor as input data, wherein the lighting feature vector corresponding to each lighting mode of the floor is obtained by weighted summing of the main input variable and the secondary input variable, wherein the weight of the main input variable is greater than twice the weight of the secondary input variable; according to the corresponding lighting mode, marking all lighting feature vectors with corresponding floor lighting scene mode labels; taking all lighting feature vectors and corresponding floor lighting scene mode labels as training sets, and learning the mapping relationship between lighting feature vectors and floor lighting scene modes through a support vector machine model; the model will output a floor lighting scene mode label, that is, the floor lighting setting scene that best suits the user's current needs, and extract the expected lighting data range corresponding to the floor.

[0024] A further improvement of the present invention is that the resource sequence construction module includes merging the set of fine recommended ranges of lighting parameters for each floor to form a feature space; taking the expected lighting data range expected by the user as the feature vector u, and obtaining the lighting scene matching sequence of the floor through a lighting clustering algorithm.

[0025] The present invention is further improved in that the light clustering algorithm includes calculating the floor light scene cluster with the shortest distance from the user demand. c i represents the set of fine recommended ranges of lighting parameters for the i-th floor, C is the total distance from the cluster center to u, k is the number of clusters, until the cluster center reaches the preset number of iterations, the floor lighting mode in the floor lighting scene set cluster with the smallest distance user demand is calculated for the user's comfort level saf on the floor; considering the matching degree and comfort score of the lighting setting comprehensively, the comprehensive fitness score M=α1||uc for each lighting scene on the floor is calculated i ||+α2saf; The comprehensive fitness scores of all lighting modes of the floor in the floor lighting scene cluster J are arranged in descending order to provide the user with a matching sequence that matches all lighting scenes, where α1 and α2 represent weight coefficients.

[0026] A further improvement of the present invention is that the current scene score is obtained by extracting the average of the lighting scene fitness of all scenes in the matching sequence of the lighting scene as the current scene score standard value, and extracting the comprehensive fitness of the current scene set by the user, and obtaining the current scene score through the current scene score standard value and the comprehensive fitness of the current scene.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention firstly uses the intelligent scenario learning module to learn the preferred usage scenarios of each floor based on historical data, and calculates the floor lighting scene adaptability, including lighting adaptability and personnel comfort, to achieve an in-depth understanding of the floor usage scenarios; the user preference model building module can build a user application preference model, predict the user's preference based on the user's historical behavior, and improve the accuracy of floor lighting recommendations and user satisfaction;

[0029] 2. Through the lighting parameter search algorithm, combined with historical data and genetic algorithm, a recommended lighting data range set is provided for each floor. These recommended parameters can meet the lighting mode requirements of users on different floors while ensuring comfort and energy saving effects;

[0030] 3. The resource sequence construction module comprehensively considers the preferred usage scenarios, usage conditions and floor user preferences of the floors. Through the lighting clustering algorithm, it can provide users with scores of all floor scenarios, thereby improving the utilization rate of floor lighting resources and user comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a framework diagram of a modeling system based on digital display according to the present invention;

[0032] Figure 2 This is a flow chart of a scene fitness calculation unit of a modeling system based on digital display of the present invention;

[0033] Figure 3 The present invention is a flowchart of a lighting parameter search algorithm in a modeling system based on digital display. DETAILED DESCRIPTION

[0034] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0035] The term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.

[0036] Example 1

[0037] Figure 1 The framework diagram of the modeling system based on digital display disclosed in this embodiment is shown, including:

[0038] The user behavior data collection module is used to collect data from lamps and sensors on different floors; establish a floor lighting scene data set, including corresponding lighting scenes and expected lighting data ranges, including collecting lighting usage data on the user's floor when the system is running, and the lighting usage data includes light brightness, duration and adjustment frequency; and collect light color temperature by installing color temperature sensors near the floor lighting equipment; the lamps equipped on each floor record the usage of lights through Internet of Things devices, including the number of switches, brightness adjustment frequency, dimming duration, and adjusted brightness value.

[0039] Intelligent scenario learning module, which calculates the preferred usage scenarios of users on each floor through the lighting usage patterns of different floors;

[0040] A user preference model building module, used to build a user application preference model and calculate the application user preference according to the user application preference model;

[0041] The resource sequence building module is used to match the floor lighting mode sequence according to the preferred usage scenarios of the users on each floor and the usage of the floor lamps and the preferences of the applicant users;

[0042] The visualization module is used to provide a visualization interface. When the user provides the current scene settings, it provides the user with the matching sequence of all lighting modes on the floor and provides the current scene score for the user to choose.

