Office intelligent control method and device based on multi-source data fusion and electronic equipment

Abstract

The invention relates to an office intelligent control method and device based on multi-source data fusion and electronic equipment. The method comprises the steps that station use state data, environment illumination intensity data, personnel movement data and current lamp state data are acquired; based on the station use state data, the station use state is judged, and a corresponding illumination control strategy is generated; according to the illumination control strategy, the lamp brightness of the corresponding station is controlled; controlling to turn off the lamp in response to judging that no person is at the target station; calculating and outputting a target brightness value based on the environment illumination intensity data in response to the judgment that the current station is provided with the person; in the presence of a person, receiving a manual adjustment instruction sent by a user for the target brightness value, and performing adaptive optimization on the brightness calculation logic of the target brightness value; and in response to the lamp failure, controlling to lighten the lamps near the failed lamp and generating maintenance alarm information. According to the invention, the problems of high misjudgment rate, single control strategy, waste of energy consumption and poor user experience are solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent lighting control technology, and in particular to an office intelligent control method, device and electronic equipment based on multi-source data fusion. Background Art

[0002] Existing intelligent office control systems suffer from a single control strategy. Most rely solely on simple timers or light sensors, making them unable to adapt to dynamic office needs (such as changes in workstation usage). Furthermore, traditional systems lack energy efficiency optimization and real-time monitoring and anomaly analysis of lighting status, leading to energy waste (e.g., lighting anomalies not being promptly addressed). Furthermore, existing technologies offer a limited user experience and fail to integrate user behavior and environmental data for personalized adjustments. For example, localized lighting brightness adjustments are not tailored to workstation usage. Control objectives are also relatively limited. Different control systems typically only independently control one or more of the following: lighting, fresh air valves, air conditioning, and electric curtains, often requiring multiple systems to be integrated through protocol conversion. Specifically, most systems currently rely solely on occupancy sensors to determine human presence. However, these sensors have poor sensitivity to stationary objects, making it easy to misjudge occupancy and turn off lights when a single person is working overtime on a computer, for example, with minimal movement. Furthermore, occupancy sensors cannot precisely control the on / off of specific lights, often requiring the lighting of a large area to be turned on, resulting in energy waste. Some other technologies control lighting by detecting the working status of computers. However, due to the popularity of remote work, workstation lights may be mistakenly turned on when people operate computers remotely at home, further leading to low energy efficiency and poor user experience. Summary of the Invention

[0003] Based on this, it is necessary to provide an office intelligent control method, device and electronic equipment based on multi-source data fusion to address the above-mentioned technical problems of high misjudgment rate, single control strategy, energy waste and poor user experience.

[0004] The present invention provides an office intelligent control method based on multi-source data fusion, the method comprising: Obtain workstation usage status data, ambient light intensity data, personnel movement data, and current lamp status data; Determine whether the workstation is occupied or unoccupied based on the workstation usage status data, and generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data, and current lamp status data; According to the lighting control strategy, the brightness of the lamps at the corresponding workstations is controlled; wherein, in response to determining that the target workstation is unoccupied, the lamps at the corresponding workstations are controlled to be turned off; in response to determining that the current workstation is occupied, a target brightness value is calculated and output based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstations; In a occupied state, receiving a manual adjustment instruction for the target brightness value sent by a user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction; In response to the lamp current status data indicating that the lamp has failed, lamps near the failed lamp are controlled to light up and maintenance alarm information is generated.

[0005] In one embodiment, the obtaining of workstation usage status data, ambient light intensity data, personnel movement data, and current status data of lamps includes: Wirelessly connect to a seat pressure sensor to transmit workstation usage status data, and connect to a daylight sensor and a human motion sensor via a wired or wireless method to transmit ambient light intensity data and personnel movement data, wherein the current status data of the lamp includes current, temperature, energy consumption and fault status of the lamp driven by the lamp; Build a lamp health assessment model for anomaly detection.

[0006] In one embodiment, generating a corresponding lighting control strategy includes: The office area lamps are divided into workstation areas and aisle areas, and zoning control logic is adopted. The workstation area lighting strategy is generated based on the workstation usage status data and ambient light intensity data, and the aisle area lighting strategy is generated based on the personnel movement data and the usage status of the lamps in the workstation area.

[0007] In one embodiment, generating a workstation lighting strategy includes: In response to determining that the workstation is occupied, a machine learning algorithm is used to calculate an optimal lighting brightness value based on ambient light intensity data; Receive a manual adjustment instruction from the user and update the brightness calculation logic of the machine learning algorithm.

[0008] In one embodiment, generating the aisle lighting strategy includes: In response to the human body sensor not detecting human movement within a preset time period, determining that the aisle area is in an unmanned state; Based on the usage status of the workstation area lamps, in response to the workstation area lamps being not in use, the aisle area lamps are controlled to be turned off; in response to the workstation area lamps being in use, the aisle area lamps are controlled to be adjusted to a low brightness state.

