Lighting system energy consumption management method in combination with user behavior analysis

Abstract

The invention discloses a lighting system energy consumption management method combined with user behavior analysis, and relates to the technical field of energy consumption management. The method comprises the following steps: obtaining a user behavior data set; mining is carried out, a plurality of user behavior modes are determined, data acquisition is carried out on the intelligent lighting equipment group, and a plurality of lighting modes are obtained; constructing a behavior-illumination mapping network; obtaining an illumination prediction scheme, simulating execution of the illumination prediction scheme to carry out energy consumption calculation, and generating illumination energy consumption simulation parameters; and feedback debugging is performed on the illumination prediction scheme according to the illumination energy consumption simulation parameters in combination with a behavior-illumination mapping network, an illumination optimization suggestion is generated, and intelligent energy consumption management is performed on the illumination system in the target illumination area. The technical problem that in the prior art, an illumination strategy cannot be adjusted in real time according to user behaviors, and consequently energy consumption is high is solved, intelligent management of the energy consumption of the illumination system is achieved by combining user behavior analysis, and the technical effects of improving the energy utilization efficiency and reducing the energy consumption cost are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management, and in particular to a lighting system energy consumption management method combined with user behavior analysis. Background Art

[0002] Smart lighting systems are widely used in residential, commercial and public places. Their main function is to automatically control lighting equipment by automatically sensing factors such as ambient light intensity and time period. However, existing smart lighting systems are usually based on fixed rules or preset sensing logic, and it is difficult to dynamically adapt to user behavior patterns and personalized needs. This approach may not only cause the lighting effect to not match the actual needs of users, but also easily cause unnecessary energy waste. In addition, existing technologies mostly use static strategies for energy management, lack the ability to dynamically adjust lighting solutions based on user behavior data, and cannot effectively improve energy efficiency and user experience. Summary of the invention

[0003] The present application provides a lighting system energy consumption management method combined with user behavior analysis, which solves the technical problem in the prior art that the lighting strategy cannot be adjusted in real time according to user behavior, resulting in high energy consumption.

[0004] In view of the above problems, the present application provides a lighting system energy consumption management method combined with user behavior analysis.

[0005] The present application provides a lighting system energy consumption management method combined with user behavior analysis, the method comprising: Data of target users are collected through multiple sensors deployed in the target lighting area to obtain a user behavior data set; mining is performed based on the user behavior data set to determine multiple user behavior patterns, and data of the intelligent lighting device group is collected according to the multiple user behavior patterns to obtain multiple lighting patterns; the multiple user behavior patterns and the multiple lighting patterns are associated and inferred to construct a behavior-lighting mapping network; lighting analysis is performed on the target lighting area through the behavior-lighting mapping network to obtain a lighting prediction plan, energy consumption calculation is performed by simulating the execution of the lighting prediction plan, and lighting energy consumption simulation parameters are generated; feedback debugging is performed on the lighting prediction plan according to the lighting energy consumption simulation parameters in combination with the behavior-lighting mapping network to generate lighting optimization suggestions, and intelligent management of energy consumption of the lighting system in the target lighting area is performed according to the lighting optimization suggestions.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, data of target users are collected through multiple sensors deployed in the target lighting area to obtain a user behavior data set. Then, mining is performed based on the user behavior data set to determine multiple user behavior patterns, and data of the intelligent lighting device group is collected according to the multiple user behavior patterns to obtain multiple lighting patterns. Further, multiple user behavior patterns and multiple lighting patterns are associated and inferred to construct a behavior-lighting mapping network. Then, lighting analysis is performed on the target lighting area through the behavior-lighting mapping network to obtain a lighting prediction plan, and the lighting prediction plan is simulated and executed to calculate energy consumption, and lighting energy consumption simulation parameters are generated. Finally, the lighting prediction plan is feedback debugged according to the lighting energy consumption simulation parameters combined with the behavior-lighting mapping network, and lighting optimization suggestions are generated. According to the lighting optimization suggestions, the energy consumption of the lighting system in the target lighting area is intelligently managed. The technical problem that the lighting strategy cannot be adjusted in real time according to user behavior in the prior art, resulting in high energy consumption, is solved. By combining user behavior analysis, intelligent management of the energy consumption of the lighting system is achieved, and the technical effect of improving energy utilization efficiency and reducing energy consumption costs is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic diagram of a lighting system energy consumption management method combined with user behavior analysis provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for determining multiple user behavior patterns in a lighting system energy consumption management method combined with user behavior analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The present application solves the technical problem in the prior art that the lighting strategy cannot be adjusted in real time according to user behavior, resulting in high energy consumption, by providing a lighting system energy consumption management method combined with user behavior analysis.

