Intelligent planning method and system based on building intelligent system

Abstract

The invention provides an intelligent planning method and system based on a building intelligent system, and the method comprises the steps: obtaining the demand data of each subsystem in the building intelligent system, and integrating the demand data into a demand data set; based on the demand data set, matching a planning model of the building intelligent system; generating an initial planning scheme according to the planning model, performing analogue simulation on the initial planning scheme, and evaluating operation effects of the initial planning scheme in different scenes; and optimizing the initial planning scheme according to an analogue simulation result to form a final planning scheme. According to the invention, the method comprises the steps: carrying out the simulation of an initial planning scheme, and evaluating the operation effects of the initial planning scheme in different scenes; and optimizing the initial planning scheme according to the analogue simulation result to form a final planning scheme, thereby overcoming the defects of low accuracy and low efficiency when the current planning scheme is optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent planning method and system based on a building intelligent system. Background Art

[0002] As building intelligent technology develops towards complexity and integration, the limitations of traditional building intelligent system planning methods in terms of demand integration and solution optimization are becoming increasingly prominent.

[0003] On the one hand, existing technologies lack a systematic mechanism for integrating demand data from various subsystems (such as security, HVAC, and lighting). This fragmented collection often makes it difficult for planning solutions to reflect the overall functional objectives of a building. For example, the layout of security monitoring points lacks coordination with HVAC airflow design, which can easily lead to wasted space resources or functional conflicts. On the other hand, the solution optimization process is highly dependent on the experience of engineers and lacks quantitative model support in balancing multiple objectives such as energy efficiency, cost, and user experience. This often leads to the problem of "losing sight of one thing while focusing on another" by selecting low-performance equipment to reduce initial costs, which in turn leads to a surge in later operation and maintenance costs. Manual adjustments are also inefficient and require repeated trial and error to meet actual needs.

[0004] Therefore, the current planning scheme has the defects of low accuracy and low efficiency during optimization. Summary of the Invention

[0005] The main purpose of the present invention is to provide an intelligent planning method and system based on a building intelligent system, aiming to overcome the defects of low accuracy and low efficiency in the optimization of current planning schemes.

[0006] To achieve the above objectives, the present invention provides an intelligent planning method based on a building intelligent system, comprising the following steps: Obtain demand data for each subsystem in the building intelligent system and integrate it into a demand data set; Based on the demand data set, matching the planning model of the building intelligent system; Generate an initial planning scheme based on the planning model, and simulate the initial planning scheme to evaluate its operating effect in different scenarios; The initial planning scheme is optimized according to the simulation results to form a final planning scheme.

[0007] Furthermore, each of the subsystems includes an intelligent security system, an intelligent lighting system, and an intelligent power system; the planning model is obtained by training using an intelligent algorithm, and the intelligent algorithm includes a genetic algorithm and a particle swarm optimization algorithm.

[0008] Furthermore, matching a planning model of a building intelligent system based on the demand data set includes: Extracting features from the demand dataset to identify key demand features, wherein the key demand features include the building's functional type, spatial layout, user performance requirements for each subsystem, budget constraints, and expected energy efficiency targets; Calling a planning model library; the planning model library contains a variety of pre-built planning models, each planning model corresponding to different features; Compare the extracted key demand features with the features of each planning model in the planning model library, and calculate the similarity score between the key demand features and each planning model; According to the similarity score, the planning models with similarity scores higher than a preset threshold are screened out as candidate planning models; The candidate planning model with the highest similarity score is taken as the final matching planning model.

[0009] Furthermore, the initial planning scheme is optimized according to the simulation results, including: Conduct multi-dimensional analysis on the simulation results to identify abnormal features in spatial layout and time series and obtain defect analysis results; Based on the defect analysis results, generate multiple sets of differentiated optimization strategies; Comprehensively quantify and score each set of differentiated optimization strategies, and automatically select the optimal solution that balances multiple objectives through intelligent algorithms; the target requirements include energy efficiency, cost, and user experience requirements; Collect operational data in real time and dynamically compare it with the target requirements, and use adaptive learning mechanisms to continuously fine-tune the optimal solution.

[0010] Furthermore, after the initial planning scheme is optimized according to the simulation results to form a final planning scheme, the following steps are performed: Obtain the approval code of each approval terminal, and construct an approval code array based on each approval code; Acquiring the approval requirements of the final planning scheme, and adjusting the approval code array based on the approval requirements to obtain an adjusted code array; Obtain historical approval efficiency trends for each approval terminal; For each approval terminal, optimize its own historical approval efficiency trend based on the historical approval efficiency trends of other approval terminals to obtain the optimized approval efficiency trend; Based on the optimized approval efficiency trend and the adjustment code array, corresponding approval authority is generated for configuring the authority of the corresponding approval terminal to the final planning scheme.

