Smart park IBMS integration method and system

Abstract

The invention provides a smart park IBMS integration method and a smart park IBMS integration system, which are applied to the technical field of smart park management, and are used for dynamically sensing the personnel state and activity property of a functional area by integrating and analyzing multi-source personnel activity data so as to intelligently match a refined environment control strategy. And self-adaptive adjustment of environmental parameters is realized through the building automatic control system, so that the problem that an existing IBMS system is difficult to carry out refined environmental control based on personnel activity data is solved, the comfort level, the energy efficiency and the intelligent level are improved, the environmental parameters can be dynamically adjusted according to the real-time activity conditions of personnel in a functional area, and the environmental control efficiency is improved. The comfort level is improved; and meanwhile, the energy utilization efficiency is optimized.

Description

Technical Field

[0001] The present application relates to the field of smart park management technology, and in particular to a smart park IBMS integration method and system. Background Art

[0002] As the core of modern park management, the Intelligent Building Management System (IBMS) integrated system brings together data from numerous independent subsystems, including building automation, security, energy management, smart parking, and visitor management. Its core goal is to achieve unified monitoring and efficient coordinated control of various park facilities.

[0003] During the daily operation of the park, these subsystems generate massive, multi-dimensional, real-time data streams. These include operating status parameters of building equipment (such as air conditioning on / off, lighting on / off), various environmental monitoring parameters (such as temperature, humidity, and air quality), detailed energy consumption data, precise vehicle entry and exit records, and data closely related to human activities, such as card swipe entry records from the access control system and appointment and visit registration information from the visitor management system. The IBMS platform continuously collects and initially normalizes this heterogeneous data from diverse sources and structures to support the basic monitoring functions and pre-set linkage control logic required for park operations. For example, these data can automatically start and stop office area lighting and air conditioning systems according to a preset schedule, or trigger the operation of the fresh air system based on simple environmental sensor thresholds (such as excessive CO2 concentration).

[0004] Among the vast amount of data aggregated by the IBMS platform, data streams related to human activity occupy a significant position. These include precise entry and exit records of employees and authorized visitors generated by the access control system; visitor management systems, which record visitor appointment times, registered identities, and expected visit areas; conference room reservation systems, which reflect meeting schedules and expected attendee numbers; and even anonymous headcount data provided by people-counting sensors deployed in key areas. However, a common problem currently exists: this human activity data typically exists as discrete, isolated events or records within their respective subsystems or within the initial integration layer of the IBMS platform, lacking effective deep correlation mechanisms and sophisticated analytical capabilities.

[0005] This separation between the data level and the analysis level makes it difficult for the I BMS system to directly and accurately conduct close and dynamic correlation analysis and predictive judgment on the real-time distribution and activity status of personnel in a specific area with the specific environmental parameters and equipment operating status of the area.

[0006] Therefore, in the complex scenario where specific functional areas of a smart park are faced with multi-source discrete and dynamically changing personnel activity data, as well as differentiated environmental demands arising from different types of personnel due to different activity purposes, how can we ensure the basic comfort of personnel while significantly improving the energy utilization efficiency of the park and the flexibility and intelligence level of spatial resource allocation?

[0007] In view of the above problems, the existing technology needs to be improved urgently. Summary of the Invention

[0008] In view of the above-mentioned shortcomings of the existing technology, the present application provides a smart park I BMS integration method and system, which has the advantage of being able to dynamically adjust environmental parameters according to the real-time activities of people in the functional area, improve comfort and optimize energy utilization efficiency.

[0009] In a first aspect, a method for integrating I BMS in a smart park is provided, the method comprising the steps of:

[0010] S1: Acquire multi-source personnel activity data in functional areas;

[0011] S2: Based on the multi-source personnel activity data, aggregate and calculate the number and density of personnel in the functional area, and divide the personnel density levels;

[0012] S3: Determine the activity type of the functional area by combining the schedule information and personnel entry and exit records in the multi-source personnel activity data;

[0013] S4: matching a scenario-based environment control strategy template according to the personnel density level and the activity type;

[0014] S5: Based on the matching scenario-based environmental control strategy template, control instructions are sent to the building automation subsystem to adjust the environmental parameters of the functional area, including temperature, lighting, and fresh air.

[0015] This application proposes a smart park IBMS integration method, which integrates and analyzes multi-source personnel activity data, dynamically perceives the personnel status (number, density) and activity nature of functional areas, and then intelligently matches refined environmental control strategies. It also realizes adaptive adjustment of environmental parameters (temperature, lighting, fresh air) through the building automatic control system, thereby solving the problem that the existing IBMS system is difficult to perform refined environmental control based on personnel activity data, improving comfort, energy efficiency and intelligence level, and has the advantage of being able to dynamically adjust environmental parameters according to the real-time activities of personnel in the functional area, improving comfort while optimizing energy utilization efficiency.

[0016] Furthermore, step S1 includes:

[0017] S11: collecting initial multi-source personnel activity data from the access control system, conference booking system, and visitor management system in real time at preset time intervals;

[0018] S12: performing a cleaning process on the initial multi-source personnel activity data to remove duplicate data and filter out invalid data;

[0019] S13: performing unified format conversion on the cleaned initial multi-source personnel activity data, converting data from different sources into a unified data structure, and obtaining the multi-source personnel activity data.

