LED bulb control system based on user behaviors

Abstract

The invention relates to the technical field of LED bulb control, in particular to an LED bulb control system based on user behaviors, and the system comprises a behavior obtaining module which is used for obtaining the behavior mode of a target user, and determining the initial light operation parameters of the target user in the corresponding behavior mode; the behavior mode further comprises a position, a scene mode and a light sequence of the target user; the behavior analysis module is used for acquiring behavior data of the target user in the behavior mode, determining a coincidence evaluation coefficient between the user behavior and the light, and setting a movement guide path of the light according to the coincidence evaluation coefficient; the light preference module is used for determining a light preference range and a preference color temperature according to the behavior data of the user, and determining an adjustment parameter of the light under the behavior data; the scene verification module is used for verifying the feedback consistency of the user behavior and the light feedback in different scene modes, and determining a feedback result related to the current light feedback; and the control efficiency and accuracy of the LED bulb are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of LED bulb control, and specifically, it is an LED bulb control system based on user behavior. Background Art

[0002] In traditional LED bulb control systems, the switching and brightness adjustment of lights usually require manual operation by users or are achieved through preset timing programs. However, this method often fails to accurately capture and respond to the actual needs of users, resulting in problems such as poor lighting effects, high energy consumption, and poor user experience.

[0003] With the continuous development of Internet of Things technology and artificial intelligence technology, intelligent lighting systems have gradually become the mainstream trend in the market. These systems can capture and analyze users' behavioral data in real time, and intelligently adjust light parameters according to the analysis results to meet users' personalized needs. However, most of the current intelligent lighting systems on the market have problems such as single functions and insufficient intelligence, and cannot fully meet users' needs for a comfortable, energy-saving, and efficient lighting environment.

[0004] For example, Chinese Patent Publication No. CN117354986A discloses an intelligent control method and system for multifunctional LED lamp beads, aiming to solve the problem that existing lighting systems cannot intelligently adapt to users' needs. This method first identifies the target user behavior pattern, combines it with the operating parameters of the LED lamp beads to obtain the behavior-light operating parameters of the target user. Identifies the environmental factors that affect users' lighting control, and accordingly obtains the environment-light operating parameters where the user is located. Constructs a target user lighting operation prediction model, predicts the future operating parameters of the LED lamp beads, and forms an automatic adjustment plan based on this. Finally, formulates an LED lamp bead control plan.

[0005] The prior art analyzes users' behaviors and related data, but ignores that when controlling lights, it is necessary to adjust the current light intensity, color temperature, and on / off according to users' behaviors, so as to adjust the current light range to meet the current needs of users and adapt to users' usage requirements in different scenarios. Summary of the Invention

[0006] To solve the above technical problems, the technical solution adopted by the present invention is: an LED bulb control system based on user behavior, including: a behavior acquisition module, which is used to acquire the behavior pattern of the target user and determine the initial light operating parameters of the target user under the corresponding behavior pattern; the behavior pattern also includes the position of the target user, the scene mode, and the light sequence.

[0007] The behavior analysis module is used to obtain the behavior data of the target user in the behavior mode, determine the coincidence evaluation coefficient between the user behavior and the light, and set the moving guidance path of the light according to the coincidence evaluation coefficient.

[0008] The light preference module is used to determine the preference range and preference color temperature of the light according to the user's behavior data, and determine the adjustment parameters of the light under the behavior data.

[0009] The scene verification module is used to verify the feedback consistency between the user behavior and the light feedback in different scene modes, and determine the feedback result related to the current light feedback.

[0010] The parameter adjustment module is used to adjust the light sequence of the light according to the behavior mode of the target user, and determine the distribution adjustment result of the light.

[0011] The parameter adjustment module includes an environmental factor unit, a behavior trend unit, and a distribution adjustment unit; the environmental factor unit is used to obtain the external temperature, weather, and light, set the environmental factors, and combine the adjustment parameters to output the environmental factor coefficient.

[0012] The behavior trend unit is used to obtain the moving guidance path of the light, and combine the moving frequency and moving interval of the current target user to set the behavior trend coefficient.

[0013] The distribution adjustment unit is used to comprehensively process the environmental factor coefficient, the behavior trend coefficient, and the feedback result, obtain the distribution adjustment coefficient of the target user in different behavior modes and positions, and output the distribution adjustment coefficient as the distribution adjustment result.

[0014] The beneficial effects of the present invention are as follows: by accurately capturing the user behavior and intelligently adjusting the light parameters, the present invention can provide a more comfortable and personalized lighting environment for users, improving the user experience; the present invention can intelligently adjust the light brightness and color temperature according to the changes of the user behavior and the external environment, effectively reducing energy consumption and achieving the goal of energy conservation and emission reduction; through the intelligent lighting control system of the present invention, users can automatically complete the work such as turning on and off the light, adjusting the light brightness, and adjusting the color temperature without manual adjustment, improving the management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below with reference to the drawings and embodiments.