[0043] The intelligent scenario learning module includes a scenario fitness calculation unit and a scenario preference matching unit; Figure 2 The flowchart of the scene fitness calculation unit of the modeling system based on digital display disclosed in this embodiment is shown. The scene fitness calculation unit is used to calculate the floor lighting scene fitness, including a lighting fitness calculation strategy. The lighting fitness calculation strategy obtains the lighting fitness by weighted summation of the bulb color temperature fitness, brightness fitness, duration fitness and adjustment frequency fitness. The bulb color temperature fitness calculation formula is:

[0044]

[0045] Where α represents the adjustment parameter, ΔT represents the average of the difference between the color temperature change reference value Rt set within the preset time and the actual color temperature change, T represents the set color temperature reference value, T max Indicates the maximum color temperature within the preset time, T min Indicates the minimum color temperature within the preset time; the brightness adaptability f1, duration adaptability f2 and adjustment frequency adaptability f3 are expressed by functions as follows: χ∈(1,2,3),F χ Indicates the current measured value. Indicates the preset value, δ χ Indicates the adjustment parameter.

[0046] The scene adaptability calculation unit also includes a personnel comfort calculation strategy, which obtains the personnel comfort by collecting the weighted average of the floor color temperature comfort and the air quality comfort; the color temperature comfort is obtained based on the deviation between the current color temperature of the floor and the most comfortable color temperature; the most suitable color temperature is set, and if the current color temperature in the floor deviates from the most suitable color temperature, the color temperature comfort will decrease. The calculation formula is: TP current Indicates the color temperature of the current floor, TP ideal Indicates the most suitable color temperature inside the floor, TP range Indicates the acceptable color temperature range (e.g. ±5°C); the air quality comfort is calculated based on the carbon dioxide concentration. If the ideal carbon dioxide concentration is set, the air quality comfort calculation formula is: Among them, Q current Indicates the carbon dioxide concentration on the current floor, Q ideal Indicates the carbon dioxide concentration under ideal air quality, Q max Indicates the set maximum carbon dioxide concentration. The floor lighting scene adaptability is obtained by weighted summation of personnel comfort and lighting adaptability.

[0047] Example 2

[0048] Figure 3 The flowchart of the lighting parameter search algorithm in the digital display-based modeling system disclosed in this embodiment is shown. The floor lighting scene adaptability is used to obtain a range set of recommended lighting data for each floor through the lighting parameter search algorithm. The specific steps of the lighting parameter search algorithm include:

[0049] Step 1: Collect historical floor user operation behaviors and corresponding fitness, store them in the operation behavior fitness database, and associate them with specific floor numbers;

[0050] Step 2: Set the lighting comfort threshold as the baseline for the system's recommended lighting settings, extract the lighting data of any floor in the operation behavior fitness database whose lighting scene fitness is greater than the lighting comfort threshold as the set of candidate lighting parameters, and obtain multiple combinations that meet the conditions {(lg1, ti1, fc1), (lg2, ti2, fc2), …, (lg m ,ti m ,fc m )},(lg m ,ti m ,fc m ) represent the brightness, duration and adjustment frequency of the mth floor respectively;

[0051] Step 3: extract the maximum and minimum values ​​of light brightness, the maximum and minimum values ​​of duration, and the maximum and minimum values ​​of adjustment frequency in the set of candidate light parameters, form a brightness recommendation range, a duration recommendation range, and an adjustment frequency recommendation range, and obtain a rough recommendation range set of light parameters;

[0052] Step 4: randomly generate K groups of lighting parameter combinations within the rough recommended range of the lighting parameters by using a genetic algorithm, calculate the lighting scene adaptability of each lighting parameter combination, and extract all lighting parameter combinations that are greater than the lighting comfort threshold;

[0053] Step 5: Extract the maximum and minimum values ​​of each parameter in the lighting parameter combination obtained in step 4 to form a set of detailed recommended ranges of lighting parameters.

[0054] Compared with a single optimal solution, the recommended parameter range allows the system to flexibly adjust the settings to meet the needs of users on different floors. Through the optimization algorithm, the system can continuously and adaptively adjust the lighting settings based on different historical data to ensure comfort. The parameter range recommendation ensures that the lighting settings on the floor achieve the best balance between energy saving and comfort.