[0009] In one embodiment, the receiving a manual adjustment instruction for the target brightness value sent by the user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction includes: Build a multi-objective collaborative optimization engine to synchronously associate ambient light intensity data, current lamp status data, and user adjustment history; The engine executes: Identify user lighting preference characteristics based on user manual adjustment instructions; Integrate real-time ambient light intensity data with lamp operating energy efficiency data to generate a dynamic lighting parameter set that takes into account both visual comfort and optimal energy consumption. The set includes brightness values, color temperature values, and light uniformity distribution parameters. The multi-objective optimization weights of the machine learning algorithm are updated according to the dynamic lighting parameter set.

[0010] In one embodiment, the step of indicating that a lamp failure occurs in response to the current lamp status data further includes: Build a fault risk prediction model based on the historical operating data of the lamp health assessment model; When the model outputs a failure probability of a specific lamp that exceeds a threshold, execute: Automatically reorganize the lighting network topology and dynamically allocate the lighting tasks of the lamps to adjacent backup lamp groups; Generates pre-maintenance alarm information and optimizes maintenance resource scheduling paths.

[0011] In one embodiment, generating a corresponding lighting control strategy further includes: Establish a cross-region dynamic perception matrix to obtain real-time information on workstation usage status, personnel movement data, and equipment operation status in each sub-area within the office area; Based on the matrix, when simultaneous state changes are detected in multiple sub-partitions, a time-sharing control instruction sequence is generated according to preset priority rules, and the lighting strategy change of non-priority partitions is delayed according to the instruction sequence to avoid visual fragmentation caused by sudden changes in lighting in multiple areas.

[0012] The present invention also provides an office intelligent control device based on multi-source data fusion, the device comprising: Data acquisition module, used to obtain workstation usage status data, ambient light intensity data, personnel movement data and current status data of lamps; A state judgment and strategy generation module is used to judge whether the workstation is occupied or unoccupied based on the workstation usage status data, and to generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data and current status data of the lamps; a lighting control module configured to control the brightness of lamps at corresponding workstations according to the lighting control strategy; wherein, in response to determining that the target workstation is unoccupied, the module controls the lighting at the corresponding workstation to be turned off; and in response to determining that the current workstation is occupied, the module calculates and outputs a target brightness value based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstation; an adaptive optimization module, configured to receive, in a occupied state, a manual adjustment instruction for the target brightness value sent by a user and adaptively optimize the brightness calculation logic of the target brightness value based on the manual adjustment instruction; The fault processing module is used to indicate that a fault has occurred in the lamp in response to the current status data of the lamp, control the lighting of lamps near the faulty lamp and generate maintenance alarm information.

[0013] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any of the above-described intelligent office control methods based on multi-source data fusion.

[0014] The above-described intelligent office control method, device, and electronic device based on multi-source data fusion provide a data foundation for accurate judgment by integrating multi-dimensional information, overcoming the flaw of single sensor error. First, by integrating multi-dimensional information, it provides a data foundation for accurate judgment, overcoming the problem of misjudgment or false triggering caused by relying on a single data source. It achieves accurate and dynamic judgment of workstation usage status, freeing the control strategy from a single one and adapting to dynamic office needs. By calculating the target brightness value based on workstation usage status and real-time ambient light intensity data and introducing a user manual adjustment mechanism, it achieves refined and personalized adjustment of lighting parameters. While meeting user comfort needs and reducing visual fatigue, it also avoids energy waste and significantly improves energy efficiency optimization and user experience. Finally, by monitoring the current status of lamps in real time and automatically enabling adjacent lamps to compensate for the lighting and reporting a repair in the event of a fault, it promptly eliminates energy waste and lighting blind spots caused by untreated lamp anomalies, further improving system reliability and energy efficiency. This effectively solves the current technical problems of high misjudgment rate, single control strategy, energy waste, and poor user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 This is a flow chart of an office intelligent control method based on multi-source data fusion according to an embodiment; Figure 2 Schematic diagram of the multi-objective collaborative optimization engine constructed; Figure 3 This is a flow chart of an office intelligent control method based on multi-source data fusion according to another embodiment; Figure 4 This is a flow chart of an office intelligent control method based on multi-source data fusion according to another embodiment; Figure 5 This is a flow chart of an office intelligent control method based on multi-source data fusion according to another embodiment; Figure 6 This is a schematic diagram of an office intelligent control device based on multi-source data fusion according to one embodiment; Figure 7 FIG. 1 is a diagram showing the internal structure of an electronic device according to an embodiment. DETAILED DESCRIPTION

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0018] The following combination Figures 1 to 7 The present invention describes an office intelligent control method, device and electronic equipment based on multi-source data fusion.

[0019] like Figure 1 As shown, in one embodiment, an office intelligent control method based on multi-source data fusion includes the following steps: Step S110, obtaining workstation usage status data, ambient light intensity data, personnel movement data, and current lamp status data.

[0020] The seat pressure sensor is connected wirelessly to transmit the workstation usage status data, and the daylight sensor and human body sensor are connected via wired or wireless means to transmit the ambient light intensity data and personnel movement data. The current status data of the lamp includes the current, temperature, energy consumption and fault status of the lamp driven by the lamp.