[0016] Figure 1 is a system framework diagram of an LED bulb control system based on user behavior.

[0017] Figure 2 is a system framework diagram of the parameter adjustment module of an LED bulb control system based on user behavior.

[0018] Figure 3 It is a system schematic diagram of an LED bulb control system based on user behavior.

[0019] Figure 4 It is a system schematic diagram of a parameter adjustment module of an LED bulb control system based on user behavior.

[0020] Figure 5 It is a process schematic diagram of a behavior analysis module of an LED bulb control system based on user behavior.

[0021] Figure 6 It is a process schematic diagram of a scene verification module of an LED bulb control system based on user behavior. Detailed implementation manners

[0022] The embodiments of the present invention will be described in detail below. The described embodiments are exemplary and are only used to explain the present invention, and should not be construed as a limitation to the present invention. For those not specified in the embodiments, the techniques or conditions described in the literature in the field or according to the product instructions are followed.

[0023] Refer to Figure 1 、 Figure 2 An LED bulb control system based on user behavior includes: a behavior acquisition module, a behavior analysis module, a lighting preference module, a scene verification module, and a parameter adjustment module; the behavior acquisition module outputs the user's behavior pattern to the behavior analysis module, and the behavior analysis module transmits the analyzed data to the lighting preference module after analyzing the behavior data; the lighting preference module analyzes the corresponding lighting under the behavior data and transmits the corresponding analysis data to the scene verification module, the scene verification module verifies the current user's scene and transmits the data to the parameter adjustment module; the parameter adjustment module adjusts and analyzes all the data to complete the processing of the overall data; the parameter adjustment module further includes an environmental factor unit, a behavior trend unit, and a distribution adjustment unit to complete the processing and evaluation of the overall data.

[0024] As Figure 3 、 Figure 4 shown, the behavior acquisition module is used to acquire the behavior pattern of the target user and determine the initial lighting operation parameters of the target user under the corresponding behavior pattern; the behavior pattern also includes the position, scene mode, and lighting sequence of the target user.

[0025] The behavior analysis module is used to acquire the behavior data of the target user under the behavior pattern, determine the coincidence evaluation coefficient between the user behavior and the lighting, and set the moving guidance path of the lighting according to the coincidence evaluation coefficient.

[0026] The lighting preference module is used to determine the preference range and color temperature of the lighting based on the user's behavior data, and determine the adjustment parameters of the lighting under the behavior data.

[0027] The scene verification module is used to verify the feedback consistency between the user behavior and the lighting feedback under different scene modes, and determine the feedback result related to the current lighting feedback.

[0028] The parameter adjustment module is used to adjust the lighting sequence of the lighting according to the behavior pattern of the target user, and determine the distribution adjustment result of the lighting.

[0029] The parameter adjustment module includes an environmental factor unit, a behavior trend unit, and a distribution adjustment unit; the environmental factor unit is used to obtain the external temperature, weather, and light, set the environmental factors, and combine the adjustment parameters to output the environmental factor coefficient.

[0030] The behavior trend unit is used to obtain the movement guidance path of the lighting, and combine the movement frequency and movement interval of the current target user to set the behavior trend coefficient.

[0031] The distribution adjustment unit is used to comprehensively process the environmental factor coefficient, the behavior trend coefficient, and the feedback result, obtain the distribution adjustment coefficient of the target user in different behavior patterns and positions, and output the distribution adjustment coefficient as the distribution adjustment result.

[0032] The behavior pattern refers to the repetitive behavior or activity pattern of the user at a specific time and place. These patterns can be identified through data collected by various sensors and intelligent devices. For example: activity time: the user's daily wake-up time, working time, rest time, etc.; activity type: the activities carried out by the user during a certain period, such as reading, working, resting, entertainment, etc.; activity frequency: the activity frequency of the user during a certain period, such as frequently entering and leaving a certain room; activity intensity: the intensity of the user's activity, such as strenuous exercise, quiet reading, etc.

[0033] The currently set lighting needs to be adjusted according to the different current user states to meet the light intensity required by the user in different behavior patterns; for the user's behavior pattern, a camera or other device can be used to identify the current user behavior and determine the content carried out by the user under the behavior pattern.

[0034] The scene mode refers to a series of lighting configurations preset by the system according to the user's behavior pattern and environmental conditions.

[0035] For example, a common example of the scene mode is: welcome mode: trigger condition: the user goes home or enters the room; response action: the lights gradually turn on to create a warm atmosphere.

[0036] Working mode: Trigger condition: The user sits down at the desk or turns on the computer; Response action: The light is adjusted to a relatively high brightness with a cold color temperature, which helps to improve concentration.

[0037] Reading mode: Trigger condition: The user picks up a book or an e-reader; Response action: The light is adjusted to a moderate brightness with a warm color temperature to reduce eye fatigue.

[0038] Relaxation mode: Trigger condition: The user sits on the sofa or plays light music; Response action: The light is adjusted to a relatively low brightness with a warm color temperature to create a relaxing atmosphere.