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0011] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0012] Examples, such as Figure 1 As shown, the embodiment of the present application provides a lighting system energy consumption management method combined with user behavior analysis, wherein the method includes: Data of target users is collected through multiple sensors deployed in the target lighting area to obtain a user behavior dataset.

[0013] By deploying multiple sensors in the target lighting area, such as infrared sensors, cameras, pressure sensors, and sound sensors, comprehensive data collection is performed on the activities of the target users. These sensors can perceive the user's behavioral characteristics in real time, such as location movement, dwell time, gestures, etc. The collected data is pre-processed and integrated to form a user behavior data set, which contains multi-dimensional user behavior information and provides a data basis for subsequent analysis of user behavior patterns.

[0014] Mining is performed based on the user behavior data set to determine a plurality of user behavior patterns, and data is collected on the smart lighting device group according to the plurality of user behavior patterns to obtain a plurality of lighting patterns.

[0015] Based on the user behavior data set, data mining algorithms (such as cluster analysis, association rule mining and time series analysis) are used to conduct in-depth analysis of user behavior data and extract different user behavior patterns, including user activity paths, stay areas, lighting use time periods, preferred brightness levels, etc. For example, cluster analysis can be used to divide users into different behavior groups, such as high-activity frequency users and low-activity frequency users. According to the extracted multiple user behavior patterns, targeted data collection is performed on the smart lighting devices in the target area. For example, in the high-activity frequency mode, parameters such as the response time and brightness adjustment frequency of the lighting devices are collected; in the static stay mode, data such as the brightness retention time and light distribution uniformity are collected. Through these collected lighting data, multiple corresponding lighting modes are further analyzed and extracted, and each lighting mode reflects the optimal lighting settings under a specific behavior mode.

[0016] Furthermore, if Figure 2 As shown, mining is performed based on the user behavior data set to determine multiple user behavior patterns, and the method includes: Feature extraction is performed on the user behavior data set to obtain multiple behavior features; cluster analysis is performed on the user behavior data set according to the multiple behavior features to generate multiple cluster centers; the user behavior data set is divided into multiple data clusters based on the multiple cluster centers, and frequency mining is performed according to time series based on the multiple data clusters to determine multiple behavior data groups; behavior preference analysis is performed on the multiple behavior data groups, and classification is performed according to the preference analysis results to determine the multiple user behavior patterns.

[0017] Preferably, the user behavior data set is preprocessed to extract multiple behavior features, including but not limited to the user's activity frequency, residence time, movement path, lighting use time period, brightness requirements, etc.; based on the extracted multiple behavior features, the user behavior data set is clustered and analyzed, and multiple cluster centers are generated using algorithms such as K-means, DBSCAN or hierarchical clustering, each cluster center represents a typical combination of user behavior features, which can preliminarily reflect the differences in users' lighting needs; based on the generated multiple cluster centers, the user behavior data set is divided into multiple data clusters, each data cluster corresponds to a specific behavior category; according to these data clusters, frequent pattern mining is performed according to time series to extract behavior data groups in different time periods; preference analysis is performed on multiple behavior data groups, and through statistical analysis and association rule mining, the user's preferred behavior in different scenarios is extracted, for example, some users prefer to use lower brightness lighting at night, and prefer high brightness lighting during office hours; according to the preference analysis results, the user behavior is further classified, and multiple representative user behavior patterns are extracted, and the user behavior patterns can accurately reflect the user's behavior habits in different situations and time periods, provide a basis for the intelligent lighting system, and realize personalized and dynamic lighting energy consumption management.

