A building space scheduling system based on multi-source perception and decision optimization

Abstract

The application relates to the technical field of building, and particularly discloses a building space scheduling system based on multi-source sensing and decision optimization. The system comprises a multi-source sensing module, a data processing module, a decision optimization module and an execution module. The multi-source sensing module collects environment data, personnel data and equipment operation data; the data processing module cleans, extracts features and fuses the multi-source data to generate structured data; the decision optimization module comprises a global optimization layer and a local optimization layer, predicts and formulates a macro scheduling strategy and a specific scheduling strategy based on the structured data, and dynamically optimizes the macro scheduling strategy and the specific scheduling strategy by adopting a machine learning model; and the execution module regulates and controls equipment and resources in the building space according to the macro scheduling strategy and the specific scheduling strategy. The application combines decision optimization and multi-source data sensing, and innovatively optimizes resource scheduling, energy efficiency management and user comfort of the building space.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of building management, in particular to a building space scheduling system based on multi-source perception and decision optimization, belonging to the category of cross-application of building intelligence and energy management technology. BACKGROUND

[0002] With the continuous improvement of building intelligence level, the scheduling system of building space gradually becomes an important direction to improve the operation efficiency of building and personnel experience. The existing building space scheduling system usually relies on a single data source for equipment control, lacks comprehensive perception ability of environmental changes, personnel activities and equipment running state, resulting in unreasonable resource allocation, high energy consumption and low space utilization efficiency. At the same time, some building space scheduling systems rely on fixed rules in the process of resource scheduling strategy formulation, lack of self-adaptive optimization ability, and are difficult to respond to the dynamic changes of demand in building space in real time. Therefore, it is urgent to develop a scheduling system that can integrate multi-source perception data and combine decision optimization mechanism to realize efficient, intelligent and self-adaptive management of building space resources. SUMMARY

[0003] The purpose of the present application is to provide a building space scheduling system based on multi-source perception and decision optimization to solve the problems of single data source, unreasonable resource allocation, insufficient energy efficiency management and lack of dynamic optimization ability in the existing building space scheduling system. By integrating environmental data, personnel data and equipment running data, combining machine learning model for real-time prediction and scheduling optimization, the dynamic scheduling of equipment and resources in building space is realized, thereby effectively improving the energy efficiency level, space utilization rate and personnel comfort.

[0004] According to the present application, a building space scheduling system based on multi-source perception and decision optimization is provided, comprising:

[0005] A multi-source perception module is used to collect multi-source data in the building space, the multi-source data including environmental data, personnel data and equipment running data, and the collection strategy of each monitoring unit is dynamically adjusted through a self-organizing network cooperation mechanism to optimize data integrity;

[0006] A data processing module is connected to the multi-source perception module and used to preprocess and extract features of the multi-source data to generate structured data;

[0007] A decision optimization module connected to the data processing module adopts a hierarchical decision architecture, which includes a global optimization layer and a local optimization layer. The global optimization layer formulates a macro scheduling strategy based on the structured data in combination with cross-space resource demand prediction. The local optimization layer formulates a specific scheduling strategy based on the structured data in combination with real-time scenarios and context information. The decision optimization module adopts a machine learning model to dynamically optimize the macro scheduling strategy and the specific scheduling strategy in combination with execution feedback.

[0008] An execution module connected to the decision optimization module is configured to perform real-time scheduling of devices and resources in the building space according to the macro scheduling strategy and the specific scheduling strategy, and feed back execution results to the decision optimization module to verify strategy effectiveness and trigger adaptive adjustment.

[0009] The system supports coordinated scheduling of multiple building spaces and realizes distributed decision-making and resource sharing among modules through a self-organizing network coordination mechanism.

[0010] Further, the multi-source perception module includes:

[0011] An environment monitoring unit configured to collect temperature, humidity, illumination, and air quality data in the building space;

[0012] A personnel monitoring unit configured to obtain personnel location, density, and behavior data;

[0013] A device monitoring unit configured to monitor the running state and energy consumption data of devices in the building space.

[0014] The multi-source perception module determines global scheduling demands across spaces according to the macro scheduling strategy generated by the global optimization layer, and determines local scheduling demands for individual spaces according to the specific scheduling strategy generated by the local optimization layer, dynamically negotiates the collection tasks and frequencies of the above monitoring units to optimize data integrity and real-time performance through a self-organizing network coordination mechanism.

[0015] Further, the data processing module includes:

[0016] A data cleaning unit configured to perform denoising and outlier processing on the multi-source data;

[0017] A feature extraction unit configured to extract scheduling-related feature vectors from the cleaned multi-source data;

[0018] A data fusion unit configured to fuse feature vectors from different sources to generate unified structured data in the form of a multi-dimensional feature matrix.

[0019] Further, the decision optimization module includes:

[0020] a prediction submodule configured to predict resource demand of the building space based on historical data and the structured data;

[0021] an optimization submodule configured to generate a scheduling strategy through a hierarchical optimization process according to the resource demand prediction of the prediction submodule and in combination with a dynamically adjusted optimization objective;

[0022] a global optimization layer configured to generate a macro scheduling strategy through an objective function based on the structured data;

[0023]

[0024] wherein, B is a cross-space resource allocation efficiency, is a cross-space resource balance degree, and λ, μ are dynamically adjusted weight coefficients satisfying λ + μ = 1; The cross-space resource allocation efficiency B is calculated by the utilization rate of resource sharing, and the cross-space resource balance degree is determined by the variance of resource allocation deviation of each building space.

[0025] a local optimization layer configured to fine-tune the macro scheduling strategy through an objective function based on the structured data, to generate a specific scheduling strategy;

[0026]

[0027] wherein, E is an energy consumption value based on the equipment operation data, U is a space utilization rate based on the personnel data, C is a personnel comfort score based on the environmental data, and α, β, γ are dynamically adjusted weight coefficients satisfying α + β + γ = 1;

[0028] The optimization objective includes the cross-space resource allocation efficiency improvement and resource balance degree optimization of the global optimization layer, and the energy consumption minimization, space utilization rate maximization, and personnel comfort optimization of the local optimization layer.

[0029] Further, the machine learning model includes a deep neural network model or a reinforcement learning model, and the machine learning model is optimized through a training data set to improve the cooperative performance of the global optimization layer and the local optimization layer.

[0030] Further, the execution module includes:

[0031] a device control unit configured to predictively adjust the operation parameters of lighting, air conditioning, and ventilation devices in the building space according to the specific scheduling strategy generated by the local optimization layer.

[0032] a resource allocation unit configured to dynamically adjust cross-space resource allocation and usage permissions according to the macro scheduling strategy generated by the global optimization layer, and to adjust resource allocation within a single building space according to the specific scheduling strategy generated by the local optimization layer;

[0033] The execution module adjusts device operating states in advance to reduce response delay through a predictive scheduling mechanism, supports cross-space execution synchronization to coordinate resource usage of multiple building spaces according to the macro scheduling strategy, and feeds back execution results to the decision optimization module to optimize subsequent scheduling.