[0055] The user preference model building module includes: when the user logs in to the lighting mode adjustment system, the system allows the user to select the lighting setting preference, for example, the floor lighting scene can include different types such as "fog lighting mode", "reading lighting mode", "art display lighting mode", "guide lighting mode", "festival atmosphere lighting mode", "security patrol lighting mode", etc.; for example, in rainy, foggy or hazy weather, the light in the corridor may be affected, and the foggy lighting mode needs to be turned on at this time. The foggy lighting mode can enhance the brightness of the LED light group and adjust the irradiation angle and range to ensure sufficient lighting in the corridor and improve safety. By using special filters or technologies, the interference of fog, rain, etc. on the light is reduced, and the lighting effect is improved;

[0056] Reading lighting mode is suitable for reading corners or rest areas in corridors. It uses lights with higher brightness and appropriate color temperature (such as around 4000K) to provide enough light to reduce eye fatigue. It can be configured with a dimmable function to allow users to adjust the brightness according to the type of reading material and the light environment.

[0057] If there are artworks or decorations in the corridor, a special lighting mode can be designed for art display; directional lighting or spotlights can be used to highlight the details and beauty of the exhibits; the color temperature and brightness of the lights can be adjusted according to the type and style of the artwork to create the best viewing effect;

[0058] Set up directional lighting in the corridor to help users quickly find the target area; use arrow-shaped lamps or light signs with appropriate brightness and color temperature to guide users forward; use eye-catching light signs in key locations such as emergency exits and stairwells to improve safety;

[0059] During specific holidays or events, you can design festive atmosphere lighting modes; use colored lights, dynamic lighting effects or special shapes of lamps to create a festive atmosphere; you can choose appropriate lighting tones according to the theme and color of the festival, such as using red and green lights for Christmas, and soft yellow lights for Mid-Autumn Festival.

[0060] Provide security patrol lighting mode for security personnel or property management personnel; use high-brightness and wide-irradiation range lamps to ensure that every corner in the corridor is illuminated; can be combined with intelligent control systems to achieve timed opening and closing of lights, as well as remote monitoring functions.

[0061] The system associates the user's historical lighting setting preferences with the light scene adaptability, and analyzes the lighting mode and range corresponding to each light scene adaptability according to the user's historical lighting setting preferences, including collecting the mean value of the lighting data corresponding to the user's historical lighting setting preferences as the main input variable for the user's lighting mode and range for the floor; for example, for the "reading lighting mode", the maximum and minimum values ​​of brightness, duration and adjustment frequency in the historical lighting data are collected as the user's historical lighting mode and range; the lighting mode and range of all historical users for the floor are extracted as secondary input variables; the lighting feature vector corresponding to each lighting mode of the floor is calculated as input data, and the lighting feature vector corresponding to each lighting mode of the floor is obtained by weighted summation of the main input variable and the secondary input variable, wherein the weight of the main input variable is greater than twice the weight of the secondary input variable; by giving a greater weight to the current user's preference data and combining it with the historical data of other users, the system can accurately recommend the floor lighting settings that best meet the user's current needs, comprehensively considering the needs of multiple people while meeting the needs of the applicant. According to the corresponding lighting modes, all lighting feature vectors are labeled with corresponding floor lighting scene mode labels; all lighting feature vectors and corresponding floor lighting scene mode labels are used as training sets, and the mapping relationship between lighting feature vectors and floor lighting scene modes is learned through the support vector machine model; the model will output a floor lighting scene mode label, that is, the floor lighting setting scene that best suits the user's current needs, and extract the expected lighting data range corresponding to the floor.

[0062] The resource sequence construction module includes merging the set of fine recommended ranges of lighting parameters for each floor to form a feature space; taking the expected lighting data range expected by the user as the feature vector u, and obtaining the lighting scene matching sequence of the floor through a lighting clustering algorithm.

[0063] The light clustering algorithm includes calculating the floor light scene cluster with the smallest distance to the user's needs. c i represents the set of fine recommended ranges of lighting parameters for the i-th floor, C is the total distance from the cluster center to u, k is the number of clusters, until the cluster center reaches the preset number of iterations, the floor lighting mode in the floor lighting scene set cluster with the smallest distance user demand is calculated for the user's comfort level saf on the floor; considering the matching degree and comfort score of the lighting setting comprehensively, the comprehensive fitness score M=α1||uc for each lighting scene on the floor is calculated i ||+α2saf; The comprehensive fitness scores of all lighting modes of the floor in the floor lighting scene cluster J are arranged in descending order to provide the user with a matching sequence that matches all lighting scenes, where α1 and α2 represent weight coefficients.