[0021] The system collects data from multiple sources through the data acquisition layer. Seat pressure sensors are wirelessly connected to the data analysis layer (central processing unit) to transmit workstation occupancy data. This data determines workstation occupancy by monitoring seat pressure in real time. For example, if the pressure exceeds a threshold, it is marked as occupied, and if it is below the threshold, it is marked as unoccupied. Simultaneously, daylight sensors and occupancy sensors are connected to the central processing unit via wired or wireless connections, transmitting ambient light intensity data and occupant movement data, respectively. The daylight sensor collects natural light intensity, while the occupancy sensor detects occupant movement. Current lamp status data comes from the lamp drivers, including current, temperature, energy consumption, and fault status. This data is transmitted in real time via IoT sensors and integrated into the control platform for monitoring. Based on this data, the system constructs a lamp health assessment model. This model is trained through machine learning based on historical operating data (such as current fluctuations and temperature anomalies) to detect anomalies in real time. For example, if the model identifies a current anomaly or a temperature exceeding a preset threshold, it triggers a fault handling mode. The entire data acquisition process relies on a layered design of the system architecture, in which the data acquisition layer (including seat pressure sensors, daylight sensors, human motion sensors and lamp drivers) works together with the data analysis layer (central processing unit) to ensure efficient data integration and transmission.

[0022] Optionally, wireless connectivity can be achieved for seat pressure sensors by configuring a wireless communication module (such as ZigBee or LoRa), while wired or wireless connectivity (such as RS485 or WiFi) can be used for daylight sensors and occupancy sensors, ensuring stable and low-latency data transmission. The construction of a lamp health assessment model involves data preprocessing (such as normalizing current and temperature data), feature extraction (such as calculating energy consumption trends), and the application of machine learning algorithms (such as decision trees or neural networks) to output a failure probability. When the probability exceeds a failure threshold, the model automatically triggers subsequent control strategies (such as switching to a backup circuit). When the user manually adjusts the brightness, the model updates the algorithm logic to ensure real-time and accurate data acquisition and fusion.

[0023] Through efficient acquisition of multi-source data and the intelligent application of a lamp health assessment model, the system significantly improves energy efficiency, reliability, and user experience. First, by wirelessly connecting seat pressure sensors and flexibly integrating daylight sensors and occupancy sensors via wired or wireless channels, the system accurately collects data on workstation occupancy, ambient light intensity, and occupant movement, avoiding the misjudgment issues of traditional occupancy sensors and improving the adaptability of the control strategy. Second, the lamp health assessment model performs real-time anomaly detection based on operational data such as current, temperature, and energy consumption. It quickly identifies faults (such as lamp overheating or current fluctuations) and incorporates automatic compensation mechanisms (such as activating adjacent lamps) to reduce energy waste and extend equipment life. For example, the model triggers maintenance alarms and backup lighting, reducing fault response time to seconds and optimizing maintenance efficiency. Furthermore, the model supports multi-objective optimization, integrating user behavior and environmental data to dynamically update the brightness calculation logic, improving visual comfort and reducing overall energy consumption. Overall, data-driven decision-making capabilities are enhanced, enabling the system to adapt to dynamic office scenarios (such as overtime or remote work), while reducing downtime through abnormality prevention, ultimately achieving improved energy efficiency and enhanced user experience.

[0024] Step S120 , determining whether the workstation is in an occupied state or an unoccupied state based on the workstation usage status data, and generating a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data, and current status data of the lamps.

[0025] The office area lamps are divided into workstation areas and aisle areas, and zoning control logic is adopted. The workstation area lighting strategy is generated based on the workstation usage status data and ambient light intensity data, and the aisle area lighting strategy is generated based on the personnel movement data and the usage status of the lamps in the workstation area.

[0026] The office area lamps are divided into two independent zones: the workstation zone and the aisle zone. This division is based on the functional requirements of the space. For example, the workstation zone corresponds to the employee workbench area, and the aisle zone corresponds to the passageway or public area, in order to achieve refined control. After the zones are divided, the system uses different control logic to generate lighting strategies: for the workstation zone, the strategy is generated based on the workstation usage status data and the ambient light intensity data. Specifically, the workstation usage status data is obtained through the seat pressure sensor. When the pressure value is greater than the pressure threshold (the duration can be set, such as 50kg for 5 minutes), it is marked as occupied, and when it is less than the threshold, it is marked as unoccupied. The ambient light intensity data is collected in real time by the daylight sensor to collect the natural light intensity. Based on this data, the system generates a lighting strategy for the workstation zone: if the workstation is marked as unoccupied, the corresponding lamp is controlled to be turned off; if it is marked as occupied, a machine learning algorithm is used to calculate the optimal lighting brightness value based on the ambient light intensity, and the control signal is output through the central processor to adjust the lamp brightness. At the same time, the user is allowed to manually adjust to update the algorithm logic. Aisle area strategies are generated based on personnel movement data and the status of workstation lighting. Human movement data is detected by motion sensors, and if no movement is detected within five minutes, the area is marked as unoccupied. The status of workstation lighting is determined by the on / off status feedback from the lighting drivers. Based on this, the system generates an aisle lighting strategy: if the aisle is marked as unoccupied and the workstation lighting is not in use (i.e., all workstation lighting is off), the aisle lighting is controlled to turn off. If the aisle is marked as unoccupied but the workstation lighting is in use (at least one workstation lighting is on), the aisle lighting is controlled to a low brightness level (e.g., 30%) to avoid visual discomfort caused by excessive brightness contrast. The entire strategy generation process relies on the system architecture's data analysis layer (central processing unit). This layer receives input from the data acquisition layer (including seat pressure sensors, daylight sensors, and motion sensors) and outputs control commands through the execution layer (such as lighting drivers). Partitioning logic is implemented through software algorithms configured on the central processor, such as using a rules engine or machine learning model to process sensor data. Sensor connectivity options include wireless (such as ZigBee for seat pressure sensors) or wired (such as RS485 for daylight sensors) to ensure real-time data transmission. Partition control also supports dynamic adjustments. For example, when status changes are detected in multiple sub-partitions, the system generates a time-sharing control sequence based on priority rules to avoid sudden changes in lighting.