[0018] Furthermore, the user behavior data set is divided into a plurality of data clusters based on the plurality of cluster centers, and frequent mining is performed according to the plurality of data clusters in accordance with time series to determine a plurality of behavior data groups, the method comprising: The method comprises the steps of: performing data distribution calculation on the user behavior data set according to the multiple clustering centers to obtain data density information; setting a partitioning threshold according to the data density information and the multiple clustering centers, partitioning the user behavior data set according to the partitioning threshold to obtain the multiple data clusters; performing data segmentation on the user behavior data set according to the time series to obtain multiple time windows, wherein the multiple time windows contain the user behavior data set; performing frequent item analysis based on the multiple time windows to determine multiple frequent items, mining the user behavior data set according to the multiple frequent items to generate data mining results, and extracting the multiple behavior data groups according to the data mining results.

[0019] Specifically, based on multiple cluster centers, the data density of the user behavior data set around each cluster center is calculated. The data density can be obtained by calculating the distance from each data point to the cluster center and counting the number of data points within a certain distance range; according to the data density information, combined with the location and density distribution of multiple cluster centers, an appropriate partitioning threshold (such as a distance or density threshold) is set; the user behavior data set is divided into multiple data clusters using the partitioning threshold, each of which contains a group of data points with high data density around a specific cluster center. These data points represent user groups with similar behavioral characteristics; the user behavior data set is segmented according to the time series, and the data is divided into multiple time windows, each of which contains data within a specific time range. The user behavior data recorded in a certain time window can capture the temporal variation pattern of user behavior. For example, time windows can be set according to time scales such as hours, days or weeks. Based on the generated multiple time windows, frequent item analysis algorithms (such as Apriori or FP-Growth) are applied to mine the user behavior data in each time window to identify the behavioral combinations with higher frequency in user behavior. The extraction of frequent items can reflect the main behavioral characteristics of users in a specific time period. According to the results of frequent item analysis, the user behavior data set is further mined to generate mining results containing behavioral characteristics and temporal patterns. Based on these mining results, multiple behavior data groups are extracted, and each behavior data group represents the typical behavior pattern of the user in a specific time window.

[0020] Furthermore, data collection is performed on the smart lighting device group according to the multiple user behavior patterns to obtain multiple lighting patterns, and the method includes: An environmental parameter set for a target lighting area is introduced, and demand analysis is performed based on the environmental parameter set in combination with the multiple user behavior patterns to determine lighting demand data; the multiple user behavior patterns are reversely verified based on the lighting demand data, and the lighting parameters to be operated are determined according to the demand verification results; the intelligent lighting device group is dynamically monitored according to the lighting parameters to be operated to obtain lighting dynamic adjustment data; the lighting dynamic adjustment data is combined with the environmental parameter set to perform lighting control analysis to determine the multiple lighting modes.

[0021] Specifically, environmental parameters of the target lighting area are collected. These parameters may include light intensity, color temperature, color saturation, humidity, temperature, time (such as daytime, nighttime, seasonal changes), etc. The collected environmental parameters are combined with multiple user behavior patterns, and targeted lighting demand data is generated through demand analysis models (such as multivariate regression analysis or fuzzy logic analysis). For example, a multivariate regression model is used to take environmental parameters as independent variables and lighting requirements in user behavior patterns (such as target brightness, color temperature, etc.) as dependent variables to establish a prediction model, for example, Y=β 0 +β1 X 1 +β 2 X 2 +⋯+β n X n +ϵ, where Y represents the lighting demand data, X 1 , X 2 , X n are environmental parameters and user behavior characteristics, β i is the regression coefficient, ϵ is the error term; fuzzy logic method is used to model the user behavior pattern and environmental parameters. For example, if the ambient light intensity is low and the user behavior pattern is "reading mode", the required brightness is high; if the ambient light intensity is medium and the user behavior pattern is "resting mode", the required brightness is low. According to these fuzzy rules, the input variables in different situations are mapped to the output lighting demand data. Using the generated lighting demand data, reverse verification is performed to verify whether the extracted user behavior pattern matches the current lighting demand. Through demand verification (such as behavior simulation or simulation comparison), the user behavior pattern that best meets the actual demand is selected, and the lighting parameters to be operated are determined accordingly, including brightness, color temperature, response time, etc. According to the lighting parameters to be operated, the intelligent lighting equipment group is monitored in real time and dynamically, and the operating status data and adjustment feedback data of the lighting equipment are collected. These dynamic adjustment data reflect the operating effects of the intelligent lighting equipment under different behavior patterns and environmental conditions, such as the sensitivity of brightness adjustment response, energy consumption changes, etc. Combine lighting dynamic adjustment data with environmental parameter sets to conduct in-depth lighting control analysis. By analyzing the impact of changes in environmental parameters (such as sudden changes in light intensity and user position movement) on device operation, the control logic is optimized and multiple lighting modes are summarized. These lighting modes include the optimal device operation configurations for different scenarios, such as office mode, rest mode, night mode, etc.

