Hybrid office efficiency optimization system based on digital twinning and space calculation

Abstract

The invention discloses a hybrid office efficiency optimization system based on digital twinning and space calculation, and relates to the technical field of computer science and technology, and the system comprises a data collection module which captures the station layout parameters, the personnel movement track, the equipment use state and the environment parameters of an entity office space in real time through an Internet of Things sensor array, and transmits the parameters to a server; the sensor array comprises a positioning base station, a thermal imager, an intelligent electric meter and an acoustic sensor. The hybrid office efficiency optimization system provided by the invention can accurately and comprehensively map the office environment through the real-time data acquisition and multi-source fusion technology, solves the problem of single data acquisition of the traditional system, and improves the efficiency of the office by utilizing the space calculation and three-dimensional modeling technology. According to the system, a three-dimensional space model comprising an interactive station unit, an equipment entity and a personnel virtual avatar is constructed, a basis is provided for dynamic modeling and intelligent optimization, and a multi-objective optimization algorithm and a genetic algorithm are combined, so that the system can be under complex constraint conditions.

Description

Technical Field

[0001] The present invention relates to the field of computer science and technology, and in particular to a hybrid office efficiency optimization system based on digital twins and spatial computing. Background Art

[0002] With the rapid development of information technology and the profound transformation of office models, hybrid office models, with their advantages of combining flexibility and collaboration, have become a mainstream trend in modern corporate offices. In this model, the integration of physical office spaces and remote working scenarios places higher demands on optimizing office efficiency. Digital twin technology, by constructing a virtual mapping of physical space, can mirror the relationships between people, objects, and space in an office environment in real time. Spatial computing provides key technical support for processing complex three-dimensional scene data and optimizing spatial resource allocation. In this context, how to leverage digital twin and spatial computing technologies to dynamically model and intelligently optimize elements such as workstation layout, equipment scheduling, and personnel collaboration in hybrid office scenarios has become an important research direction for improving office efficiency and reducing operating costs.

[0003] However, current efficiency optimization solutions for hybrid office environments still leave much to be desired. On the one hand, traditional office space management systems often limit their data collection of the physical environment to a single dimension, such as focusing solely on workstation usage or equipment energy consumption. They lack the integrated perception and in-depth analysis of multiple sources of data, including personnel movement trajectories, environmental parameters, and collaboration needs. This results in an inaccurate and comprehensive digital mapping of the office scene. On the other hand, existing optimization models often rely on static layout planning and fixed policy configurations, making them difficult to adapt to the dynamic scenarios of hybrid offices, characterized by high personnel mobility and changing task demands. They also have significant shortcomings in balancing multi-objective optimization objectives such as space utilization, equipment energy efficiency, and personnel collaboration efficiency, and lack mechanisms for coordinating optimization between remote collaboration tools and physical office resources. Furthermore, some systems oversimplify the calculation of key parameters such as spatial topology and accessibility metrics during data processing and model construction, ignoring practical constraints such as obstacle occlusion and path attenuation. This limits the feasibility and effectiveness of optimization solutions. To address this issue, we propose a hybrid office efficiency optimization system based on digital twins and spatial computing. Summary of the Invention

[0004] In order to solve the above technical problems, a hybrid office efficiency optimization system based on digital twins and spatial computing is provided. This technical solution solves the above problems.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] A hybrid office efficiency optimization system based on digital twins and spatial computing includes:

[0007] A data acquisition module that captures the physical office space's workstation layout parameters, personnel movement trajectories, equipment usage status, and environmental parameters in real time through an IoT sensor array. The sensor array includes a positioning base station, thermal imagers, smart meters, and acoustic sensors.

[0008] The 3D modeling module builds a virtual twin mapped to the physical space based on the spatial computing engine, generating a 3D spatial model that includes interactive workstation units, equipment entities, and personnel avatars;

[0009] A simulation analysis module uses a multi-objective optimization algorithm to establish a space-time constraint model that minimizes the combined costs of space idleness, equipment energy consumption, and personnel waiting and movement time through a weighted summation method;

[0010] The optimization configuration module generates the optimal solution set based on the genetic algorithm iteration, dynamically adjusts the workstation layout matrix, meeting time allocation vector and remote collaboration tool combination matrix;

[0011] Configure the output module to generate an executable strategy package containing the optimal space layout plan, equipment configuration list and schedule planning table, and output control instructions through the building management system interface.