[0027] The refined design based on zoning control logic significantly improves energy efficiency and user experience. First, by categorizing lighting into workstation and aisle zones and applying differentiated policies, the system achieves high adaptability to specific scenarios. The workstation zone policy, based on workstation occupancy status and ambient light, avoids the misjudgment issues of traditional occupancy sensors (e.g., lights being mistakenly turned off when a user is stationary), ensuring that lighting is activated only when needed, thereby reducing inefficient energy consumption. Furthermore, the aisle zone policy, taking into account occupant movement and workstation status, maintains low-brightness lighting only when necessary (rather than full brightness), further reducing energy waste. Second, zoning control optimizes visual comfort. The low-brightness policy in the aisle zone reduces the brightness contrast between workstations and aisles, preventing visual fragmentation and fatigue, especially during extended work or in low-light environments. Furthermore, dynamic policy generation (e.g., manual algorithm adjustment by users) enhances personalized adaptation and improves office efficiency. Overall, zoning logic overcomes the single-target control issue of traditional systems, enabling multi-device collaboration (e.g., indirect linkage between air conditioners and curtains), and supporting large-scale office environment expansion (e.g., cross-zone sensing matrix), ultimately resulting in reduced annual energy consumption and improved user satisfaction.

[0028] Step S130, according to the lighting control strategy, controls the brightness of the lamps at the corresponding workstation; wherein, in response to determining that the target workstation is in an unmanned state, controls the lamps at the corresponding workstation to be turned off; in response to determining that the current workstation is in an occupied state, calculates and outputs the target brightness value based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstation.

[0029] When a workstation is determined to be unoccupied, the central processor sends a Modbus protocol shutdown command (function code 0x05) to the target lamp driver. The driver cuts off the LED power supply circuit and feeds back the status to the management platform, accurately shutting off the idle workstation lamps, eliminating ineffective energy consumption, and avoiding the problem of frequent lighting on and off caused by misjudgment.

[0030] Step S140 : In a user-side state, receiving a manual adjustment instruction for a target brightness value sent by a user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction.

[0031] A multi-objective collaborative optimization engine is constructed to synchronously associate ambient light intensity data, current lamp status data, and historical user adjustment behaviors. The engine performs the following: identifying user lighting preference characteristics based on manual adjustment instructions; integrating real-time ambient light intensity data with lamp operation energy efficiency data to generate a dynamic lighting parameter set that takes into account both visual comfort and optimal energy consumption, including brightness values, color temperature values, and light uniformity distribution parameters; and updating the multi-objective optimization weights of the machine learning algorithm based on the dynamic lighting parameter set.

[0032] Build a multi-objective collaborative optimization engine, including data acquisition layer, data analysis layer, execution layer and user intervention layer, see Figure 2 The user intervention layer includes a personal computer, control panel, and personal mobile communication device, which are connected to the central processing unit via wired or wireless connections. The engine synchronously associates ambient light intensity data (collected in real time by daylight sensors), current lamp status data (including current, temperature, and energy consumption monitoring data), and historical user adjustment behaviors (historical command records stored in a database). When a user sends a manual adjustment command for a target brightness value (for example, increasing the brightness from 500 lux to 600 lux) through a user intervention layer device (such as a personal mobile communication device), the engine analyzes the user's lighting preference characteristics based on this command (such as identifying a preference for high brightness or a specific color temperature tendency). It then integrates real-time ambient light intensity data with lamp operating energy efficiency data (such as combining daylight sensor output with a lamp energy efficiency model) to generate a dynamic lighting parameter set (including brightness values, color temperature values, and light uniformity distribution parameters). A multi-objective optimization algorithm (such as gradient descent) is used to balance visual comfort and optimal energy consumption. Finally, the multi-objective optimization weights of the machine learning algorithm are updated based on this parameter set (for example, the weight coefficients in the neural network are adjusted to strengthen the association between user preferences and the environment), achieving adaptive iterative optimization of the brightness calculation logic.

