Lamp cluster intelligent control method and system based on multi-element information

Abstract

This invention relates to the field of lighting control technology and discloses a method and system for intelligent control of lighting clusters based on multi-source information. The method includes: monitoring the target area of ​​the lighting cluster, synchronizing the monitoring results in the time domain to obtain a synchronized sensing data stream; evaluating the activation duration based on the target trajectory prediction data to obtain the dynamic activation maintenance duration of the lighting cluster; using the dynamic activation maintenance duration as a window to identify the critical moment of the state data in the area to obtain the state transition moment point; when the state transition moment point exceeds the termination moment, backtracking and analyzing the trajectory continuity to obtain the trajectory continuity feature; when the feature is a direction reversal, mapping the power parameter and speed to obtain the attenuation control curve and generating a dynamic dimming control signal; when the feature is a trajectory interruption, analyzing the maintenance parameter response time to obtain the interruption response maintenance duration and generating a continuous lighting control signal. This invention can improve the efficiency of intelligent control of lighting clusters.

Description

Technical Field

[0001] This invention relates to the field of lighting control technology, and in particular to a method and system for intelligent control of lighting clusters based on multi-source information. Background Technology

[0002] With the deep application of IoT and intelligent control technologies in indoor and outdoor lighting scenarios, lighting clusters have gradually evolved from independent switch control to intelligent lighting systems with multi-sensor collaboration. Current mainstream solutions deploy infrared human body sensors, visible light positioning, and ambient illuminance monitoring devices in target areas to collect data on personnel location, ambient light intensity, and lighting fixture operating status. This data, combined with preset thresholds or timing strategies, enables the starting, stopping, and brightness adjustment of the lights. These systems often employ a distributed sensor acquisition and centralized data aggregation architecture, using a unified clock for basic timing calibration and fixed-area occupancy detection to drive the lights to perform switching or graded dimming actions. This approach has been widely adopted in scenarios such as offices, shopping malls, and underground parking garages, improving lighting efficiency and ease of use to a certain extent.

[0003] Most existing solutions control lighting fixtures solely based on personnel movement trajectories or area occupancy status, lacking a mechanism for synchronously linking these two in the time domain. For example, when personnel linger in an area or briefly turn back, the lighting activation duration predicted based on the trajectory often deviates from the actual occupancy status change, causing the lighting fixtures to turn off prematurely before the personnel have left, or continue to illuminate after the personnel have left. It is difficult to achieve a balance between lighting continuity and energy-saving effects. Furthermore, existing solutions lack refined control response strategies for abnormal trajectory states, such as when personnel suddenly turn back or the trajectory is interrupted. They typically only use fixed-duration delay shutdown or simple power switching, failing to dynamically adjust the dimming parameters and duration of the lighting fixtures according to the specific characteristics of trajectory direction changes or trajectory interruptions. For example, when personnel suddenly turn while moving, traditional control methods struggle to synchronously adjust the activation sequence of the lights in front and the decay rate of the lights behind, easily leading to lighting response lag or power adjustment mismatch, affecting the accuracy and adaptability of lighting control. Summary of the Invention

[0004] This invention provides a method and system for intelligent control of lighting clusters based on multi-source information, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a lighting cluster intelligent control method based on multi-source information, comprising: S1. Perform dynamic full-domain monitoring on the target area of ​​the lighting cluster and synchronize the monitoring results in the time domain to obtain the synchronous sensing data stream of the target area. The synchronous sensing data stream includes target trajectory prediction data with directional attributes and area existence status data without directional attributes. S2. Based on the target trajectory prediction data, evaluate the activation duration of the lighting cluster to obtain the dynamic activation duration of the lighting cluster. S3. Based on the time window of dynamic activation retention duration, identify the critical moment of the state data of the region to obtain the state transition moment of the target region. S4. When the state transition time point is later than the end time of the dynamic activation hold duration, backtracking analysis is performed on the trajectory continuity of the target trajectory prediction data within the dynamic activation hold duration to obtain the trajectory continuity characteristics of the target trajectory prediction data. S5. When the trajectory continuity characteristic is reverse direction, speed correlation mapping is performed on the power parameters of the lighting cluster to obtain the attenuation control curve of the lighting cluster, and dynamic dimming control signal of the lighting cluster is generated based on the attenuation control curve. S6. When the trajectory continuity characteristic is trajectory interruption, the response time analysis is performed on the maintenance parameters of the lighting cluster to obtain the interruption response maintenance duration of the lighting cluster, and the continuous lighting control signal of the lighting cluster is obtained based on the interruption response maintenance duration.

[0006] In a preferred embodiment, the process of obtaining the synchronous sensing data stream of the target area is as follows: The target area of ​​the lighting cluster is collected by full-domain sensing to obtain multi-source sensing data of the target area. By performing time-series alignment of multi-source sensing data, a synchronous sensing data stream for the target area is obtained; Oriented trajectory analysis is performed on the synchronous sensing data stream to obtain target trajectory prediction data carrying directional attributes in the synchronous sensing data stream; Spatial occupancy detection is performed on the synchronous sensing data stream to obtain the existence status data of regions in the synchronous sensing data stream that do not carry directional attributes.

[0007] In a preferred embodiment, the process for obtaining the dynamic activation duration of the lighting cluster is as follows: The target trajectory prediction data is segmented into trajectory segments to obtain a sequence of trajectory segments for the target trajectory prediction data; Perform direction comparison on adjacent trajectory segments in the trajectory segment sequence to obtain direction consistency markers for adjacent trajectory segments; Extract the activation hold interval corresponding to the directional consistency marker, and use the activation hold interval as the dynamic activation reference duration of the lighting cluster; Based on the dynamic activation baseline duration, the activation duration of the lighting cluster is evaluated to generate the dynamic activation retention duration of the lighting cluster.