[0011] The present invention also provides an intelligent planning system based on a building intelligent system, comprising: The acquisition module is used to obtain the demand data of each subsystem in the building intelligent system and integrate it into a demand data set; A matching module, configured to match a planning model of a building intelligent system based on the demand data set; An evaluation module is used to generate an initial planning scheme based on the planning model, and simulate the initial planning scheme to evaluate its operating effect in different scenarios; The optimization module is used to optimize the initial planning scheme according to the simulation results to form a final planning scheme.

[0012] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0013] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0014] The intelligent planning method and system based on a building intelligent system provided by the present invention include: obtaining demand data of each subsystem in the building intelligent system and integrating it into a demand data set; matching a planning model of the building intelligent system based on the demand data set; generating an initial planning scheme based on the planning model, and simulating the initial planning scheme to evaluate its operating effect in different scenarios; optimizing the initial planning scheme based on the simulation results to form a final planning scheme. In the present invention, by simulating the initial planning scheme to evaluate its operating effect in different scenarios; and optimizing the initial planning scheme based on the simulation results to form a final planning scheme, the shortcomings of low accuracy and low efficiency in the optimization of current planning schemes are overcome. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of the steps of an intelligent planning method based on a building intelligent system in one embodiment of the present invention; Figure 2 This is a structural block diagram of an intelligent planning system based on a building intelligent system in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0016] The implementation, functional features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with embodiments. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] Reference Figure 1 In one embodiment of the present invention, a smart planning method based on a building intelligent system is provided, comprising the following steps: Step S1, obtaining the demand data of each subsystem in the building intelligent system and integrating it into a demand data set; Step S2, matching a planning model of a building intelligent system based on the demand data set; Step S3, generating an initial planning scheme based on the planning model, and performing simulation on the initial planning scheme to evaluate its operating effect under different scenarios; Step S4: Optimize the initial planning scheme according to the simulation results to form a final planning scheme.

[0019] In this embodiment, as described in step S1 above, by collecting and integrating dispersed subsystem requirements, the conflicting objectives caused by data fragmentation in traditional planning are resolved, providing a unified, standardized data foundation for subsequent intelligent planning. First, data from each subsystem is collected through diverse channels. This includes functional requirements such as the monitoring range and accuracy requirements of the intelligent security system, the temperature and humidity control ranges of the intelligent HVAC system, and the light intensity standards of the intelligent lighting system. Constraints such as building space layout drawings, user usage survey results, and regulatory restrictions on equipment deployment (such as fire safety spacing requirements) are also collected.

[0020] Secondly, data cleaning technology is used to eliminate abnormal data (such as energy consumption values that clearly exceed the physical range), and through semantic mapping and format conversion, heterogeneous data (such as coordinate data of security systems and current parameters of power systems) are unified into structured demand data sets, such as building a three-dimensional data model that includes regional functions, subsystem indicators, and constraints.

[0021] In this embodiment, a demand dataset covering all elements of the building is formed to ensure that the requirements of each subsystem are spatially and logically coordinated, avoiding resource waste (such as repeated deployment of sensors) or functional conflicts (such as mismatch between lighting illumination and surveillance camera sensitivity parameters) caused by independent planning.

[0022] As described in step S2 above, the limitations of traditional fixed templates are overcome, and the planning model is accurately adapted to the personalized needs of the building, thereby improving the pertinence and effectiveness of the plan.

[0023] First, key features are extracted from the demand dataset, such as building type (residential, commercial complex, industrial plant), spatial complexity (single-story / multi-story / high-rise), energy efficiency target (standard energy-saving requirements or green building three-star certification), and security level (basic monitoring or high-security level). This constructs a multidimensional demand feature vector. Second, an intelligent matching algorithm (such as fuzzy logic search or deep learning models) is used to search within a pre-built planning model library. This library contains planning models for different scenarios, such as a security-energy-lighting linkage model for high-rise commercial complexes and an integrated photovoltaic energy storage-intelligent temperature control model for low-carbon residential buildings. During the matching process, the algorithm automatically selects the most suitable model by calculating the similarity (e.g., cosine similarity) between the demand feature vector and the model feature labels. This embodiment avoids the adaptability issues caused by one-size-fits-all planning. For example, a lightweight, low-cost equipment deployment model is matched to an old residential renovation project, rather than directly applying the complex system architecture of a new office building. This ensures that the planning solution is more aligned with actual needs and reduces initial investment waste.

[0024] As described in step S3 above, an initial plan is generated based on the planning model, and its operating effects in different scenarios are evaluated through simulation. The traditional "post-completion debugging" is replaced by a virtual environment preview, which exposes potential problems of the planning plan in the real scenario in advance and reduces implementation risks and costs.