[0034] Further, the building space scheduling system further comprises:

[0035] a communication module configured to realize data transmission between the multi-source perception module, the data processing module, the decision optimization module and the execution module, and interconnection and intercommunication with external systems; wherein the communication module supports wired communication and wireless communication protocols.

[0036] Further, the building space scheduling system further comprises:

[0037] a user interaction module configured to receive scheduling requirements input by a user, and to feed back scheduling results and system operating states to the user, wherein the user interaction module comprises a display interface and a voice interaction unit.

[0038] Further, the building space scheduling system further comprises:

[0039] an adaptive learning module configured to continuously optimize performance of the machine learning model according to operating data of the building space and user feedback; wherein the adaptive learning module supports online learning and offline learning.

[0040] Further, the building space scheduling system further comprises:

[0041] a cloud service platform configured to store the multi-source data and scheduling strategies, and to provide remote monitoring and data analysis functions; wherein the cloud service platform interacts with the system through an encrypted communication protocol.

[0042] The present application effectively solves the problems of single data, scheduling lag, unreasonable resource allocation, high energy consumption and the like in the prior art by realizing multi-source data perception and decision optimization. Specifically, the following points can be summarized:

[0043] 1. Improve the efficiency of building space resource utilization: By introducing a scheduling system based on multi-source perception and decision optimization, the invention can real-time schedule the equipment and resources in the building space, ensure the rational allocation and utilization of resources, and improve the overall resource use efficiency. In particular, through the optimization of cross-space resource allocation efficiency (B) and cross-space resource balance (Eq), the phenomenon of waste or uneven use of building space resources is avoided;

[0044] 2. Dynamic optimization of scheduling strategy: Through the hierarchical decision-making architecture of global optimization layer and local optimization layer, the system can dynamically adjust the scheduling strategy. The global optimization layer coordinates the resource allocation between different building spaces through macro scheduling strategy, and the local optimization layer adjusts the resource scheduling strategy of single building space according to real-time scene and specific demand. The introduction of machine learning model makes the strategy continuously optimized through execution feedback, improving the scheduling efficiency;

[0045] 3. Enhance the adaptive ability of the system: The system has the function of self-adaptive adjustment, which can automatically optimize the scheduling strategy according to the real-time feedback data, to ensure the maximum scheduling effect in different time and scene. Through the self-organizing network cooperation mechanism, the system can realize distributed decision and resource sharing among multiple building spaces, improving the resource scheduling cooperation efficiency of the whole building group;

[0046] 4. Improve the accuracy of data collection and processing: The introduction of multi-source perception module enables the system to collect real-time environmental data, personnel data and equipment operation data, ensuring the accuracy and timeliness of the data. The self-organizing network cooperation mechanism can optimize the negotiation of data collection tasks and frequency, further improve the data integrity and real-time performance, and ensure that the scheduling decision can be made based on the latest and most comprehensive data information;

[0047] 5. Optimize energy efficiency and comfort: Through the comprehensive optimization of multi-dimensional data such as equipment running state, energy consumption, space utilization rate and personnel comfort, the system can ensure efficient operation of building space while maximizing energy saving and improving user comfort. Minimizing energy consumption, maximizing space utilization and optimizing personnel comfort can effectively reduce energy consumption and improve the sustainability of building environment.

[0048] In summary, the invention combines decision optimization with multi-source data perception, innovatively optimizes the resource scheduling, energy efficiency management and user comfort of building space, and has significant technical and application advantages. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 A building space scheduling system framework based on multi-source perception and decision optimization is provided for the invention;

[0050] Figure 2A multi-source perception module structure schematic diagram provided by the present application is provided.

[0051] Figure 3 A data processing module structure schematic diagram provided by the present application is provided.

[0052] Figure 4 A decision optimization module structure schematic diagram provided by the present application is provided.

[0053] Figure 5 An execution module structure schematic diagram provided by the present application is provided.

[0054] Reference signs:

[0055] A building space scheduling system 100 based on multi-source perception and decision optimization, a multi-source perception module 101, a data processing module 102, a decision optimization module 103, an execution module 104, an adaptive learning module 105, a communication module 106, a user interaction module 107, and a cloud service platform 108 are provided.

[0056] An environment monitoring unit 1011, a personnel monitoring unit 1012, a device monitoring unit 1013, a data cleaning unit 1021, a feature extraction unit 1022, a data fusion unit 1023, a prediction sub-module 1031, an optimization sub-module 1032, a device control unit 1041, and a resource allocation unit 1042 are provided. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0058] The terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features; in the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more.

[0059] In order to make the technical solutions of the present application clearer, the present application will be described in detail below in combination with specific embodiments, but should not be understood as limiting the scope of protection of the present application.

[0060] In the present embodiment, as shown in FIG. 1, the building space scheduling system 100 based on multi-source perception and decision optimization comprises a multi-source perception module 101, a data processing module 102, a decision optimization module 103, an execution module 104, an adaptive learning module 105, a communication module 106, a user interaction module 107, and a cloud service platform 108. Figure 1As shown, a building space scheduling system 100 based on multi-source perception and decision optimization is provided, including a multi-source perception module 101, a data processing module 102, a decision optimization module 103, and an execution module 104. Through the close cooperation of each module, the system realizes intelligent scheduling and optimized control of equipment and resources in the building space.

[0061] Specifically, the multi-source perception module 101 is used to collect multi-source data in the building space in real time. The multi-source data includes but is not limited to environmental data, personnel data, and equipment operation data. The environmental data includes parameters such as temperature, humidity, light intensity, and air quality, comprehensively reflecting the physical environment status in the building space; the personnel data covers the number, location distribution, and activity trajectory of personnel, for real-time monitoring of the use and personnel flow of the building space; the equipment operation data includes information such as the on-off state, working mode, and energy consumption of lighting, air conditioning, ventilation, and other equipment, for mastering the operation of building facilities.

[0062] It can be understood that the self-organizing network is used to support the collaborative perception task of the multi-source perception module, composed of multiple perception nodes with data collection and communication capabilities, and adopts a mesh topology to realize multi-hop communication and information sharing between nodes. Each perception node has the ability to adaptively adjust the task based on the local state, and can determine the overall perception demand according to the macro scheduling strategy generated by the global optimization layer, and dynamically negotiate the collection task and frequency in combination with the specific scheduling strategy generated by the local optimization layer. During network operation, nodes can dynamically optimize routing paths and task allocation methods based on historical communication quality, remaining energy, task priority, and other factors, to improve the coverage and energy efficiency of data collection. Without centralized control, the self-organizing network realizes distributed collaboration of perception tasks and rapid response of scheduling strategies, improving the real-time performance and flexibility of the system.