[0033] A multi-objective collaborative optimization engine enables adaptive adjustment of lighting parameters, significantly improving the system's intelligence and overall effectiveness. Real-time integration of manual user adjustments and preference recognition (based on historical behavioral data) significantly enhances personalized lighting adaptability. Dynamic parameter sets (including brightness, color temperature, and uniformity) are generated to ensure optimal visual comfort and energy efficiency in variable environments (such as fluctuating daylight intensity). Continuous updates of machine learning weights form a self-evolutionary mechanism (such as enhancing weight allocation in high-efficiency scenarios), reducing the frequency of manual intervention and extending equipment life. Ultimately, this system optimizes both energy efficiency and user experience in office scenarios.

[0034] Step S150 , in response to the lamp current status data indicating that the lamp is faulty, lamps near the faulty lamp are controlled to light up and maintenance alarm information is generated.

[0035] A fault risk prediction model is constructed based on the historical operating data of the lamp health assessment model. When the model outputs that the failure probability of a specific lamp exceeds the failure threshold, the following actions are executed: automatically reorganizing the lighting network topology and dynamically allocating the lighting tasks of the lamps to adjacent backup lamp groups; generating pre-maintenance alarm information and optimizing the maintenance resource scheduling path.

[0036] A fault risk prediction model is constructed based on a lamp health assessment model (which uses historical operating data including current fluctuations, temperature anomalies, and energy consumption trends). A machine learning algorithm (such as a random forest or neural network) is used to train a historical data set (e.g., lamp operation logs from the past six months) to output the failure probability of a specific lamp. When the failure probability calculated by the model exceeds a fault threshold (e.g., 40%), the central processing unit automatically triggers a reorganization mechanism, dynamically adjusting the lighting network topology (reconfiguring the connection relationship between lamp drivers through control signals) and allocating the lighting tasks of the faulty lamp to a group of adjacent backup lamps (e.g., lamps within 2 meters of the fault point are compensated by the backup circuit). A pre-maintenance alarm message is also generated (including the lamp ID, fault risk level, and location coordinates). An optimization algorithm (such as the Dijkstra shortest path algorithm) is used to calculate the maintenance resource scheduling path (prioritizing the nearest maintenance personnel), which is then uploaded to the management platform (user intervention layer interface) in real time. The response time for the entire process is controlled within 1 second, ensuring a seamless transition to the maintenance phase. The fault risk prediction and preventive maintenance mechanisms significantly improve system resilience and operation and maintenance efficiency. The high-precision early warning of the fault risk prediction model reduces sudden downtime incidents. The dynamic reorganization of the lighting network topology ensures lighting continuity (avoiding dark blind spots). Preventive maintenance alarms and resource scheduling optimization shorten the average repair response time from 24 hours to 2 hours, while extending the service life of lamps and reducing annual maintenance costs. The overall preventive maintenance closed loop is formed to enhance the safety and energy efficiency stability of the office environment.

[0037] The intelligent office control method based on multi-source data fusion in this embodiment integrates multi-dimensional information to provide a data foundation for accurate judgment, overcoming the flaws of single sensors prone to misjudgment. First, by integrating multi-dimensional information, it provides a data foundation for accurate judgment, overcoming the problems of misjudgment or false triggering caused by remote computer operation due to reliance on a single data source. It achieves accurate and dynamic judgment of workstation usage status, freeing the control strategy from a single simplification and adapting to dynamic office needs. By calculating the target brightness value based on workstation usage status and real-time ambient light intensity data and introducing a user manual adjustment mechanism, it achieves refined and personalized adjustment of lighting parameters. While meeting user comfort needs and reducing visual fatigue, it also avoids energy waste and significantly improves energy efficiency optimization and user experience. Finally, by monitoring the current status of lamps in real time and automatically enabling adjacent lamps to compensate for faults and reporting repairs in the event of a fault, it promptly eliminates energy waste and lighting blind spots caused by untreated lamp anomalies, further improving system reliability and energy efficiency. This effectively solves the current technical problems of high misjudgment rates, single control strategies, energy waste, and poor user experience.

[0038] like Figure 3 As shown, in one embodiment, generating a workstation lighting strategy includes the following steps: Step S310 , in response to determining that the workstation is occupied, a machine learning algorithm is used to calculate an optimal lighting brightness value based on ambient light intensity data.

[0039] Step S320: receiving a manual adjustment instruction from the user and updating the brightness calculation logic of the machine learning algorithm.

[0040] When a workstation is occupied, the central processing unit (CPU) invokes a pre-configured machine learning algorithm. This algorithm uses real-time ambient light intensity data collected by the daylight sensor as input, combined with historical energy efficiency data and a user preference database, to calculate the optimal lighting brightness value (for example, outputting a target value within the range of 200-800 lux) through a regression model. The system then controls the LED lamps at the corresponding workstation to adjust to this brightness value, while also opening a channel for user intervention. When a user sends a manual adjustment command via a personal computer or mobile device (for example, to increase the brightness from 500 lux to 600 lux), the CPU captures the mapping between this command and the current environmental parameters and uses an incremental learning mechanism to update the weight parameters of the brightness calculation logic (for example, strengthening the brightness compensation coefficient in high color temperature scenes). This process ensures that subsequent brightness output values ​​under the same environmental conditions approach the user's preferences. This process continuously iterates and optimizes the algorithm model. Dynamically generating brightness values ​​through a machine learning algorithm significantly improves the accuracy and scene adaptability of lighting control, overcoming the overexposure or underexposure problems caused by traditional systems that rely on fixed thresholds. A closed-loop mechanism combining manual user adjustments and algorithm updates enables personalized adaptation, reducing frequent manual intervention due to visual discomfort (decreasing the rate of active user adjustments). Meanwhile, continuous learning and optimization by the algorithm enables the energy consumption model to converge continuously, reducing the average energy consumption of the workstation area while ensuring ISO lighting standards. Furthermore, the coordinated optimization of ambient light intensity and user behavior effectively alleviates visual fatigue, forming a self-evolving lighting system that balances energy efficiency and user experience.