[0022] The multiple user behavior patterns and the multiple lighting patterns are associated and inferred to construct a behavior-lighting mapping network.

[0023] Extract key features of user behavior patterns (such as activity frequency, location preference, brightness requirements) and key parameters of lighting modes (such as brightness level, color temperature range, start-stop response time). Perform preliminary matching based on the similarity or correlation between these features and parameters. For example, the behavior pattern "reading mode" matches the lighting mode "high brightness + neutral white light". Based on the matching results of user behavior patterns and lighting modes, use association rule mining algorithms (such as Apriori algorithm) to extract rules. For example, if the user behavior is "high activity frequency + preference for high brightness", the lighting mode is "high brightness mode"; if the user behavior is "rest mode + preference for soft light", the lighting mode is "low brightness + warm light mode". Each rule contains behavioral features and corresponding lighting modes to form a preliminary association logic. Use a graph model (such as a directed graph) to map user behavior patterns and lighting modes to nodes, and establish edges based on association rules; the weight of each edge represents the strength of the association between behavior and lighting, and the weight can be determined by statistical matching frequency or user feedback scores. By analyzing the paths and weights in the network, the association logic is optimized; the feedback mechanism (such as lighting effect satisfaction, energy efficiency, etc.) is introduced to dynamically adjust the weights in the network. For example, if the user's lighting effect feedback for a specific behavior mode is poor, the corresponding lighting mode is adjusted. Finally, a behavior-lighting mapping network is constructed, which can reflect the dynamic association between user behavior patterns and lighting modes, and provide a decision-making basis for the intelligent lighting system.

[0024] The target lighting area is subjected to lighting analysis through the behavior-lighting mapping network to obtain a lighting prediction scheme, and the lighting prediction scheme is simulated and executed to perform energy consumption calculation and generate lighting energy consumption simulation parameters.

[0025] Based on the user behavior data and environmental parameters of the current target lighting area, the behavior-lighting mapping network is input to obtain the optimal lighting mode combination that matches the current user behavior pattern. The output of the behavior-lighting mapping network contains key parameters of the lighting mode, such as brightness level, color temperature range, dimming rate, etc. According to the output results of the mapping network, combined with the spatial layout, number of users and activity range of the target area, a lighting prediction plan is generated. The lighting prediction plan includes detailed lighting configuration, such as brightness distribution in different areas, equipment start-stop schedule and color temperature adjustment strategy. The generated lighting prediction plan is simulated and executed in a virtual environment. Based on the actual equipment characteristics (such as power consumption, response time) and the environmental conditions of the target area, the operating effect of the lighting system is analyzed, and the energy consumption data and dynamic adjustment behavior of the lighting equipment are recorded during the simulation process; the energy consumption is calculated for the results of the simulation execution, and the energy consumption level of different time periods and spatial areas is evaluated; the energy consumption of each lighting device is calculated through the power model and running time of the lighting system, and the lighting energy consumption simulation parameters are generated.

[0026] Furthermore, the target lighting area is subjected to lighting analysis by the behavior-lighting mapping network to obtain a lighting prediction scheme, and the method includes: Based on the behavior-lighting mapping network, user behavior is predicted according to the time series to generate user behavior prediction results; according to the environmental parameter set, environmental change analysis of the target lighting area is performed to construct environmental change trends; the user behavior prediction results are associated with the environmental change trends to generate multiple associated data; the multiple associated data are used as indexes, synchronized to the behavior-lighting mapping network for retrieval and matching, and multiple matching results are generated; according to the multiple matching results, the multiple lighting modes are integrated to obtain the lighting prediction plan.