[0064] The current scene score is obtained by extracting the mean of the light scene fitness of all scenes in the matching sequence of the light scene as the current scene score standard value, and extracting the comprehensive fitness of the current scene set by the user, and obtaining the current scene score through the current scene score standard value Mst and the comprehensive fitness Mcs of the current scene. If the score is within ±20% of the current scene score standard value, it is considered to be "excellent" or close to the standard, and a higher score can be obtained. Then, a corresponding score is given according to the degree to which the comprehensive fitness of the current scene deviates from the current scene score standard value; for example, if the current scene score standard value is set to be within ±20%, the score is 8-10 points; if it exceeds this range but does not exceed ±50%, the score is 5-8 points; if it exceeds ±50%, the score is 0-5 points; specifically, it is as follows:

[0065] If the absolute value of the difference between the comprehensive fitness of the current scene and the current scene scoring standard value is less than or equal to Mst×0.2, the current scene scoring

[0066] If the absolute value of the difference between the comprehensive fitness of the current scene and the current scene scoring standard value is greater than Mst×0.2 and less than or equal to Mst×0.5, the current scene scoring

[0067] If the absolute value of the difference between the comprehensive fitness of the current scene and the current scene scoring standard value is greater than Mst×0.5, the current scene scoring

[0068] The threshold and weight may be set by default according to the present invention, or may be set by an operator.

[0069] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A modeling system based on digital display, characterized by: include: User behavior data collection module, used to collect data from lamps and sensors on different floors; Intelligent scenario learning module, which calculates the preferred usage scenarios of users on each floor through the lighting usage patterns of different floors; A user preference model building module, used to build a user application preference model and calculate the application user preference according to the user application preference model; The resource sequence building module is used to match the floor lighting mode sequence according to the preferred usage scenarios of the users on each floor and the usage of the floor lamps and the preferences of the applicant users; The visualization module is used to provide a visualization interface. When the user provides the current scene settings, it provides the user with the matching sequence of all lighting modes on the floor and provides the current scene score for the user to choose.

2. The modeling system based on digital display according to claim 1, characterized in that: The user behavior data collection module is used to establish a floor lighting scene data set, including corresponding lighting scenes and expected lighting data ranges, including collecting lighting usage data on the user's floor when the system is running, and the lighting usage data includes light brightness, duration and adjustment frequency; and collecting light color temperature by installing color temperature sensors near floor lighting equipment; the lamps equipped on each floor record the usage of lights through Internet of Things devices, including the number of switches, brightness adjustment frequency, dimming duration, and adjusted brightness value.

3. The modeling system based on digital display according to claim 2, characterized in that: The intelligent scenario learning module includes a scenario fitness calculation unit and a scenario preference matching unit; The scene fitness calculation unit is used to calculate the floor lighting scene fitness, including a lighting fitness calculation strategy, which obtains the lighting fitness by weighted summation of the bulb color temperature fitness, brightness fitness, duration fitness and adjustment frequency fitness; the bulb color temperature fitness calculation formula is: Where α represents the adjustment parameter, ΔT represents the average of the difference between the color temperature change reference value Rt set within the preset time and the actual color temperature change, T represents the set color temperature reference value, T max Indicates the maximum color temperature within the preset time, T min Indicates the minimum color temperature within the preset time; the brightness adaptability f1, duration adaptability f2 and adjustment frequency adaptability f3 are expressed by functions as follows: χ∈(1,2,3),F χ Indicates the current measured value. Indicates the preset value, δ χ Indicates the adjustment parameter.

4. The modeling system based on digital display according to claim 3, characterized in that: The scene adaptability calculation unit also includes a personnel comfort calculation strategy, which obtains the personnel comfort by collecting the weighted average of the floor color temperature comfort and the air quality comfort; the color temperature comfort is obtained based on the deviation between the current color temperature of the floor and the most comfortable color temperature; the air quality comfort is calculated based on the carbon dioxide concentration, and the air quality comfort calculation formula is: Among them, Q current Indicates the current floor air carbon dioxide concentration, Q ideal Indicates the carbon dioxide concentration under ideal air quality, Q max Indicates the set maximum carbon dioxide concentration.