[0012] Preferably, the data acquisition module includes:

[0013] The workstation status perception submodule deploys a pressure sensor array to collect workstation contact time data and calculate the workstation utilization rate per unit time;

[0014] The environmental parameter acquisition submodule builds a three-dimensional thermal map integrating temperature, humidity, and gas concentration through a distributed sensor network;

[0015] The personnel trajectory tracking submodule calculates the deviation ratio between the actual movement path of the personnel and the theoretical straight line path through the positioning system composed of positioning tags and base stations;

[0016] The data preprocessing unit uses a filtering algorithm to eliminate noise from the original data and establish a time series database containing timestamps, spatial coordinates and motion vectors.

[0017] Preferably, the three-dimensional modeling module:

[0018] The point cloud data is converted into a regular grid model using voxel reconstruction technology, and the spatial resolution automatically sets a dynamic threshold based on the site size;

[0019] The dynamic update mechanism triggers model reconstruction by calculating the volume change rate of the model in adjacent time periods;

[0020] The workstation unit modeling uses parametric templates to define size specifications, interface types and viewing angle range;

[0021] The person's virtual avatar maps the real posture through the coordinates of the skeleton joint points;

[0022] The spatial topology analysis submodule calculates the accessibility index between workstations based on distance attenuation.

[0023] Preferably, the simulation analysis module:

[0024] A multi-objective genetic algorithm framework is used to define a set of decision variables including a workstation layout matrix, a set of meeting time intervals, and a remote tool weight vector.

[0025] Constraints include the lower limit of workstation spacing, equipment service radius limit, and collaboration path length threshold;

[0026] The objective function is set as a weighted index that comprehensively optimizes space utilization, energy efficiency, and time efficiency;

[0027] The space utilization is measured by the proportion of used area, the energy efficiency is calculated by the sum of the products of the equipment operating power and the usage time, and the time efficiency is evaluated by the linear combination of waiting time, communication delay and meeting preparation time.

[0028] Preferably, the genetic algorithm implementation process of the optimization configuration module includes:

[0029] In the initialization phase, the population size and the maximum number of iterations are set, and a hybrid encoding method is used to perform chromosome encoding on the workstation layout, meeting time, and tool combination;

[0030] The fitness function balances the optimization objectives through dynamic weight coefficients, and the selection operator adopts a competitive screening strategy;

[0031] The cross operation implements the block exchange of the workstation layout matrix and the reorganization of the meeting time interval. The mutation operation includes the workstation position replacement, time window offset and random adjustment of tool weights.

[0032] Preferably, the configuration output module includes:

[0033] The space utilization optimization submodule implements a multi-level optimization strategy. At the macro level, it divides functional areas by geometric figures and calculates the compactness of regional morphology. At the meso level, it uses a mechanical model to adjust the spacing of workstation layouts. At the micro level, it optimizes the orientation angle of workstations through visibility scoring.

[0034] The spatial overlap detection submodule uses the bounding box projection method to identify layout conflicts.

[0035] Preferably, the data preprocessing unit adopts a multi-source data fusion architecture to perform spatiotemporal alignment processing on heterogeneous sensor data, specifically including:

[0036] A dynamic compensation model is established to calibrate the motion trajectory of the positioning base station and thermal imager data through the state transfer matrix and the observation matrix. The state update includes process noise compensation, and the observation value calculation includes observation noise correction.

[0037] Implement cross-modal data registration, use a point cloud matching algorithm to align the spatially distributed data of the acoustic sensor and the thermal imager with rigid transformation, and calculate the optimal rotation and translation parameters to minimize the spatial deviation of the corresponding point sets;

[0038] Construct a multi-stage data cleaning pipeline. The first stage uses time domain filtering to eliminate instantaneous pulse interference from the workstation pressure sensor. The second stage uses a statistical distribution model to identify and eliminate abnormal measurement values that are outside the reasonable range.

[0039] The time series database adopts a hierarchical storage structure, cyclically storing high-frequency data in the cache area, and storing low-frequency data using timestamp-associated compression coding. The compression ratio is dynamically configured according to the data sampling frequency.

