Twin scene light dynamic adjustment method and device, computer equipment and storage medium

Abstract

The invention discloses a twinborn scene light dynamic adjustment method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring data acquired by a sensor in a target environment and preference information of a user for light effects in different scenes; creating a digital twin model corresponding to the target environment; mapping the data into the digital twin model; generating a light configuration scheme by adopting a light configuration model in combination with the data; and dynamically adjusting the light in the target environment according to the light configuration scheme. By implementing the method provided by the invention, the problems that the flexibility is insufficient, the real-time response capability is influenced and the diversified requirements in a dynamic scene are difficult to meet due to the fact that an existing lamplight configuration mode often depends on manual setting can be solved.

Description

Technical Field

[0001] The present invention relates to a digital twin system, and more specifically to a method, device, computer equipment and storage medium for dynamically adjusting lighting of a twin scene. Background Art

[0002] With the rapid development of science and technology, digital twin technology, as an emerging integrated technology, has become a key force in promoting the intelligent transformation of various industries. Digital twin technology achieves seamless connection between the physical world and the digital world by creating a virtual model of the physical system, making it possible to simulate, predict and optimize the performance of the physical system. This technology not only shows great potential in traditional industrial fields such as manufacturing and aerospace, but also finds a wide range of application scenarios in emerging fields such as architecture, entertainment and virtual reality. In particular, its importance is becoming increasingly prominent in the intelligent configuration of lighting effects.

[0003] Traditional lighting configuration methods mainly rely on manual settings, that is, technicians manually adjust the position, angle, color and other parameters of the lamps according to the predetermined design plan. Although this approach has met basic needs in the past, it has also exposed obvious limitations. First, the manual setting method is less flexible. Once the design plan is determined, it is difficult to make quick adjustments to adapt to new needs or environmental changes. Secondly, slow response speed is also an issue that cannot be ignored. In the face of emergencies or when the lighting effects need to be changed immediately, manual adjustments are obviously unable to respond in time. Furthermore, due to the lack of effective monitoring and feedback mechanisms, traditional methods are difficult to ensure the consistency of lighting effects with the expected goals, especially in large or complex scenes. This inconsistency may greatly reduce the user experience.

[0004] Therefore, it is necessary to design a new method to solve the problem that the existing lighting configuration method often relies on manual settings, which not only leads to insufficient flexibility, but also affects the real-time response capability and is difficult to meet the diverse needs in dynamic scenes. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the prior art and provide a method, device, computer equipment and storage medium for dynamic adjustment of twin scene lighting.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: a twin scene lighting dynamic adjustment method, comprising: Obtain data collected by sensors in the target environment and user preferences for lighting effects in different scenarios; Creating a digital twin model corresponding to the target environment; mapping the data into the digital twin model; Generate a lighting configuration plan by using a lighting configuration model combined with the data; The lighting in the target environment is dynamically adjusted according to the lighting configuration scheme.

[0007] A further technical solution is: after dynamically adjusting the lighting in the target environment according to the lighting configuration scheme, the method further comprises: Get feedback from users; The lighting configuration model is updated according to the feedback information.

[0008] A further technical solution is: the sensor includes a light intensity sensor.

[0009] A further technical solution is: creating a digital twin model corresponding to the target environment includes: Use CAD or BIM software to build a three-dimensional model of the building and its interior space corresponding to the target environment to obtain a digital twin model.

[0010] Its further technical solution is: the lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features using feature engineering, and then training a supervised learning model.

[0011] The further technical solution is: the lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a deep neural network, including: Obtain historical lighting usage data and user preference data to obtain initial data; Preprocessing the initial data to obtain a preprocessing result; Analyzing the preprocessing results using an unsupervised learning model to obtain potential user preferences and behavior patterns; Using feature engineering to extract key features from the preprocessing results and potential user preferences and behavior patterns; Build supervised learning models; The supervised learning model is trained using the key features to obtain a lighting configuration model.

[0012] A further technical solution is: the feature engineering is used to extract key features from the preprocessing results and potential user preferences and behavior patterns, including: Using an unsupervised learning method to reduce the data dimension of the preprocessing results and potential user preferences and behavior patterns, and extract important key features to obtain important key features; Applying clustering algorithms to identify user behavior patterns within the important key features to obtain new features; The important key features and the new features are combined to form key features.