[0008] In a preferred embodiment, the process of obtaining the state transition time point of the target region is as follows: Within the time window of dynamic activation duration, the status data of the area is identified to obtain the area occupancy status of the lighting cluster at different times. Perform state difference analysis on the state values ​​of adjacent time points in the region's occupancy state to obtain the state change amount of adjacent time points; Based on the state change amount, if the absolute value of the state change amount is greater than the preset threshold, it is determined to be a state transition, and the transition time point of the region's occupancy state is marked to obtain the state transition time point of the target region.

[0009] In a preferred embodiment, the process of obtaining the trajectory continuity characteristics of the target trajectory prediction data is as follows: Based on the termination time of the dynamic activation hold duration, the temporal difference of the state transition time point is measured to obtain the temporal offset of the state transition time point relative to the termination time. Based on the time offset, the state transition time point and the termination time are judged to exceed the state, and the judgment result of the state transition time point exceeding the termination time is obtained. When the judgment result exceeds the termination time, the target trajectory prediction data is truncated according to the time boundary of the dynamic activation duration to obtain the trajectory data segment within the dynamic activation duration. Trajectory morphology analysis is performed on trajectory data segments to obtain trajectory direction characteristics within the trajectory data segments; By identifying the continuity of trajectory characteristics, the trajectory continuity characteristics of the target trajectory prediction data are obtained.

[0010] In a preferred embodiment, the process of obtaining the trajectory direction features in the trajectory data segment is as follows: Discrete sampling is performed on the trajectory data segment to obtain the trajectory point sequence of the trajectory data segment; Perform direction fitting on the trajectory point sequence to obtain the dominant direction vector of the trajectory point sequence; The dominant direction vector is used to determine the trajectory direction, thus obtaining the trajectory direction characteristics of the trajectory data segment.

[0011] In a preferred embodiment, the process of obtaining the attenuation control curve of the lighting cluster is as follows: When the trajectory continuity characteristic is reverse direction, the power parameters of the lighting cluster are mapped to obtain the speed parameters of the lighting cluster. The speed parameters and the power parameters of the lighting cluster are correlated to obtain the speed-power correlation between the speed parameters and the power parameters; Based on the speed-power correlation, the power parameters are curve-fitted to obtain the attenuation control curve of the lighting cluster.

[0012] In a preferred embodiment, the process of generating a dynamic dimming control signal for the luminaire cluster based on the attenuation control curve is as follows: Discretize the attenuation control curve to obtain the control node parameter set of the attenuation control curve; Based on the control node parameter set, the attenuation control curve is divided into time intervals to obtain the power configuration sequence of the lighting cluster; The power configuration sequence is compiled into control instructions to obtain the dynamic dimming control signal for the lighting cluster.

[0013] In a preferred embodiment, the process of obtaining the continuous lighting control signal for the luminaire cluster based on the duration of the interruption response is as follows: When the trajectory continuity feature indicates trajectory interruption, obtain the interruption start time from the trajectory continuity feature; Based on the interruption start time, the maintenance parameters of the lighting cluster are anchored to obtain the maintenance reference duration of the lighting cluster; Based on the maintenance reference duration, the response interval is divided between the maintenance reference duration and the interruption start time to obtain the response time window of the lighting cluster; Within the response time window, the duration of the maintenance parameters is calibrated to obtain the interruption response maintenance duration of the lighting cluster; Based on the duration of the interrupt response, the lighting cluster is controlled and encoded to obtain the continuous lighting instruction set of the lighting cluster; The continuous lighting instruction set execution signal is encapsulated to obtain the continuous lighting control signal for the luminaire cluster.

[0014] To address the above problems, the present invention also provides an intelligent control system for lighting clusters based on multi-source information, the system comprising: The full-domain monitoring and synchronization module is used to dynamically monitor the target area of ​​the lighting cluster and synchronize the monitoring results in the time domain to obtain the synchronous sensing data stream of the target area. The synchronous sensing data stream includes target trajectory prediction data with directional attributes and area existence status data without directional attributes. The activation duration evaluation module is used to evaluate the activation duration of the lighting cluster based on the target trajectory prediction data, and obtain the dynamic activation duration of the lighting cluster. The state transition identification module is used to identify the critical moments of state data in a region based on a time window of dynamic activation duration, and to obtain the state transition moment points of the target region. The trajectory continuity backtracking module is used to perform backtracking analysis on the trajectory continuity of the target trajectory prediction data within the dynamic activation duration when the state transition time point is later than the end time of the dynamic activation duration, so as to obtain the trajectory continuity characteristics of the target trajectory prediction data. The attenuation dimming control module is used to perform speed correlation mapping on the power parameters of the lighting cluster when the trajectory continuity characteristic is reversed, to obtain the attenuation control curve of the lighting cluster, and to generate the dynamic dimming control signal of the lighting cluster based on the attenuation control curve. The continuous lighting control module is used to analyze the response time of the maintenance parameters of the lighting cluster when the trajectory continuity characteristic is trajectory interruption, to obtain the interruption response maintenance duration of the lighting cluster, and to obtain the continuous lighting control signal of the lighting cluster based on the interruption response maintenance duration.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. By performing full-domain sensing and time-series alignment of the target area of ​​the lighting cluster, a synchronous sensing data stream containing directional trajectory prediction data and non-directional area existence status data is constructed. In subsequent control, the state transition time point is identified based on the time window of dynamic activation duration. Then, dynamic dimming control signals or continuous lighting control signals are generated according to the trajectory continuity characteristics. This achieves dynamic synchronous association between target trajectory prediction and area occupancy status in the time domain, avoiding premature shutdown or ineffective lighting of the lighting fixtures due to people wandering or short-term return, thus improving energy-saving effect while ensuring lighting continuity.