[0040] Preferably, the dynamic update mechanism realizes adaptive reconstruction by constructing a spatial change rate evaluation model, specifically including:

[0041] The volume change rate is defined as the ratio of the model volume change to the original volume per unit time. When the rate exceeds the preset critical value, a full model reconstruction is triggered, otherwise a local incremental update is performed.

[0042] Incremental update uses a tree-like spatial partitioning structure to implement local adjustments to the grid topology within the subdivided spatial units;

[0043] Personnel posture mapping uses joint motion interpolation algorithm to achieve smooth transition, and sets physiological kinematic constraints to limit the range of joint rotation angles;

[0044] The accessibility index calculation introduces the impact factor of spatial obstacles and establishes a composite evaluation function based on distance exponential decay and obstacle occlusion status. The decay coefficient is related to the distance between workstations, and the occlusion coefficient reflects the density of obstacles on the path.

[0045] Implement real-time spatial interference detection, use geometric projection method to calculate the minimum separation distance between workstation boundaries, and generate spatial layout feasibility judgment rules.

[0046] Preferably, the multi-objective optimization algorithm establishes a decision model based on the Pareto frontier, specifically including:

[0047] A multidimensional decision space is defined, which includes a workstation layout matrix, a meeting time set, and a tool weight vector. The elements of the workstation layout matrix use binary identifiers to represent the workstation occupancy status.

[0048] Establish equipment service coverage constraints, requiring each device to meet the minimum number of workstation service requirements within its effective range;

[0049] A time overlap detection mechanism is introduced to impose a conflict penalty coefficient on overlapping meeting time periods;

[0050] The objective function adopts a multi-objective balance strategy and simultaneously optimizes space utilization, energy efficiency and time efficiency indicators through the weighted extreme value minimization method;

[0051] Establish a dynamic preference adjustment mechanism to adjust the weight ratio of each optimization goal in real time according to the goal priority set by decision makers.

[0052] Preferably, the genetic algorithm implements evolutionary optimization of a hybrid strategy, specifically including:

[0053] The chromosome adopts a composite coding structure: the workstation layout segment uses binary matrix coding, the meeting time segment uses the time window center point real number coding, and the tool combination segment uses option index integer coding;

[0054] The fitness function is designed as the inverse of the multi-objective comprehensive evaluation value, and the weight coefficient is dynamically adjusted according to the annealing strategy during the iteration process;

[0055] Implement an elite retention mechanism, whereby each generation iteratively retains high-ranking individuals in the non-inferior solution set and directly inherits them to the next generation;

[0056] The crossover operation includes the exchange of workstation layout sub-matrices and the linear interpolation of meeting time to generate a new time window;

[0057] Mutation operations include workstation status flipping, random time window offset, and random tool combination replacement;

[0058] The termination condition is set as the optimization effect of multiple generations is stable within the set threshold or the maximum number of iterations is reached.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] The hybrid office efficiency optimization system proposed in the present invention can accurately and comprehensively map the office environment through real-time data collection and multi-source fusion technology, solving the problem of single data collection in traditional systems. Utilizing spatial computing and three-dimensional modeling technology, the system constructs a three-dimensional spatial model including interactive workstation units, equipment entities and personnel virtual avatars, providing a basis for dynamic modeling and intelligent optimization. The combination of multi-objective optimization algorithm and genetic algorithm enables the system to simultaneously optimize space utilization, energy efficiency and time efficiency under complex constraints, significantly improving office efficiency and reducing operating costs. In addition, the system's dynamic update mechanism and real-time spatial interference detection function ensure the feasibility and effectiveness of the optimization plan, effectively responding to the challenges of high personnel mobility and changing task requirements under the hybrid office model. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a system module framework diagram of the present invention;

[0062] Figure 2 It is a system workflow diagram of the present invention. DETAILED DESCRIPTION

[0063] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0064] Reference Figure 1 As shown in the figure, the hybrid office efficiency optimization system based on digital twin and spatial computing includes:

[0065] The data acquisition module is the foundation of the entire system, acting as its "senses," capturing key information about the physical office space in real time. An IoT sensor array, comprised of positioning base stations, thermal imagers, smart meters, and acoustic sensors, is deployed here. The workstation status perception submodule utilizes a pressure sensor array to accurately collect workstation contact time data and, by calculating workstation utilization rates per unit time, provides real-time insights into each workstation's usage. The environmental parameter acquisition submodule utilizes a distributed sensor network to construct three-dimensional thermal maps incorporating information such as temperature, humidity, and gas concentration, providing detailed data support for understanding office comfort and air quality. The personnel trajectory tracking submodule, utilizing a positioning system comprised of positioning tags and base stations, accurately calculates the deviation between a person's actual movement path and a theoretical straight-line path, providing a clear understanding of their movements within the office space. To ensure data quality, the data preprocessing unit uses filtering algorithms to remove noise from the raw data and constructs a time series database containing timestamps, spatial coordinates, and motion vectors, providing a clean and organized data foundation for subsequent analysis and processing.