5. The modeling system based on digital display according to claim 4, characterized in that: The floor lighting scene adaptability is obtained by weighted summing of personnel comfort and lighting adaptability.

6. The modeling system based on digital display according to claim 5, characterized in that: The floor lighting scene adaptability is used to obtain a range set of recommended lighting data for each floor through a lighting parameter search algorithm; The specific steps of the lighting parameter search algorithm include: Step 1: Collect historical floor user operation behaviors and corresponding fitness, store them in the operation behavior fitness database, and associate them with specific floor numbers; Step 2: Set a lighting comfort threshold as a baseline for the system's recommended lighting settings, and extract lighting data from the operation behavior fitness database whose lighting scene fitness is greater than the lighting comfort threshold on any floor as a set of lighting parameters to be selected; Step 3: extract the maximum and minimum values ​​of light brightness, the maximum and minimum values ​​of duration, and the maximum and minimum values ​​of adjustment frequency in the set of selected light parameters, form a brightness recommendation range, a duration recommendation range, and an adjustment frequency recommendation range, and obtain a rough recommendation range set of light parameters; Step 4: randomly generate K groups of lighting parameter combinations within the rough recommended range of the lighting parameters by using a genetic algorithm, calculate the lighting scene adaptability of each lighting parameter combination, and extract all lighting parameter combinations that are greater than the lighting comfort threshold; Step 5: Extract the maximum and minimum values ​​of each parameter in the lighting parameter combination obtained in step 4 to form a set of detailed recommended ranges of lighting parameters.

7. The modeling system based on digital display according to claim 6, characterized in that: The user preference model building module includes: when a user logs in to the lighting mode adjustment system, the system allows the user to select a lighting setting preference, associates the user's historical lighting setting preference with the lighting scene adaptability, and the system analyzes the lighting mode and range corresponding to each lighting scene adaptability according to the user's historical lighting setting preference, including collecting the mean value of the lighting data corresponding to the user's historical lighting setting preference as the user's lighting mode and range for the floor as the main input variable; extracting the lighting mode and range of all historical users for the floor as the secondary input variable; calculating the lighting feature vector corresponding to each lighting mode of the floor as input data, wherein the lighting feature vector corresponding to each lighting mode of the floor is obtained by weighted summation of the main input variable and the secondary input variable, wherein the weight of the main input variable is greater than twice the weight of the secondary input variable; according to the corresponding lighting mode, labeling all lighting feature vectors with corresponding floor lighting scene mode labels; using all lighting feature vectors and corresponding floor lighting scene mode labels as training sets, and learning the mapping relationship between lighting feature vectors and floor lighting scene modes through a support vector machine model; the model will output a floor lighting scene mode label, that is, the floor lighting setting scene that best suits the user's current needs, and extract the expected lighting data range corresponding to the floor.

8. The modeling system based on digital display according to claim 7, characterized in that: The resource sequence construction module includes merging the set of fine recommended ranges of lighting parameters for each floor to form a feature space; taking the expected lighting data range expected by the user as the feature vector u, and obtaining the lighting scene matching sequence of the floor through a lighting clustering algorithm.

9. The modeling system based on digital display according to claim 8, characterized in that: The light clustering algorithm includes calculating the floor light scene cluster with the smallest distance to the user's needs. c i represents the set of fine recommended ranges of lighting parameters for the i-th floor, C is the total distance from the cluster center to u, k is the number of clusters, until the cluster center reaches the preset number of iterations, the floor lighting mode in the floor lighting scene set cluster with the smallest distance user demand is calculated for the user's comfort level saf on the floor; considering the matching degree and comfort score of the lighting setting comprehensively, the comprehensive fitness score M=α1||uc for each lighting scene on the floor is calculated i ||+α2saf; The comprehensive fitness scores of all lighting modes of the floor in the floor lighting scene cluster J are arranged in descending order to provide the user with a matching sequence that matches all lighting scenes, where α1 and α2 represent weight coefficients.

10. The modeling system based on digital display according to claim 9, characterized in that: The current scene score is obtained by extracting the average of the light scene fitness of all scenes in the matching sequence of the light scene as the current scene score standard value, and extracting the comprehensive fitness of the current scene set by the user, and obtaining the current scene score through the current scene score standard value and the comprehensive fitness of the current scene.

Images