[0016] 2. By extracting the trajectory segment sequence from the target trajectory prediction data and comparing the directions of adjacent trajectory segments, when a direction reversal is identified, a velocity-power correlation relationship between velocity parameters and power parameters is constructed and an attenuation control curve is fitted. When a trajectory interruption is identified, the interruption response duration is calibrated based on the interruption start time and a continuous lighting control signal is generated. This enables dynamic adjustment of the dimming parameters and duration of the lamps according to the specific characteristics of trajectory direction changes or trajectory interruptions. It solves the problem of mismatch between the activation sequence and attenuation rate of the lamps before and after a person suddenly turns, and improves the accuracy and adaptability of lighting control. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a method for intelligent control of lighting clusters based on multi-source information, provided in an embodiment of the present invention. Figure 2 This is a functional block diagram of a lighting cluster intelligent control system based on multi-source information provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a method for intelligent control of lighting clusters based on multi-source information. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for intelligent control of lighting clusters based on multi-source information can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a method for intelligent control of lighting clusters based on multi-source information according to an embodiment of the present invention. In this embodiment, the method for intelligent control of lighting clusters based on multi-source information includes: S1. Perform dynamic full-domain monitoring on the target area of ​​the lighting cluster and synchronize the monitoring results in the time domain to obtain the synchronous sensing data stream of the target area. The synchronous sensing data stream includes target trajectory prediction data with directional attributes and area existence status data without directional attributes. In this embodiment of the invention, the process of obtaining the synchronous sensing data stream of the target area is as follows: The target area of ​​the lighting cluster is collected by full-domain sensing to obtain multi-source sensing data of the target area. In the target area illuminated by the cluster of lights, infrared human body sensors, visible light positioning, and ambient illuminance monitoring devices are evenly installed around the perimeter and top of the area. This ensures that the monitoring ranges of all devices are interconnected, completely covering the entire target area without any blind spots. The system's control core sends a synchronous acquisition start signal to all sensors. Upon receiving the signal, all devices simultaneously begin data collection, gathering information such as the real-time spatial location of personnel, ambient light intensity, and the current operating status of the lights in the target area. Each sensor binds its collected information, acquisition time, its own identification number, and the identification number of the sub-area it is responsible for monitoring together before transmitting it outward. All the binding information returned by the sensors is aggregated to form multi-source sensing data for the target area. This multi-source sensing data is a collection of all the original monitoring information of personnel, environment, and lights in the target area.

[0021] By performing time-series alignment of multi-source sensing data, a synchronous sensing data stream for the target area is obtained; Using the internal clock of the system control core as the sole time standard, the acquisition time corresponding to each piece of information in the multi-source sensing data is first read. Then, the acquisition time of each piece of information is used to calculate the difference with the unified time standard. All information whose calculated time difference falls within the same fixed interval is grouped into the same time slice. The information in each time slice is arranged in ascending order according to the number of the monitoring sub-area. The personnel, environment, and lighting information of the same sub-area are bound into a complete unit. Then, all time slices are spliced ​​together one by one in the order from early to late according to the time standard. After splicing, a continuous information string without time misalignment and information loss is obtained. This continuous information string is the synchronous sensing data stream of the target area. The synchronous sensing data stream is the set of continuous sensing information of the whole domain obtained after eliminating the time difference of acquisition by different sensing devices.

[0022] Oriented trajectory analysis is performed on the synchronous sensing data stream to obtain target trajectory prediction data carrying directional attributes in the synchronous sensing data stream; From the various time slices of the synchronous sensing data stream, the continuous spatial location information corresponding to the same person is extracted. These location information are then strung together into a continuous list of location points according to the chronological order of the time slices. The spatial coordinate values ​​of the next location are subtracted from the spatial coordinate values ​​of the previous location to calculate the change in coordinate values. The direction of movement between two adjacent locations is then determined by the change in coordinate values. By integrating the movement directions of all adjacent locations, the complete movement trajectory of the person is obtained. The movement direction and coordinate change patterns of the last few location points in the movement trajectory are then extracted. Following this pattern, the location coordinates and movement directions corresponding to subsequent time slices are continuously calculated. The calculated coordinates and directions are strung together to form a predicted movement path. This predicted path is the target trajectory prediction data with directional attributes. The target trajectory prediction data is the predictive information that reflects the future movement path and fixed direction of the person.

[0023] Spatial occupancy detection is performed on the synchronous sensing data stream to obtain the existence status data of regions in the synchronous sensing data stream that do not carry directional attributes. Based on the number of independently controllable lighting units in the lighting cluster, the target area is divided into an equal number of independent sub-areas, each corresponding to a specific lighting unit. Each independent sub-area is matched with a dedicated set of independently controllable lighting units. Spatial location information of personnel in each sub-area under different time slices is extracted from the synchronous sensing data stream. The presence of personnel spatial location data in each sub-area is determined one by one: if data is present, the sub-area is marked as occupied; otherwise, it is marked as unoccupied. The status markings of all sub-areas are then organized according to the time slice order and sub-area number order to form a fixed set of status information, which is the area presence status data without directional attributes. This data is only used to statically reflect the personnel occupancy status of each sub-area within the target area.

[0024] S2. Based on the target trajectory prediction data, evaluate the activation duration of the lighting cluster to obtain the dynamic activation duration of the lighting cluster. In this embodiment of the invention, the process of obtaining the dynamic activation duration of the lighting cluster is as follows: The target trajectory prediction data is segmented into trajectory segments to obtain a sequence of trajectory segments for the target trajectory prediction data; The target trajectory prediction data is the predicted movement path information of personnel with directional attributes, which includes continuous time points and corresponding spatial location information. According to the time sequence of the target trajectory prediction data, based on fixed time intervals, all continuous spatial location information within each fixed time interval in the target trajectory prediction data is completely extracted. Each group of extracted continuous spatial location information and corresponding time information is combined into an independent trajectory segment. All independent trajectory segments divided according to time sequence are arranged in order, and the complete combination formed after the arrangement is the trajectory segment sequence of the target trajectory prediction data.