[0013] The present invention also provides a twin scene lighting dynamic adjustment method, comprising: A data acquisition unit, used to acquire data collected by sensors in the target environment; A creation unit, used to create a digital twin model corresponding to the target environment; A mapping unit, used for mapping the data into the digital twin model; A solution generating unit, configured to generate a lighting configuration solution by using a lighting configuration model in combination with the data; An adjustment unit is used to dynamically adjust the lighting in the target environment according to the lighting configuration scheme.

[0014] The present invention further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above method when executing the computer program.

[0015] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0016] Compared with the prior art, the present invention has the following beneficial effects: by acquiring sensor data and user lighting preference information, the present invention first creates a digital twin model of the target environment to ensure the virtual presentation of the environment, and then maps these data into the digital twin model to provide a basis for subsequent analysis, and uses the lighting configuration model to automatically generate a lighting configuration plan that meets current needs in combination with the collected data. By dynamically adjusting the lighting configuration plan, real-time response is achieved and lighting effects are optimized. Ultimately, this intelligent configuration method not only improves flexibility, but also can cope with diverse dynamic scene requirements.

[0017] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0019] Figure 1 A schematic diagram of a process flow of a twin scene lighting dynamic adjustment method provided in an embodiment of the present invention; Figure 2A schematic diagram of a sub-process of a twin scene lighting dynamic adjustment method provided in an embodiment of the present invention; Figure 3 A schematic block diagram of a twin scene lighting dynamic adjustment device provided in an embodiment of the present invention; Figure 4 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0022] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0023] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] See also Figure 1 , Figure 1A schematic flow chart of a twin scene lighting dynamic adjustment method provided by an embodiment of the present invention. The twin scene lighting dynamic adjustment method is applied to a server, which interacts with a lighting controller for data. The lighting intelligent configuration method based on digital twin technology has significant advantages, which can not only reduce labor costs, but also improve resource utilization efficiency, thereby achieving cost reduction and efficiency improvement, and providing users with a better experience and a more efficient management solution. The method enables the lighting configuration to be adjusted and optimized in real time in a virtual environment by creating a virtual model that is highly consistent with the actual environment. Specifically, environmental data and user preferences are collected by sensors, and after input into the digital twin model, the model is combined with a machine learning algorithm for analysis to automatically generate the best lighting configuration solution. This intelligent configuration method reduces manual intervention, can flexibly respond to environmental changes, and improve the accuracy of lighting management. In addition, digital twin technology also supports comprehensive monitoring and feedback of lighting effects. The system can automatically identify and make corresponding adjustments when the environment changes or user needs are adjusted, ensuring that the lighting effect is always kept in the best state, while reducing energy consumption and promoting sustainable development. Through this intelligent management, not only can the user experience be improved, but also the operating costs can be reduced, thereby gaining an advantage in a highly competitive market.

[0025] Figure 1 FIG. 1 is a flow chart of a twin scene lighting dynamic adjustment method provided by an embodiment of the present invention. Figure 1 As shown, the method includes the following steps S110 to S170.

[0026] S110: Acquire data collected by sensors in the target environment.

[0027] In this embodiment, the sensor includes a light intensity sensor.

[0028] Specifically, with the development of Internet of Things (IoT) technology, intelligent environmental monitoring has become possible. In a specific target environment (such as smart home, smart agriculture, industrial production site, etc.), various types of sensors are deployed to monitor various parameters of the environment. These sensors are not limited to a single type, but include but are not limited to multiple sensors such as light intensity sensors, temperature and humidity sensors, motion sensors, etc., which work together to achieve all-round and multi-dimensional monitoring of the environment.

[0029] Among them, the light intensity sensor is used to measure the light intensity in the environment, which is particularly important for application scenarios that require precise control of lighting conditions, such as plant growth rooms and photo studios. The temperature and humidity sensor monitors the temperature and humidity of the environment at the same time, and is an indispensable part of many application scenarios, especially in places where a constant temperature and humidity environment needs to be maintained, such as archives and laboratories. Motion sensors are used to detect whether there are moving objects or people entering the monitoring area, and are widely used in security systems, smart homes and other fields.