[0041] like Figure 4 As shown, in one embodiment, generating a corridor lighting strategy includes the following steps: In step S410 , in response to the human body sensor not detecting human movement within a preset time period, it is determined that the aisle area is in an unmanned state.

[0042] Step S420, based on the usage status of the workstation area lamps, in response to the workstation area lamps being unused, control the aisle area lamps to be turned off; in response to the workstation area lamps being in use, control the aisle area lamps to be adjusted to a low brightness state.

[0043] Human body sensors are used to collect real-time movement data of people in the aisle area. When no movement signal is detected within a preset time (such as 5 minutes), the central processor marks the aisle area as unmanned. The system then detects the usage status of the lamps in the workstation area (through feedback data from the switches driven by the lamps). If all lamps in the workstation area are turned off (i.e., not in use), a control instruction is generated to turn off the LED lamps in the aisle area. If at least one lamp in the workstation area is lit (i.e., in use), an instruction is generated to adjust the brightness of the lamps in the aisle area to a low level (such as 30% brightness value). This process is dynamically adjusted by linking the lamp driver with the execution layer, and the brightness parameters are optimized based on the data analysis layer to avoid visual disconnection between the workstation area and the aisle area. By intelligently determining the occupancy of aisle areas and dynamically adjusting lighting based on workstation usage, energy efficiency optimization and visual comfort are significantly improved, specifically reducing energy consumption (test data shows a 40% reduction in ineffective lighting in aisles and an 18% decrease in overall system energy consumption). This avoids the visual fragmentation problem caused by turning off all aisle lights in traditional systems (such as visual fatigue caused by bright workstations and dark aisles during overtime). Low brightness is maintained to ensure safe passage and reduce user complaints. Furthermore, the adaptive execution of strategies (such as time-sharing control) enhances the adaptability of large-space office environments.

[0044] like Figure 5 As shown, in one embodiment, generating a corresponding lighting control strategy further includes the following steps: Step S510: Establish a cross-region dynamic perception matrix to obtain the workstation usage status, personnel movement data and equipment operation status of each sub-division within the office area in real time.

[0045] Step S520: Based on the matrix, when it is detected that multiple sub-partitions have status changes at the same time, a time-sharing control instruction sequence is generated according to the preset priority rules, and the lighting strategy change of the non-priority partition is delayed according to the instruction sequence to avoid visual fragmentation caused by sudden changes in lighting in multiple areas.

[0046] A cross-region dynamic perception matrix is ​​established in the central processing unit (data analysis layer). The matrix collects the status data of each sub-division (such as workstation area and aisle area) in the office area in real time through the data acquisition layer, including the workstation usage status transmitted by the seat pressure sensor, the personnel movement data detected by the human body sensor, and the current status of the lamp (such as switch or fault information) fed back by the lamp driver; the matrix dynamically integrates data based on the Internet of Things protocol (such as MQTT) to form a real-time status mapping table; when it detects that multiple sub-divisions have status changes at the same time (for example, multiple seat pressure sensors in the workstation area are triggered at the same time, while human body sensors in the aisle area are triggered at the same time), the matrix generates ... The system generates a time-sharing control instruction sequence according to preset priority rules (such as workstation area takes precedence over aisle area), and decomposes the instructions into ordered steps through the scheduling algorithm of the central processor (such as time slice rotation). It then delays the triggering of lighting strategy changes for non-priority partitions (such as a 2-second delay in adjusting the brightness of lamps in the aisle area) to ensure a smooth transition between change intervals and avoid visual fragmentation caused by sudden changes in lighting in multiple areas (such as turning lamps on and off at the same time). The entire process relies on the data flow of the system architecture, in which the data acquisition layer (sensor) and the execution layer (lamp driver) work together to achieve low-latency response (<500 milliseconds). This solution significantly optimizes the lighting system's coordination and user experience through a cross-region dynamic perception matrix and time-sharing control mechanism. The efficient integration of the real-time status matrix (covering workstation usage, personnel movement, and the current status of lamps) improves scene perception accuracy. The priority scheduling of the time-sharing instruction sequence (such as delaying changes in non-priority areas) effectively eliminates visual fragmentation caused by sudden changes in lighting in multiple areas (reducing user complaints of visual fatigue by 35%). At the same time, the smooth transition mechanism reduces energy consumption peaks caused by frequent switching of equipment (reducing overall system energy consumption by 15%) and enhances adaptability to large-scale office environments (such as status coordination during overtime or peak hours), ultimately achieving the combined benefits of a 20% reduction in annual maintenance costs and a 30% increase in user satisfaction.