[0020] This application proposes a smart park IBMS integration method, which solves the problem of effective acquisition and preprocessing of multi-source heterogeneous personnel activity data through three sub-steps: collection, cleaning, and format conversion, and provides a reliable data basis for the subsequent accurate calculation of personnel quantity, density, and judgment of activity types.

[0021] Furthermore, step S2 includes:

[0022] S21: Constructing a personnel density calculation model, using the multi-source personnel activity data as input, to calculate the number of personnel in the functional area;

[0023] S22: Calculate the personnel density based on the area of ​​the functional area and the number of personnel, where personnel density = number of personnel / area of ​​the functional area;

[0024] S23: Obtain a preset threshold for dividing the population density level, and divide the population density level into low density, medium density and high density according to the preset threshold for dividing the population density level and the population density.

[0025] This application proposes a smart park IBMS integration method that accurately calculates the number and density of personnel based on multi-source personnel activity data and divides them into levels, solving the problem of unclear implementation details and providing a basis for subsequent precise matching of environmental control strategies.

[0026] Furthermore, step S21 includes:

[0027] S211: Analyzing the characteristics of the multi-source personnel activity data based on the multi-source personnel activity data to determine the contribution of each type of data to the personnel quantity calculation; wherein the contribution of the conference reservation system data is greater than or equal to the contribution of the access control system data, which is greater than or equal to the contribution of the visitor management system data;

[0028] S222: According to the contribution of each type of data to the personnel calculation, combined with historical data statistical analysis, corresponding weight coefficients are set; wherein the weight coefficient of the conference reservation system data is α, the weight coefficient of the access control system data is β, and the weight coefficient of the visitor management system data is γ, and α>β>γ, α+β+γ=1;

[0029] S223: Based on the data characteristics and weight coefficients, the personnel density calculation model is constructed; the number of personnel = α*the number of participants in the conference reservation system + β*(the number of people entering the gate - the number of people leaving the gate) + γ*the number of people registered in the visitor management system.

[0030] This application proposes a smart park IBMS integration method that analyzes the characteristics and contribution of data from different sources and assigns corresponding weights to more accurately estimate the number of personnel.

[0031] Furthermore, step S3 includes:

[0032] S31: extracting schedule information from multi-source personnel activity data and determining whether schedule information exists;

[0033] S32: If it does not exist, count the number of people entering and leaving the functional area per unit time based on the personnel entry and exit records of the access control system, and calculate the personnel flow rate;

[0034] S33: If not, extract the conference theme information and determine whether the conference theme information exists. If the conference theme information exists, determine the activity type by combining the conference theme information with a preset activity type knowledge base.

[0035] S34: If the conference theme information does not exist, determining the activity type according to the personnel turnover rate and a preset activity type knowledge base.

[0036] Furthermore, step S34 includes:

[0037] S341: Constructing the preset activity type knowledge base, wherein the preset activity type knowledge base includes a mapping relationship between conference theme keywords and activity types, and a mapping relationship between staff turnover rate thresholds and activity types;

[0038] S342: If the conference topic information does not exist, compare the personnel turnover rate with the personnel turnover rate threshold corresponding to each activity type in the activity type knowledge base, and select the activity type corresponding to the threshold range to which the personnel turnover rate belongs.

[0039] Furthermore, step S4 includes:

[0040] S41: Building an environmental parameter history database; the environmental parameter history database records historical environmental parameters of functional areas in different time periods;

[0041] S42: Preliminarily screening candidate policy templates from a preset scenario-based environment control policy template library based on the personnel density level and the activity type;

[0042] S43: Predicting, based on the historical data, the change trend and fluctuation range of the current environmental parameters after adopting each of the candidate strategy templates;

[0043] S44: According to the change trend and fluctuation range, a candidate policy template that makes the current environmental parameter approach the target value as quickly as possible and has the smallest fluctuation range is selected as the scenario-based environmental control policy template to be finally matched.

[0044] Furthermore, step S43 includes:

[0045] S431: Using historical environmental parameters in the environmental parameter history database as a training set, construct a temperature prediction model, a lighting prediction model, and a fresh air prediction model;

[0046] S432: Inputting the current environmental parameters into the temperature prediction model, the lighting prediction model, and the fresh air prediction model, and predicting the change trend of the current environmental parameters after adopting each candidate strategy template;

[0047] S433: Calculate the variance between the predicted environmental parameter and the historical environmental parameter based on the change trend to obtain the fluctuation amplitude.

[0048] Furthermore, step S5 includes:

[0049] S51: monitor the operating status of the building automation subsystem in real time to determine whether the building automation subsystem is operating normally; if the building automation subsystem is operating abnormally, generate an alarm message and send it to the management platform;

[0050] S52: If the building automation subsystem operates normally, the matching scenario-based environment control strategy template is parsed into a control instruction set recognizable by the building automation subsystem;

[0051] S53: Evaluate the adjustment effect of the environmental parameters based on the real-time environmental parameters fed back by the building automation subsystem. If the environmental parameters do not reach the target values, adjust the control instructions based on the fed-back real-time environmental parameters and resend them to the building automation subsystem until the environmental parameters reach the target values.