[0030] First, arrange the various sensors mentioned above in the target environment. Select the appropriate sensor type and quantity according to specific needs, and determine the best installation location to ensure that the required environmental information can be accurately captured. The sensor sends the collected data to the gateway device in real time through the built-in wireless communication module (such as Wi-Fi, Bluetooth, Zigbee, etc.) or wired connection. As an intermediate bridge, the gateway device is responsible for uploading the received sensor data to the cloud server via the Internet. Lightweight message transmission protocols such as MQTT may be used in this process to improve data transmission efficiency and reduce network latency. In the cloud, the received raw data will be stored and necessary preprocessing will be performed, such as data cleaning, format conversion, etc., to facilitate subsequent in-depth analysis and application development.

[0031] The user interface collects user preference information on lighting effects in different scenarios and combines it with environmental data to provide a basis for subsequent intelligent configuration.

[0032] S120: Create a digital twin model corresponding to the target environment.

[0033] In this embodiment, CAD or BIM software is used to construct a three-dimensional model of the building and the interior space of the building corresponding to the target environment to obtain a digital twin model, ensuring that the model is highly consistent with the actual environment.

[0034] Specifically, creating a digital twin model corresponding to the target environment is an important part of the overall system design. A digital twin model refers to a virtual copy of the target environment built using computer-aided design (CAD) or building information modeling (BIM) software. The copy includes not only a three-dimensional model of the physical structure, but also the attribute information of various elements in the environment and their relationships. When creating, first collect relevant information about the target environment, including architectural design drawings, environmental layout drawings, material lists, etc. These materials will provide a basis for establishing an accurate digital twin model; select suitable CAD or BIM software, such as Autodesk Revit, SketchUp, AutoCAD, etc. These software provide a wealth of modeling tools and functions to meet the modeling needs of different precision requirements; according to the architectural design drawings, use the selected software to build the external structure model of the building, including walls, roofs, windows, doors and other elements; refine the design of the internal space, divide different rooms, corridors, stairs and other areas according to the environmental layout diagram, and ensure the functionality and accessibility of each space; add other important elements in the environment to the model, such as furniture, decorations, mechanical equipment, etc., to make the model richer and more realistic; define detailed attribute information for each object in the model, including but not limited to size, material, color, brand, model, etc.; for variable attributes (such as temperature, humidity, light intensity, etc.), the corresponding values ​​in the model can be updated through real-time synchronization with sensor data to maintain the consistency of the model with the actual situation; compare and verify the constructed digital twin model with the actual environment to ensure the accuracy of the model. This step may require multiple iterations until the model is highly consistent with the actual environment. Based on actual usage, the model is continuously adjusted and optimized to improve its performance, such as improving the model loading speed and enhancing the interactive experience.

[0035] S130. Map the data into the digital twin model.

[0036] In this embodiment, the data stream of the sensor is connected to the digital twin model to realize the visualization and analysis of real-time data.

[0037] S140: Generate a lighting configuration plan by using a lighting configuration model combined with the data.

[0038] In this embodiment, the lighting configuration scheme refers to a set of lighting setting plans customized according to the specific needs and preferences of the user. This set of plans usually takes into account multiple factors, such as time, activity type, ambient light intensity, etc., and aims to create the most suitable lighting environment for the current scene by intelligently adjusting the brightness, color temperature, color and other factors of the light. An effective lighting configuration scheme can improve the comfort of living or working, improve the visual experience, and even affect people's emotions and health.

[0039] In a smart home environment, lighting configurations can be automatically executed by the intelligent system or manually selected through the user interface. The system dynamically adjusts lighting settings based on the user's preference history, current activity type (such as reading, resting, partying, etc.), and external conditions (such as changes in natural light). For example: Reading mode: Brightness may be turned up and cool white light may be selected to reduce eye strain.

[0040] Sleep mode: reduce brightness and select warm colors to create a relaxing atmosphere and help you fall asleep.

[0041] Entertainment Mode: Automatically adjusts the color and brightness of the light according to the different content being played to enhance the viewing experience.

[0042] The process of generating lighting configuration plans involves multiple steps such as data collection, user preference analysis, and model training. The purpose is to make lighting not only meet basic lighting needs, but also become an important element to improve the quality of life and user experience. Through the application of intelligent algorithms, lighting configuration plans can be customized to meet the unique needs of different users in different scenarios.

[0043] The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features using feature engineering, and then training a supervised learning model.