[0027] Specifically, based on the behavior-lighting mapping network, the time series user behavior data in the target area is analyzed, and the user's behavior patterns in different time periods, such as activity frequency, stay location and lighting needs, are predicted through time series modeling of historical behavior data (such as using LSTM or ARIMA model), and user behavior prediction results are generated; the environmental parameter set (such as light intensity, temperature and humidity, time period, etc.) of the target lighting area is dynamically monitored, and the trend analysis algorithm (such as multivariate linear regression or Bayesian update) is used to construct the environmental change trend and predict the change of environmental parameters in the future, such as light intensity reduction or temperature and humidity fluctuations; the user behavior prediction results are correlated with the environmental change trend, and the user behavior prediction results are matched with the environmental conditions by matching the behavior pattern with the environmental conditions. The dynamic relationship between components is used to generate multiple sets of associated data. For example, when the user behavior prediction results show a high activity frequency and the ambient light intensity gradually decreases, the associated data can point to the demand for high-brightness lighting; the associated data is used as an index and synchronized to the behavior-lighting mapping network, and the association rules in the network are used for retrieval to extract the lighting mode combination that matches the associated data, and generate multiple matching results. For example, the matching results may include "high-brightness mode", "low-brightness warm light mode", etc., which specifically include key parameters such as the brightness level, color temperature range, and response time of the lighting equipment; based on the integrated analysis of multiple matching results, the lighting mode is divided into regions and optimized according to different user behavior patterns and environmental change requirements to form a final lighting prediction plan.

[0028] Furthermore, the method of simulating and executing the lighting prediction scheme to calculate energy consumption and generate lighting energy consumption simulation parameters includes: Based on the environmental change trend, simulated environmental parameters of the target lighting area are constructed; the lighting prediction plan is simulated and executed according to the simulated environmental parameters, and the intelligent lighting equipment group is simulated and monitored according to the execution results to determine the equipment simulation operation status information; energy consumption is calculated according to the equipment simulation operation status information to generate a lighting energy consumption coefficient, and energy-saving evaluation is performed according to the lighting energy consumption coefficient to obtain a lighting simulation energy-saving score; the lighting simulation energy-saving score is added to the lighting energy consumption simulation parameters.

[0029] Specifically, according to the trend of environmental changes, combined with the spatial layout of the target lighting area, user behavior characteristics and external environmental parameters (such as light intensity, temperature and humidity, etc.), a simulation environment parameter set is constructed. The simulation environment parameters include the possible range of light intensity changes, temperature and humidity changes in different time periods, and the distribution characteristics of user activities in the target area, so as to truly reproduce the possible future operating environment; the lighting prediction plan is loaded into the simulation environment for execution, and the operation process of the intelligent lighting equipment group is simulated through the virtual simulation platform. The simulation process monitors the equipment operation status information, including dynamic parameters such as the lighting equipment startup frequency, brightness adjustment response time, and color temperature change trajectory. These simulated operation status information reflects the working performance of the equipment under different environmental conditions; according to the equipment simulation operation status information, combined with the equipment power parameters and operation time, the energy consumption calculation is performed item by item, for example, E i =P i ×T i , where E i is the energy consumption of the ith device, P i is power, T i For the running time, the energy consumption values ​​of all devices are summarized to generate an overall lighting energy consumption coefficient, which is used to measure the energy consumption level of the entire system; based on the lighting energy consumption coefficient, combined with industry standards or set energy-saving goals, the energy efficiency of the system is evaluated, and by comparing with the benchmark energy consumption value (such as the energy consumption of traditional lighting methods), a lighting simulation energy-saving score is generated. The lighting simulation energy-saving score reflects the performance of the predicted solution in energy saving. For example, the higher the score, the more energy-saving the solution; the lighting simulation energy-saving score is added to the lighting energy consumption simulation parameters to form a complete simulation data set. The simulation parameters include: total energy consumption, equipment energy consumption distribution, dynamically adjusted energy consumption efficiency, energy-saving score, etc., which provide a detailed basis for subsequent optimization and actual operation.