[0025] Perform direction comparison on adjacent trajectory segments in the trajectory segment sequence to obtain direction consistency markers for adjacent trajectory segments; The trajectory segment sequence is a combination of all independent trajectory segments arranged in time. Two groups of trajectory segments that are immediately adjacent in time are selected from the sequence. The overall movement direction of the preceding and following trajectory segments in each group is determined. The overall movement directions of the preceding and following trajectory segments are then compared to match perfectly. If the directions are exactly the same, the adjacent trajectory segments in the group are marked as having the same direction. If the directions differ, the adjacent trajectory segments in the group are marked as having different directions. All the corresponding marks for adjacent trajectory segments are then organized sequentially. The resulting combination of marks is the direction consistency mark for adjacent trajectory segments.

[0026] Extract the activation hold interval corresponding to the directional consistency marker, and use the activation hold interval as the dynamic activation reference duration of the lighting cluster; The direction consistency marker is a combination of direction matching identifiers for all adjacent trajectory segments; from the direction consistency markers, all adjacent trajectory segments marked with the same direction are selected one by one, and the time ranges corresponding to these adjacent trajectory segments with the same direction are connected in sequence. The continuous and uninterrupted time range formed after connection is the activation and maintenance interval. The total time length covered by the activation and maintenance interval is fully counted, and the total time length obtained is the dynamic activation reference time of the lighting cluster.

[0027] Based on the dynamic activation baseline duration, the activation duration of the lighting cluster is evaluated to generate the dynamic activation retention duration of the lighting cluster; The dynamic activation reference duration is the total time length of the activation hold interval. First, determine the overall extension direction and trend of the trajectory segment sequence in the target trajectory prediction data. Then, based on the extension trend, calculate the time length that perfectly matches the trajectory extension trend by extending the dynamic activation reference duration. The time length obtained by this extension calculation is the activation duration. Add the time length of the dynamic activation reference duration to the time length of the activation duration. The total time length obtained after adding them is the dynamic activation hold duration of the lighting cluster.

[0028] S3. Based on the time window of dynamic activation retention duration, identify the critical moment of the state data of the region to obtain the state transition moment of the target region. In this embodiment of the invention, the process of obtaining the state transition time point of the target region is as follows: Within the time window of dynamic activation duration, the status data of the area is identified to obtain the area occupancy status of the lighting cluster at different times. According to the start and end times of the dynamic activation duration time window, the regional existence status data is retrieved piece by piece. The dynamic activation duration time window is the range of continuous lighting activation time for the lighting cluster, determined by the target trajectory prediction data after trajectory segmentation, direction comparison of adjacent trajectory segments, extraction of activation duration intervals, and evaluation of activation duration. The regional existence status data is a set of personnel occupancy status markers for each sub-region, formed by spatial occupancy detection of the synchronous sensing data stream collected and time-aligned across the entire target area, organized according to the time slice order and sub-region number order. The critical moment identification rule is: traverse all time slices within the time window and filter continuous... For a stable interval where the occupancy status of a region remains unchanged for three or more consecutive time slices, the first time slice where the occupancy status changes after the end of the stable interval is marked as the critical moment. Status identification involves extracting the status markers of all sub-regions corresponding to each time slice within the time window. Each sub-region is then confirmed to be either occupied or unoccupied under that time slice. The occupancy status of all sub-regions under the same time slice is integrated in order of sub-region number to form the occupancy status of the region corresponding to that time slice. Using the critical moment as the key decision node, the status integration process of all time slices within the time window is completed sequentially to obtain the occupancy status of the lighting cluster at different times.

[0029] Perform state difference analysis on the state values ​​of adjacent time points in the region's occupancy state to obtain the state change amount of adjacent time points; Select two adjacent regions within the time window, one before and one after the critical moment, to determine their occupied status. The status value of each region's occupied status is the identifier corresponding to the occupied status and the identifier corresponding to the unoccupied status of each sub-region at the corresponding moment. State difference is achieved by comparing the status value of each sub-region in the occupied status of the region at the later moment with the status value of the same numbered sub-region at the previous moment. The total number of sub-regions whose status values ​​change between two adjacent moments is counted. The total number of sub-regions whose status values ​​change is counted is taken as the state change amount between adjacent moments. The state comparison and count of adjacent moments corresponding to all critical moments are completed to obtain the state change amount between all adjacent moments.

[0030] Based on the state change amount, if the absolute value of the state change amount is greater than the preset threshold, it is determined to be a state transition, and the transition time point of the region occupancy state is marked to obtain the state transition time point of the target region. The transition time points of the domain occupancy state are calibrated to obtain the state transition time points of the target area. The preset threshold is a fixed standard of state change quantity pre-calibrated based on the response accuracy of the lighting cluster control and the normal variation range of personnel activities in the target area. This standard is used to define whether the occupancy state of the area has changed significantly. The state change quantity of each adjacent time is converted into an absolute value without positive or negative distinction. This value is the absolute value of the state change quantity. The absolute value of the state change quantity is compared with the preset threshold. When the absolute value of the state change quantity is greater than the preset threshold, and the time interval corresponding to the state change is the critical time or the next time slice immediately adjacent to the critical time, it is determined that the occupancy state of the area between the adjacent time has transitioned. The specific time of the next time in the adjacent time of the state transition is determined, and this time is taken as the transition time point of this state transition. The transition time points corresponding to all state transitions are summarized in chronological order to obtain the state transition time points of the target area.