[0025] First, an initial planning scheme is automatically generated based on the matching planning model, including equipment deployment points (such as camera and sensor installation locations), network topology (such as wired-wireless hybrid networking solutions), control strategies (such as air conditioning automatically adjusting temperature based on traffic flow), etc. Second, digital twin technology is used to build a virtual simulation environment for the building intelligent system, simulating multi-dimensional scenarios: Daily operation scenarios: such as elevator dispatch efficiency during the morning rush hour on weekdays and lighting comfort in office areas; Extreme environmental scenarios: such as the energy consumption performance of HVAC systems in hot weather and the stability of security systems in heavy rain; Emergency response scenarios: such as the linkage timeliness of smoke detection, sprinkler, and evacuation indication systems during fire alarms.

[0026] By integrating sensor data and dynamically adjusting parameters, the solution evaluates key indicators (such as equipment failure rate, energy consumption, and user experience scores) in various scenarios, generating an assessment report that includes performance curves and risk points. This allows for early detection of cross-system collaboration flaws (such as delays in the linkage between smart lighting and security monitoring in low-light environments), avoiding the multiple on-site rectifications required by traditional methods. This can shorten planning cycles by 20%-30% and reduce subsequent operations and maintenance costs by approximately 25%.

[0027] As described in step S4 above, the initial plan is optimized based on the simulation results to form a final planning plan. Through a data-driven intelligent optimization mechanism, a scientific balance is achieved among multiple objectives such as energy efficiency, cost, and user experience, thereby improving the comprehensive performance and adaptability of the plan.

[0028] First, analyze the simulation evaluation report and use anomaly detection algorithms (such as statistical process control) to locate performance bottlenecks (such as energy consumption on a certain floor exceeding the standard by 15%). Then, use causal analysis (such as decision tree models) to trace the root causes (such as improper equipment selection or rigid control strategies).

[0029] Secondly, multiple optimization strategies are automatically generated based on the knowledge graph, such as: Equipment level: Replace high-efficiency air conditioning units or add smart meters to achieve itemized metering; Layout level: Adjust sensor locations to eliminate monitoring blind spots or optimize air duct directions to improve ventilation efficiency; Strategic level: Introduce a dynamic electricity price response mechanism to achieve staggered electricity consumption or design adaptive lighting adjustment logic.

[0030] Then, a multi-objective optimization algorithm (such as NSGA-III) is used to evaluate the strategy combinations and select the solution with the highest overall score from the Pareto optimal solution set (for example, the solution that balances a "10% cost increase" with a "20% energy efficiency improvement"). Finally, during the implementation of the solution, edge computing is used to collect real-time operating data, and reinforcement learning models are used to dynamically adjust strategy parameters (for example, automatically adjusting air conditioning temperature thresholds based on seasonal changes), forming a closed-loop iteration of planning, implementation, feedback, and optimization.

[0031] In this embodiment, the subjectivity of manual experience adjustment is avoided, so that the solution reaches the optimal state in the multi-objective balance. According to tests, the overall performance of the system can be improved by 25%-40%, and it has the self-evolution capability to cope with future changes in demand (such as the addition of new smart building rating indicators in policies).

[0032] In one embodiment, each of the subsystems includes an intelligent security system, an intelligent lighting system, and an intelligent power system; the planning model is trained using an intelligent algorithm, and the intelligent algorithm includes a genetic algorithm and a particle swarm optimization algorithm.

[0033] In one embodiment, matching a planning model of a building intelligent system based on the demand data set includes: Extracting features from the demand dataset to identify key demand features, wherein the key demand features include the building's functional type, spatial layout, user performance requirements for each subsystem, budget constraints, and expected energy efficiency targets; Calling a planning model library; the planning model library contains a variety of pre-built planning models, each planning model corresponding to different features; Compare the extracted key demand features with the features of each planning model in the planning model library, and calculate the similarity score between the key demand features and each planning model; According to the similarity score, the planning models with similarity scores higher than a preset threshold are screened out as candidate planning models; The candidate planning model with the highest similarity score is taken as the final matching planning model.

[0034] In this embodiment, when matching the building intelligent system planning model, the first step is to extract features from the acquired and integrated demand dataset. This is because the demand dataset contains a large amount of information about various aspects of the building intelligent system, but not all information is equally important for matching the planning model. Therefore, it is necessary to identify key demand features from it.

[0035] Key requirement characteristics encompass several important aspects. A building's functional type defines its purpose, such as residential, commercial office, hospital, or school. Different functional types place significant demands on intelligent systems. For example, residential buildings prioritize comfort and safety, while commercial office buildings prioritize productivity and stable information transmission. Spatial layout encompasses the building's internal structure, floor plan, and zoning, which influences equipment installation locations and signal coverage. User performance requirements for each subsystem are based on actual usage needs, such as monitoring accuracy for intelligent security systems and illumination intensity and uniformity for intelligent lighting systems. Budgetary constraints determine the amount of funds available for intelligent system planning, influencing equipment selection and system configuration. Targeted energy efficiency targets reflect the building's commitment to energy conservation and environmental protection, such as desired energy consumption standards or green building ratings. Accurately extracting these key requirement characteristics provides a precise basis for subsequently matching appropriate planning models.