[0030] The lighting prediction scheme is feedback-adjusted according to the lighting energy consumption simulation parameters in combination with the behavior-lighting mapping network to generate lighting optimization suggestions, and the energy consumption of the lighting system in the target lighting area is intelligently managed according to the lighting optimization suggestions.

[0031] Input the lighting energy consumption simulation parameters (including total energy consumption, energy-saving score, equipment energy consumption distribution, etc.) into the behavior-lighting mapping network to analyze the energy consumption performance and adaptability of each user behavior mode and the corresponding lighting mode. For example, some lighting modes may consume too much energy or have low user satisfaction in a specific behavior mode. Through the feedback mechanism, these abnormal energy consumption points are marked as optimization targets. Based on the part with low energy-saving scores in the simulation parameters, feedback debugging is performed on the lighting prediction plan; the association relationship in the behavior-lighting mapping network is used to dynamically adjust the unmatched behavior-lighting mode, for example, reduce the lighting brightness in unnecessary areas, adjust the color temperature to match user needs, and optimize the response time to reduce the startup frequency. Combined with the feedback debugging results, lighting optimization suggestions are generated, including: adjusting equipment operating parameters (such as brightness, color temperature, and time period settings); optimizing equipment start-stop logic (such as dynamically allocating lighting resources according to user distribution and activity hotspots); and enhancing energy-saving modes (such as setting low-activity areas to low-brightness mode). Apply the lighting optimization suggestions to the intelligent lighting system in the target lighting area, and realize intelligent energy consumption management through real-time dynamic adjustment.

[0032] Furthermore, the lighting prediction scheme is feedback-adjusted according to the lighting energy consumption simulation parameters in combination with the behavior-lighting mapping network to generate lighting optimization suggestions, the method comprising: Energy consumption analysis is performed based on the simulated operating status information of the equipment, and an expected energy-saving threshold is set; it is determined whether the lighting simulation energy-saving score is greater than or equal to the expected energy-saving threshold; if the simulation energy-saving score is less than the expected energy-saving threshold, a feedback mechanism is activated, and feedback search is performed on the behavior-lighting mapping network through the feedback mechanism to construct a lighting energy consumption optimization space; lighting debugging is performed on the lighting prediction scheme according to the lighting energy consumption optimization space to generate the lighting optimization suggestion.

[0033] Specifically, energy consumption analysis is performed based on the equipment simulation operation status information, key indicators such as equipment energy consumption distribution and regional energy consumption ratio are extracted, and the expected energy-saving threshold is set as the evaluation standard in combination with the actual energy-saving needs and industry standards to measure whether the system's energy-saving performance meets the standard; it is judged whether the lighting simulation energy-saving score reaches the set energy-saving threshold. If the score meets the standard, no adjustment is required; if the score does not meet the standard, the feedback mechanism is activated, and the key parameters that cause excessive energy consumption (such as brightness, color temperature, response time, etc.) are located by inputting the low-scoring data into the behavior-lighting mapping network for feedback search, and a lighting energy consumption optimization space is constructed based on these parameters; the lighting prediction plan is debugged in the optimization space to reduce energy consumption by adjusting brightness, optimizing equipment start and stop schedules, adjusting color temperature range, etc.; lighting optimization suggestions are generated based on the debugging results, including operating parameter adjustments, equipment distribution optimization, and energy consumption strategy updates.

[0034] Furthermore, the feedback search is performed on the behavior-lighting mapping network through the feedback mechanism to construct a lighting energy consumption optimization space, and the method includes: Based on the behavior-lighting mapping network, fuzzy reasoning is performed to formulate a search strategy; the lighting energy consumption simulation parameters are synchronized to the behavior-lighting mapping network through the feedback mechanism to perform feedback search according to the search strategy, and potential improvement intervals are determined based on the search results; the potential improvement intervals are screened and associated according to the expected energy-saving threshold to construct the lighting energy consumption optimization space.