[0039] Sleep mode: Trigger condition: The user enters the bedroom and lies down; Response action: The light gradually dims until it is completely turned off to help the user fall asleep better.

[0040] Away mode: Trigger condition: The user leaves the room or the house; Response action: All lights are turned off to ensure safety and energy conservation.

[0041] Entertainment mode: Trigger condition: The user turns on the TV or audio equipment; Response action: The light is adjusted to an appropriate brightness and color temperature to enhance the movie-watching or music-listening experience.

[0042] Party mode: Trigger condition: Multiple people are active in the living room or music is playing; Response action: The light is adjusted to a warm tone with a moderate brightness to create a happy atmosphere.

[0043] Security mode: Trigger condition: Abnormal sounds or movements are detected; Response action: Some or all lights are turned on to alert the user to pay attention to safety.

[0044] At this time, after recognizing the user's behavior pattern, the initial lighting operation parameters will be set according to the user's current scene mode and the location of the target user. At the same time, the lighting sequence also needs to be set according to the user's relative position, so as to complete the setting of the initial lighting operation parameters. The purpose of recognizing the lighting sequence after obtaining the behavior pattern at this time is to adjust the set lighting lines according to the current scene mode and the location of the target user. If the lighting sequence is the same in two settings, no modification is made, which can reduce the energy consumption during the dynamic change of the lights.

[0045] In an embodiment of the present invention, a behavior acquisition module is used to acquire the behavior pattern of the target user and determine the initial lighting operation parameters of the target user under the corresponding behavior pattern; the behavior pattern also includes the location of the target user, the scene mode, and the lighting sequence.

[0046] When this module is implemented, the behavior pattern of the current target user can be identified by setting corresponding devices. For example, deploy sensors: install passive infrared sensors, photosensitive sensors, sound sensors, etc. in the room; connect smart devices: ensure that devices such as the user's smartphone and smartwatch are connected to the central controller; environmental monitoring: use photosensitive sensors and temperature sensors to monitor the external light intensity and temperature; extract features such as the user's activity time, activity type, activity frequency, and activity intensity; use machine learning algorithms to identify the user's behavior pattern, such as getting up in the morning, working hours, coming home at night, etc.; thus, the behavior pattern related to the user can be obtained. After the behavior pattern is identified, the location and scene pattern of the target user will also be obtained. As for the lighting sequence, when the lights are already in use currently, the current lighting sequence is obtained, otherwise the lighting sequence is regarded as the value in the default initial lighting operation parameters.

[0047] At this time, the behavior pattern of the current target user during the action can be identified by obtaining video data and inputting the video data, historical human models, and human behavior annotations into the neural network.

[0048] In an embodiment of the present invention, the implementation method of the behavior analysis module includes the following content.

[0049] For the moving guiding path of the lights in the behavior analysis module, a guiding path of the lights is generated according to the user's moving path to help the user walk safely at night or in low-light environments.

[0050] The behavior data obtained in this module mainly includes the activity time, activity type, and activity frequency of the target user in the behavior pattern. Determine the coincidence situation between the illumination range of the lights and the user's movement at this time, calculate the coincidence rate between the illumination range of the lights and the user's moving path, and obtain the coincidence evaluation coefficient at this time; for the illumination range of the lights, the illumination range of the lights at this time can be determined by the irradiation angle of the current LED. At the same time, an isophote diagram can also be used to represent the light intensity distribution emitted by the lights at the current position to represent the illumination range of the lights, and according to the distribution of the light intensity, identify the coincidence situation between the user position points under the isophote and the corresponding illumination range of the lights.

[0051] As Figure 5 shown, the implementation method of obtaining the coincidence evaluation coefficient at this time can be as follows: based on the behavior data of the target user, obtain the activity time, activity type, and activity frequency of the target user; based on the activity time, activity type, and activity frequency of the target user, identify the user's moving path of the current target user, calculate the coincidence situation between the position points on the user's moving path and the illumination range of the lights, obtain the coincidence rate of the position points on the user's moving path, and calculate the coincidence evaluation coefficient according to the coincidence rate of the position points.

[0052] The user's movement path can be obtained through the currently recognized activity time, activity type, and activity frequency, obtaining the position points of the target user when moving, so as to determine the specific movement situation of the user under different types, and regarding these appeared position points as the user's movement path; clustering the position points to obtain multiple clustering clusters; the clustering method includes using the activity time, activity type, and activity frequency as clustering clusters, clustering the user's position points, obtaining the features related to the activity time, activity type, and activity frequency, calculating the difference in feature data between the features of the center point of each clustering cluster and other features in the current clustering cluster, and matching the feature data difference with the lighting range to obtain the user's movement path; at this time, the matching method is to cluster the position points under the corresponding lighting range according to the feature data difference to obtain some position points that are most closely related to the user's behavior data at this time, so as to evaluate what form of guiding path is generally required for the user under the relevant action mode to improve the control of the LED bulb.