[0031] S4. When the state transition time point is later than the end time of the dynamic activation hold duration, backtracking analysis is performed on the trajectory continuity of the target trajectory prediction data within the dynamic activation hold duration to obtain the trajectory continuity characteristics of the target trajectory prediction data. In this embodiment of the invention, the process of obtaining the trajectory continuity characteristics of the target trajectory prediction data is as follows: Based on the termination time of the dynamic activation hold duration, the temporal difference of the state transition time point is measured to obtain the temporal offset of the state transition time point relative to the termination time. First, determine the end time of the dynamic activation duration. This time is the fixed point at which the lighting activation state needs to end, as determined by the lighting cluster based on the predicted trajectory data of the personnel target. Then, define the state transition time point. This time point is the point at which the occupancy status of personnel in the target area suddenly changes. The state change includes two situations: from occupied to unoccupied, and from unoccupied to occupied. Following the natural flow of time from morning to night, first calculate the total duration from the start time to the state transition time point, and then calculate the total duration from the start time to the end time of the dynamic activation duration. Subtract the total duration corresponding to the end time of the dynamic activation duration from the total duration corresponding to the state transition time point. The resulting time difference is the temporal offset of the state transition time point relative to the end time. The temporal offset is a dedicated data point used to reflect the time distance between two time points, which can intuitively reflect the positional relationship between the state transition time point and the end time of the dynamic activation duration.

[0032] Based on the time offset, the state transition time point and the termination time are judged to exceed the state, and the judgment result of the state transition time point exceeding the termination time is obtained. The calculated time offset value is compared with zero. If the time offset value is greater than zero, it is determined that the state transition time point is after the end time of the dynamic activation hold duration. If the time offset value is equal to zero or less than zero, it is determined that the state transition time point is before or coincides with the end time of the dynamic activation hold duration. This determination is used as the judgment result that the state transition time point exceeds the end time. The judgment result is the only basis for determining whether trajectory backtracking analysis needs to be carried out, and it can directly determine the execution direction of subsequent data processing.

[0033] When the judgment result exceeds the termination time, the target trajectory prediction data is truncated according to the time boundary of the dynamic activation duration to obtain the trajectory data segment within the dynamic activation duration. Once the determination that the state transition time exceeds the termination time is confirmed, the target trajectory prediction data is processed. The time boundary of the dynamic activation duration includes two fixed nodes: the start time and the end time. The target trajectory prediction data is the pre-predicted continuous movement path information with personnel movement direction attributes. From the complete target trajectory prediction data, all trajectory information between the start time and the end time of the dynamic activation duration is selected. These selected trajectory information are then completely spliced ​​together in chronological order. The resulting continuous and uninterrupted data segment is the trajectory data fragment within the dynamic activation duration. The trajectory data fragment is an independent data set containing only personnel movement trajectory information within a specified time range, without any invalid trajectory information outside the time range.

[0034] The process of performing trajectory morphology analysis on trajectory data segments to obtain the trajectory direction features within those segments is as follows: Discrete sampling is performed on the trajectory data segment to obtain the trajectory point sequence of the trajectory data segment; A trajectory data segment is a continuous movement trajectory information of personnel within a dynamically activated duration. At fixed time intervals, the spatial location information of personnel corresponding to each time node is extracted from the trajectory data segment. Each extracted spatial location information corresponds to an independent trajectory point. All extracted trajectory points are arranged in chronological order from earliest to latest. The resulting combination of trajectory points is the trajectory point sequence of the trajectory data segment. The trajectory point sequence is an ordered data set composed of trajectory points corresponding to discrete time nodes, which can clearly show the position and status of the trajectory at different time points.

[0035] Perform direction fitting on the trajectory point sequence to obtain the dominant direction vector of the trajectory point sequence; A trajectory point sequence is a set of discrete trajectory points arranged in time order. The spatial position information of each pair of adjacent trajectory points in the sequence is read sequentially. Based on the changes in the spatial position of these two adjacent trajectory points, the movement direction of the person between them is determined. All movement directions of adjacent trajectory points in the sequence are summarized, and the direction that appears most frequently and corresponds to the longest trajectory is selected. This direction is taken as the overall core movement direction of the trajectory point sequence. This overall core movement direction is then transformed into a unique directional identifier that represents the overall direction of the trajectory. This unique directional identifier is the dominant direction vector of the trajectory point sequence. The dominant direction vector is the only directional data that accurately reflects the overall movement trend of the trajectory and is not affected by local trajectory fluctuations.

[0036] The dominant direction vector is used to determine the trajectory direction, thus obtaining the trajectory direction characteristics of the trajectory data segment; The dominant direction vector is a unique directional identifier that represents the overall movement trend of the trajectory. The overall movement direction of the trajectory data segment is determined directly based on the directional identifier corresponding to the dominant direction vector. The determined overall movement direction is directly used as the trajectory direction feature of the trajectory data segment. The trajectory direction feature is an intuitive feature data that can directly reflect the overall movement direction of the trajectory data segment and is the core basis for judging the continuity of the trajectory.

[0037] By identifying the continuity of trajectory characteristics, the trajectory continuity characteristics of the target trajectory prediction data are obtained. The trajectory direction feature is a direct characteristic data reflecting the overall movement direction of the trajectory. By comparing the overall movement direction of the first half of the trajectory with that of the second half, the trajectory continuity feature is directly determined to be a direction reversal when the overall movement directions of the two segments are completely opposite. When there are missing continuous trajectory points or no subsequent personnel spatial location information in the trajectory direction feature, the trajectory continuity feature is directly determined to be a trajectory interruption. The final conclusion of direction reversal or trajectory interruption is used as the trajectory continuity feature of the target trajectory prediction data. The trajectory continuity feature is the core state data that determines which control method to use for the lighting cluster.