[0035] Specifically, fuzzy reasoning is performed based on the behavior-lighting mapping network to analyze the correlation between user behavior patterns and lighting patterns. Combined with the low-scoring areas in the lighting energy consumption simulation parameters, key factors affecting energy consumption performance (such as excessive brightness, too short response time, or unnecessary equipment operation) are identified, and search strategies are formulated to focus the optimization on these key issues. The lighting energy consumption simulation parameters are synchronized to the behavior-lighting mapping network through a feedback mechanism, and feedback search is performed in the network according to the formulated search strategy. During the search process, the parameters are dynamically adjusted according to the association rules in the network to extract potential improvement intervals, such as reducing the brightness range of the high-brightness mode, extending the device response time, or adjusting the color temperature boundary conditions. These potential improvement intervals are matched and screened with the expected energy-saving thresholds, and solutions that do not meet the energy-saving goals are eliminated, retaining adjustment combinations with high energy-saving efficiency and adapted to user behavior. The screened improvement intervals are integrated into a lighting energy consumption optimization space, which contains multiple candidate lighting solutions, each of which is executable and meets the energy-saving goals, and can provide specific optimization directions for subsequent lighting prediction solution debugging, thereby achieving a dynamic balance between system energy consumption and user needs.

[0036] In summary, the embodiments of the present application have at least the following technical effects: First, data of target users are collected through multiple sensors deployed in the target lighting area to obtain a user behavior data set. Then, mining is performed based on the user behavior data set to determine multiple user behavior patterns, and data of the intelligent lighting device group is collected according to the multiple user behavior patterns to obtain multiple lighting patterns. Further, multiple user behavior patterns and multiple lighting patterns are associated and inferred to construct a behavior-lighting mapping network. Then, lighting analysis is performed on the target lighting area through the behavior-lighting mapping network to obtain a lighting prediction plan, and the lighting prediction plan is simulated and executed to calculate energy consumption, and lighting energy consumption simulation parameters are generated. Finally, the lighting prediction plan is feedback debugged according to the lighting energy consumption simulation parameters combined with the behavior-lighting mapping network, and lighting optimization suggestions are generated. According to the lighting optimization suggestions, the energy consumption of the lighting system in the target lighting area is intelligently managed. The technical problem that the lighting strategy cannot be adjusted in real time according to user behavior in the prior art, resulting in high energy consumption, is solved. By combining user behavior analysis, intelligent management of the energy consumption of the lighting system is achieved, and the technical effect of improving energy utilization efficiency and reducing energy consumption costs is achieved.

[0037] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0038] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0039] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A lighting system energy consumption management method combined with user behavior analysis, characterized in that: The method comprises: Data of target users is collected through multiple sensors deployed in the target lighting area to obtain a user behavior data set; Mining the user behavior data set to determine a plurality of user behavior patterns, collecting data on the smart lighting device group according to the plurality of user behavior patterns to obtain a plurality of lighting patterns; Associating and reasoning the multiple user behavior patterns with the multiple lighting patterns to construct a behavior-lighting mapping network; Performing lighting analysis on the target lighting area through the behavior-lighting mapping network to obtain a lighting prediction plan, simulating and executing the lighting prediction plan to calculate energy consumption, and generating lighting energy consumption simulation parameters; The lighting prediction scheme is feedback-adjusted according to the lighting energy consumption simulation parameters in combination with the behavior-lighting mapping network to generate lighting optimization suggestions, and the energy consumption of the lighting system in the target lighting area is intelligently managed according to the lighting optimization suggestions.

2. The method for energy consumption management of a lighting system combined with user behavior analysis according to claim 1, characterized in that: Mining is performed based on the user behavior data set to determine multiple user behavior patterns, the method comprising: Perform feature extraction based on the user behavior data set to obtain multiple behavior features; Performing cluster analysis on the user behavior data set according to the multiple behavior features to generate multiple cluster centers; Dividing the user behavior data set into a plurality of data clusters based on the plurality of cluster centers, and performing frequent mining according to the plurality of data clusters in time series to determine a plurality of behavior data groups; Behavior preference analysis is performed based on the multiple behavior data groups, and classification is performed based on the preference analysis results to determine the multiple user behavior patterns.