[0053] The coincidence rate is set to a logical value by sequentially judging the distance between the position points on the user's movement path and the center point of the lighting range and the radius of the lighting range. When the distance between the position points on the user's movement path and the center point of the lighting range is less than the radius of the lighting range, the logical value is set to 1 for this position point, and if it is greater, the logical value is set to 0. Traverse all the position points on the user's movement path, and take the average value of the logical values as the coincidence rate of the position points on the user's movement path.

[0054] The coincidence evaluation coefficient is expressed as obtaining the position matching coefficient and time matching coefficient corresponding to the position points under the corresponding coincidence rate value to obtain the coincidence evaluation coefficient.

[0055] At this time, the position matching coefficient is to match the position of the position point, and the time matching coefficient is the matching value between the activity time of the target user at this time and the expected time of the lighting. Finally, the position matching coefficient, time matching coefficient, and coincidence rate are comprehensively evaluated to obtain the coincidence evaluation coefficient.

[0056] For the position matching coefficient, it is expressed as ; where represents the position matching coefficient of the i-th position point, represents the radius of the lighting range, represents the distance between the i-th position point and the center point of the lighting range;

[0057] For the time matching coefficient, it is expressed as ; where represents the time matching coefficient of the i-th position point, represents the difference between the time stamp corresponding to the i-th position point and the expected time stamp, Denote the time difference threshold. At this time, the time matching coefficient is used to determine whether the user is active within the expected time range when the lights are displayed according to the set path. The expected timestamp represents the expected time of the user at the corresponding moving position, and the time difference threshold represents the moving situation of the user within the corresponding time period. At this time, the moving time length in a small area will be used as the time difference threshold at this time. At the same time, the time difference threshold will be set from the average time required for the user to move in a certain area in the historical data.

[0058] The coincidence evaluation coefficient is expressed as ; where Denote the coincidence evaluation coefficient Denote the coincidence rate Denote the number of position points, and the value range of i is from 1 to n.

[0059] At this time, the obtained coincidence evaluation coefficient is to determine how the current LED bulb control system moves the light of the currently set LED bulb according to the user's movement when the user moves within the expected time or at the relative distance between the user and the light. This moving guidance path of the light can be dynamically realized by adjusting the angle at which the light is emitted and the on / off of multiple groups of lights to obtain the final output moving guidance path of the light.

[0060] The implementation method of setting the moving guidance path of the light is as follows: when the coincidence evaluation coefficient is greater than the first coincidence threshold, it means that the overall setting is relatively ideal and no obvious adjustment is required. The position points where the product value of the position matching coefficient and the time matching coefficient is greater than the preset threshold can be used as the moving guidance path of the light at this time. The preset threshold set here can be 0.6, and the points with values greater than 0.6 are used as the positions mainly irradiated by the light; when the coincidence evaluation coefficient is less than the second coincidence threshold, it means that the overall setting of the light is not ideal, resulting in different illuminations at some positions. It is necessary to optimize and adjust these positions with insufficient illumination. For example, the position points where the product value of the coincidence rate, the position matching coefficient, and the time matching coefficient is less than the preset product value are used as the moving guidance path of the light. The preset product value set at this time can be 0.3, which is used to represent the part with significantly less light irradiation at present, so as to adjust the on / off and illumination range of the set LED bulb.

[0061] When the coincidence evaluation coefficient is less than the first coincidence threshold and greater than the second coincidence threshold, obtain the position point corresponding to the average value of the position matching coefficient and the time matching coefficient, and use the user movement path where the position point corresponding to the average value of the position matching coefficient and the time matching coefficient is located as the movement guiding path of the light; At this time, making an adjustment indicates that the current light setting is in a relatively ordinary situation. At this time, the corresponding path can be evaluated according to the average value. Therefore, select the user movement path where the position point is located as the movement guiding path at this time to complete the overall light setting.

[0062] At the same time, for the first coincidence threshold and the second coincidence threshold, they can be set to 0.5 and 0.3 respectively. Since the value of the product is affected by multiple position points at this time, the finally calculated value will be relatively small. The thresholds set at this time will also be adjusted according to the finally calculated range. It is also possible to use historical data for setting. Sort the historical data from largest to smallest according to the position matching coefficient and the time matching coefficient. At this time, the position matching coefficient is used as the first sorting field. When the position matching coefficients are the same, sort according to the value of the time matching coefficient. Use the coincidence evaluation coefficient of the top 10% of the sorted historical data at this time as the first coincidence threshold at this time, and use the coincidence evaluation coefficient of the last 30% of the data as the second coincidence threshold at this time to complete the adjustment of the current light and behavior.

[0063] The implementation of this module can be illustrated by the following example.