[0063] Further, the multi-source perception module 101 transmits the collected multi-source data to the data processing module 102 in real time through wired or wireless means. After receiving the original data, the data processing module 102 first pre-processes the data. The pre-processing process includes noise removal, missing data completion, and data format unification, etc. to improve the quality and reliability of the data. The pre-processed data then enters the feature extraction stage, extracting key features of the building space operation status such as temperature fluctuation range, personnel density change, and equipment energy consumption curve, to ensure the effectiveness of subsequent analysis.

[0064] The decision optimization module 103 is connected to the data processing module 102, receives structured data and conducts in-depth analysis. The decision optimization module 103 generates and optimizes the building space scheduling strategy by introducing a global optimization layer and a local optimization layer. Specifically, the global optimization layer generates a macro scheduling strategy based on the overall demand prediction of all resources in the building space, and optimizes the resource scheduling across spaces. This layer focuses on the global configuration of resources, striving to achieve the balance of energy efficiency maximization, space use optimization and personnel comfort. The local optimization layer generates specific scheduling strategies based on real-time scene data and context information, and conducts micro-level scheduling adjustment, mainly focusing on the allocation of resources in specific spaces, such as adjusting environmental parameters such as temperature and humidity in a single area, to ensure efficient use of equipment and resources in the space. Among them, the context information refers to auxiliary information that dynamically affects resource prediction and strategy formulation during building space scheduling, mainly including but not limited to: current time (such as weekdays or holidays, time period, etc.), space use type (such as office, meeting, rest, etc.), device running state (such as whether the air conditioner is on, lighting mode, etc.), user behavior pattern (such as activity frequency, path distribution, historical behavior trajectory) and environmental mutation information (such as external weather changes or emergencies) and the like. The context information is mainly processed and utilized by the local optimization layer in the decision optimization module, to improve the adaptability and precision of the specific scheduling strategy. When formulating specific scheduling strategies, the local optimization layer can dynamically correct the optimization target and strategy parameters based on structured data combined with context information in real-time scenarios, so that the system can more accurately respond to the actual running state and user demand of the current space, thereby achieving more flexible and fine scheduling control.

[0065] Further, the decision optimization module 103 internally deploys at least one machine learning model, which can combine historical data and real-time data to predict the dynamic changes of building space resource demand through continuous training. Based on the prediction results, the decision optimization module 103 dynamically generates scheduling strategies for the building space, including device operation plans, space use arrangements, resource priority configurations, etc., to ensure the comprehensive optimization of building space in terms of energy efficiency utilization, comfort maintenance and resource coordination.

[0066] Specifically, the execution module 104 is connected with the decision optimization module 103 for performing real-time scheduling operation on the devices and resources in the building space according to the macro scheduling strategy and the specific scheduling strategy, the devices and resources including lighting devices, air conditioning systems, fresh air systems, and allocable space areas and energy units. Further, the execution module 104 determines the overall scheduling target according to the macro scheduling strategy, for example, prioritizing the energy supply of high-usage areas, and then generates corresponding control instructions according to the specific scheduling strategy and issues them to the control interfaces of the related devices to trigger actions, such as adjusting the air conditioning temperature, adjusting the lighting brightness, or switching the resource allocation path. Understandably, after the devices complete the response operation, the execution module 104 collects the device operating state, space resource allocation data, and energy efficiency indicators in the corresponding time period as the execution result, and feeds back the execution result to the decision optimization module 103 for evaluating the adaptability and effectiveness of the current strategy. Further, if the decision optimization module 103 judges that the strategy effect is not ideal according to the feedback data, it automatically triggers the adaptive adjustment process of the scheduling strategy to form a new optimal strategy, thereby realizing the continuous optimization of the building space operating state.

[0067] Further, the building space scheduling system supports collaborative scheduling of multiple building spaces, and each building space is deployed with a scheduling subsystem having independent sensing, decision-making, and execution capabilities. Each subsystem communicates and coordinates through a self-organizing network coordination mechanism, thereby realizing dynamic resource scheduling and optimal control across spaces. Further, the self-organizing network coordination mechanism is based on a peer-to-peer communication structure, allowing each subsystem to establish communication connections autonomously without a central control node, and negotiating resource use schemes according to local and global states, for example, when a load peak occurs in a building space, it can request neighboring spaces to share redundant energy or reconfigure device tasks through the network negotiation mechanism to relieve local pressure. Understandably, each subsystem shares sensing data, scheduling intentions, and execution feedback through the coordination mechanism, thereby participating in the distributed decision-making process together, gradually approaching the globally optimal resource allocation scheme, while retaining their own control priority over local resources, realizing the flexibility and adaptability of system-level scheduling.

[0068] This invention effectively solves the problems of single data, delayed scheduling, unreasonable resource allocation, and high energy consumption in existing technologies by realizing multi-source data perception and decision optimization. This building space scheduling system collects multi-source data such as environmental, personnel, and equipment operation data through a multi-source perception module 101 and dynamically adjusts the collection strategy to optimize data integrity using a self-organizing network collaborative mechanism. Preprocessing and feature extraction by the data processing module 101 generate structured data to provide high-quality input for decision-making. A global optimization layer in a hierarchical decision architecture, combined with cross-space resource demand prediction, formulates macro-level scheduling strategies to achieve balanced resource allocation across multiple building spaces. A local optimization layer, combined with real-time scene and contextual information, predicts and formulates specific scheduling strategies to improve the energy efficiency, space utilization, and comfort of a single space. A machine learning model, combined with execution feedback, dynamically optimizes the scheduling strategy to achieve adaptive adjustment. The execution module 104, based on macro and specific scheduling strategies, schedules equipment and resources in real time and supports cross-space execution synchronization to improve the collaborative efficiency of multiple building spaces. This significantly improves the resource utilization, energy efficiency, comfort, and multi-space collaborative scheduling capabilities of building spaces.

[0069] In some embodiments, such as Figure 2 As shown, the multi-source sensing module 101 further includes an environmental monitoring unit 1011, a personnel monitoring unit 1012, and an equipment monitoring unit 1013. The environmental monitoring unit 1011 is configured at multiple locations within the building space to collect environmental parameter data within the space in real time. Specifically, the environmental monitoring unit 1011 can collect temperature, humidity, light intensity, and air quality-related indicators, such as carbon dioxide concentration, PM2.5 concentration, and formaldehyde content. Through multi-point sampling and comprehensive analysis, it forms a complete perception of the building space's environmental status.

[0070] Furthermore, the personnel monitoring unit 1012 is deployed in the main passageways, entrances and exits, and important areas of the building space to detect the location, distribution density, and behavioral characteristics of personnel in real time. Understandably, the personnel monitoring unit 1012 can employ infrared sensors, cameras combined with image recognition algorithms, radio frequency identification (RFID) technology, or Bluetooth beacons to achieve personnel detection. Through the personnel monitoring unit 1012, not only can the real-time location and quantity changes of personnel in the space be accurately obtained, but also personnel activity paths, dwell time, and behavioral patterns can be inferred, thereby providing accurate dynamic data support for subsequent intelligent scheduling.