[0052] In a second aspect, a smart park IBMS integrated system is applied to the steps of any of the above methods, the system comprising:

[0053] Acquisition module: acquires multi-source personnel activity data of functional areas;

[0054] Division module: Based on the multi-source personnel activity data, aggregate and calculate the number and density of personnel in the functional area, and divide the personnel density levels;

[0055] Determination module: combining the schedule information and personnel entry and exit records in the multi-source personnel activity data to determine the activity type of the functional area;

[0056] Matching module: matching scenario-based environment control strategy template according to the personnel density level and the activity type;

[0057] Adjustment module: Based on the matching scenario-based environmental control strategy template, it sends control instructions to the building automation subsystem to adjust the environmental parameters of the functional area, including temperature, lighting and fresh air.

[0058] Beneficial effects: The IBMS integration method and system for a smart park proposed in this application integrates and analyzes multi-source personnel activity data, dynamically perceives the personnel status (quantity, density) and activity nature of the functional area, and then intelligently matches the refined environmental control strategy, and realizes adaptive adjustment of environmental parameters (temperature, lighting, fresh air) through the building automatic control system, thereby solving the problem that the existing IBMS system is difficult to perform refined environmental control based on personnel activity data, improving comfort, energy efficiency and intelligence level, and having the advantage of being able to dynamically adjust environmental parameters according to the real-time activities of personnel in the functional area, improving comfort while optimizing energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a flowchart of the smart park I BMS integration method proposed in this application.

[0060] Figure 2 This is a structural diagram of the smart park I BMS integrated system proposed in this application.

[0061] Figure 3 This is an architectural diagram of the smart park I BMS integrated system proposed in this application.

[0062] Description of reference numerals: 201, acquisition module; 202, division module; 203, judgment module; 204, matching module; 205, adjustment module. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and marked in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0064] It should be noted that similar reference numerals and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined or explained in subsequent figures. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0065] Please refer to Figure 1 A method for integrating I BMS in a smart park, comprising the steps of:

[0066] S1: Acquire multi-source personnel activity data in functional areas;

[0067] S2: Based on multi-source personnel activity data, aggregate and calculate the number and density of personnel within the functional area, and divide the personnel density levels;

[0068] S3: Determine the activity type of the functional area by combining the schedule information and personnel entry and exit records in the multi-source personnel activity data;

[0069] S4: Match scenario-based environmental control strategy templates based on personnel density levels and activity types;

[0070] S5: Based on the matching scenario-based environmental control strategy template, control instructions are sent to the building automation subsystem to adjust the environmental parameters of the functional area, including temperature, lighting, and fresh air.

[0071] Multi-source human activity data refers to information about the presence, movement, and planned activities of people within a functional area, collected from multiple independent systems. This information can be obtained from access control systems, conference room reservation systems, visitor management systems, or other sources such as Wi-Fi location data or anonymous people counting sensors. The goal of acquiring multi-source data is to provide a comprehensive and accurate view of the status of people within a functional area, overcoming the limitations of single-source data.

[0072] Aggregate calculation of the number and density of people in a functional area and classification of the density of people means processing the collected multi-source data, determining the current number of people in the area, calculating the density based on the area, and classifying the density into preset levels.

[0073] The occupancy calculation can integrate data from different sources, potentially using weighting factors based on data reliability or contribution. Density is calculated by dividing the calculated occupancy by the physical area of ​​the area. Density is then compared to a threshold to assign a rating, such as low, medium, or high. This process transforms raw activity data into a quantifiable measure of area occupancy that is directly relevant to environmental needs.

[0074] Combining schedule information and personnel entry and exit records to determine the activity type of functional areas means analyzing information related to planned events (such as meetings) and the patterns of personnel entering and exiting the area to infer the nature of the activities ongoing in the area. Schedule information may indicate a planned meeting or event. Personnel entry and exit patterns, such as flow rate or length of stay, can indicate the type of activity, such as focused work, leisure gathering, or passage. This step aims to understand the purpose of occupancy, as different activities have different requirements for the environment. Matching scenario-based environmental control policy templates means selecting a set of predefined, scenario-specific environmental control parameters or rules from the policy library based on the determined personnel density level and activity type. The policy template represents an optimized environmental parameter configuration (temperature, lighting, fresh air) suitable for a specific combination of density and activity.

[0075] The matching process identifies the template that best suits the current conditions. This allows the environmental control to be customized to the actual usage scenario of the functional area.

[0076] Sending control instructions to the building automation subsystem to adjust the environmental parameters of functional areas involves converting the selected policy template into specific commands that the building automation system (BAS) can understand and execute, and transmitting these commands to the BAS. The BAS then adjusts environmental parameters such as temperature set points, lighting levels, or ventilation rates based on these commands. This is the execution phase, where the determined policy is put into action to physically change the environment.

[0077] The core innovation of this application lies in the dynamic determination of occupant density levels and activity types within functional areas through the integrated analysis of multi-source human activity data. Combining these two dimensions (density and activity type), the system intelligently matches and applies scenario-based environmental control strategies, enabling refined and adaptive environmental adjustments. This significantly improves comfort, enhances energy efficiency, and raises the overall level of intelligent environmental management within smart parks.