[0036] After completing the extraction of key demand features, the next step is to call the planning model library. The planning model library is a pre-built collection that contains a variety of different planning models. These planning models are built based on past experience, a large number of cases, and professional knowledge. Each planning model corresponds to a different combination of features. The above features may be related to the key demand features extracted previously. For example, buildings of different functional types may correspond to different planning models, and multi-story buildings and high-rise buildings will also have their own adapted models. The planning model library is like a "model warehouse" that stores various planning models suitable for different scenarios, providing us with a wealth of choices for finding models that match current needs.

[0037] Once we have the extracted key demand features and the planning model library, we need to compare them. This comparison allows us to determine how well each planning model aligns with the current requirements. This is done by calculating the similarity score between the key demand features and the features of each planning model in the planning model library.

[0038] This calculation typically utilizes a specific algorithm to comprehensively evaluate key demand characteristics and planning model characteristics. For example, if the current demand is for commercial office space and a planning model is also constructed for commercial office space, the similarity score for this characteristic will be higher. Similarly, if the spatial layout of the planning model is similar to the spatial layout of the actual demand, the similarity score will also increase. By comprehensively considering various key demand characteristics, a quantitative similarity score is ultimately derived, which intuitively reflects the degree of match between each planning model and the current demand.

[0039] After obtaining the similarity score between each planning model and the key demand features, a screening operation is required. The preset threshold is a pre-set standard used to determine whether a planning model sufficiently matches the current demand. If the similarity score of a planning model is higher than the preset threshold, it means that the degree of matching with the current demand has met certain requirements and it can be used as a candidate planning model. The purpose of screening out candidate planning models is to narrow the selection range, avoid analyzing many planning models one by one, and improve matching efficiency. For example, if the preset threshold is set to 70 points, then planning models with a similarity score higher than 70 points will be selected into the candidate list, while those with a score lower than 70 points will be excluded.

[0040] After screening candidate planning models, the model with the highest similarity score is selected as the final matching planning model. This is because the highest similarity score indicates that the planning model best aligns with the current requirements across all key demand characteristics and best meets the planning requirements for the building intelligent system. Selecting such a model ensures that the planning solution achieves the optimal balance between functional implementation, performance, cost control, and energy efficiency. For example, if among the candidate planning models, Model A has a similarity score of 85, Model B has a similarity score of 82, and Model C has a similarity score of 80, then Model A will be selected as the final matching planning model and used as the basis for subsequent building intelligent system planning.

[0041] In one embodiment, optimizing the initial planning scheme according to the simulation results includes: Conduct multi-dimensional analysis on the simulation results to identify abnormal features in spatial layout and time series and obtain defect analysis results; Based on the defect analysis results, generate multiple sets of differentiated optimization strategies; Comprehensively quantify and score each set of differentiated optimization strategies, and automatically select the optimal solution that balances multiple objectives through intelligent algorithms; the target requirements include energy efficiency, cost, and user experience requirements; Collect operational data in real time and dynamically compare it with the target requirements, and use adaptive learning mechanisms to continuously fine-tune the optimal solution.

[0042] In this example, after completing the simulation of the initial planning scheme, an in-depth multi-dimensional analysis of the simulation results is required to fully reveal potential problems in the scheme. This analysis process covers two key dimensions: spatial layout and time series: Spatial Layout: Focus on the rationality of intelligent system deployment in various areas of the building. For example, check whether there are blind spots in security cameras, whether the HVAC system duct layout causes uneven airflow, and whether sensor points fail to cover key areas. Using 3D visualization tools or heat map analysis, locate areas with excessive device density or insufficient resource allocation, and identify performance bottlenecks caused by inappropriate spatial planning.

[0043] Time series analysis: Analyze system operating data at different time periods, such as whether equipment load exceeds limits during weekday peak hours, whether energy consumption increases abnormally during nighttime off-peak hours, and the impact of seasonal climate change on system efficiency. Trend curve or spectrum analysis can be used to capture periodic or sudden abnormal fluctuations (such as a network latency spike occurring at the 30th minute of each hour) and trace their correlation with equipment scheduling strategies and external environmental changes.

[0044] By integrating the analysis results of spatial and temporal dimensions, a structured defect analysis report is formed to identify the specific defects of the initial plan (such as "Wi-Fi signal coverage in the underground garage area is less than 60% during peak hours in the morning and evening" and "Energy consumption of the air-conditioning system exceeds the budget by 18% between 2:00 PM and 4:00 PM in summer"), providing precise targets for subsequent optimization.

[0045] Based on the issues identified in the defect analysis report, multiple sets of targeted optimization strategies are automatically generated, covering three levels: equipment, layout, and strategy, ensuring diversity and flexibility of solutions: Equipment level: To address issues of insufficient equipment performance or inappropriate equipment selection, strategies such as replacing high-efficiency equipment (such as replacing traditional lighting fixtures with smart LED dimming fixtures), adjusting the number of devices (such as adding WiFi repeaters in signal blind spots), or upgrading hardware configurations (such as replacing low-latency chips for elevator control systems) are proposed.