[0071] Further, the equipment monitoring unit 1013 is configured to monitor the status of key operating equipment in the building space in real time. It can be understood that the equipment monitoring unit 1013 can collect the start-stop state, operation mode, working time and energy consumption data of various equipment. For example, for air conditioning equipment, the equipment monitoring unit 1013 can record its current temperature setting value, air speed gear and power consumption; for the lighting system, the on-off state and illumination output can be collected; for the ventilation system, the fresh air volume and fan speed and other parameters can be monitored. Through the equipment monitoring unit 1013, the operation condition and energy consumption of various facilities and equipment in the building space can be comprehensively mastered, providing accurate and detailed basic data support for subsequent data processing and optimization decision-making.

[0072] Further, the multi-source perception module 101 determines the global scheduling demand across regions in the building space according to the macro scheduling strategy generated by the decision optimization module 103 during system operation. Specifically, the macro scheduling strategy can be embodied as a resource linkage target across floors and functional areas, such as increasing ventilation intensity in personnel-intensive areas and adjusting lighting brightness during energy consumption peak periods. The multi-source perception module 101 coordinates the monitoring units in multiple regions through a self-organizing mechanism, adjusts the collection range, frequency and data upload mode as needed, to ensure the coverage breadth and timeliness of global perception data, supporting the scheduling execution of the global optimization layer.

[0073] Further, the multi-source perception module 101 also identifies the local scheduling demand of a single space according to the scheduling strategy of the specific space. For example, before a conference room is scheduled to be used, according to the predicted personnel density and activity time period, the local optimization layer will generate a corresponding comfort guarantee strategy, involving the timing scheduling of lighting, air conditioning and other equipment operation. The multi-source perception module 101 dynamically adjusts the sampling interval of the personnel monitoring unit 1012 and the environment monitoring unit 1011 accordingly, preferentially allocates processing resources for high-frequency collection of key parameters, thereby improving the timeliness and resolution of local data.

[0074] It can be understood that the multi-source perception module 101, while handling global and local scheduling demands, realizes dynamic task negotiation among monitoring units through a self-organizing mechanism. For example, when a regional sensor node performance degrades due to power reduction or channel interference, the system can automatically adjust the task coverage range of adjacent nodes to temporarily compensate for the perception blind area. Through the task negotiation and frequency adjustment mechanism, the perception data maintains a high level in terms of spatial coverage and temporal continuity, effectively optimizing the integrity and real-time of the overall data, and providing high-quality perception support for the scheduling strategy of the system.

[0075] In some embodiments, as Figure 3As shown, the data processing module 102 further includes a data cleaning unit 1021 for denoising and outlier processing of the multi-source data, and a feature extraction unit 1022 for extracting scheduling-related feature vectors from the cleaned multi-source data. Furthermore, the data processing module 102 includes a data fusion unit 1023 for fusing feature vectors from different sources to generate unified structured data, which is represented in the form of a multi-dimensional matrix or vector.

[0076] Specifically, the data processing module 102 works collaboratively through multiple sub-units. First, the data cleaning unit 1021 performs denoising and outlier processing on the raw data obtained from the multi-source perception module 101. For example, a temperature sensor may generate noise due to external interference, and the data cleaning unit 1021 will exclude these abnormal data to ensure that the subsequent processing is based on accurate data. Understandably, the data cleaning unit 1021 can use mean deviation detection, standard deviation analysis, or machine learning-based anomaly detection methods to identify and filter abnormal values in temperature, personnel density, and other sensor data, thereby improving the accuracy and robustness of subsequent scheduling strategies.

[0077] Further, the cleaned data is transmitted to the feature extraction unit 1022, which extracts key feature vectors related to building space scheduling from the data. For example, environmental data such as temperature, humidity, and air quality can be converted into feature vectors that affect comfort, while personnel location and behavior data can be used to determine the frequency and density of space usage, and equipment operation data can extract features such as energy consumption levels and equipment failure. Then, the feature extraction unit 1022 converts these data into structured feature vectors according to certain rules, ensuring that each data point can be effectively utilized.

[0078] Understandably, the feature extraction unit 1022 can identify which data is most critical to scheduling optimization and which data has less impact on the decision-making process.

[0079] Finally, the extracted feature vectors are transmitted to the data fusion unit 1023, where data from different sources is fused into unified structured data through an incremental fusion algorithm. Specifically, the data fusion unit 1023 combines feature vectors from multiple aspects such as environment, personnel, and equipment to form a multi-dimensional feature matrix. The goal of this process is to ensure that each input data is reasonably utilized and organized in a form that can support subsequent decision analysis, so as to ultimately form a clear data structure that can guide building space resource scheduling.

[0080] It can be understood that the incremental fusion algorithm is used to support the dynamic integration of real-time perception data in multi-building space, and has good scalability and timeliness. The algorithm only performs feature extraction and vector fusion operations on new data at each data update, without the need to repeatedly process existing data, thereby effectively reducing computational redundancy and improving system response efficiency. Specifically, after receiving perception data from different spaces, the data fusion unit first standardizes the environmental parameters, device states, and space usage information of each space, and extracts multi-dimensional feature vectors. Then, an incremental update strategy is used to weight and integrate the new feature vectors at the current time and the historical fusion results, generating unified structured data with consistent structure.

[0081] The structured data is represented in the form of a multi-dimensional feature matrix, where the row vectors represent different data dimensions such as temperature, humidity, lighting intensity, and personnel density, and the column vectors represent time evolution or spatial distribution, thereby providing high-dimensional input data support for subsequent prediction and optimization modules.

[0082] In some embodiments, as shown in Figure 4 The decision optimization module 103 further includes a prediction submodule 1031 for predicting resource demand of the building space based on historical data and the structured data, and an optimization submodule 1032 for generating an optimal scheduling strategy based on the predicted resource demand of the prediction submodule 1031 and a predetermined optimization objective.

[0083] Specifically, in this embodiment, the prediction submodule 1031 predicts the resource demand of the building space based on historical data and structured data. First, the prediction submodule 1031 receives data from the multi-source perception module, including temperature, humidity, lighting, personnel behavior data, and device operating status and energy consumption data. By analyzing these structured data, the prediction submodule 1031 can identify the resource demand pattern in the building space and predict the resource demand in the future period. Specifically, the prediction submodule 1031 uses time series analysis and regression analysis methods to process historical data and dynamically predicts in combination with real-time input data. By establishing a prediction model, the system can consider factors such as personnel activity, environmental change, and device load in different time periods to accurately predict energy consumption demand, device operation demand, and space utilization in the building space.