[0064] For example, use a passive infrared sensor to detect that a user enters the home, and use smartphone positioning technology to determine the user's position in the entrance hall; Calculate the coincidence evaluation coefficient of the user at different position points. Assume that the coincidence evaluation coefficient at the entrance hall is relatively low; A lamp can be added at the entrance hall to ensure sufficient lighting when the user enters the home, or the light at the entrance hall can be adjusted to the position where the user most frequently passes, and then the light at the entrance hall is adjusted to a moderate brightness and warm color tone to create a warm welcome atmosphere. When the user moves from the entrance hall to the living room, the system adjusts the light in the living room in advance to ensure that the user is always in a suitable lighting environment. According to the activity type of the user in the living room (such as watching TV, reading, etc.), dynamically adjust the brightness and color temperature of the light.

[0065] At this time, in addition to using the implementation method of image recognition processing, multiple sensors can also be used for setting to complete the intelligent adjustment of the LED bulb control system.

[0066] In one embodiment of the present invention, in the lighting preference module, it is necessary to determine that both the range and color temperature of the lighting can meet the user's requirements at this time. For example, adjust the irradiation range of the lighting to ensure uniform illumination; learn the user's color temperature preferences in different scenarios through the user's historical data and feedback; at the same time, the preference range for lighting refers to the preference range of light intensity, which is used to describe the intensity of the current lighting.

[0067] At this time, it can be processed according to the user's behavior data. Therefore, the way to obtain the adjustment parameters is to use the light intensity and color temperature set by the lighting as independent variables, and the user's behavior data as the dependent variable. Analyze the regression coefficient between the user's behavior data and the data corresponding to the light intensity and color temperature set by the current lighting, perform a t-test analysis on the regression coefficient to obtain a significant coefficient, and set the adjustment parameters according to the significant coefficient.

[0068] At this time, the form of setting the lighting preference is mainly based on the preference range affected by the light intensity of the lighting and the color temperature setting value. For example, when performing regression analysis and calculating the regression coefficient, the probabilities of the light intensity and color temperature of the lighting in each time period are used as inputs to obtain the regression coefficient corresponding to the current light intensity and color temperature of the lighting; then perform a t-test analysis on the regression coefficient to obtain a significant coefficient, compare these significant coefficients with the preset preference factors of the preference range and preference color temperature to obtain the adjustment parameters; the comparison method is to compare the numerical values of the significant coefficients corresponding to the light intensity and color temperature at this time with the preset preference factors, and select the significant coefficient corresponding to the maximum difference between the significant coefficient and the preset preference factor at this time to select the parameters that need to be adjusted at this time. At this time, the light intensity and color temperature corresponding to the maximum difference between the significant coefficient and the preset preference factor are selected; the preset preference factor is the average value of the corresponding significant coefficients of the light intensity and color temperature in the historical data when the user sets the lighting; according to the obtained light intensity and color temperature, it can be known the light intensity and color temperature that need to be set currently, so as to improve the accuracy of the adaptation between the lighting preference range and preference color temperature and the user's behavior.

[0069] The bulb control system set under the adjustment parameters mainly tends to control single or multiple LED bulbs, controls in scenarios where no corresponding precise patterns are executed, and completes the control of the light emitted by the LED bulbs according to the light intensity and color temperature of the bulbs set at this time, so as to meet the user's lighting requirements in specific scenarios.

[0070] The adjustment parameters can be expressed as the light intensity and color temperature of the lighting; adjust the light intensity of the lighting according to the significant coefficient and the preset preference factor; adjust the color temperature of the lighting according to the significant coefficient and the preset preference factor.

[0071] For example, if the significant coefficient indicates that the current light intensity is too high and the user prefers low brightness in the relaxation mode, the light intensity is reduced; conversely, if the significant coefficient indicates that the current light intensity is too low and the user prefers high brightness in the work mode, the light intensity is increased.

[0072] For example, if the significant coefficient indicates that the current color temperature is on the cool side and the user prefers a warm color temperature in the relaxation mode, the color temperature is adjusted to a warm tone; conversely, if the significant coefficient indicates that the current color temperature is on the warm side and the user prefers a cool color temperature in the work mode, the color temperature is adjusted to a cool tone.

[0073] In an embodiment of the present invention, a scene verification module is used to verify the feedback consistency between user behavior and light feedback in different scene modes and determine the feedback result related to the current light feedback.

[0074] This module verifies the consistency and satisfaction between user behavior and light feedback in different scenes and times through experiments and user feedback; for example, by identifying and analyzing the data of the current light, it determines the similarity between user behavior and light feedback and historical data in the scene mode to judge how to adjust the light at this time.

[0075] At this time, it can also be evaluated by the time it takes for the current control system to meet the user's needs when the user behavior changes, or by judging whether the scene mode is consistent with the user feedback form when the scene mode changes following the user, so as to identify whether the current control system can meet the user's needs during adaptive adjustment.

[0076] As Figure 6 shown, the implementation method for verifying the feedback consistency between user behavior and light feedback in different scene modes and determining the feedback result related to the current light feedback at this time is: obtaining the light setting data of the target user in the corresponding scene mode and calculating the first similarity regarding user behavior between the current light setting data and the behavior data.