[0066] The 3D modeling module, serving as one of the system's "brains," builds a virtual twin based on a spatial computing engine, mirroring the physical space. It utilizes voxelized reconstruction technology to convert point cloud data into a regular grid model. It automatically adjusts spatial resolution based on site dimensions using dynamic thresholds, ensuring both accurate and efficient models. A dynamic update mechanism triggers model reconstruction by calculating the rate of change in the model volume over time, enabling the virtual model to reflect changes in the physical space in real time. For workstation unit modeling, parametric templates are used to define dimensions, interface types, and viewing angles, ensuring each workstation has a precise digital representation in virtual space. Personnel avatars map their real-world postures using skeletal joint coordinates, making human movement in virtual space more realistic and believable. Furthermore, the spatial topology analysis submodule calculates distance-attenuated accessibility metrics between workstations, providing crucial spatial relationship data for subsequent simulation analysis and configuration optimization.

[0067] The simulation and analysis module applies a multi-objective optimization algorithm to establish a space-time constraint model, aiming to find the optimal solution for office space utilization through scientific calculation and analysis. This module uses a multi-objective genetic algorithm framework to define a set of decision variables, including a workstation layout matrix, a set of meeting time intervals, and a remote tool weight vector. These variables cover the key factors in office space management. Constraints include a lower limit on workstation spacing, equipment service radius limits, and collaboration path length thresholds to ensure the feasibility of the optimization solution in practical applications. The objective function is set as a weighted indicator that comprehensively optimizes space utilization, energy efficiency, and time efficiency. Space utilization is measured by the proportion of used area, energy efficiency is calculated by the sum of the products of equipment operating power and usage time, and time efficiency is evaluated by a linear combination of waiting time, communication delay, and meeting preparation time, comprehensively considering all aspects of office efficiency.

[0068] The optimization configuration module generates the optimal solution set based on the iterative genetic algorithm, which is a key link in achieving precise optimization of the system. In the initialization phase, the appropriate population size and maximum number of iterations are set, and a hybrid encoding method is used to perform chromosome encoding on the workstation layout, meeting time and tool combination, converting the actual problem into a form that the algorithm can handle. The fitness function balances the various optimization objectives through dynamic weight coefficients to ensure that the algorithm does not favor a certain goal and ignore other goals during the optimization process. The selection operator adopts a competitive screening strategy to retain excellent individuals and eliminate poor individuals to improve the overall quality of the population. The crossover operation implements the block exchange of the workstation layout matrix and the reorganization of the meeting time interval. The mutation operation includes the replacement of workstation positions, the offset of time windows and the random adjustment of tool weights. These operations increase the diversity of the population, prevent the algorithm from falling into the local optimum, and thus find a better solution.

[0069] The configuration output module serves as a bridge between the system and actual applications. It generates an executable strategy package containing the optimal space layout plan, equipment configuration list, and schedule planning table, and outputs control instructions through the building management system interface to effectively apply the optimization plan to the actual office environment. This module includes a space utilization optimization submodule and a space overlap detection submodule. The space utilization optimization submodule implements a multi-level optimization strategy. At the macro level, it divides functional areas through geometric shapes and calculates the compactness of regional morphology to make the functional zoning of office space more reasonable; at the meso level, it uses mechanical models to adjust the layout spacing of workstations, improving space utilization while ensuring employee comfort; at the micro level, it optimizes the orientation angle of workstations through visibility scoring to enhance the employee work experience. The space overlap detection submodule uses the bounding box projection method to identify layout conflicts, ensuring that there are no physical conflicts in the optimized space layout, ensuring the feasibility and safety of the plan.