[0046] Layout level: To address space planning deficiencies, strategies such as redesigning equipment installation locations (e.g., moving security cameras from corners to the center of corridors to expand the field of view), optimizing wiring routes (e.g., shortening HVAC ducts to reduce heat loss), or adjusting area functional divisions (e.g., centralizing high-energy-consuming equipment to simplify energy management) are proposed.

[0047] At the strategic level: To address defects in control logic or scheduling rules, we propose strategies such as improving algorithms (such as introducing human infrared sensing + light intensity linkage control logic into the lighting system), optimizing energy scheduling strategies (such as adjusting the charging and discharging periods of energy storage equipment based on peak and valley electricity prices), or adjusting user interaction processes (such as simplifying the operating interface of smart terminals to improve ease of use).

[0048] By combining optimization measures at different levels, multiple sets of differentiated solutions are generated (such as "equipment replacement + strategy optimization", "layout adjustment + algorithm upgrade", etc.), providing sufficient options for subsequent multi-objective trade-offs.

[0049] To achieve a scientific balance between multiple objectives such as energy efficiency, cost, and user experience, each optimization strategy needs to be quantitatively evaluated and intelligently screened: Build an evaluation indicator system: Establish an evaluation model that includes energy efficiency indicators (such as energy consumption reduction rate per unit area and renewable energy utilization rate), cost indicators (such as initial investment growth rate and full life cycle operation and maintenance costs), and user experience indicators (such as indoor temperature and humidity comfort score and equipment response delay). Assign weights to each indicator (such as 40% for energy efficiency, 35% for cost, and 25% for user experience). The weights can be dynamically adjusted according to project priorities.

[0050] Intelligent algorithm scoring and screening: Each strategy is simulated using a multi-objective optimization algorithm (such as the non-dominated sorting genetic algorithm (NSGA-II)) to calculate its scores on various indicators and an overall score. By simulating the biological evolution process, the algorithm searches for a Pareto optimal solution set that simultaneously meets multiple optimization objectives. For example, a solution that increases initial costs by 15% but improves energy efficiency by 20% and user experience by 12% may outperform a solution with a 5% increase in costs but only an 8% improvement in energy efficiency in terms of overall score.

[0051] Automatically screen the optimal solution: The system automatically sorts the solutions based on the comprehensive scores and selects the solution with the highest score as the current optimal solution, ensuring that it maximizes the overall benefits in the face of multi-objective conflicts and avoiding the subjectivity and one-sidedness of manual decision-making.

[0052] During the implementation of the optimal solution, a closed-loop mechanism of "data collection - deviation analysis - strategy fine-tuning" is established to ensure that system performance continues to meet standards and adapt to dynamic changes: Real-time data collection: Through edge computing nodes or IoT gateways, device operation data (such as energy consumption and device load rate), environmental data (such as temperature and humidity, and light intensity), and user feedback data (such as app operation logs and satisfaction scores) are collected in real time to form a dynamic data stream.

[0053] Dynamic comparison and deviation identification: Real-time data is compared with the target requirements set in the planning phase (such as energy consumption thresholds and comfort standards). Statistical process control (SPC) or machine learning anomaly detection models are used to identify deviations that exceed the allowable fluctuation range (for example, the actual energy consumption of a certain floor exceeds the target value by 10% for three consecutive days).

[0054] Adaptive learning and strategy fine-tuning: Upon identifying deviations, the system automatically triggers an adaptive learning mechanism. If the deviation is caused by environmental changes (e.g., a temporary increase in office workstations leading to unexpected foot traffic), the system dynamically adjusts the control strategy (e.g., increasing the air flow rate of the air conditioner in that area) through a reinforcement learning algorithm. If the deviation stems from equipment aging due to long-term operation, the system continuously optimizes the plan by updating the planning model parameters online (e.g., correcting the equipment energy efficiency degradation coefficient). This process elevates the planning solution from a static design to a dynamic evolutionary one, continuously adapting to changes in building usage scenarios (e.g., seasonal changes, policy adjustments).

[0055] In one embodiment, after optimizing the initial planning scheme according to the simulation results to form a final planning scheme, the following steps are performed: Obtain the approval code of each approval terminal, and construct an approval code array based on each approval code; Acquiring the approval requirements of the final planning scheme, and adjusting the approval code array based on the approval requirements to obtain an adjusted code array; Obtain historical approval efficiency trends for each approval terminal; For each approval terminal, optimize its own historical approval efficiency trend based on the historical approval efficiency trends of other approval terminals to obtain the optimized approval efficiency trend; Based on the optimized approval efficiency trend and the adjustment code array, corresponding approval authority is generated for configuring the authority of the corresponding approval terminal to the final planning scheme.