[0078] As a preferred embodiment, the solution of this application is specifically implemented as follows:

[0079] For example, in an office building conference room, the system can collect data at preset intervals from the access control system (recording entries and exits), the conference room reservation system (providing scheduled meeting times and expected attendee numbers), and the visitor management system (recording visitor entry). This raw data is then cleaned to remove duplicate and invalid entries and converted to a unified format.

[0080] Based on the processed data, the system calculates the current number of occupants in the room. For example, a weighted formula might be used, taking into account the number of people booked in, actual door entries and exits, and visitor registrations. This number is divided by the known area of ​​the room to determine the occupancy density. The density is then classified into a level, such as low, medium, or high. The system also checks the booking data to see if there are any scheduled meetings. If so, the activity type is identified as "meeting." If not, the system might analyze the flow of people in and out; a high flow rate over a short period of time might indicate "passing through" activity, while a low, stable occupancy rate might indicate "individual work." After determining the density level (e.g., "medium") and activity type (e.g., "meeting"), the system consults a library of policy templates. It finds a template specifically designed for "medium-density meeting." This template might specify a temperature setpoint, lighting intensity, and fresh air supply rate. This template is then parsed into commands compatible with the room's building automation controller (e.g., BACnet commands for HVAC units, DALI commands for lighting). These commands are sent to the controller, causing the air conditioning, lighting, and ventilation systems to adjust their operation according to the "medium-density meeting" policy.

[0081] Through the above scheme, this application effectively solves the limitations of environmental control based on static or single-source data in smart parks. By integrating intelligent processing of multi-source personnel activity data and dynamically determining occupancy density and activity type, the system achieves highly adaptive and scenario-based environmental adjustment. By adjusting temperature, lighting and ventilation according to the actual conditions and needs of functional areas, the comfort of occupants is improved. At the same time, by optimizing system operation based on real-time occupancy and activity, unnecessary energy consumption in underutilized or improperly regulated spaces is avoided, thereby enhancing energy efficiency. The overall intelligence and responsiveness of the building management system have been significantly improved, resulting in a more efficient and user-centric operation of the smart park environment.

[0082] Furthermore, step S1 includes:

[0083] S11: collecting initial multi-source personnel activity data from the access control system, conference booking system, and visitor management system in real time at preset time intervals;

[0084] S12: Clean the initial multi-source personnel activity data by removing duplicate data and filtering out invalid data;

[0085] S13: Convert the cleaned initial multi-source personnel activity data into a unified format, convert the data from different sources into a unified data structure, and obtain the multi-source personnel activity data.

[0086] The preset time interval refers to the time period during which the system periodically performs the collection operation during the data collection process, which can be implemented by using configuration parameters, system timers, or scheduling tasks.

[0087] Among them, the access control system refers to an electronic system used to control and record the entry and exit of people in a specific area. It can be implemented by technologies such as card swiping, fingerprint recognition, face recognition or QR code scanning.

[0088] Among them, the conference reservation system refers to a system used to manage conference room reservations, arrange meeting schedules and record participant information. It can be implemented using a web-based software platform or an independent application.

[0089] Among them, the visitor management system refers to a system used to register, authorize and track visitors entering and leaving the park. It can be implemented through processes such as visitor appointment registration, on-site identity verification or visitor pass issuance.

[0090] Among them, real-time collection means that the time interval between the data collection process and the actual event is very short, and the data is obtained almost synchronously. It can be achieved by using technologies such as system API calls, message queue subscriptions or database log monitoring.

[0091] Among them, the initial multi-source personnel activity data refers to the unprocessed original personnel activity records directly obtained from different source systems, which may contain personnel identity, timestamp, event type (such as entry, exit, reservation, registration) or location information, etc.

[0092] Among them, deduplication refers to the process of identifying and deleting the same personnel activity records that appear repeatedly in different sources or the same source. It can be achieved by using a deduplication algorithm based on a combination of record unique identifier, timestamp and personnel identity.

[0093] Among them, filtering invalid data refers to the process of identifying and deleting personnel activity records that do not comply with preset rules or logical errors. It can be achieved by using methods such as data verification rules, business logic judgment or outlier detection.

[0094] Among them, cleaning processing refers to the process of performing a series of operations on raw data to improve data quality and reliability, which may include steps such as removing duplications, filtering invalid data, filling in gaps, or correcting errors.

[0095] Among them, unified format conversion refers to the process of converting data from different sources and with different data structures into a predefined, standardized data structure, which can be implemented using data mapping rules, ETL (extraction, transformation, loading) tools or custom scripts.

[0096] Among them, a unified data structure refers to a standardized data model designed for integrating multi-source data. This model defines the name, type, and meaning of data fields, so that data from different sources can be represented and processed in a consistent manner. It can be defined using a relational database table structure, JSON format, or XML format.

[0097] In a specific implementation scenario, the system can be configured with a preset time interval, for example, every 5 minutes, and obtain the latest entry and exit records, meeting reservation information and visitor registration information in real time by calling the API interfaces provided by the access control system, conference reservation system and visitor management system. These raw data constitute the initial multi-source personnel activity data.

[0098] The system then cleans the initial data, for example, checking the timestamp and person ID of the access control records. If it is found that the same person has exactly the same entry and exit records in a very short period of time, it will be regarded as duplicate data and removed; check whether the visitor registration information contains a valid visitor name and visited area. If key information is missing, it will be regarded as invalid data and filtered out.