[0044] In one embodiment, see Figure 2 The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features using feature engineering, and then training a supervised learning model, which may include steps S141 to S146.

[0045] S141. Acquire historical lighting usage data and user preference data to obtain initial data.

[0046] In this embodiment, the historical light usage data includes information such as the time, brightness, color, scene, etc. of the user's use of the light. The user preference data includes the user's feedback and selection records for different light settings.

[0047] This data can be collected automatically through smart home systems or obtained through user surveys and other means.

[0048] S142: preprocess the initial data to obtain a preprocessing result.

[0049] In this embodiment, the goal of preprocessing is to improve the quality of data and prepare for subsequent feature engineering and model training. This step includes: Data cleaning and data transformation, where data cleaning refers to deleting or filling missing values ​​and removing outliers. Data transformation refers to encoding categorical variables (such as one-hot encoding) and standardizing or normalizing continuous variables.

[0050] S143. Analyze the preprocessing results using an unsupervised learning model to obtain potential user preferences and behavior patterns.

[0051] In this embodiment, the preprocessed data is analyzed by unsupervised learning methods to discover potential user preferences and behavior patterns. Common methods include principal component analysis (PCA) and clustering algorithms (such as K-Means). Among them, principal component analysis (PCA) is used for dimensionality reduction to help discover the main trend of changes in the data. Clustering algorithms (such as K-Means) are used to identify natural groupings in the data, which helps to understand the differences between different user groups.

[0052] S144. Feature engineering is used to extract key features from the preprocessing results and potential user preferences and behavior patterns.

[0053] In one embodiment, the above-mentioned step S144 may include steps S1441 - S1443 .

[0054] S1441. Use an unsupervised learning method to reduce the data dimension of the preprocessing results and potential user preferences and behavior patterns, and extract important key features to obtain important key features.

[0055] In this embodiment, the preprocessed data is first processed using an unsupervised learning method. Unsupervised learning refers to allowing the machine to self-discover and learn the laws or patterns in the data without pre-given labels. In this application scenario, the main purpose is to reduce the data dimension while retaining those features that best reflect the characteristics of the data. Commonly used data dimensionality reduction techniques include principal component analysis (PCA), independent component analysis (ICA), t-distributed random neighbor embedding (t-SNE), etc. Through these methods, important key features can be extracted from the original data, which are crucial for subsequent user behavior pattern recognition.

[0056] By applying unsupervised learning methods to the preprocessing results and potential user preferences and behavior patterns for data dimensionality reduction, features that are critical to identifying user behavior patterns can be screened out. These features help reduce computational complexity while maintaining or improving model performance.

[0057] S1442, applying a clustering algorithm to identify user behavior patterns within the important key features to obtain new features; In this embodiment, new features are user behavior pattern features identified by clustering algorithms based on further analysis of important key features. These features are derived from existing data and represent a certain pattern or trend of user behavior, which may not appear directly in the original data.

[0058] New features identified by clustering algorithms can reveal the segmentation structure within user groups and help understand the similarities and differences between different users. For example, in recommendation systems, new features can help locate user groups more accurately and provide more personalized services; in anomaly detection scenarios, new features may help identify user activities that do not conform to normal behavior patterns, thereby providing timely warnings of potential risks.

[0059] Specifically, after obtaining the important key features, the next step is to apply clustering algorithms to these features. Clustering is a common unsupervised learning method that attempts to divide the samples in the data set into several groups (or clusters) so that the similarity of samples in the same group is as high as possible, while the similarity of samples between different groups is as low as possible. Through clustering algorithms, common features in user behavior patterns can be identified, that is, new features. Common clustering algorithms include K-means, hierarchical clustering, DBSCAN, etc. This step helps to deeply understand the user's preferences and behavior patterns, and provide a basis for further optimizing the lighting configuration plan.

[0060] S1443. Combine the important key features and the new features to form key features.

[0061] In this embodiment, finally, the important key features extracted from S1441 are combined with the new features identified by the clustering algorithm in S1442 to form a final key feature set. This set not only contains important information in the original data, but also incorporates the behavioral pattern features obtained through clustering analysis, which can more comprehensively and accurately describe the user's behavioral habits and preferences. These key features will serve as the basis for building personalized lighting configuration solutions, helping the system to better understand and predict user needs, thereby providing more personalized services.