[0070] In summary, the hybrid office efficiency optimization system based on digital twins and spatial computing achieves intelligent management and optimization of office space through the collaborative work of various modules. From data acquisition to 3D modeling, from simulation analysis to optimized configuration, and finally to configuration output, each link is closely interconnected and interconnected, providing strong technical support for improving hybrid office efficiency. With the continuous development and improvement of technology, this system is expected to play an even more important role in future office environments, promoting the development of more efficient, intelligent, and comfortable working models.

[0071] The data preprocessing unit adopts a multi-source data fusion architecture to perform spatiotemporal alignment processing on heterogeneous sensor data, specifically including:

[0072] A dynamic compensation model based on Kalman filtering is established. The motion trajectory of the positioning base station and thermal imager data is calibrated through the state equation x(k) = A·x(k-1) + B·u(k) + w(k) and the observation equation z(k) = H·x(k) + v(k), where A is the state transfer matrix, H is the observation matrix, w(k) and v(k) are process noise and observation noise, respectively.

[0073] Implement cross-modal data registration, using the iterative closest point algorithm to rigidly register the sound field distribution point cloud obtained by the acoustic sensor with the temperature distribution point cloud output by the thermal imager, and calculate the rotation matrix R and translation vector t to minimize the sum of squared errors of the corresponding point sets;

[0074] A multi-stage data cleaning pipeline was constructed. The first stage used a sliding window filter to eliminate transient interference signals from the workstation pressure sensor. The second stage used Z-score-based outlier detection to remove outliers outside the 3σ range.

[0075] The time series database adopts a hybrid storage structure, storing high-frequency sampling data in a ring buffer, and lossy compressing low-frequency state change data using a time series compression algorithm. The compression rate is dynamically adjusted according to the data type.

[0076] The dynamic update mechanism realizes adaptive reconstruction by constructing a spatial change rate evaluation model, which specifically includes:

[0077] Define the model volume change rate When δ exceeds the preset threshold θ, a full reconstruction is triggered, otherwise an incremental update is performed;

[0078] Incremental updates use a hierarchical octree structure to implement local mesh subdivision and merging operations at the sub-node granularity;

[0079] The quaternion interpolation algorithm is used to smooth the motion trajectory of the joint points in the personnel posture mapping, and the joint rotation angle constraints are set to prevent non-physiological deformation;

[0080] The obstacle correction factor is introduced into the accessibility index calculation to establish an improved attenuation function:

[0081] A ij =exp(-αd ij )·∏(1-β k ·O k )

[0082] Where α is the distance attenuation coefficient, β k is the occlusion coefficient of the kth obstacle, O k A Boolean value indicating the path occlusion status;

[0083] Implement real-time collision detection, use the separating axis theorem to calculate the minimum translation vector between the bounding boxes of workstations, and generate feasible layout constraints.

[0084] The multi-objective optimization algorithm establishes a decision model based on the Pareto frontier, specifically including:

[0085] Defining the decision space The elements of the m×n workstation layout matrix L take 0 / 1 to indicate the workstation occupancy status;

[0086] Construct device service radius constraints:

[0087]

[0088] Where D is the device set, r i is the service radius, N i Minimum coverage requirement;

[0089] Introducing time conflict detection function When C(T)>0, a penalty term is imposed;

[0090] The objective function adopts the weighted Chebyshev form: Where f1 is the space idle rate, f2 is the total energy consumption, and f3 is the time efficiency loss;

[0091] Establish a preference guidance mechanism to dynamically adjust the weight coefficient ω according to the target priority set by the decision maker i .

[0092] The genetic algorithm implements evolutionary optimization of hybrid strategies, specifically including:

[0093] The chromosome encoding adopts a composite structure: the workstation layout segment uses a binary encoding matrix, the meeting time segment uses real number encoding to represent the time window center point, and the tool combination segment uses integer encoding to represent the option index;

[0094] The fitness function is designed as where λ i Dynamic weights are adjusted by simulated annealing strategy according to generations T is the temperature parameter;

[0095] Implement the elite retention strategy, retaining the top 10% of the non-dominated solution set in each generation and directly entering the next generation;

[0096] Crossover operator design: The workstation layout adopts block crossover, randomly selecting k×k sub-matrices for exchange; the meeting time adopts arithmetic crossover to generate a new time window t new =αt p +(1-α)t q ;

[0097] Mutation operators include: bit-flip mutation of workstation layout, Gaussian perturbation mutation of meeting time window, and uniform random replacement of tool combination;

[0098] The termination condition is set as the improvement rate of the optimal solution is less than 0.1% for 20 consecutive generations or the preset maximum number of evaluations is reached.