[0038] S5. When the trajectory continuity characteristic is reverse direction, speed correlation mapping is performed on the power parameters of the lighting cluster to obtain the attenuation control curve of the lighting cluster, and dynamic dimming control signal of the lighting cluster is generated based on the attenuation control curve. In this embodiment of the invention, the process of obtaining the attenuation control curve of the lighting cluster is as follows: When the trajectory continuity characteristic is reverse direction, the power parameters of the lighting cluster are mapped to obtain the speed parameters of the lighting cluster. First, the power acquisition unit of the lighting cluster is used to obtain the current output power of each lighting fixture in the cluster. The output power values ​​of all lighting fixtures are added together in sequence. The total value obtained is the power parameter of the lighting cluster. When performing power mapping operation, a fixed conversion base is determined in advance. The total value of the power parameter is directly divided by the fixed conversion base. The result value after division directly corresponds to the speed of personnel movement. This result value is the speed parameter of the lighting cluster.

[0039] The speed parameters and the power parameters of the lighting cluster are correlated to obtain the speed-power correlation between the speed parameters and the power parameters; The speed parameter and power parameter are synchronously bound. When the value of the speed parameter increases, the value of the power parameter increases synchronously by the same amount of change. When the value of the speed parameter decreases, the value of the power parameter decreases synchronously by the same amount of change. When the value of the speed parameter remains unchanged, the value of the power parameter also remains unchanged. The fixed correspondence formed according to this rule is the speed-power correlation relationship.

[0040] Based on the speed-power correlation, the power parameters are curve-fitted to obtain the attenuation control curve of the lighting cluster; Using the chronological order as the horizontal standard and the magnitude of the power parameter as the vertical standard, the power parameter values ​​at different times are marked on the time axis one by one. Then, all the marked value points are connected sequentially with a continuous and smooth line. The line has no breaks or abrupt changes and can clearly show the trend of the power parameter gradually decreasing over time. The final continuous and smooth curve is the attenuation control curve of the lighting cluster.

[0041] Discretize the attenuation control curve to obtain the control node parameter set of the attenuation control curve; Starting from the initial time node of the decay control curve, the power parameter values ​​of the curve at the corresponding time nodes are extracted sequentially at fixed time intervals. Each extracted value is a precise record. All extracted and recorded values ​​are arranged in chronological order of extraction time. The ordered set of values ​​formed after arrangement is the control node parameter set of the decay control curve.

[0042] Based on the control node parameter set, the attenuation control curve is divided into time intervals to obtain the power configuration sequence of the lighting cluster; Using the time node corresponding to each power parameter value in the control node parameter set as the dividing boundary, the entire time range covered by the attenuation control curve is divided into multiple continuous and non-overlapping time intervals. Each time interval uniquely corresponds to a fixed power parameter value. All time intervals and corresponding power parameter values ​​are combined in chronological order, and the ordered content formed by the combination is the power configuration sequence of the lighting cluster.

[0043] The power configuration sequence is compiled into control instructions to obtain the dynamic dimming control signal for the lighting cluster; Based on each time interval and corresponding power parameter value in the power configuration sequence, an adjustment command that the lighting cluster can directly recognize and execute is generated. The start and end times of the time interval and the power value to be output within the interval are clearly marked in the command. All adjustment commands are completely encapsulated in chronological order. The encapsulated command set that can directly drive the dimming of the lighting fixtures is the dynamic dimming control signal of the lighting cluster.

[0044] S6. When the trajectory continuity characteristic is trajectory interruption, the response time analysis is performed on the maintenance parameters of the lighting cluster to obtain the interruption response maintenance duration of the lighting cluster, and the continuous lighting control signal of the lighting cluster is obtained based on the interruption response maintenance duration. In this embodiment of the invention, when the trajectory continuity feature is trajectory interruption, the interruption start time in the trajectory continuity feature is obtained; The trajectory continuity feature is the characteristic information that reflects the complete running state of the trajectory after identifying the continuity of the target trajectory prediction data within the dynamic activation duration. The trajectory interruption is an abnormal trajectory state in this feature where trajectory points are continuously missing and subsequent personnel spatial location information cannot be identified. The trajectory data segment is a complete data set containing only the movement trajectory of personnel within the long time boundary of the dynamic activation duration. Starting from the last time node of the trajectory data segment, the trajectory points corresponding to each time node are checked one by one in chronological order from back to front to see if they exist completely. The status of the trajectory points at each time node is recorded until the first time node with continuously missing trajectory points and no personnel location information is found. This time node is determined as the interruption start time in the trajectory continuity feature.

[0045] Based on the interruption start time, the maintenance parameters of the lighting cluster are anchored to obtain the maintenance reference duration of the lighting cluster; The maintenance parameters are fixed-time configuration information used by the lighting cluster to maintain the basic lighting status when abnormal personnel trajectory is detected. This information is preset by the control terminal of the lighting cluster. The predetermined interruption start time is used as the time anchor point, and the time anchor point is used as the starting point of the timing. The total duration of basic lighting maintenance preset in the maintenance parameters is directly extracted. This extracted total duration is used as the maintenance reference duration of the lighting cluster.

[0046] Based on the maintenance reference duration, the response interval is divided between the maintenance reference duration and the interruption start time to obtain the response time window of the lighting cluster; Set the interruption start time as the start time of the response time range; starting from the start time, extend the corresponding time according to the total length of the maintenance reference duration; the time point reached after the extension is the end time of the response time range; the continuous and uninterrupted time period between the start time and the end time is the response time window of the lighting cluster.

[0047] Within the response time window, the duration of the maintenance parameters is calibrated to obtain the interruption response maintenance duration of the lighting cluster; After locking the start and end times of the response time window, the total time length between the start and end times is fully calculated. During the calculation, each minimum time unit is added up sequentially to obtain the total duration of the response time window. This total duration is matched with the lighting maintenance requirements corresponding to the maintenance parameters. After the matching results are completely consistent, this total duration is marked as the interruption response maintenance duration of the lighting cluster.