[0099] After cleaning, the system converts data from different sources into a unified data structure. For example, the access control system's "card swipe time," "personnel number," and "event type (entry / exit)" fields; the conference booking system's "meeting start time," "attendee list," and "conference room number" fields; and the visitor management system's "arrival time," "visiter name," and "visited area" fields are all mapped uniformly into a standard data structure containing fields such as "timestamp," "personnel ID," "event type," and "associated area." After format conversion, the resulting multi-source personnel activity data can be used for subsequent calculations of personnel count and density, as well as for determining activity types.

[0100] Furthermore, step S2 includes:

[0101] S21: Construct a personnel density calculation model, using multi-source personnel activity data as input to calculate the number of personnel in the functional area;

[0102] S22: Calculate the personnel density based on the area of ​​the functional area and the number of personnel, personnel density = number of personnel / area of ​​the functional area;

[0103] S23: Obtain a preset threshold for dividing the population density level, and divide the population density level into low density, medium density, and high density levels according to the preset threshold for dividing the population density level and the population density.

[0104] Specifically, building a population density calculation model involves establishing a logical structure or algorithm for comprehensively analyzing multi-source personnel activity data to estimate or count the real-time number of people within a specific functional area. This model can be based on statistical rules, weight distribution, or more complex machine learning methods. Its purpose is to overcome the limitations of a single data source and the inconsistencies of multi-source data, thereby improving the accuracy of personnel count calculations.

[0105] Multi-source personnel activity data serves as the input of the model. Its sources are diverse (such as access control, conference, and visitor systems) and may be discrete, heterogeneous, and incomplete. The model needs to handle this complexity. The preset personnel density level division threshold is a set of numerical boundaries used to define different personnel density states. These thresholds can be set according to building codes, comfort standards, safety requirements, or historical experience. By comparing with the calculated personnel density, continuous density values ​​can be mapped to discrete levels. Dividing personnel density levels is to classify continuous personnel density values ​​into several predefined discrete states (such as low, medium, and high).

[0106] This division simplifies the understanding and judgment of the degree of regional congestion and provides clear input for subsequent state-based decision-making (such as environmental control strategy matching).

[0107] This application uses the above steps to accurately obtain the occupant density and rank of functional areas, resolving the environmental control mismatch problem caused by insufficient data processing in existing technologies and improving the intelligent management level and energy efficiency of the park. This method of calculating density and grading based on multi-source data modeling provides a reliable basis for dynamic and refined environmental control.

[0108] Furthermore, step S21 includes:

[0109] S211: Analyze the characteristics of the multi-source personnel activity data based on the multi-source personnel activity data, and determine the contribution of each type of data to the calculation of the number of personnel; wherein the contribution of the conference reservation system data is greater than or equal to the contribution of the access control system data, and the contribution of the visitor management system data is greater than or equal to the contribution of the visitor management system data;

[0110] S222: According to the contribution of each type of data to the personnel calculation, combined with historical data statistical analysis, corresponding weight coefficients are set; wherein the weight coefficient of the conference reservation system data is α, the weight coefficient of the access control system data is β, and the weight coefficient of the visitor management system data is γ, and α>β>γ, α+β+γ=1;

[0111] S223: Based on the data characteristics and weight coefficients, a personnel density calculation model is constructed; the number of personnel = α*number of participants in the conference reservation system + β*(number of people entering the gate - number of people leaving the gate) + γ*number of people registered in the visitor management system.

[0112] Among them, "analyzing the characteristics of multi-source personnel activity data" refers to identifying the inherent properties and limitations of data from different sources (such as conference booking, access control, and visitor management) in reflecting the real-time number of people in functional areas. This can be achieved through data quality assessment, data correlation analysis, or expert experience judgment.

[0113] "Determining the contribution of various types of data to the calculation of the number of employees" refers to quantifying the importance or reliability of different data sources in estimating the actual number of employees. This can be achieved using methods based on statistical analysis, machine learning models, or rules engines.

[0114] "Combining statistical analysis with historical data" means using multi-source personnel activity data collected over a period of time and possible records of actual personnel numbers to conduct trend analysis, correlation analysis or model training, which can be achieved through time series analysis, regression analysis or cluster analysis.

[0115] "Setting corresponding weight coefficients" means assigning numerical weights to different data sources based on the contribution determined by the analysis and the results of statistical analysis of historical data to reflect their influence ratio in the final calculation model. This can be achieved using the least squares method, maximum likelihood estimation, or a hierarchical analysis method.

[0116] "Constructing the personnel density calculation model" means establishing a mathematical expression or algorithm to combine the weighted indicators of various data sources and output an estimated value of the number of people in the functional area. It can be implemented using a linear regression model, a support vector regression model or a neural network model.

[0117] Furthermore, step S3 includes:

[0118] S31: extracting schedule information from multi-source personnel activity data and determining whether schedule information exists;

[0119] S32: If it does not exist, count the number of people entering and leaving the functional area per unit time based on the personnel entry and exit records of the access control system, and calculate the personnel flow rate;

[0120] S33: If not, extract the conference theme information and determine whether the conference theme information exists. If the conference theme information exists, determine the activity type by combining the conference theme information with a preset activity type knowledge base.