[0062] Through the above three steps, valuable user preference and behavior pattern information can be effectively mined from large amounts of data, providing strong support for subsequent intelligent decision-making.

[0063] S145. Build a supervised learning model.

[0064] In this embodiment, a suitable supervised learning model is selected according to the task requirements, such as random forest, support vector machine (SVM), deep learning model, etc. The selection of the model depends on the characteristics of the data and the business objectives.

[0065] S146: Use the key features to train the supervised learning model to obtain a lighting configuration model.

[0066] In this embodiment, the selected supervised learning model is trained using the key feature set determined in the previous step. During the training process, it is important to note that the optimal model parameters are found through methods such as cross-validation. The model performance is evaluated using indicators such as accuracy, recall, and F1-score to ensure that the model performs well on unseen data.

[0067] Once the model is trained and optimized, it can be used to generate personalized lighting configuration recommendations based on the user's current environment (such as time, activity type) and personal historical preferences. In addition, a real-time feedback mechanism should be set up to allow users to give comments on the recommended lighting configuration in order to continuously optimize the model and improve the user experience.

[0068] This approach can not only generate lighting configuration plans that suit the user's personal preferences, but also evolve as the user's usage habits change, providing more intelligent services.

[0069] S150: Dynamically adjust the lighting in the target environment according to the lighting configuration plan.

[0070] In this embodiment, according to a predetermined lighting configuration scheme, the lighting settings in the target environment are automatically adjusted to meet the current environmental conditions and the expected user experience standards.

[0071] Use light sensors to monitor the light intensity and other related parameters of the environment in real time, such as temperature and humidity, to fully understand the state of the environment. Use historical data and machine learning models to predict potential user needs, such as the light brightness and color temperature that users may prefer during a specific time period. Automatically adjust the brightness, color, and mode of the light based on the monitored environmental data and predicted user needs. For example, when the intensity of natural light increases, appropriately reduce the brightness of artificial light; or when a user is detected entering the room, automatically turn on the light and adjust it to the settings that the user uses most frequently.

[0072] S160: Obtain user feedback information.

[0073] In this embodiment, user satisfaction feedback on current lighting settings is collected as an important basis for optimizing lighting configuration.

[0074] Provide a friendly and easy-to-operate user interface that allows users to quickly express their opinions on the current lighting effects, including satisfaction, dissatisfaction, or specific suggestions for improvement, through buttons, touch screens, etc. Introduce a quantitative scoring system (such as 1 to 5 points) so that users can express their satisfaction level more specifically, which is convenient for the system to conduct quantitative analysis. All user feedback will be recorded with timestamps and environmental conditions at the time to facilitate subsequent data analysis and model training.

[0075] S170: Update the lighting configuration model according to the feedback information.

[0076] In this embodiment, based on user feedback information, the lighting configuration model is continuously optimized and updated to better meet user needs and improve user experience.

[0077] Use statistical methods and machine learning techniques to conduct in-depth analysis of the collected user feedback data to identify key factors and patterns that affect user satisfaction. Based on the analysis results, adjust the existing lighting configuration model parameters, such as improving the user behavior prediction algorithm and optimizing the automatic adjustment logic of light brightness and color temperature. For users who frequently use the system, you can create personalized lighting profiles for them based on their historical feedback and personal preferences to achieve more accurate services. After updating the model, verify the effect of model optimization through simulation tests and field trials to ensure the stability and reliability of the system under different environmental conditions. Establish a continuous feedback loop to encourage users to provide more feedback to support the continuous iteration and optimization of the model, and ultimately achieve the best user experience.

[0078] Through the above steps, the system can not only realize the intelligent management of lights in the target environment, but also provide a lighting experience that better meets user expectations through continuous learning and optimization.

[0079] In this embodiment, a user interface that is both aesthetically pleasing and practical is designed to enable users to easily interact with the intelligent lighting system while providing necessary information feedback to enhance the user experience.