[0084] Predictive models are typically implemented based on trend analysis of historical data, identifying patterns such as seasonal fluctuations and human activity patterns, and then further optimized using machine learning techniques. Common predictive algorithms include Support Vector Machines (SVM), Random Forest Regression, and Long Short-Term Memory (LSTM) networks. The prediction submodule 1031 learns the changing trends of historical data through these algorithms and can perform personalized resource demand predictions based on the characteristics of different building spaces. For example, the system can predict the lighting and air conditioning load of a specific floor or area during a specific period, or predict the impact of changes in population density on the demand for air conditioning systems.

[0085] The optimization submodule 1032, based on the resource demand forecast results provided by the prediction submodule 1031, combines dynamically adjusted optimization objectives to generate a scheduling strategy through a hierarchical optimization process. The task of the optimization submodule is to generate a reasonable resource scheduling scheme based on changes in resource demand and different optimization objectives. Within the optimization submodule, the demand for different resources within the building space is first determined based on the forecast results, and appropriate priorities are assigned to each resource. The optimization process is conducted through a two-tiered structure. The global optimization layer focuses on the allocation of resources across spaces, aiming to improve the sharing efficiency of resources between different building spaces and optimize the utilization and balance of cross-space resources. The local optimization layer focuses on the optimal allocation of resources within a single building space, particularly balancing equipment energy consumption, space utilization, and personnel comfort. Both the global and local optimization layers guide the generation of the scheduling strategy through optimization objective functions.

[0086] Furthermore, in the global optimization objective function, Let λ represent the global optimization objective value, and λ and μ be dynamically adjusted weight coefficients during the optimization process. The objective function has the following form:

[0087]

[0088] Here, B represents cross-spatial resource allocation efficiency, which measures the allocation efficiency of each building's spatial resources by calculating the utilization rate of resource sharing. Specifically, the decision optimization module 103 calculates resource allocation efficiency by statistically analyzing the ratio of resource usage to total available resources for each space based on the structured multidimensional feature matrix provided by the data processing module 102. Improving resource allocation efficiency ensures the rational sharing and full utilization of spatial resources, thereby maximizing overall resource utilization efficiency. To represent the cross-space resource balance degree, it measures whether the resource allocation is balanced by calculating the variance of the resource allocation deviation among each building space. The decision optimization module 103 calculates this variance according to the difference distribution of the utilization rate of each space and the overall average utilization rate. A smaller resource deviation variance indicates that the resource allocation among different spaces is more uniform, avoiding the situation that some spaces are over-utilized while other spaces are idle. The λ and μ in the objective function are dynamic adjustment weight coefficients, and the sum of the two coefficients is always equal to 1, i.e. λ + μ = 1. By adjusting the values of the two coefficients, the relationship between resource allocation efficiency and resource balance degree can be balanced. In practical applications, the values of λ and μ can be dynamically adjusted according to the needs of different scenarios. For example, in the case of improving resource utilization, the value of λ can be increased; while in the scenario of optimizing resource balance degree, the value of μ can be increased.

[0089] In the global optimization layer, a global scheduling strategy is generated by minimizing to guide the overall resource scheduling in the building space to ensure efficient use of cross-space resources.

[0090] Then enter the local optimization layer. In the local optimization layer, the optimization target is to fine-tune the macro scheduling strategy generated by the global optimization layer, so as to generate a specific scheduling strategy to meet the specific needs of each building space. In this layer, the form of the optimization objective function is:

[0091]

[0092] wherein, is the local optimization target value, E is the energy consumption value based on the device operation data, U is the space utilization rate based on the personnel data, C is the personnel comfort score based on the environmental data, which mainly calculates the comfort of personnel in the space according to environmental data (such as temperature, humidity, etc.). α, β and γ are dynamic adjustment weight coefficients, and satisfy α + β + γ = 1. By adjusting these weight coefficients, the system can find the optimal balance between energy consumption, space utilization and personnel comfort.

[0093] It can be understood that the acquisition of the three parameters E, U and C depends on the raw data collected by the multi-source perception module 101 and the structured data output by the data processing module, and is calculated by the decision optimization module 103 in the global or local optimization layer according to these data. Specifically, E is the energy consumption value based on the device operation data, which is collected by the device monitoring unit 1013 of the multi-source perception module 101 in real time, including the power, running time and start-stop times of each device and other information. After the data processing module 102 cleanses and extracts features from the data, it provides the energy consumption statistics in numerical form to the decision optimization module 103, which directly reads the result as the energy consumption value E. U is the space utilization rate based on the personnel data collected by the personnel monitoring unit 1012 in the multi-source perception module 101, including personnel density, entry and exit frequency, and stay time, etc. After the data processing module 102 fuses and normalizes the personnel behavior data, it calculates the ratio of the actual occupied area to the available area in each space and passes the ratio to the decision optimization module to determine the space utilization rate U. C is the personnel comfort score based on the environmental data collected by the environmental monitoring unit 1011 in the multi-source perception module 101, including temperature, humidity, light intensity and air quality, etc. After the data processing module 102 compares the thresholds and calculates the weighted values of these environmental parameters, it outputs the comfort score, which is directly called by the decision optimization module 103 as the personnel comfort score C. The calculation of the above three parameters is completed in the decision optimization module, ensuring that the optimization strategy can be dynamically adjusted and accurately controlled based on real perception data.

[0094] Specifically, the minimization of E helps to reduce energy consumption in the building space and improve energy use efficiency; the maximization of U helps to improve the utilization rate of the space, especially in areas with high personnel density, ensuring that resources can be used efficiently; and the maximization of C can improve the comfort of personnel at work or residence, especially in terms of air conditioning, lighting and other adjustments that can be optimized according to actual needs.

[0095] In the local optimization layer, the specific scheduling strategy is adjusted by minimizing in combination with the macro scheduling strategy generated by the global optimization layer. This process ensures that the resource allocation of each building space can meet both the requirements of global optimization and the local needs of each space.

[0096] Further, in the decision optimization module 103, it is also crucial to implement a feedback mechanism. The system continuously monitors and feeds back the equipment operation status, resource allocation effectiveness, and energy efficiency data to the decision optimization module 103 to verify the effectiveness of the scheduling strategy and trigger adaptive adjustment. This process is supported by machine learning models, enabling global and local optimization strategies to be continuously optimized according to actual execution, improving the system's response speed and flexibility.

[0097] This system based on a hierarchical decision-making architecture can fully consider the various needs of building spaces and provide a dynamic adjustment and real-time response resource scheduling solution through optimization algorithms. This not only ensures efficient use of resources in each building space, but also ensures the sustainability and comfort of the system.

[0098] In some embodiments, the machine learning model used in the decision optimization module 103 can include a deep neural network model or a reinforcement learning model. Specifically, the deep neural network model is based on a multi-layer perceptron structure, the input layer receives the multi-dimensional structured feature matrix output by the data processing module 102, the intermediate hidden layer extracts high-dimensional abstract features through a nonlinear activation function, and the output layer outputs the prediction results of resource demand, such as energy consumption load, personnel density distribution, or device usage trends in different areas in the future. It can be understood that this deep neural network model is trained with a large amount of historical building space operation data, enabling the model to accurately learn the rules of resource demand changes from complex and variable input data.