[0048] Based on the duration of the interrupt response, the lighting cluster is controlled and encoded to obtain the continuous lighting instruction set of the lighting cluster; Based on the duration of the interruption response, an independent control command is generated for each independently controllable luminaire unit in the luminaire cluster to maintain the lighting state for the duration. All independent control commands are arranged in the order of the luminaire numbers in the luminaire cluster. All commands after arrangement are combined to form the continuous lighting command set of the luminaire cluster.

[0049] The continuous lighting instruction set execution signal is encapsulated to obtain the continuous lighting control signal for the luminaire cluster; According to the preset communication transmission rules between the lighting cluster control terminal and the lighting execution terminal, each independent control instruction in the continuous lighting instruction set is formatted in sequence; all the formatted instructions are packaged into a complete signal packet that can be directly transmitted; this signal packet is the continuous lighting control signal that can be received and executed by the lighting cluster execution terminal.

[0050] like Figure 2 The diagram shown is a functional block diagram of a lighting cluster intelligent control system based on multi-source information provided in an embodiment of the present invention.

[0051] The intelligent control system 100 for lighting clusters based on multi-source information described in this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent control system 100 for lighting clusters based on multi-source information may include a global monitoring and synchronization module 101, an activation duration evaluation module 102, a state transition identification module 103, a trajectory continuity backtracking module 104, an attenuation dimming control module 105, and a continuous lighting control module 106. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, stored in the memory of the electronic device.

[0052] In this embodiment, the functions of each module / unit are as follows: The full-domain monitoring synchronization module 101 is used to perform dynamic full-domain monitoring of the target area of ​​the lighting cluster and to synchronize the monitoring results in the time domain to obtain the synchronous sensing data stream of the target area. The synchronous sensing data stream includes target trajectory prediction data with directional attributes and area existence status data without directional attributes. The activation duration evaluation module 102 is used to evaluate the activation duration of the lighting cluster based on the target trajectory prediction data, and obtain the dynamic activation duration of the lighting cluster. The state transition identification module 103 is used to identify the critical moment of the state data in the region based on the time window of the dynamic activation duration, so as to obtain the state transition moment point of the target region. The trajectory continuity backtracking module 104 is used to perform backtracking analysis on the trajectory continuity of the target trajectory prediction data within the dynamic activation duration when the state transition time point is later than the termination time of the dynamic activation duration, so as to obtain the trajectory continuity characteristics of the target trajectory prediction data. The attenuation dimming control module 105 is used to perform speed correlation mapping on the power parameters of the lighting cluster when the trajectory continuity characteristic is reverse direction, to obtain the attenuation control curve of the lighting cluster, and to generate a dynamic dimming control signal for the lighting cluster based on the attenuation control curve. The continuous lighting control module 106 is used to perform response time analysis on the maintenance parameters of the lighting cluster when the trajectory continuity characteristic is trajectory interruption, to obtain the interruption response maintenance duration of the lighting cluster, and to obtain the continuous lighting control signal of the lighting cluster based on the interruption response maintenance duration.

[0053] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0054] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0055] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0056] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0057] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for intelligent control of a cluster of luminaires based on multi-element information, characterized in that, The method includes: S1. Perform dynamic full-domain monitoring on the target area of ​​the lighting cluster and synchronize the monitoring results in the time domain to obtain the synchronous sensing data stream of the target area. The synchronous sensing data stream includes target trajectory prediction data with directional attributes and area existence status data without directional attributes. S2. Based on the target trajectory prediction data, evaluate the activation duration of the lighting cluster to obtain the dynamic activation duration of the lighting cluster. S3. Based on the time window of dynamic activation retention duration, identify the critical moment of the state data of the region to obtain the state transition moment of the target region. S4. When the state transition time point is later than the end time of the dynamic activation hold duration, backtracking analysis is performed on the trajectory continuity of the target trajectory prediction data within the dynamic activation hold duration to obtain the trajectory continuity characteristics of the target trajectory prediction data. S5. When the trajectory continuity characteristic is reverse direction, speed correlation mapping is performed on the power parameters of the lighting cluster to obtain the attenuation control curve of the lighting cluster, and dynamic dimming control signal of the lighting cluster is generated based on the attenuation control curve. S6. When the trajectory continuity characteristic is trajectory interruption, the response time analysis is performed on the maintenance parameters of the lighting cluster to obtain the interruption response maintenance duration of the lighting cluster, and the continuous lighting control signal of the lighting cluster is obtained based on the interruption response maintenance duration. 2.The multi-element information based intelligent control method of luminaire cluster of claim 1, wherein, The process of obtaining the synchronous sensing data stream of the target area is as follows: The target area of ​​the lighting cluster is collected by full-domain sensing to obtain multi-source sensing data of the target area. By performing time-series alignment of multi-source sensing data, a synchronous sensing data stream for the target area is obtained; Oriented trajectory analysis is performed on the synchronous sensing data stream to obtain target trajectory prediction data carrying directional attributes in the synchronous sensing data stream; Spatial occupancy detection is performed on the synchronous sensing data stream to obtain the existence status data of regions in the synchronous sensing data stream that do not carry directional attributes. 3.The multi-element information based intelligent control method of luminaire cluster of claim 1, wherein, The process of obtaining the dynamic activation duration of the lighting cluster is as follows: The target trajectory prediction data is segmented into trajectory segments to obtain a sequence of trajectory segments for the target trajectory prediction data; Perform direction comparison on adjacent trajectory segments in the trajectory segment sequence to obtain direction consistency markers for adjacent trajectory segments; Extract the activation hold interval corresponding to the directional consistency marker, and use the activation hold interval as the dynamic activation reference duration of the lighting cluster; Based on the dynamic activation baseline duration, the activation duration of the lighting cluster is evaluated to generate the dynamic activation retention duration of the lighting cluster. 4.The multi-element information based intelligent control method of luminaire cluster of claim 1, wherein, The process of obtaining the state transition time points of the target region is as follows: Within the time window of dynamic activation duration, the status data of the area is identified to obtain the area occupancy status of the lighting cluster at different times. Perform state difference analysis on the state values ​​of adjacent time points in the region's occupancy state to obtain the state change amount of adjacent time points; Based on the state change amount, if the absolute value of the state change amount is greater than the preset threshold, it is determined to be a state transition, and the transition time point of the region's occupancy state is marked to obtain the state transition time point of the target region. 5.The multi-element information based intelligent control method of luminaire cluster of claim 1, wherein, The process of obtaining the trajectory continuity characteristics of the target trajectory prediction data is as follows: Based on the termination time of the dynamic activation hold duration, the temporal difference of the state transition time point is measured to obtain the temporal offset of the state transition time point relative to the termination time. Based on the time offset, the state transition time point and the termination time are judged to exceed the state, and the judgment result of the state transition time point exceeding the termination time is obtained. When the judgment result exceeds the termination time, the target trajectory prediction data is truncated according to the time boundary of the dynamic activation duration to obtain the trajectory data segment within the dynamic activation duration. Trajectory morphology analysis is performed on trajectory data segments to obtain trajectory direction characteristics within the trajectory data segments; By identifying the continuity of trajectory characteristics, the trajectory continuity characteristics of the target trajectory prediction data are obtained. 6.The multi-element information based intelligent control method of luminaire cluster of claim 5, wherein, The process of obtaining the trajectory direction features from the trajectory data segment is as follows: Discrete sampling is performed on the trajectory data segment to obtain the trajectory point sequence of the trajectory data segment; Perform direction fitting on the trajectory point sequence to obtain the dominant direction vector of the trajectory point sequence; The dominant direction vector is used to determine the trajectory direction, thus obtaining the trajectory direction characteristics of the trajectory data segment.