[0080] It adopts a modern and simple style, reduces unnecessary icons and text descriptions, and ensures that users can understand the operation at a glance. It provides a variety of preset modes for users to choose, such as reading mode, relaxation mode, party mode, etc. Each mode presets a specific brightness, color temperature and light distribution to meet the needs of different scenes. It allows users to manually adjust parameters such as light brightness and color temperature to meet personalized needs. Through controls such as sliders and knobs, the adjustment process becomes intuitive and simple. There is a special area on the interface to display the current light status (such as brightness, color temperature) and environmental parameters (such as light intensity, temperature, humidity), so that users can keep abreast of changes in the surrounding environment. The integrated user feedback function allows users to submit opinions or suggestions on the current light settings directly from the interface to promote continuous optimization of the system.

[0081] Through precise monitoring and intelligent control, unnecessary energy consumption is reduced while maintaining good lighting effects to achieve the goal of energy conservation and environmental protection. The system has a built-in energy consumption monitoring function that can record the power consumption of each lamp in real time to help managers understand energy usage. According to factors such as ambient light intensity and user activity patterns, the working status of the lamp is automatically adjusted, such as reducing the output of artificial light when natural light is sufficient, or automatically turning off the lights in unmanned areas. An energy-saving mode option is provided, and users can choose to enable it during specific periods to further reduce energy consumption, which is suitable for nighttime or low activity periods.

[0082] Through intelligent management and energy-saving measures, we can not only improve user experience, but also reduce operating costs, improve competitiveness and contribute to environmental protection. Through intelligent lighting adjustment, we can create a comfortable living and working environment and improve the quality of life and work efficiency of users. By optimizing energy use, we can significantly reduce electricity bills and long-term operating costs, bringing economic benefits to enterprises or families. Reducing energy waste and carbon emissions can help to cope with climate change and promote the society to move towards sustainable development. In the context of a society that pays more and more attention to environmental protection and energy conservation, products with these characteristics are more likely to be favored by consumers and help brands stand out in the market.

[0083] In summary, the combination of a friendly operating interface and energy-saving and sustainable development characteristics can not only provide a high-quality user experience, but also bring economic benefits and social value. It is an important consideration in the design of intelligent lighting systems.

[0084] The above twin scene lighting dynamic adjustment method first creates a digital twin model of the target environment by acquiring sensor data and user lighting preference information to ensure the virtual presentation of the environment. Then, the data is mapped to the digital twin model to provide a basis for subsequent analysis. The lighting configuration model is used in combination with the collected data to automatically generate a lighting configuration plan that meets current needs. By dynamically adjusting the lighting configuration plan, real-time response and optimization of lighting effects are achieved. Ultimately, this intelligent configuration method not only improves flexibility, but also can cope with diverse dynamic scene requirements.

[0085] Figure 3 is a schematic block diagram of a twin scene lighting dynamic adjustment device 300 provided in an embodiment of the present invention. Figure 3 As shown, corresponding to the above twin scene lighting dynamic adjustment method, the present invention also provides a twin scene lighting dynamic adjustment device 300. The twin scene lighting dynamic adjustment device 300 includes a unit for executing the above twin scene lighting dynamic adjustment method, and the device can be configured in a server. Figure 3 The twin scene lighting dynamic adjustment device 300 includes a data acquisition unit 301, a creation unit 302, a mapping unit 303, a scheme generation unit 304 and an adjustment unit 305.

[0086] The data acquisition unit 301 is used to acquire data collected by sensors in the target environment; the creation unit 302 is used to create a digital twin model corresponding to the target environment; the mapping unit 303 is used to map the data to the digital twin model; the solution generation unit 304 is used to generate a lighting configuration solution by adopting a lighting configuration model in combination with the data; the adjustment unit 305 is used to dynamically adjust the lighting in the target environment according to the lighting configuration solution.

[0087] Also includes: An information acquisition unit 306, used to acquire user feedback information; The updating unit 307 is configured to update the lighting configuration model according to the feedback information.

[0088] In one embodiment, the creation unit 302 is used to use CAD or BIM software to construct a three-dimensional model of the building and the interior space of the building corresponding to the target environment to obtain a digital twin model.

[0089] In one embodiment, a model training unit is further included, which is used to collect historical lighting usage data and user preference data, extract key features through feature engineering, and then train a deep neural network to obtain a lighting configuration model.