[0077] Obtaining the second similarity regarding the response time in the light setting data when the scene mode switches.

[0078] Obtaining the third similarity regarding light feedback between the light setting data and the behavior data.

[0079] Combining the first similarity, the second similarity, and the third similarity and outputting the feedback result related to the light feedback.

[0080] At this time, the feedback consistency between user behavior and light feedback is represented by three situations. One is whether there is a match between user behavior and light feedback, the second is the response time of the light to user behavior, and the third is whether the light feedback reflects the user's intentions and needs.

[0081] These three situations respectively correspond to the first similarity, the second similarity, and the third similarity. By synthesizing these three similarities, it is possible to determine whether there is a corresponding match between the current lighting and the user feedback, thereby enabling an assessment of whether the adjustment parameters and the moving guidance path set by the current system can correspond to the user's needs. After completing this part of the verification, parameter adjustment is still required. When implementing this module, it is also possible to evaluate the content after parameter adjustment to improve the implementation of the overall bulb control system.

[0082] The lighting setting data includes the illumination intensity of the current lighting, the color temperature value, the irradiation range of the lighting, and the response time corresponding to the switching of the scene mode.

[0083] The first similarity uses the calculation method of the Pearson correlation coefficient. The lighting setting data is used as the input and compared with the average values of the illumination intensity, color temperature value, and irradiation range of the lighting in the historical data. Indexed by the behavior data, the Pearson correlation coefficient under the corresponding behavior data is calculated. The purpose of this Pearson correlation coefficient is to verify whether the parameters of the current lighting correspond to the behavior data. It can be judged by observing the value of the Pearson correlation coefficient under the corresponding behavior data. When the value is greater than 0.6, the corresponding behavior data and lighting setting data are marked. The ratio of the marked behavior data and lighting setting data to all behavior data and lighting setting data is regarded as the first similarity at this time.

[0084] The second similarity is to calculate the ratio of the standard deviation of the current response time to the standard deviation of the historical data.

[0085] The third similarity is to record the ratio of the accurate data of the current lighting feedback to the total data; this accurate feedback data is obtained through the evaluation of the user.

[0086] Finally, the first similarity, the second similarity, and the third similarity are weighted and averaged to obtain a feedback result related to the lighting feedback; at the same time, the output of the feedback result will also include the values of the first similarity, the second similarity, and the third similarity, enabling the external monitoring system to accurately identify the operating conditions of the current system.

[0087] In an embodiment of the present invention, in the environmental factor unit, certain values will be set for the external temperature, weather, and lighting to represent the current environmental conditions. For the adjustment parameters, the illumination intensity and color temperature corresponding to the adjustment parameters are selected, and these values are comprehensively processed to obtain the environmental factor coefficient.

[0088] Therefore, the environmental factor coefficient can be expressed as follows: obtain the environmental factors and adjustment parameters. The adjustment parameters include light intensity and color temperature, and the environmental factors include temperature coefficient, weather coefficient, and external light coefficient. Normalize the environmental factors and adjustment parameters in sequence, and calculate the environmental factor coefficient according to the index values of the environmental factors and adjustment parameters.

[0089] ; where represents the environmental factor coefficient, represents the temperature coefficient, represents the weather coefficient, represents the external light coefficient, represents the index value of light intensity, represents the index value of color temperature; represents the weight factor of the temperature coefficient, represents the weight factor of the weather coefficient, represents the weight factor of the external light coefficient, represents the weight factor of light intensity, represents the weight factor of color temperature, represents the exponential constant; the set weight factors can be set to 0.2, 0.15, 0.15, 0.25, 0.25 in sequence according to the order of temperature coefficient, weather coefficient, external light coefficient, light intensity, and color temperature.

[0090] For the temperature coefficient, it can be expressed as follows: set the coefficient value according to the value range of temperature. The value range of the temperature coefficient is 0 - 1. At this time, the maximum and minimum temperatures of the corresponding date can be used to equally divide the corresponding temperature into five temperature intervals, and set the coefficient values for these five temperatures. For example, set the coefficient values to 0.8, 0.9, 1, 0.9, 0.8 in sequence, or select the average value of the coefficient values set for the current temperature in the historical data as the value of the temperature coefficient at this time.

[0091] For the weather coefficient and external light coefficient, they are the same as the temperature coefficient, and the value range is 0 - 1. The weather coefficient and external light coefficient can adopt the average value of the coefficient values set for the corresponding weather and light intensity in the historical data.

[0092] The behavior trend unit is used to obtain the moving guidance path of the light, and set the behavior trend coefficient in combination with the moving frequency and moving interval of the current target user.

[0093] At this time, the obtained moving frequency and moving interval are expressed as the ratio relative to the moving frequency and moving interval in the historical data, and in combination with the coincidence evaluation coefficient obtained on the current moving guidance path, to determine the corresponding trend situation when guiding the movement at this time.