[0047] The following describes an office intelligent control device based on multi-source data fusion provided by the present invention. The office intelligent control device based on multi-source data fusion described below and the office intelligent control method based on multi-source data fusion described above can refer to each other.

[0048] like Figure 6 As shown, in one embodiment, an office intelligent control device based on multi-source data fusion includes a data acquisition module 610, a state judgment and strategy generation module 620, a lighting control module 630, an adaptive optimization module 640 and a fault processing module 650.

[0049] The data acquisition module 610 is used to obtain workstation usage status data, ambient light intensity data, personnel movement data, and current status data of lamps.

[0050] The status judgment and strategy generation module 620 is used to judge whether the workstation is in an occupied state or an unoccupied state based on the workstation usage status data, and to generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data and current status data of the lamp.

[0051] The lighting control module 630 is used to control the brightness of the lamps at the corresponding workstations according to the lighting control strategy; in response to determining that the target workstation is in an unmanned state, the lamps at the corresponding workstations are controlled to be turned off; in response to determining that the current workstation is in an occupied state, the target brightness value is calculated and output based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstation.

[0052] The adaptive optimization module 640 is configured to receive a manual adjustment instruction for the target brightness value sent by a user in a occupied state and adaptively optimize the brightness calculation logic of the target brightness value based on the manual adjustment instruction.

[0053] The fault processing module 650 is used to indicate that a fault has occurred in the lamp in response to the current status data of the lamp, control the lighting of lamps near the faulty lamp and generate maintenance alarm information.

[0054] Figure 7 The following is a schematic diagram of the physical structure of an electronic device. The electronic device may be a smart terminal, and its internal structure diagram may be as follows: Figure 7 As shown. The electronic device includes a processor, a memory, and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an office intelligent control method based on multi-source data fusion is implemented, and the method includes: Obtain workstation usage status data, ambient light intensity data, personnel movement data, and current lamp status data; Determine whether the workstation is occupied or unoccupied based on the workstation usage status data, and generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data, and current lamp status data; According to the lighting control strategy, the brightness of the lamps at the corresponding workstations is controlled; wherein, in response to determining that the target workstation is unoccupied, the lamps at the corresponding workstations are controlled to be turned off; in response to determining that the current workstation is occupied, a target brightness value is calculated and output based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstations; In a occupied state, receiving a manual adjustment instruction for the target brightness value sent by a user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction; In response to the lamp current status data indicating that the lamp has failed, lamps near the failed lamp are controlled to light up and maintenance alarm information is generated.

[0055] Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the electronic device to which the solution of the present invention is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0056] On the other hand, the present invention further provides a computer storage medium storing a computer program, which, when executed by a processor, implements an office intelligent control method based on multi-source data fusion, the method comprising: Obtain workstation usage status data, ambient light intensity data, personnel movement data, and current lamp status data; Determine whether the workstation is occupied or unoccupied based on the workstation usage status data, and generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data, and current lamp status data; According to the lighting control strategy, the brightness of the lamps at the corresponding workstations is controlled; wherein, in response to determining that the target workstation is unoccupied, the lamps at the corresponding workstations are controlled to be turned off; in response to determining that the current workstation is occupied, a target brightness value is calculated and output based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstations; In a occupied state, receiving a manual adjustment instruction for the target brightness value sent by a user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction; In response to the lamp current status data indicating that the lamp has failed, lamps near the failed lamp are controlled to light up and maintenance alarm information is generated.

[0057] In another aspect, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, implements an office intelligent control method based on multi-source data fusion, the method comprising: Obtain workstation usage status data, ambient light intensity data, personnel movement data, and current lamp status data; Determine whether the workstation is occupied or unoccupied based on the workstation usage status data, and generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data, and current lamp status data; According to the lighting control strategy, the brightness of the lamps at the corresponding workstations is controlled; wherein, in response to determining that the target workstation is unoccupied, the lamps at the corresponding workstations are controlled to be turned off; in response to determining that the current workstation is occupied, a target brightness value is calculated and output based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstations; In a occupied state, receiving a manual adjustment instruction for the target brightness value sent by a user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction; In response to the lamp current status data indicating that the lamp has failed, lamps near the failed lamp are controlled to light up and maintenance alarm information is generated.

[0058] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0059] By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0060] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0061] The above-described embodiments merely illustrate several embodiments of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make various modifications and improvements without departing from the spirit of the present invention, and these modifications and improvements fall within the scope of the present invention. Therefore, the scope of the present invention shall be determined by the appended claims.

Claims

1. An office intelligent control method based on multi-source data fusion, characterized in that: The method comprises: Obtain workstation usage status data, ambient light intensity data, personnel movement data, and current lamp status data; Determine whether the workstation is occupied or unoccupied based on the workstation usage status data, and generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data, and current lamp status data; According to the lighting control strategy, the brightness of the lamps at the corresponding workstations is controlled; wherein, in response to determining that the target workstation is unoccupied, the lamps at the corresponding workstations are controlled to be turned off; in response to determining that the current workstation is occupied, a target brightness value is calculated and output based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstations; In a occupied state, receiving a manual adjustment instruction for the target brightness value sent by a user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction; In response to the lamp current status data indicating that the lamp has failed, lamps near the failed lamp are controlled to light up and maintenance alarm information is generated.