[0090] In one embodiment, the model training unit includes: An initial data acquisition subunit, used to acquire historical lighting usage data and user preference data to obtain initial data; A preprocessing subunit, used for preprocessing the initial data to obtain a preprocessing result; An analysis subunit, used for analyzing the preprocessing results using an unsupervised learning model to obtain potential user preferences and behavior patterns; An extraction subunit, for extracting key features from the preprocessing results and potential user preferences and behavior patterns by using feature engineering; Construct subunits for building supervised learning models; The training subunit is used to train the supervised learning model using the key features to obtain a lighting configuration model.

[0091] In one embodiment, the extraction subunit is used to use an unsupervised learning method to reduce the data dimension of the preprocessing results and potential user preferences and behavior patterns, and extract important key features to obtain important key features; apply a clustering algorithm to identify user behavior patterns within the important key features to obtain new features; and combine the important key features and the new features to form key features.

[0092] It should be noted that technical personnel in the relevant field can clearly understand that the specific implementation process of the above-mentioned twin scene lighting dynamic adjustment device 300 and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and conciseness of the description, it will not be repeated here.

[0093] The twin scene lighting dynamic adjustment device 300 can be implemented in the form of a computer program. Figure 4 Runs on the computer device shown.

[0094] See also Figure 4 , Figure 4 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a server, wherein the server may be an independent server or a server cluster composed of multiple servers.

[0095] See also Figure 4 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0096] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a twin scene lighting dynamic adjustment method.

[0097] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0098] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a twin scene lighting dynamic adjustment method.

[0099] The network interface 505 is used to communicate with other devices over the network. Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0100] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps: Acquire data collected by sensors in a target environment and user preference information for lighting effects in different scenarios; create a digital twin model corresponding to the target environment; map the data to the digital twin model; use a lighting configuration model combined with the data to generate a lighting configuration plan; and dynamically adjust the lighting in the target environment according to the lighting configuration plan.

[0101] Wherein, the sensor comprises a light intensity sensor.

[0102] The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a supervised learning model.

[0103] In one embodiment, after implementing the step of dynamically adjusting the lighting in the target environment according to the lighting configuration scheme, the processor 502 further implements the following steps: Acquire user feedback information; and update the lighting configuration model according to the feedback information.

[0104] In one embodiment, when implementing the step of creating a digital twin model corresponding to the target environment, the processor 502 specifically implements the following steps: Use CAD or BIM software to build a three-dimensional model of the building and its interior space corresponding to the target environment to obtain a digital twin model.

[0105] In one embodiment, when the processor 502 implements the lighting configuration model by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a deep neural network, the processor 502 specifically implements the following steps: Acquire historical lighting usage data and user preference data to obtain initial data; preprocess the initial data to obtain preprocessing results; use an unsupervised learning model to analyze the preprocessing results to obtain potential user preferences and behavior patterns; use feature engineering to extract key features from the preprocessing results and potential user preferences and behavior patterns; construct a supervised learning model; and use the key features to train the supervised learning model to obtain a lighting configuration model.

[0106] In one embodiment, when the processor 502 implements the step of extracting key features from the preprocessing results and potential user preferences and behavior patterns by using feature engineering, the processor 502 specifically implements the following steps: An unsupervised learning method is used to reduce the data dimension of the preprocessing results and potential user preferences and behavior patterns, and important key features are extracted to obtain important key features; a clustering algorithm is applied to identify user behavior patterns within the important key features to obtain new features; and the important key features and the new features are combined to form key features.

[0107] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0108] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0109] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein when the computer program is executed by a processor, the processor executes the following steps: Acquire data collected by sensors in a target environment and user preference information for lighting effects in different scenarios; create a digital twin model corresponding to the target environment; map the data to the digital twin model; use a lighting configuration model combined with the data to generate a lighting configuration plan; and dynamically adjust the lighting in the target environment according to the lighting configuration plan.

[0110] Wherein, the sensor comprises a light intensity sensor.

[0111] The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a supervised learning model.

[0112] In one embodiment, after executing the computer program to implement the step of dynamically adjusting the lighting in the target environment according to the lighting configuration scheme, the processor further implements the following steps: Acquire user feedback information; and update the lighting configuration model according to the feedback information.

[0113] In one embodiment, when the processor executes the computer program to implement the step of creating a digital twin model corresponding to the target environment, the processor specifically implements the following steps: Use CAD or BIM software to build a three-dimensional model of the building and its interior space corresponding to the target environment to obtain a digital twin model.