7. The multi-element information based intelligent control method of a luminaire cluster as claimed in claim 1, wherein, The process of obtaining the attenuation control curve of the lighting cluster is as follows: When the trajectory continuity characteristic is reverse direction, the power parameters of the lighting cluster are mapped to obtain the speed parameters of the lighting cluster. The speed parameters and the power parameters of the lighting cluster are correlated to obtain the speed-power correlation between the speed parameters and the power parameters; Based on the speed-power correlation, the power parameters are curve-fitted to obtain the attenuation control curve of the lighting cluster.

8. The intelligent control method for lighting clusters based on multi-source information as described in claim 1, characterized in that, The process of generating dynamic dimming control signals for the lighting cluster based on the attenuation control curve is as follows: Discretize the attenuation control curve to obtain the control node parameter set of the attenuation control curve; Based on the control node parameter set, the attenuation control curve is divided into time intervals to obtain the power configuration sequence of the lighting cluster; The power configuration sequence is compiled into control instructions to obtain the dynamic dimming control signal for the lighting cluster.

9. The intelligent control method for lighting clusters based on multi-source information as described in claim 7, characterized in that, The process of obtaining the continuous lighting control signal for the lighting cluster based on the duration of the interruption response is as follows: When the trajectory continuity feature indicates trajectory interruption, obtain the interruption start time from the trajectory continuity feature; Based on the interruption start time, the maintenance parameters of the lighting cluster are anchored to obtain the maintenance reference duration of the lighting cluster; Based on the maintenance reference duration, the response interval is divided between the maintenance reference duration and the interruption start time to obtain the response time window of the lighting cluster; Within the response time window, the duration of the maintenance parameters is calibrated to obtain the interruption response maintenance duration of the lighting cluster; Based on the duration of the interrupt response, the lighting cluster is controlled and encoded to obtain the continuous lighting instruction set of the lighting cluster; The continuous lighting instruction set execution signal is encapsulated to obtain the continuous lighting control signal for the luminaire cluster.

10. A lighting cluster intelligent control system based on multi-source information, characterized in that, The system for implementing the intelligent control method for lighting clusters based on multi-source information as described in claim 1 includes: The full-domain monitoring and synchronization module is used to dynamically monitor the target area of ​​the lighting cluster and synchronize the monitoring results in the time domain to obtain the synchronous sensing data stream of the target area. The synchronous sensing data stream includes target trajectory prediction data with directional attributes and area existence status data without directional attributes. The activation duration evaluation module is used to evaluate the activation duration of the lighting cluster based on the target trajectory prediction data, and obtain the dynamic activation duration of the lighting cluster. The state transition identification module is used to identify the critical moments of state data in a region based on a time window of dynamic activation duration, and to obtain the state transition moment points of the target region. The trajectory continuity backtracking module is used to perform backtracking analysis on the trajectory continuity of the target trajectory prediction data within the dynamic activation duration when the state transition time point is later than the end time of the dynamic activation duration, so as to obtain the trajectory continuity characteristics of the target trajectory prediction data. The attenuation dimming control module is used to perform speed correlation mapping on the power parameters of the lighting cluster when the trajectory continuity characteristic is reversed, to obtain the attenuation control curve of the lighting cluster, and to generate the dynamic dimming control signal of the lighting cluster based on the attenuation control curve. The continuous lighting control module is used to analyze the response time of the maintenance parameters of the lighting cluster when the trajectory continuity characteristic is trajectory interruption, to obtain the interruption response maintenance duration of the lighting cluster, and to obtain the continuous lighting control signal of the lighting cluster based on the interruption response maintenance duration.

Images