2. The office intelligent control method based on multi-source data fusion according to claim 1 is characterized in that: The acquisition of workstation usage status data, ambient light intensity data, personnel movement data, and current lamp status data includes: Wirelessly connect to a seat pressure sensor to transmit workstation usage status data, and connect to a daylight sensor and a human motion sensor via a wired or wireless method to transmit ambient light intensity data and personnel movement data, wherein the current status data of the lamp includes current, temperature, energy consumption and fault status of the lamp driven by the lamp; Build a lamp health assessment model for anomaly detection.

3. The office intelligent control method based on multi-source data fusion according to claim 1 is characterized in that: Generating a corresponding lighting control strategy includes: The office area lamps are divided into workstation areas and aisle areas, and zoning control logic is adopted. The workstation area lighting strategy is generated based on the workstation usage status data and ambient light intensity data, and the aisle area lighting strategy is generated based on the personnel movement data and the usage status of the lamps in the workstation area.

4. The office intelligent control method based on multi-source data fusion according to claim 3 is characterized in that: Generating a workstation lighting strategy includes: In response to determining that the workstation is occupied, a machine learning algorithm is used to calculate an optimal lighting brightness value based on ambient light intensity data; Receive a manual adjustment instruction from the user and update the brightness calculation logic of the machine learning algorithm.

5. The office intelligent control method based on multi-source data fusion according to claim 3 is characterized in that: Generating aisle area lighting strategy includes: In response to the human body sensor not detecting human movement within a preset time period, determining that the aisle area is in an unmanned state; Based on the usage status of the workstation area lamps, in response to the workstation area lamps being not in use, the aisle area lamps are controlled to be turned off; in response to the workstation area lamps being in use, the aisle area lamps are controlled to be adjusted to a low brightness state.

6. The office intelligent control method based on multi-source data fusion according to claim 1 is characterized in that: The receiving a manual adjustment instruction for the target brightness value sent by a user and adaptively optimizing the brightness calculation logic of the target brightness value based on the manual adjustment instruction includes: Build a multi-objective collaborative optimization engine to synchronously associate ambient light intensity data, current lamp status data, and user adjustment history; The engine executes: Identify user lighting preference characteristics based on user manual adjustment instructions; Integrate real-time ambient light intensity data with lamp operating energy efficiency data to generate a dynamic lighting parameter set that takes into account both visual comfort and optimal energy consumption. The set includes brightness values, color temperature values, and light uniformity distribution parameters. The multi-objective optimization weights of the machine learning algorithm are updated according to the dynamic lighting parameter set.

7. The office intelligent control method based on multi-source data fusion according to claim 1 is characterized in that: The method further includes indicating that a lamp failure occurs in response to the current state data of the lamp: Build a fault risk prediction model based on the historical operating data of the lamp health assessment model; When the model outputs a failure probability of a specific lamp that exceeds a threshold, execute: Automatically reorganize the lighting network topology and dynamically allocate the lighting tasks of the lamps to adjacent backup lamp groups; Generates pre-maintenance alarm information and optimizes maintenance resource scheduling paths.

8. The office intelligent control method based on multi-source data fusion according to claim 1 or 3, characterized in that: Generating the corresponding lighting control strategy further includes: Establish a cross-region dynamic perception matrix to obtain real-time information on workstation usage status, personnel movement data, and equipment operation status in each sub-area within the office area; Based on the matrix, when simultaneous state changes are detected in multiple sub-partitions, a time-sharing control instruction sequence is generated according to preset priority rules, and the lighting strategy change of non-priority partitions is delayed according to the instruction sequence to avoid visual fragmentation caused by sudden changes in lighting in multiple areas.

9. An office intelligent control device based on multi-source data fusion, characterized in that: The device comprises: Data acquisition module, used to obtain workstation usage status data, ambient light intensity data, personnel movement data and current status data of lamps; A state judgment and strategy generation module is used to judge whether the workstation is occupied or unoccupied based on the workstation usage status data, and to generate a corresponding lighting control strategy based on the ambient light intensity data, personnel movement data and current status data of the lamps; a lighting control module configured to control the brightness of lamps at corresponding workstations according to the lighting control strategy; wherein, in response to determining that the target workstation is unoccupied, the module controls the lighting at the corresponding workstation to be turned off; and in response to determining that the current workstation is occupied, the module calculates and outputs a target brightness value based on the ambient light intensity data to control the brightness of the lamps at the corresponding workstation; an adaptive optimization module, configured to receive, in a occupied state, a manual adjustment instruction for the target brightness value sent by a user and adaptively optimize the brightness calculation logic of the target brightness value based on the manual adjustment instruction; The fault processing module is used to indicate that a fault has occurred in the lamp in response to the current status data of the lamp, control the lighting of lamps near the faulty lamp and generate maintenance alarm information.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the office intelligent control method based on multi-source data fusion according to any one of claims 1 to 8 is implemented.

Images