[0121] S34: If the meeting topic information does not exist, the activity type is determined according to the staff turnover rate and a preset activity type knowledge base.

[0122] Among them, multi-source personnel activity data refers to data related to personnel activities in functional areas collected from different sources, which may include access records of the access control system, reservation information of the conference reservation system, and registration information of the visitor management system.

[0123] Schedule information refers to the pre-arranged functional area usage plan or activity schedule, which may include meeting time, location, participants, meeting theme and other information in the conference booking system.

[0124] The personnel entry and exit records of the access control system refer to the event records recorded by the access control system of a specific person entering or leaving a functional area through a specific access point at a specific time.

[0125] The number of people flowing refers to the total number of people entering and leaving a functional area recorded by the access control system within a specific time period.

[0126] The personnel turnover rate refers to the rate of change in the number of people entering or leaving a functional area per unit time, reflecting the frequency of personnel activities in the area.

[0127] Conference subject information refers to the main content or topic description of the conference recorded in the conference booking system.

[0128] The preset activity type knowledge base refers to a pre-established collection that stores relevant feature information of different activity types, which is used to infer the type of activity currently being carried out in the functional area based on input data.

[0129] Activity type refers to the specific category of activities currently taking place in the functional area, which may include meetings, office work, visitor reception, and rest.

[0130] Based on these technical features, the technical solution of this application operates as follows. First, the system acquires multi-source personnel activity data and extracts schedule information from it. Determining whether valid schedule information exists is the primary step, as schedule information generally directly reflects the type of scheduled activity and has a high degree of accuracy. If no clear schedule information exists, the system turns to the personnel entry and exit data recorded by the access control system.

[0131] The system counts the number of people entering and leaving functional areas within a given timeframe and calculates turnover rate. Turnover rate, as a dynamic behavioral indicator, indirectly reflects the intensity and patterns of activity within a region. In the absence of schedule information, the system further attempts to extract meeting topic information from multiple data sources.

[0132] If meeting topic information exists, the system combines this information with a pre-built knowledge base of activity types to infer the type of activity. The meeting topic provides semantic content for the activity, helping to more accurately determine its nature.

[0133] If neither schedule nor meeting topic information is available, the system relies entirely on the previously calculated turnover rate. By comparing or matching this rate with the turnover rate signatures associated with different activity types in the activity type knowledge base, the system ultimately determines the current activity type for the functional area.

[0134] This precise identification of activity types, combined with the occupant density calculated from aggregated activity data, provides critical and reliable input for accurately matching scenario-based environmental control strategies. By correctly identifying activity types, the system can more finely adjust environmental parameters to better meet the actual needs of occupants in the area while avoiding unnecessary energy waste.

[0135] Furthermore, step S34 includes:

[0136] S341: Build a preset activity type knowledge base, where the preset activity type knowledge base includes a mapping relationship between conference theme keywords and activity types, and a mapping relationship between staff turnover rate thresholds and activity types;

[0137] S342: If the conference topic information does not exist, compare the personnel turnover rate with the personnel turnover rate threshold corresponding to each activity type in the activity type knowledge base, and select an activity type corresponding to the threshold range to which the personnel turnover rate belongs.

[0138] The preset activity type knowledge base refers to a structured data set used to store association rules between different information and functional area activity types, which can be implemented using a database, a configuration file, or a data structure in memory.

[0139] The mapping relationship between conference theme keywords and activity types refers to establishing a corresponding relationship between specific conference theme words or phrases and preset activity types (for example, formal meetings, training, seminars, etc.), which can be implemented using key-value pairs, lookup tables or rule sets.

[0140] The mapping relationship between the personnel turnover rate threshold and the activity type refers to establishing a corresponding relationship between different personnel turnover rate ranges (defined by the threshold) and preset activity types (for example, daily office work, temporary gatherings, personnel evacuation, etc.), which can be implemented using piecewise functions, interval mapping tables or decision trees.

[0141] By building a knowledge base that maps turnover rate thresholds to activity types, and then comparing the real-time turnover rate with the thresholds in the knowledge base to determine activity types when no meeting topic information is available, this solution provides a specific, practical, and reasonably accurate method for determining activity types. This solves the problem of effectively using turnover rate to determine activity types in the absence of direct information, enabling subsequent environmental control strategy matching to be based on more reliable activity type information, thereby enhancing the intelligence level of the smart park IBMS integrated system and the sophistication of environmental control.

[0142] Furthermore, step S4 includes:

[0143] S41: Build an environmental parameter history database; the environmental parameter history database records historical environmental parameters of functional areas in different time periods;

[0144] S42: Preliminarily screen candidate policy templates from a preset scenario-based environmental control policy template library based on the personnel density level and activity type;

[0145] S43: Based on historical data, predict the change trend and fluctuation range of the current environmental parameters after adopting each candidate strategy template;

[0146] S44: According to the change trend and fluctuation range, a candidate policy template that makes the current environmental parameter approach the target value as quickly as possible and has the smallest fluctuation range is selected as the final matching scenario-based environmental control policy template.