[0094] Therefore, the way to obtain the behavior trend coefficient is to obtain the coincidence evaluation coefficient, movement frequency, and movement interval under the current movement guidance path, and after normalizing the coincidence evaluation coefficient, movement frequency, and movement interval, calculate the behavior trend coefficient.

[0095] ; where represents the behavior trend coefficient, represents the index value of the movement frequency, represents the index value of the movement interval. At this time, the index values of the movement frequency and movement interval represent the normalized values; represents the coincidence evaluation coefficient, represents the standard value of the movement frequency, represents the standard value of the movement interval. The standard values of the movement frequency and movement interval are represented by the standard deviations of the movement frequency and movement interval in historical data; represents the weight factor of the movement frequency, represents the weight factor of the movement interval, represents the weight factor of the coincidence evaluation coefficient.

[0096] In the distribution adjustment unit, the distribution adjustment coefficient is matched by the value obtained through comprehensive processing of the current environmental factor coefficient, behavior trend coefficient, and feedback result, so as to obtain the solution corresponding to the current setting in historical data to complete the rapid adjustment of the lighting.

[0097] The distribution adjustment coefficient is expressed as ; where represents the distribution adjustment coefficient, represents the environmental factor coefficient, represents the behavior trend coefficient, represents the index value of the feedback result.

[0098] At this time, after obtaining the distribution adjustment coefficient, according to the value of the current distribution adjustment coefficient, the required distribution adjustment result can be selected from historical data to keep the user always in a suitable lighting environment.

[0099] When adjusting in the behavior trend unit, the adjustment can be carried out in the following way.

[0100] Movement interval: Identify the movement interval of the user through the camera, judge whether the user is about to rest or go out, and adjust the lighting settings.

[0101] Movement frequency: Monitor the movement frequency of the user through the sensor, judge the current activity state of the user, and adjust the brightness and color temperature of the lighting.

[0102] The environmental factor unit can be adjusted in the following way.

[0103] Temperature: In high or low temperature environments, adjust the color temperature of the lights to provide a more comfortable lighting environment.

[0104] Weather: On rainy or sunny days, adjust the brightness and color temperature of the lights to compensate for changes in natural light.

[0105] Lighting: Automatically adjust the brightness of indoor lights according to the external light intensity to ensure uniform and comfortable indoor lighting.

[0106] The distribution adjustment unit can be implemented in the following ways.

[0107] Step position: Adjust the distribution and irradiation range of the lights according to the user's specific position in different behavior modes.

[0108] Dynamic adjustment: When the user moves, dynamically adjust the distribution of the lights to ensure that the user is always in a suitable lighting environment.

[0109] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention, and still be covered by the protection scope of the present invention.

Claims

1. An LED bulb control system based on user behavior, characterized in that, Including: A behavior acquisition module, configured to acquire the behavior pattern of a target user and determine the initial lighting operation parameters of the target user under the corresponding behavior pattern. The behavior pattern also includes the position of the target user, the scene mode, and the lighting sequence; A behavior analysis module, configured to acquire the behavior data of the target user under the behavior pattern, determine the coincidence evaluation coefficient between the user behavior and the lighting, and set the moving guidance path of the lighting according to the coincidence evaluation coefficient; A lighting preference module, configured to determine the preference range and preference color temperature of the lighting according to the behavior data of the user, and determine the adjustment parameters of the lighting under the behavior data; A scene verification module, configured to verify the feedback consistency between the user behavior and the lighting feedback under different scene modes, and determine the feedback result related to the current lighting feedback; A parameter adjustment module, configured to adjust the lighting sequence of the lighting according to the behavior pattern of the target user, and determine the distribution adjustment result of the lighting; The parameter adjustment module includes an environmental factor unit, a behavior trend unit, and a distribution adjustment unit; The environmental factor unit is configured to acquire the external temperature, weather, and illumination, set the environmental factors, and output the environmental factor coefficient in combination with the adjustment parameters; The behavior trend unit is configured to acquire the moving guidance path of the lighting, and set the behavior trend coefficient in combination with the moving frequency and moving interval of the current target user; The distribution adjustment unit is configured to comprehensively process the environmental factor coefficient, the behavior trend coefficient, and the feedback result, obtain the distribution adjustment coefficient of the target user under different behavior patterns and positions, and output the distribution adjustment coefficient as the distribution adjustment result.

2. The LED bulb control system based on user behavior according to claim 1, characterized in that, The implementation method of the coincidence evaluation coefficient is: Based on the behavior data of the target user, acquire the activity time, activity type, and activity frequency of the target user; based on the activity time, activity type, and activity frequency of the target user, identify the user movement path of the current target user, calculate the coincidence between the position points on the user movement path and the lighting irradiation range, obtain the coincidence rate of the position points on the user movement path, and obtain the position matching coefficient and time matching coefficient corresponding to the position points under the corresponding coincidence rate value, so as to obtain the coincidence evaluation coefficient.