[0099] Further, the reinforcement learning model takes the building space as the environment, the scheduling strategy as the action, and the state of the building space (such as real-time energy consumption level, personnel distribution, and environmental comfort) as the state input. The system selects a scheduling action based on the current state and obtains a reward value based on the feedback after the action (such as energy consumption reduction, space utilization improvement, or personnel comfort improvement). Through continuous trial and error and reward mechanism, the optimal scheduling strategy is learned. It can be understood that the reinforcement learning model can continuously adapt to the dynamic changes in the building space environment to achieve optimization of resource allocation.

[0100] Further, to improve the generalization ability of the model and adapt to the needs of different building space scenarios, the machine learning model is trained through a specially constructed training data set that covers multiple different types of building space usage scenarios, such as office buildings, shopping malls, schools, and hospitals, ensuring that the model can output reasonable prediction and decision results when facing different building characteristics.

[0101] It can be understood that, in order to realize the synergy of the global optimization layer and the local optimization layer, the machine learning model needs to share information and coordinate between the global and local layers. Specifically, the machine learning model exchanges information in the system, thereby improving the overall scheduling efficiency. For example, a deep neural network model can provide predictions of global resource allocation within a building space, while a reinforcement learning model dynamically adjusts the allocation of local resources based on these predictions, thereby achieving coordinated scheduling of resources across spaces.

[0102] In this way, the machine learning model not only improves the global scheduling capability of the building space scheduling system, but also optimizes the resource utilization of local spaces, enabling the system to achieve efficient and accurate scheduling in a complex environment of multiple building spaces and multiple resources.

[0103] In some embodiments, as shown in FIG. 1, the execution module 104 further includes a device control unit 1041 and a resource allocation unit 1042. Figure 5

[0104] Specifically, in the present embodiment, the execution module 104 is configured to perform real-time scheduling of devices and resources within the building space according to the macro scheduling strategy and the specific scheduling strategy output by the decision optimization module, and feed back the execution results to the decision optimization module to verify the effectiveness of the strategy and trigger adaptive adjustment. The execution module 104 mainly includes the device control unit 1041 and the resource allocation unit 1042, which complement each other in function and together realize the optimal scheduling of resources and devices within the building space.

[0105] Specifically, the device control unit 1041 is responsible for predictive adjustment of lighting, air conditioning, ventilation and other devices within the building space according to the specific scheduling strategy generated by the local optimization layer. The device control unit 1041 adjusts the operating parameters of the devices in advance according to the device operation requirements in the scheduling strategy, to ensure that the operating state of the devices within the building space is consistent with the real-time scheduling requirements. The core of predictive adjustment is that the system can predict device requirements according to the specific scheduling strategy in the local optimization layer and respond in advance, thereby reducing the response delay in actual execution.

[0106] For example, if the specific scheduling strategy generated by the local optimization layer indicates that the air conditioning demand in certain areas is high during a certain period, the device control unit 1041 will adjust the operating state of the air conditioning device in advance, including adjusting the temperature setting, air speed and other operating parameters, to ensure that the required temperature environment can be provided quickly when needed. Similarly, lighting and ventilation devices will also be adjusted according to the scheduling strategy to achieve optimal energy efficiency and maximum comfort for personnel.

[0107] ​The resource allocation unit 1042 is primarily responsible for cross-space resource allocation and resource usage adjustment within a single building space. Based on the macro-scheduling strategy generated by the global optimization layer, the resource allocation unit 1042 dynamically adjusts the allocation and usage permissions of cross-space resources in conjunction with real-time priorities. In the case of multi-building space scheduling, the resource allocation unit 1042 coordinates resource sharing between different building spaces to ensure the efficiency and fairness of overall resource allocation. The resource allocation unit 1042 also adjusts resource allocation within a single building space according to the specific scheduling strategy generated by the local optimization layer to achieve optimal configuration of equipment and resources within the space.

[0108] For example, assuming a multi-building space environment, the equipment in one building space is operating well, while another building space has higher resource demands, the resource allocation unit 1042 will adjust the cross-space allocation of resources according to the global optimization strategy to ensure that the resource utilization of the entire system reaches the best effect. At the same time, the specific scheduling strategy of the local optimization layer will also be adjusted in real time within a single building space. For example, the energy consumption of lighting or air conditioning in a certain space will be adjusted to reduce the total energy consumption and improve the space utilization efficiency.

[0109] During execution, the execution module 104 also feeds back the execution results, such as equipment operating status, resource allocation effectiveness, and energy efficiency data, to the decision optimization module. This feedback mechanism is crucial for verifying the effectiveness of the scheduling strategy. If, during execution, it is found that some equipment fails to adjust according to the predetermined scheduling strategy, or that the resource allocation of certain building spaces is unreasonable, the execution module 104 will feed this information back to the decision optimization module, thereby triggering the system's adaptive adjustment. This adaptive adjustment mechanism enables the entire system to dynamically optimize the scheduling strategy based on the actual execution results, gradually improving the accuracy and effectiveness of scheduling.

[0110] In summary, this embodiment, through the coordinated operation of the equipment control unit 1041 and the resource allocation unit 1042, enables the building space scheduling system to perform precise equipment control and resource allocation based on the macro and local scheduling strategies provided by the decision optimization module. Through predictive adjustment and dynamic resource adjustment, the execution module 104 achieves efficient scheduling of equipment and resources within the building space, and continuously optimizes the scheduling strategy through a feedback mechanism, thereby improving the system's adaptability and scheduling effectiveness.

[0111] In some embodiments, such as Figure 1 As shown, the system also includes a communication module 106, which is used to realize data transmission between the multi-source sensing module 101, the data processing module 102, the decision optimization module 103 and the execution module 104, and to support interconnection with external systems.

[0112] Furthermore, the communication module 106 can employ local area network communication, cellular mobile communication, Wi-Fi communication, Bluetooth communication, ZigBee communication, or other mainstream wired or wireless communication protocols to ensure stable data transmission, low latency, and a certain degree of fault tolerance between modules within the system. Understandably, the communication module 106 plays the role of an information hub in the system architecture, not only carrying the uploading of data collected by sensors within the building space but also responsible for distributing processing results and scheduling instructions to each execution unit in real time, thereby forming an end-to-end closed-loop scheduling link.

[0113] Furthermore, the communication module 106 also features protocol conversion capabilities to coordinate communication protocol differences between devices from different manufacturers, enabling interconnection and interoperability between heterogeneous devices. For example, when connecting to external building automation systems (BAS), energy management systems (EMS), or virtual security systems (VMS), the communication module 106 can achieve data interoperability with external systems through standard industrial communication protocol interfaces such as OPC UA, BACnet, and Modbus, improving system compatibility and scalability. Understandably, the communication module 106 uses its built-in communication management unit to schedule and control the flow of various communication tasks, ensuring stable system operation and preventing data congestion or packet loss when multiple modules transmit data simultaneously.