[0147] The environmental parameter history database refers to a data structure or system used to store environmental parameter records of functional areas in different time periods, which can be implemented using a relational database, a non-relational database or a file system.

[0148] Among them, the scenario-based environmental control strategy template library refers to a pre-defined and stored set of environmental control strategies for different personnel density levels and activity types, which can be organized and stored in the form of structured data files, database tables or configuration files.

[0149] The candidate policy templates refer to a group of policy templates that are preliminarily screened from the policy template library based on the current personnel density level and activity type and may be applicable to the current scenario.

[0150] Among them, historical data refers to the data records stored in the environmental parameter history database that reflect the past environmental parameter status of the functional area.

[0151] Among them, the change trend refers to the evolution direction and rate of the predicted environmental parameters over time, and the fluctuation amplitude refers to the degree of dispersion of the predicted environmental parameters around their trend line or target value during the change process.

[0152] The target value refers to the ideal value or range that the environmental parameters are expected to reach, which is set according to the current scenario requirements.

[0153] In a specific embodiment, the environmental parameter history database can be implemented as a database system deployed on a cloud server, for example, using PostgreSQL. The database stores detailed environmental parameter data of each functional area in the park over a period of time, including temperature, humidity, CO2 concentration, lighting brightness, etc., and is associated with corresponding timestamps.

[0154] The scenario-based environmental control policy template library can be organized into a set of structured data files, such as JSON format. Each file represents a policy template, which defines the personnel density level, activity type, target environmental parameter value and corresponding control logic applicable to the policy.

[0155] After the system obtains the occupant density level and activity type for the current functional area, it queries these data files and preliminarily selects all eligible policy templates as candidates. To predict changes in environmental parameters after adopting each candidate policy template, the system can utilize pre-trained prediction models, such as recurrent neural networks (RNNs) trained on historical data. Using the current environmental parameter state as input and combining it with the control rules defined in the candidate policy templates, it predicts the sequence of changes in environmental parameters (such as temperature, lighting, and fresh air) over a period of time.

[0156] The system also quantifies the magnitude of the predicted fluctuation by calculating statistical differences, such as variance, between the predicted sequence and historical data. Finally, the system compares the predictions of all candidate policy templates and selects the policy template that predicts the fastest change in environmental parameters toward the target value and minimizes the predicted fluctuation. This policy template is then selected as the final strategy for controlling the building automation subsystem.

[0157] Furthermore, step S43 includes:

[0158] S431: Using historical environmental parameters in the environmental parameter history database as a training set, construct a temperature prediction model, a lighting prediction model, and a fresh air prediction model;

[0159] S432: Inputting the current environmental parameters into the temperature prediction model, the lighting prediction model, and the fresh air prediction model, and predicting the changing trend of the current environmental parameters after adopting each candidate strategy template;

[0160] S433: Based on the change trend, the variance between the predicted environmental parameters and the historical environmental parameters is calculated to obtain the fluctuation range.

[0161] The environmental parameter history database refers to a data storage structure used to store historical environmental parameters of functional areas in different time periods, which can be implemented using a relational database, a time series database, or a file system.

[0162] The temperature prediction model, lighting prediction model and fresh air prediction model refer to mathematical models or algorithmic models trained based on historical environmental parameter data that can predict future changes in environmental parameters. They can be implemented using a time series prediction model (such as the ARI MA model).

[0163] A trend is the direction and rate of change of an environmental parameter over time, whether it increases, decreases, or remains stable. Fluctuation refers to the degree to which an environmental parameter deviates from its mean or target value during the change process. This can be quantified by calculating the variance.

[0164] In one embodiment, the environmental parameter history database may be a time series database stored on a server, which records the temperature, lighting brightness, and fresh air volume data of the functional area every day in the past year.

[0165] The training process uses data from the historical database to train and optimize these models. In the prediction stage, when a candidate policy template needs to be evaluated, the system obtains the real-time temperature, lighting brightness, and fresh air volume of the current functional area, and inputs these current parameters as inputs into the trained ARI MA model. At the same time, the control instructions contained in the candidate policy template (for example, target temperature, target brightness, target fresh air volume, and the time curve or control logic to achieve the target) are used as auxiliary inputs or constraints of the model. Based on the current state, policy instructions, and historically learned rules, the model predicts the change sequence of temperature, lighting brightness, and fresh air volume in the future (for example, the next hour).

[0166] For example, a predicted temperature series might be a series of temperature values ​​that change over time. When calculating the fluctuation amplitude, the variance between the predicted temperature series and the historical temperature series (for example, a typical temperature variation series under similar occupancy density and activity types in a historical database) can be calculated, or the variance of each point in the predicted temperature series relative to the target temperature can be calculated to represent the temperature fluctuation amplitude. Similarly, the variance between the predicted series of lighting brightness and fresh air volume and the historical series or target values ​​can be calculated to obtain the corresponding fluctuation amplitude.

[0167] Furthermore, step S5 includes:

[0168] S51: monitor the operating status of the building automation subsystem in real time to determine whether the building automation subsystem is operating normally; if the building automation subsystem is operating abnormally, generate an alarm message and send it to the management platform;

[0169] S52: If the building automation subsystem operates normally, the matching scenario-based environment control strategy template is parsed into a control instruction set recognizable by the building automation subsystem;

[0170] S53: Evaluate the adjustment effect of the environmental parameters based on the real-time environmental parameters fed back by the building automation subsystem. If the environmental parameters do not reach the target values, adjust the control instructions based on the fed-back real-time environmental parameters and resend them to the building automation subsystem until the environmental parameters reach the target values.