[0099] Reference Figure 2 As shown, the present invention utilizes real-time data from physical office spaces collected through an IoT sensor array, and constructs a three-dimensional virtual twin after data preprocessing. A multi-objective optimization algorithm is used to establish a space-time constraint model, comprehensively considering space utilization, energy efficiency, and time efficiency. An optimal solution set is generated through iterative genetic algorithms. The system dynamically adjusts workstation layout, meeting time allocation, and remote collaboration tool combinations to generate an executable policy package containing the optimal space layout plan, equipment configuration list, and schedule. Control instructions are then output through the building management system interface to optimize hybrid office efficiency.

[0100] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions merely illustrate the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A hybrid office efficiency optimization system based on digital twins and spatial computing, characterized by: include: A data acquisition module that captures the physical office space's workstation layout parameters, personnel movement trajectories, equipment usage status, and environmental parameters in real time through an IoT sensor array. The sensor array includes a positioning base station, thermal imagers, smart meters, and acoustic sensors. The 3D modeling module builds a virtual twin mapped to the physical space based on the spatial computing engine, generating a 3D spatial model that includes interactive workstation units, equipment entities, and personnel avatars; A simulation analysis module uses a multi-objective optimization algorithm to establish a space-time constraint model that minimizes the combined costs of space idleness, equipment energy consumption, and personnel waiting and movement time through a weighted summation method; The optimization configuration module generates the optimal solution set based on the genetic algorithm iteration, dynamically adjusts the workstation layout matrix, meeting time allocation vector and remote collaboration tool combination matrix; Configure the output module to generate an executable strategy package containing the optimal space layout plan, equipment configuration list and schedule planning table, and output control instructions through the building management system interface.

2. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 1 is characterized in that: The data acquisition module includes: The workstation status perception submodule deploys a pressure sensor array to collect workstation contact time data and calculate the workstation utilization rate per unit time; The environmental parameter acquisition submodule builds a three-dimensional thermal map integrating temperature, humidity, and gas concentration through a distributed sensor network; The personnel trajectory tracking submodule calculates the deviation ratio between the actual movement path of the personnel and the theoretical straight line path through the positioning system composed of positioning tags and base stations; The data preprocessing unit uses a filtering algorithm to eliminate noise from the original data and establish a time series database containing timestamps, spatial coordinates and motion vectors.

3. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 1 is characterized in that: The three-dimensional modeling module: The point cloud data is converted into a regular grid model using voxel reconstruction technology, and the spatial resolution automatically sets a dynamic threshold based on the site size; The dynamic update mechanism triggers model reconstruction by calculating the volume change rate of the model in adjacent time periods; The workstation unit modeling uses parametric templates to define size specifications, interface types and viewing angle range; The person's virtual avatar maps the real posture through the coordinates of the skeleton joint points; The spatial topology analysis submodule calculates the accessibility index between workstations based on distance attenuation.

4. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 1 is characterized in that: The simulation analysis module: A multi-objective genetic algorithm framework is used to define a set of decision variables including a workstation layout matrix, a set of meeting time intervals, and a remote tool weight vector. Constraints include the lower limit of workstation spacing, equipment service radius limit, and collaboration path length threshold; The objective function is set as a weighted index that comprehensively optimizes space utilization, energy efficiency, and time efficiency; The space utilization is measured by the proportion of used area, the energy efficiency is calculated by the sum of the products of the equipment operating power and the usage time, and the time efficiency is evaluated by the linear combination of waiting time, communication delay and meeting preparation time.

5. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 1 is characterized in that: The genetic algorithm implementation process of the optimization configuration module includes: In the initialization phase, the population size and the maximum number of iterations are set, and a hybrid encoding method is used to perform chromosome encoding on the workstation layout, meeting time, and tool combination; The fitness function balances the optimization objectives through dynamic weight coefficients, and the selection operator adopts a competitive screening strategy; The cross operation implements the block exchange of the workstation layout matrix and the reorganization of the meeting time interval. The mutation operation includes the workstation position replacement, time window offset and random adjustment of tool weights.

6. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 1 is characterized in that: The configuration output module includes: The space utilization optimization submodule implements a multi-level optimization strategy. At the macro level, it divides functional areas by geometric figures and calculates the compactness of regional morphology. At the meso level, it uses a mechanical model to adjust the spacing of workstation layouts. At the micro level, it optimizes the orientation angle of workstations through visibility scoring. The spatial overlap detection submodule uses the bounding box projection method to identify layout conflicts.

7. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 2 is characterized in that: The data preprocessing unit adopts a multi-source data fusion architecture to perform spatiotemporal alignment processing on heterogeneous sensor data, specifically including: A dynamic compensation model is established to calibrate the motion trajectory of the positioning base station and thermal imager data through the state transfer matrix and the observation matrix. The state update includes process noise compensation, and the observation value calculation includes observation noise correction. Implement cross-modal data registration, use a point cloud matching algorithm to align the spatially distributed data of the acoustic sensor and the thermal imager with rigid transformation, and calculate the optimal rotation and translation parameters to minimize the spatial deviation of the corresponding point sets; Construct a multi-stage data cleaning pipeline. The first stage uses time domain filtering to eliminate instantaneous pulse interference from the workstation pressure sensor. The second stage uses a statistical distribution model to identify and eliminate abnormal measurement values that are outside the reasonable range. The time series database adopts a hierarchical storage structure, cyclically storing high-frequency data in the cache area, and storing low-frequency data using timestamp-associated compression coding. The compression ratio is dynamically configured according to the data sampling frequency.

8. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 3 is characterized in that: The dynamic update mechanism realizes adaptive reconstruction by constructing a spatial change rate evaluation model, which specifically includes: The volume change rate is defined as the ratio of the model volume change to the original volume per unit time. When the rate exceeds a preset critical value, a full model reconstruction is triggered, otherwise a local incremental update is performed. Incremental update uses a tree-like spatial partitioning structure to implement local adjustments to the grid topology within the subdivided spatial units; Personnel posture mapping uses joint motion interpolation algorithm to achieve smooth transition, and sets physiological kinematic constraints to limit the range of joint rotation angles; The accessibility index calculation introduces the impact factor of spatial obstacles and establishes a composite evaluation function based on distance exponential decay and obstacle occlusion status. The decay coefficient is related to the distance between workstations, and the occlusion coefficient reflects the density of obstacles on the path. Implement real-time spatial interference detection, use geometric projection method to calculate the minimum separation distance between workstation boundaries, and generate spatial layout feasibility judgment rules.

9. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 4 is characterized in that: The multi-objective optimization algorithm establishes a decision model based on the Pareto frontier, specifically including: A multidimensional decision space is defined, which includes a workstation layout matrix, a meeting time set, and a tool weight vector. The elements of the workstation layout matrix use binary identifiers to represent the workstation occupancy status. Establish equipment service coverage constraints, requiring each device to meet the minimum number of workstation service requirements within its effective range; A time overlap detection mechanism is introduced to impose a conflict penalty coefficient on overlapping meeting time periods; The objective function adopts a multi-objective balance strategy and simultaneously optimizes space utilization, energy efficiency and time efficiency indicators through the weighted extreme value minimization method; Establish a dynamic preference adjustment mechanism to adjust the weight ratio of each optimization goal in real time according to the goal priority set by decision makers.

10. The hybrid office efficiency optimization system based on digital twin and spatial computing according to claim 5 is characterized in that: The genetic algorithm implements evolutionary optimization of hybrid strategies, specifically including: The chromosome adopts a composite coding structure: the workstation layout segment uses binary matrix coding, the meeting time segment uses the time window center point real number coding, and the tool combination segment uses option index integer coding; The fitness function is designed as the inverse of the multi-objective comprehensive evaluation value, and the weight coefficient is dynamically adjusted according to the annealing strategy during the iteration process; Implement an elite retention mechanism, whereby each generation iteratively retains high-ranking individuals in the non-inferior solution set and directly inherits them to the next generation; The crossover operation includes the exchange of workstation layout sub-matrices and the linear interpolation of meeting time to generate a new time window; Mutation operations include workstation status flipping, random time window offset, and random tool combination replacement; The termination condition is set as the optimization effect of multiple generations is stable within the set threshold or the maximum number of iterations is reached.

Images