[0114] Furthermore, to ensure data security, the communication module 106 employs encrypted communication protocols such as HTTPS, SSL / TLS, and AES to encrypt data interaction processes within the system and between the system and external platforms, preventing data from being illegally intercepted, tampered with, or forged during transmission. The communication module 106 can also work in conjunction with authentication mechanisms, device authentication mechanisms, and access control mechanisms to ensure that all internal modules and externally accessed systems are trusted nodes, effectively preventing unauthorized access and control and enhancing the overall system's security capabilities.

[0115] Understandably, by introducing this communication module 106, efficient and stable data interaction can be achieved between the various sub-modules of the system, while also possessing good scalability and security, providing a solid foundation for the stable operation and functional expansion of the building space scheduling system.

[0116] In some embodiments, such as Figure 1 As shown, the system also includes a user interaction module 107, which is used to receive scheduling requests input by the user and to provide feedback on scheduling results and system operating status to the user.

[0117] Specifically, the user interaction module 107 comprises a display interface and a voice interaction unit, for providing a multi-modal human-computer interaction mode, enabling the user to communicate with the system in a graphical, textual or vocal manner. It can be understood that the display interface can take the form of a touch screen, a mobile application interface or a web-based visual interface, intuitively displaying the real-time status of each area in the building space, including temperature, humidity, personnel distribution, equipment operation and the current executed scheduling strategy, etc., facilitating the user to have a global grasp of the system operation.

[0118] Further, the user can customize scheduling preferences or input specific management strategy instructions through the display interface, such as setting a certain area to maintain a certain comfort level at a certain time period, or manually prioritizing the allocation of a certain type of resource to a specific area. The voice interaction unit, through natural language processing technology, realizes the voice control and query of the system by the user, such as the user can start the system scheduling, query energy consumption report, adjust resource allocation strategy, etc. through voice instructions, improving the operation convenience and intelligent level. It can be understood that the voice interaction unit can integrate a microphone array and a voice recognition processing chip, and combine a pre-trained semantic recognition model to perform command analysis and intent understanding, thereby realizing high-accuracy voice recognition and response.

[0119] Further, to improve user experience, the user interaction module 107 also supports personalized settings and interaction history recording functions, and the system can dynamically adjust the display content and interaction process according to the user's usage habits, feedback preferences and historical input data, providing customized operation suggestions and scheduling recommendations. For example, for high-frequency users, the system can prioritize the display of their commonly used function modules in the interaction interface, and for repeated instructions in specific scenarios, it can automatically complete and prompt for confirmation. It can be understood that this module interacts with the data interface of the decision optimization module 103, feeding back user input information to the core decision logic of the system in real time, ensuring that user needs can be quickly and accurately identified and executed by the system.

[0120] It can be understood that by setting the display interface and the voice interaction unit, the user interaction module 107 effectively improves the operability and user-friendliness of the system, enabling the user to conveniently and efficiently participate in the scheduling process and real-time control the building space operation status, providing key human-computer collaboration support for building space intelligent management.

[0121] In some embodiments, as Figure 1As shown, the system further comprises an adaptive learning module 105 for continuously optimizing the performance of the machine learning model according to the operation data of the building space and user feedback. Specifically, the adaptive learning module 105 supports both online learning and offline learning modes, where online learning refers to the system collecting newly generated data in real time during the actual operation of the building space, dynamically updating model parameters to adapt to changes in the environment and user behavior patterns; offline learning refers to the system processing and training large-scale historical data collected in a centralized manner during non-peak operation periods to comprehensively improve the performance of the model.

[0122] Understandably, the adaptive learning module 105 synchronously integrates the real-time collected multi-source data (including environmental change data, personnel dynamic data, equipment operation state data, etc.) and user interaction data (such as user satisfaction feedback on scheduling results, manual adjustment records, etc.) through the establishment of a data caching mechanism, forming a new training sample set. Further, in the online learning mode, the module uses an incremental learning algorithm to fine-tune the existing machine learning model rather than completely retrain it, thereby ensuring that the system maintains response speed and inference efficiency during continuous operation and avoiding system downtime or performance degradation due to frequent retraining.

[0123] Further, in the offline learning mode, the adaptive learning module 105 uses batch training based on a complete data set and applies methods including but not limited to transfer learning, reinforcement learning, or deep neural network retraining to explore more optimal feature expression and decision logic in building space resource scheduling strategies. Understandably, to ensure data security and privacy protection during offline training, the adaptive learning module 105 also combines data desensitization processing, encrypted storage, and access control strategies to ensure that all operation data and user feedback meet data security standards during training.

[0124] Further, the adaptive learning module 105 has a model evaluation and verification mechanism after model updating, which tests and compares the updated model through a set of key performance indicators (such as energy consumption reduction ratio, space utilization rate improvement amplitude, user comfort score change, etc.) to ensure that the new model is better than the old model in actual application before replacing it in the decision optimization module 103 for formal application. Understandably, the system also supports model version management functions, allowing rollback to a previously better-performing model version when necessary to ensure system stability and continuous optimization of scheduling effectiveness.

[0125] Understandably, the adaptive learning module 105 enables the system to dynamically evolve according to changes in the building space environment and user behavior, continuously improving the intelligent level and operation efficiency of building space resource scheduling, thereby significantly improving the problems of slow response and poor adaptability of traditional fixed model systems.

[0126] In some embodiments, as shown in Figure 1 The system includes a cloud service platform 108 for storing the multi-source data and scheduling strategies, and providing remote monitoring and data analysis functions.

[0127] Specifically, the cloud service platform 108 interacts with the system through an encrypted communication protocol to ensure the security and integrity of data transmission and storage. Understandably, the cloud service platform 108 has a distributed architecture with high availability and high scalability, supporting centralized management and unified analysis of data from different building space systems, and providing collaborative optimization support for multiple buildings.

[0128] Further, after the multi-source data is collected and preliminarily processed by the edge node, it is uploaded to the cloud service platform 108, which classifies and labels the data and builds a time series data warehouse for subsequent big data analysis and model training. The scheduling strategies are also uploaded to the cloud for historical tracing, optimization strategy comparison, and cross-regional strategy migration application. Understandably, the platform also provides a visual data analysis interface, which can be accessed by users or administrators through a web or mobile interface to view various operation indicators, equipment status, and optimization effects of the building space.

[0129] Further, the remote monitoring function supports real-time data stream presentation and alarm functions. In the event of device abnormalities, environmental parameter exceedances, or energy consumption surges, the system sends alarm information to the pre-set users through the cloud platform and automatically generates emergency scheduling recommendations. At the same time, the platform supports manual remote intervention in scheduling control, improving the flexibility and safety of system response. Understandably, the cloud service platform 108 also integrates an AI-based data mining engine that can identify patterns and predict trends from long-term operation data to assist building managers in developing energy optimization strategies and operation plans.