3. The LED bulb control system based on user behavior according to claim 2, wherein The user movement path is expressed as follows: acquire the position points of the target user during movement, cluster the position points, and obtain multiple clustering clusters; the clustering method includes using the activity time, activity type, and activity frequency as the clustering clusters to cluster the position points of the user, obtain the features related to the activity time, activity type, and activity frequency, calculate the feature data difference between the features of the center point of each clustering cluster and the other features in the current clustering cluster, and match the feature data difference with the lighting irradiation range to obtain the user movement path.

4. The LED bulb control system based on user behavior according to claim 2, wherein The position matching coefficient is expressed as ; where represents the position matching coefficient of the i-th position point, represents the radius of the light irradiation range, represents the distance between the i-th position point and the center point of the light irradiation range; The time matching coefficient is expressed as ; where represents the time matching coefficient of the i-th position point, represents the difference between the timestamp corresponding to the i-th position point and the expected timestamp, represents the time difference threshold; The coincidence evaluation coefficient is expressed as, ; where, represents the coincidence evaluation coefficient, represents the coincidence rate, represents the number of position points, and the value range of i is from 1 to n.

5. The LED bulb control system based on user behavior according to claim 2, wherein The implementation method of the moving guidance path of the lighting is as follows: when the coincidence evaluation coefficient is greater than the first coincidence threshold, use the position points where the product value of the position matching coefficient and the time matching coefficient is greater than the preset threshold as the moving guidance path of the lighting at this time; when the coincidence evaluation coefficient is less than the second coincidence threshold, use the position points where the product value of the coincidence rate, the position matching coefficient, and the time matching coefficient is less than the preset product value as the moving guidance path of the lighting; When the coincidence evaluation coefficient is less than the first coincidence threshold and greater than the second coincidence threshold, obtain the position point corresponding to the average value of the position matching coefficient and the time matching coefficient, and use the user movement path where the position point corresponding to the average value of the position matching coefficient and the time matching coefficient is located as the movement guidance path of the light.

6. The LED bulb control system based on user behavior according to claim 1, characterized in that The method for obtaining the adjustment parameters is as follows: taking the illumination intensity and color temperature set by the light as independent variables and the user's behavior data as the dependent variable, analyzing the regression coefficient between the user behavior data and the data corresponding to the current illumination intensity and color temperature set by the light, performing a t-test analysis on the regression coefficient to obtain a significant coefficient, and setting the adjustment parameters according to the significant coefficient.

7. A user behavior-based LED bulb control system according to claim 1, characterized in that, To verify the feedback consistency between user behavior and light feedback in different scenario modes, the implementation method for determining the feedback result related to the current light feedback is as follows: Obtain the light setting data of the target user in the corresponding scenario mode, and calculate the first similarity regarding the user behavior between the current light setting data and the behavior data; Obtain the second similarity regarding the response time in the light setting data when the scenario mode is switched; Obtain the third similarity regarding the light feedback between the light setting data and the behavior data; Combine the first similarity, the second similarity, and the third similarity, and output the feedback result related to the light feedback.

8. The LED bulb control system based on user behavior according to claim 1, wherein The environmental factor coefficient can be expressed as follows: obtain the environmental factor and the adjustment parameters. The adjustment parameters include the illumination intensity and the color temperature, and the environmental factor includes the temperature coefficient, the weather coefficient, and the external illumination coefficient. Normalize the environmental factor and the adjustment parameters in sequence, and calculate the environmental factor coefficient according to the index values of the environmental factor and the adjustment parameters; ； Among them, represents the environmental factor coefficient, represents the temperature coefficient, represents the weather coefficient, represents the external light coefficient, represents the index value of the light intensity, represents the index value of the color temperature; represents the weight factor of the temperature coefficient, represents the weight factor of the weather coefficient, represents the weight factor of the external light coefficient, represents the weight factor of the light intensity, represents the weight factor of the color temperature, represents the exponential constant.

9. The LED bulb control system based on user behavior according to claim 1, wherein The method for obtaining the behavior trend coefficient is as follows: obtain the coincidence evaluation coefficient, the movement frequency, and the movement interval under the current movement guidance path, and calculate the behavior trend coefficient after normalizing the coincidence evaluation coefficient, the movement frequency, and the movement interval; ； Among them, represents the behavior trend coefficient, represents the index value of the movement frequency, represents the index value of the movement interval. At this time, the index values of the movement frequency and the movement interval represent the normalized values; represents the coincidence evaluation coefficient, represents the standard value of the movement frequency, represents the standard value of the movement interval, represents the exponential constant; represents the weight factor of the movement frequency, represents the weight factor of the movement interval, represents the weight factor of the coincidence evaluation coefficient.

10. The LED bulb control system based on user behavior according to claim 1, wherein The distribution adjustment coefficient is expressed as: ； Among them, represents the distribution adjustment coefficient, represents the environmental factor coefficient, represents the behavior trend coefficient, represents the index value of the feedback result, represents the exponential constant.

Images