[0056] In this embodiment, after the building intelligent system planning scheme is optimized, the approval process management phase must begin. First, the system obtains the unique identification code, or approval code, for each terminal involved in the approval process (such as the planning department, fire protection agency, and energy conservation regulatory agency) through interface docking or manual entry. These codes can include information such as the department number and approval type code (for example, "GH-2025-001" represents the planning department's Approval Terminal No. 1 of 2025). Subsequently, all approval codes are structured and arranged according to pre-set rules (such as approval priority and process sequence) to form an approval code array. This array serves as the basic data framework for the approval process and is used for subsequent permission configuration and process scheduling, ensuring that the identity of each approval terminal can be quickly identified and managed by the system.

[0057] Approval requirements refer to specific requirements for the approval process based on project characteristics, policies, regulations, or industry standards. By parsing key information in the planning scheme (such as building area, intelligent level, fire protection design standards, etc.), the corresponding approval requirements are automatically matched (such as triggering the rule that "high-rise buildings need to add structural safety approval terminals"). Based on this, the approval code array will be dynamically adjusted: adding necessary approval terminal codes (such as expert review terminals), deleting redundant codes (such as removing confidentiality review terminals for non-confidential projects), or modifying the priority of existing codes (such as advancing the order of energy-saving approval terminals to before fire protection approval). The adjusted code array is more in line with actual approval needs, ensuring a streamlined and compliant process.

[0058] By collecting key data from each terminal's past approval records (such as approval time, rejection rate, and number of rectifications), and applying time series analysis algorithms (such as ARIMA models or exponential smoothing), we generate historical approval efficiency trend curves for each terminal. For example, the average approval time for a fire safety approval terminal has been reduced from 15 days to 10 days over the past three months, showing an improving trend.

[0059] Furthermore, collaborative analysis is used to improve the accuracy of predictions on the approval efficiency of a single terminal. Specifically, the system conducts a correlation analysis (such as calculating the Pearson correlation coefficient) on the historical efficiency trends of a certain approval terminal and those of all other terminals, identifying terminals that have a significant impact on their efficiency (such as the positive correlation between the approval speed of the planning department and the filing efficiency of the housing and construction department). Then, using machine learning models (such as random forests or LSTM neural networks), the trend data of the relevant terminals is used as input features to predict and optimize the trend of the target terminal. For example, if it is predicted that the approval time for a certain planning terminal will increase by 20% in the next two weeks due to project concentration, its efficiency trend curve will be automatically adjusted and marked as an efficiency warning state. The optimized trend more accurately reflects the global coordination of the approval process, avoiding the impact of efficiency fluctuations of a single terminal on the overall progress.

[0060] After integrating the identity information and efficiency data of the approval terminals, the authority generation phase begins. First, based on the adjusted code array and optimized approval efficiency trends, the corresponding approval key (i.e., approval authority) is generated. Then, based on the corresponding approval key, the final plan is encrypted and transmitted to the corresponding approval terminal. In other words, each approval terminal will use a different approval key to obtain the corresponding plan. Furthermore, the approval keys for different approval terminals are generated based on their corresponding historical approval efficiency trends, enhancing uniqueness, pertinence, and security.

[0061] In one embodiment, adjusting the approval code array based on the approval requirement to obtain an adjusted code array includes: Obtain keywords from the approval requirements and convert the keywords into key characters; Based on the key characters, the coded data columns in the standard coding table are modified to obtain a modified coding table; wherein the standard coding table includes a one-to-one mapping of the original data columns and the coded data columns; Based on the key character, obtaining a plurality of target array elements in the approval code array; The target array element is encoded based on the modified encoding table, and other array elements are kept unchanged to obtain an adjustment code array.

[0062] In this embodiment, the approval requirements are first semantically parsed, and natural language processing techniques (such as keyword extraction and named entity recognition) are used to accurately identify core information from the text. For example, keywords such as "expedited" and "green building two-star" are extracted from "needing expedited approval and meeting the green building two-star standard." These keywords represent special requirements or constraints of the approval process. Subsequently, according to preset mapping rules, each keyword is converted into a unique key character to form a machine-recognizable instruction symbol. Through this standardized conversion, unstructured natural language requirements are converted into structured key character sequences, providing a clear operational basis for subsequent coding table corrections and array adjustments.

[0063] The standard coding table is a pre-established mapping table between approval terminals and codes, containing both original and coded data columns. After obtaining key characters, the system makes targeted corrections to the coded data columns based on the requirements represented by the characters. Correction rules include replacing, rearranging, and inserting coded data columns.

[0064] The approval code array is an ordered list of the approval terminal codes. Using the filtering rules generated by the key characters, locate the target element in the array that needs adjustment. This can be done by extracting features from each code in the array (such as suffixes, prefixes, or characters at specific positions) and performing pattern matching against the key characters.