[0130] Further, the encrypted communication protocol includes a combination of symmetric and asymmetric encryption for transmitted data, as well as identity authentication mechanisms, access control, and data integrity verification methods to ensure that all data interactions during system operation meet enterprise-level security standards, preventing data leakage, tampering, and unauthorized access. Understandably, the cloud service platform 108 also supports deploying trained models to edge devices, implementing a cloud-edge collaborative intelligent scheduling strategy deployment mechanism, thereby balancing the real-time performance of the system and the intelligence of the model.

[0131] Understandably, by setting the cloud service platform 108, not only the system's data processing capacity and remote management efficiency are improved, but also the building space scheduling system has cross-scene and cross-region unified scheduling capability, meets the intelligent operation demand of large-scale building cluster, effectively reduces the single point failure risk, and enhances the stability and expansibility of the system.

[0132] The above merely describes exemplary embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields, or direct / indirect application in other related technical fields under the technical concept of the present application are included in the patent protection scope of the present application.

Claims

1. A multi-source perception and decision optimization based building space scheduling system, characterized in that, The building space scheduling system comprises: a multi-source perception module for collecting multi-source data in a building space, the multi-source data comprising environmental data, personnel data and equipment operation data, and dynamically adjusting the collection strategies of each monitoring unit through a self-organizing network collaboration mechanism to optimize data integrity; a data processing module connected to the multi-source perception module for pre-processing and feature extraction of the multi-source data to generate structured data; a decision optimization module connected to the data processing module, adopting a hierarchical decision architecture, the hierarchical decision architecture comprising a global optimization layer and a local optimization layer, wherein the global optimization layer formulates a macro scheduling strategy based on the structured data in combination with cross-space resource demand prediction; the local optimization layer formulates a specific scheduling strategy based on the structured data in combination with real-time scene and context information; the decision optimization module adopts a machine learning model to dynamically optimize the macro scheduling strategy and the specific scheduling strategy in combination with execution feedback; the decision optimization module comprises: a prediction submodule for predicting resource demand of the building space based on historical data and the structured data; an optimization submodule for generating a scheduling strategy through a hierarchical optimization process in combination with a dynamically adjusted optimization target according to the resource demand prediction of the prediction submodule: a global optimization layer for generating a macro scheduling strategy through a target function based on the structured data: Wherein, B is a cross-space resource allocation efficiency, is a cross-space resource balance degree, , is a dynamically adjusted weight coefficient, satisfying + = 1; the cross-space resource allocation efficiency B is calculated by the utilization rate of resource sharing, and the cross-space resource balance degree is determined by the variance of the resource allocation deviation of each building space. a local optimization layer for fine-tuning the macro scheduling strategy through a target function based on the structured data to generate a specific scheduling strategy: wherein, is a local optimization target value, E is an energy consumption value based on the equipment operation data, U is a space utilization based on the personnel data, C is a personnel comfort score based on the environment data, , , is a dynamically adjusted weight coefficient, satisfying + + = 1. wherein the optimization target comprises cross-space resource allocation efficiency improvement and resource balance optimization of the global optimization layer, and energy consumption minimization, space utilization maximization and personnel comfort optimization of the local optimization layer; an execution module connected to the decision optimization module for real-time scheduling of equipment and resources in the building space according to the macro scheduling strategy and the specific scheduling strategy, and feeding back execution results to the decision optimization module to verify strategy effectiveness and trigger adaptive adjustment; wherein the building space scheduling system supports collaborative scheduling of multiple building spaces, and realizes distributed decision-making and resource sharing among modules through a self-organizing network collaboration mechanism.

2. The building space scheduling system of claim 1, wherein, The multi-source perception module comprises: an environmental monitoring unit for collecting temperature, humidity, illumination and air quality data in the building space; a personnel monitoring unit for obtaining personnel location, density and behavior data; an equipment monitoring unit for monitoring the running state and energy consumption data of equipment in the building space; wherein the multi-source perception module determines global scheduling demand across spaces according to the macro scheduling strategy generated by the global optimization layer, and determines local scheduling demand of individual spaces according to the specific scheduling strategy generated by the local optimization layer, dynamically negotiates the collection tasks and frequencies of the above monitoring units to optimize data integrity and real-time performance through a self-organizing network collaboration mechanism.

3. The building space scheduling system of claim 1, wherein, The data processing module comprises: a data cleaning unit for denoising and outlier processing of the multi-source data; The feature extraction unit is configured to dynamically select a feature vector related to the global optimization layer and the local optimization layer scheduling target from the cleaned multi-source data through hierarchical feature extraction. The data fusion unit is configured to integrate feature vectors of different building spaces into unified structured data in the form of a multi-dimensional feature matrix through an incremental fusion algorithm.

4. The building space scheduling system of claim 1, wherein, The machine learning model includes a deep neural network model or a reinforcement learning model, which is optimized through a training data set to improve the collaborative performance of the global optimization layer and the local optimization layer.

5. The building space scheduling system of claim 1, wherein, The execution module includes: The device control unit is configured to predictively adjust the operating parameters of lighting, air conditioning and ventilation devices in the building space according to the specific scheduling strategy generated by the local optimization layer; The resource allocation unit is configured to dynamically adjust cross-space resource allocation and usage permissions according to the macro scheduling strategy generated by the global optimization layer, and adjust resource allocation in a single building space according to the specific scheduling strategy generated by the local optimization layer; The execution module adjusts the device operating state in advance to reduce response delay through a predictive scheduling mechanism, supports cross-space execution synchronization to coordinate resource use in multiple building spaces according to the macro scheduling strategy, and feeds back the execution result to the decision optimization module to optimize subsequent scheduling.

6. The building space scheduling system of claim 1, wherein, The system further includes: The communication module is configured to realize data transmission between the multi-source perception module, the data processing module, the decision optimization module and the execution module, and interconnection and intercommunication with external systems; wherein the communication module supports wired communication and wireless communication protocols.

7. The building space scheduling system of claim 1, wherein, The system further includes: The user interaction module is configured to receive user input scheduling requirements and feed back scheduling results and system operating states to the user; wherein the user interaction module includes a display interface and a voice interaction unit.

8. The building space scheduling system of claim 1, wherein, The system further includes: The adaptive learning module is configured to continuously optimize the performance of the machine learning model according to the operating data of the building space and user feedback; wherein the adaptive learning module supports online learning and offline learning.

9. The building space scheduling system according to any one of claims 1 to 8, characterized in that, The system further includes: The cloud service platform is configured to store the multi-source data and scheduling strategy, and provide remote monitoring and data analysis functions; The cloud service platform interacts with the system through an encrypted communication protocol.

Images