[0114] In one embodiment, when the processor executes the computer program to implement the lighting configuration model by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a deep neural network, the processor specifically implements the following steps: Acquire historical lighting usage data and user preference data to obtain initial data; preprocess the initial data to obtain preprocessing results; use an unsupervised learning model to analyze the preprocessing results to obtain potential user preferences and behavior patterns; use feature engineering to extract key features from the preprocessing results and potential user preferences and behavior patterns; construct a supervised learning model; and use the key features to train the supervised learning model to obtain a lighting configuration model.

[0115] In one embodiment, when the processor executes the computer program to implement the step of extracting key features from the preprocessing results and potential user preferences and behavior patterns using feature engineering, the processor specifically implements the following steps: An unsupervised learning method is used to reduce the data dimension of the preprocessing results and potential user preferences and behavior patterns, and important key features are extracted to obtain important key features; a clustering algorithm is applied to identify user behavior patterns within the important key features to obtain new features; and the important key features and the new features are combined to form key features.

[0116] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0117] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0118] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0119] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0120] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0121] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A twin scene lighting dynamic adjustment method, characterized in that: include: Obtain data collected by sensors in the target environment and user preferences for lighting effects in different scenarios; Creating a digital twin model corresponding to the target environment; mapping the data into the digital twin model; Using a lighting configuration model in combination with the data to generate a lighting configuration plan; Dynamically adjust the lighting in the target environment according to the lighting configuration scheme; The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a supervised learning model; The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a deep neural network, including: Obtain historical lighting usage data and user preference data to obtain initial data; Preprocessing the initial data to obtain a preprocessing result; Analyzing the preprocessing results using an unsupervised learning model to obtain potential user preferences and behavior patterns; Using feature engineering to extract key features from the preprocessing results and potential user preferences and behavior patterns; Build supervised learning models; Using the key features to train the supervised learning model to obtain a lighting configuration model; The feature engineering is used to extract key features from the preprocessing results and potential user preferences and behavior patterns, including: Using an unsupervised learning method to reduce the data dimension of the preprocessing results and potential user preferences and behavior patterns, and extract important key features to obtain important key features; Applying clustering algorithms to identify user behavior patterns within the important key features to obtain new features; The important key features and the new features are combined to form key features.

2. The twin scene lighting dynamic adjustment method according to claim 1, characterized in that: After dynamically adjusting the lighting in the target environment according to the lighting configuration scheme, the method further includes: Obtain user feedback; The lighting configuration model is updated according to the feedback information.

3. The twin scene lighting dynamic adjustment method according to claim 1, characterized in that: The sensor comprises a light intensity sensor.

4. The twin scene lighting dynamic adjustment method according to claim 1, characterized in that: The creating a digital twin model corresponding to the target environment includes: Use CAD or BIM software to build a three-dimensional model of the building and its interior space corresponding to the target environment to obtain a digital twin model.

5. The twin scene lighting dynamic adjustment method is characterized by: include: A data acquisition unit, used to acquire data collected by sensors in the target environment; A creation unit, used to create a digital twin model corresponding to the target environment; A mapping unit, used for mapping the data into the digital twin model; A solution generating unit, configured to generate a lighting configuration solution by combining the lighting configuration model with the data; An adjustment unit, configured to dynamically adjust the lighting in the target environment according to the lighting configuration scheme; The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a supervised learning model; The lighting configuration model is obtained by collecting historical lighting usage data and user preference data, extracting key features through feature engineering, and then training a deep neural network, including: Obtain historical lighting usage data and user preference data to obtain initial data; Preprocessing the initial data to obtain a preprocessing result; Analyzing the preprocessing results using an unsupervised learning model to obtain potential user preferences and behavior patterns; Using feature engineering to extract key features from the preprocessing results and potential user preferences and behavior patterns; Build supervised learning models; Using the key features to train the supervised learning model to obtain a lighting configuration model; The feature engineering is used to extract key features from the preprocessing results and potential user preferences and behavior patterns, including: Using an unsupervised learning method to reduce the data dimension of the preprocessing results and potential user preferences and behavior patterns, and extract important key features to obtain important key features; Applying clustering algorithms to identify user behavior patterns within the important key features to obtain new features; The important key features and the new features are combined to form key features.

6. A computer device, characterized in that: The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 4 when executing the computer program.

7. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images