3. The lighting system energy consumption management method combined with user behavior analysis according to claim 2, characterized in that: The user behavior data set is divided into a plurality of data clusters based on the plurality of cluster centers, and frequent mining is performed according to the plurality of data clusters in accordance with time series to determine a plurality of behavior data groups, the method comprising: Performing data distribution calculation on the user behavior data set according to the multiple cluster centers to obtain data density information; According to the data density information and the multiple cluster centers, a partition threshold is set, and the user behavior data set is partitioned according to the partition threshold to obtain the multiple data clusters; Segmenting the user behavior data set according to the time series to obtain a plurality of time windows, wherein the plurality of time windows contain the user behavior data set; Frequent item analysis is performed based on the multiple time windows to determine multiple frequent items, the user behavior data set is mined according to the multiple frequent items to generate data mining results, and the multiple behavior data groups are extracted according to the data mining results.

4. The lighting system energy consumption management method combined with user behavior analysis according to claim 2, characterized in that: According to the multiple user behavior patterns, data is collected from the smart lighting device group to obtain multiple lighting patterns, and the method includes: Introducing an environmental parameter set of a target lighting area, performing demand analysis based on the environmental parameter set combined with the multiple user behavior patterns, and determining lighting demand data; Reversely verify the multiple user behavior patterns based on the lighting demand data, and determine the lighting parameters to be operated according to the demand verification results; Dynamically monitor the intelligent lighting equipment group according to the lighting parameters to be operated to obtain lighting dynamic adjustment data; The lighting dynamic adjustment data is combined with the environmental parameter set to perform lighting control analysis to determine the multiple lighting modes.

5. The method for managing lighting system energy consumption in combination with user behavior analysis according to claim 4, characterized in that: Performing lighting analysis on the target lighting area through the behavior-lighting mapping network to obtain a lighting prediction solution, the method comprising: Performing user behavior prediction according to the time series based on the behavior-lighting mapping network to generate a user behavior prediction result; Performing an environmental change analysis of the target lighting area according to the environmental parameter set and constructing an environmental change trend; Associating the user behavior prediction result with the environmental change trend to generate a plurality of associated data; The multiple associated data are used as indexes and synchronized to the behavior-lighting mapping network for retrieval and matching to generate multiple matching results. The multiple matching results are integrated according to the multiple lighting modes to obtain the lighting prediction solution.

6. The method for managing lighting system energy consumption in combination with user behavior analysis according to claim 5, characterized in that: The lighting prediction scheme is simulated and executed to calculate energy consumption and generate lighting energy consumption simulation parameters, the method comprising: Constructing simulated environmental parameters of the target lighting area based on the environmental change trend; The lighting prediction scheme is simulated and executed according to the simulated environment parameters, and the intelligent lighting device group is simulated and monitored according to the execution results to determine the device simulation operation status information; Calculate energy consumption based on the simulated operation status information of the device to generate a lighting energy consumption coefficient, perform energy saving evaluation based on the lighting energy consumption coefficient, and obtain a lighting simulation energy saving score; The lighting simulation energy saving score is added to the lighting energy consumption simulation parameters.

7. The method for managing lighting system energy consumption in combination with user behavior analysis according to claim 6, characterized in that: Feedback debugging of the lighting prediction scheme is performed according to the lighting energy consumption simulation parameters in combination with the behavior-lighting mapping network to generate lighting optimization suggestions, the method comprising: Perform energy consumption analysis based on the simulated operation status information of the device and set an expected energy saving threshold; Determining whether the lighting simulation energy saving score is greater than or equal to the expected energy saving threshold; If the simulated energy saving score is less than the expected energy saving threshold, the feedback mechanism is activated, and the behavior-lighting mapping network is feedback searched through the feedback mechanism to construct a lighting energy consumption optimization space; The lighting prediction scheme is subjected to lighting debugging according to the lighting energy consumption optimization space to generate the lighting optimization suggestion.

8. The method for managing lighting system energy consumption in combination with user behavior analysis according to claim 7, characterized in that: Feedback search is performed on the behavior-lighting mapping network through the feedback mechanism to construct a lighting energy consumption optimization space, and the method includes: Perform fuzzy reasoning based on the behavior-lighting mapping network to formulate a search strategy; The lighting energy consumption simulation parameters are synchronized to the behavior-lighting mapping network through the feedback mechanism to perform feedback search according to the search strategy, and a potential improvement interval is determined according to the search results; The potential improvement intervals are screened and associated according to the expected energy-saving threshold to construct the lighting energy consumption optimization space.

Images