[0065] After determining the target array element, its encoding is updated according to the correction encoding table. The updating process follows the principle of minimum disturbance: Target elements are directly replaced with new codes from the revised code table. Non-target elements retain their original codes. Ultimately, the updated target elements are recombined with the original, unadjusted elements to form an adjusted approval code array. This array not only meets the specific needs of current approvals but also maximizes the preservation of the existing process framework, ensuring the continuity and traceability of the approval process.

[0066] In one embodiment, for each approval terminal, its own historical approval efficiency trend is optimized based on the historical approval efficiency trends of other approval terminals to obtain an optimized approval efficiency trend, including: For each approval terminal, the historical approval efficiency trends of other approval terminals are fitted into a comprehensive approval efficiency trend; The comprehensive approval efficiency trend is superimposed on the historical approval efficiency trend of the approval terminal itself, and the part overlapping with the comprehensive approval efficiency trend is removed from the historical approval efficiency trend of the approval terminal itself for optimization to obtain the optimized approval efficiency trend.

[0067] In this embodiment, for each approval terminal to be optimized (e.g., the planning department's approval terminal), historical approval efficiency data is first collected from all other approval terminals (e.g., those in fire protection, energy conservation, and housing and construction departments). This data includes key indicators such as approval time, approval rate, and number of rectifications at different time points for each terminal. Next, data fitting techniques (such as polynomial fitting, spline interpolation, or regression models in machine learning) are used to aggregate this dispersed historical data, eliminating individual fluctuations and noise, and generating a comprehensive approval efficiency trend curve that reflects the overall efficiency trends of all other approval terminals.

[0068] The generated comprehensive approval efficiency trend curve is then spatially aligned with the historical approval efficiency trend curve for the current approval terminal, and the overlap between the two is identified through comparative analysis. The common fluctuation components of this overlap are then separated and removed from the terminal's historical trends, preserving its unique efficiency characteristics. The optimized trend curve more accurately reflects the independent efficiency performance of each terminal. This embodiment transcends the limitations of analyzing a single terminal independently and considers the approval process as a dynamic system in which each terminal influences the other.

[0069] In one embodiment, generating corresponding approval authority based on the optimized approval efficiency trend and the adjustment code array includes: Adding a plurality of character boxes arranged at preset intervals on the optimized approval efficiency trend; wherein the optimized approval efficiency trend is a continuous broken line graph; Adding the array elements in the adjustment code array to each character frame in sequence to obtain a character trend graph; Analyzing the character trend graph and determining character box screening rules based on the analysis results; Based on the character frame screening rule, a corresponding character frame is screened out as a target character frame; and array elements in the target character frame are combined to obtain a character combination as the approval authority.

[0070] In this embodiment, a continuous line graph of optimized approval efficiency trends is first treated as sequential data along the time dimension. Based on preset time intervals, the time axis of the line graph is evenly divided into multiple time intervals, each corresponding to a character box. For example, the efficiency trends over the past 12 weeks are divided into 12 character boxes, each corresponding to a weekly efficiency data interval. The position and size of the character boxes strictly adhere to the principle of time alignment, ensuring that subsequent additions to the array elements have clear time indexes, providing a foundation for spatiotemporal correlation analysis of approval authority.

[0071] The adjustment code array is an ordered list of approval terminal codes. Each element is assigned to its corresponding character box in the order of the array. For example, the first character box is assigned the first element, the second the second, and so on until all array elements have been assigned. If there are more character boxes than array elements, the remaining boxes are automatically assigned default identifiers. If there are more array elements than character boxes, the process loops or truncates. The resulting character trend chart is a two-dimensional mapping table between time and approval terminal codes, visually displaying the correlation between approval authority for each terminal over different time periods.

[0072] In one embodiment, the character trend graph may be analyzed using the following dimensions to generate screening rules: Time-efficiency correlation: Identify the character boxes corresponding to the efficiency peaks / valleys in the efficiency trend curve; Code feature matching: Check whether the code in the character box contains a specific identifier, and set mandatory rules for the boxes that meet the conditions; Sequence pattern mining: Use association rule algorithms (such as Apriori) to discover frequently occurring coding combinations and set combination screening rules.

[0073] In another embodiment, the screening rule may be: identifying the number of upward trending broken lines and downward trending broken lines in the character trend graph, taking the broken lines with the largest number as target broken lines, and taking the character boxes on the target broken lines as target character boxes.

[0074] Finally, all character frames in the character trend chart are filtered according to the filtering rules, retaining the target character frames that meet the criteria. Subsequently, the array elements within the target character frames are extracted and combined in chronological order or priority order to form a character combination, which serves as the generated approval permission. The resulting approval permission can be directly used in the system permission management module to control the approval operation permissions of each terminal within the corresponding time period.

[0075] Reference Figure 2 In another embodiment of the present invention, an intelligent planning system based on a building intelligent system is provided, comprising: The acquisition module is used to obtain the demand data of each subsystem in the building intelligent system and integrate it into a demand data set; A matching module, configured to match a planning model of a building intelligent system based on the demand data set; An evaluation module is used to generate an initial planning scheme based on the planning model, and simulate the initial planning scheme to evaluate its operating effect in different scenarios; The optimization module is used to optimize the initial planning scheme according to the simulation results to form a final planning scheme.

[0076] In this embodiment, for the specific implementation of each module in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0077] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0078] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0079] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0080] In summary, the intelligent planning method and system based on the building intelligent system provided in the embodiments of the present invention include: obtaining the demand data of each subsystem in the building intelligent system and integrating them into a demand data set; matching the planning model of the building intelligent system based on the demand data set; generating an initial planning scheme according to the planning model, and simulating the initial planning scheme to evaluate its operating effect in different scenarios; optimizing the initial planning scheme according to the results of the simulation to form a final planning scheme. In the present invention, by simulating the initial planning scheme to evaluate its operating effect in different scenarios; optimizing the initial planning scheme according to the results of the simulation to form a final planning scheme, the defects of low accuracy and low efficiency in the optimization of current planning schemes are overcome.

[0081] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0082] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0083] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent planning method based on a building intelligent system, characterized in that: The following steps are involved: Obtain demand data for each subsystem in the building intelligent system and integrate it into a demand data set; Based on the demand data set, matching the planning model of the building intelligent system; Generate an initial planning scheme based on the planning model, and simulate the initial planning scheme to evaluate its operating effect in different scenarios; The initial planning scheme is optimized according to the simulation results to form a final planning scheme.

2. The intelligent planning method based on building intelligent system according to claim 1 is characterized in that: Each of the subsystems includes an intelligent security system, an intelligent lighting system, and an intelligent power system; the planning model is trained using an intelligent algorithm, which includes a genetic algorithm and a particle swarm optimization algorithm.

3. The intelligent planning method based on building intelligent system according to claim 1 is characterized in that: Based on the demand data set, a planning model of the building intelligent system is matched, including: Extracting features from the demand dataset to identify key demand features, wherein the key demand features include the building's functional type, spatial layout, user performance requirements for each subsystem, budget constraints, and expected energy efficiency targets; Calling a planning model library; the planning model library contains a variety of pre-built planning models, each planning model corresponding to different features; Compare the extracted key demand features with the features of each planning model in the planning model library, and calculate the similarity score between the key demand features and each planning model; According to the similarity score, the planning models with similarity scores higher than a preset threshold are screened out as candidate planning models; The candidate planning model with the highest similarity score is taken as the final matching planning model.

4. The intelligent planning method based on building intelligent system according to claim 1, characterized in that: The initial planning scheme is optimized according to the simulation results, including: Conduct multi-dimensional analysis on the simulation results to identify abnormal features in spatial layout and time series and obtain defect analysis results; Based on the defect analysis results, generate multiple sets of differentiated optimization strategies; Comprehensively quantify and score each set of differentiated optimization strategies, and automatically select the optimal solution that balances multiple objectives through intelligent algorithms; the target requirements include energy efficiency, cost, and user experience requirements; Collect operational data in real time and dynamically compare it with the target requirements, and use adaptive learning mechanisms to continuously fine-tune the optimal solution.

5. The intelligent planning method based on building intelligent system according to claim 1 is characterized in that: After optimizing the initial planning scheme according to the simulation results to form the final planning scheme, the following steps are performed: Obtain the approval code of each approval terminal, and construct an approval code array based on each approval code; Acquiring the approval requirements of the final planning scheme, and adjusting the approval code array based on the approval requirements to obtain an adjusted code array; Obtain historical approval efficiency trends for each approval terminal; For each approval terminal, optimize its own historical approval efficiency trend based on the historical approval efficiency trends of other approval terminals to obtain the optimized approval efficiency trend; Based on the optimized approval efficiency trend and the adjustment code array, corresponding approval authority is generated for configuring the authority of the corresponding approval terminal to the final planning scheme.

6. The intelligent planning method based on building intelligent system according to claim 5 is characterized in that: Based on the optimized approval efficiency trend and the adjustment code array, corresponding approval authority is generated, including: Adding a plurality of character boxes arranged at preset intervals on the optimized approval efficiency trend; wherein the optimized approval efficiency trend is a continuous broken line graph; Adding the array elements in the adjustment code array to each character frame in sequence to obtain a character trend graph; Analyzing the character trend graph and determining character box screening rules based on the analysis results; Based on the character frame screening rule, a corresponding character frame is screened out as a target character frame; and array elements in the target character frame are combined to obtain a character combination as the approval authority.

7. An intelligent planning system based on a building intelligent system, characterized in that: include: The acquisition module is used to obtain the demand data of each subsystem in the building intelligent system and integrate it into a demand data set; A matching module, configured to match a planning model of a building intelligent system based on the demand data set; An evaluation module is used to generate an initial planning scheme based on the planning model, and simulate the initial planning scheme to evaluate its operating effect in different scenarios; The optimization module is used to optimize the initial planning scheme according to the simulation results to form a final planning scheme.

Images