[0171] Among them, the building automation subsystem refers to the specific control units that constitute the IBMS integrated system of the smart park, such as the HVAC system, lighting control system, fresh air system, etc., which can be implemented using a controller network based on bus protocols (such as BACnet, Modbus).

[0172] The operating status refers to the current working status of the building automation subsystem, including but not limited to whether the equipment is online, whether the communication is normal, whether there is a hardware or software failure, etc. It can be obtained by periodically sending query instructions and receiving subsystem responses.

[0173] Alarm information refers to the data record or notification generated by the system when the building automation subsystem is judged to be operating abnormally. It can contain information such as the type of abnormality, time of occurrence, and equipment involved, and can be sent using a message queue or API interface.

[0174] The management platform is a higher-level software system used to receive and display alarm information and provide manual intervention or management functions. It can be deployed on a server and communicate with the IBMS integrated system via the network. Scenario-based environmental control policy templates are pre-defined environmental parameter control plans based on specific occupancy levels and activity types. These templates can be stored as structured data files or database records and include parameters such as temperature set points, lighting levels, and fresh air volume.

[0175] The control instruction set refers to a command sequence generated after parsing the scenario-based environmental control strategy template, which can be directly recognized and executed by the building automation subsystem and can comply with the communication protocol specifications used by the building automation subsystem.

[0176] Real-time environmental parameters refer to the current temperature, humidity, illumination, air quality and other data of the functional area collected by sensors or other monitoring equipment, which can be obtained by periodically reading sensor data.

[0177] The target value refers to the ideal value or range that the functional area environmental parameters are expected to reach under a specific scenario-based environmental control strategy, which can be extracted from the matching strategy template.

[0178] In a specific embodiment, this method is applied to a functional area within a conference room. After matching the corresponding environmental control policy template based on the conference room's current occupancy level and activity type—for example, a policy template with a set temperature of 24 degrees Celsius, medium lighting brightness, and automatic fresh air mode—before executing control commands, the system first sends a status query command to the HVAC controller, lighting controller, and fresh air controller that control the conference room environment via a communication interface of the building automation network, such as the BACnet protocol.

[0179] If any controller fails to respond within the preset time or returns an error status code, the system will determine that the building automation subsystem is operating abnormally and generate an alarm message containing the device identification, abnormality type and timestamp, which will be sent via the network to the management platform server deployed in the campus data center. The administrator can view the alarm message on the management platform interface.

[0180] If all relevant controllers respond normally, the system interprets the matching policy template. For example, the temperature setpoint of 24 degrees Celsius in the policy template is interpreted as a temperature setting instruction recognized by the HVAC controller, the lighting brightness level is interpreted as a dimming instruction recognized by the lighting controller, and the fresh air mode is interpreted as an operating mode instruction recognized by the fresh air controller. These parsed control command sets are then sent to the corresponding controllers via the building automation network.

[0181] After issuing the command, the system continuously reads real-time data from sensor interfaces connected to the building automation network, such as temperature sensors, illuminance sensors, and CO2 sensors connected to the BACnet network. The system compares the real-time temperature data with the target temperature of 24°C, the real-time illuminance data with the target brightness, and the real-time CO2 concentration data with the target concentration range for the fresh air mode. If the real-time temperature is 25°C, which does not meet the target value, the system calculates the control variables that need further adjustment based on the current real-time data at 25°C, such as increasing the opening percentage of the cold water valve. It then generates a new HVAC control command and resends it to the HVAC controller. If the real-time illuminance or CO2 concentration also does not meet the target, the system adjusts the lighting and fresh air control commands accordingly and resends them. This monitoring, evaluation, adjustment, and resending process is repeated periodically, for example, every 15 minutes, until the meeting room's real-time environmental parameters, such as temperature, illuminance, and CO2 concentration, reach or remain within the target values ​​or ranges specified in the policy template.

[0182] Please refer to Figure 2 、 Figure 3 A smart park IBMS integrated system, applied to the steps of any of the above methods, includes:

[0183] Acquisition module 201: Acquisition of multi-source personnel activity data in functional areas;

[0184] Division module 202: Based on multi-source personnel activity data, aggregate and calculate the number and density of personnel in the functional area, and divide the personnel density levels;

[0185] Determination module 203: Determine the activity type of the functional area by combining the schedule information and personnel entry and exit records in the multi-source personnel activity data;

[0186] Matching module 204: matching scenario-based environment control strategy templates based on personnel density level and activity type;

[0187] Adjustment module 205: sends control instructions to the building automation subsystem according to the matched scenario-based environmental control strategy template to adjust the environmental parameters of the functional area, including temperature, lighting and fresh air.

[0188] The acquisition module 201 refers to a unit for collecting and receiving personnel activity data from different sources, and can be implemented by using a data interface, a sensor, a data bus, etc.

[0189] The division module 202 is a unit for processing acquired data, calculating the number and density of personnel, and determining the density level according to preset rules. It can be implemented using a data processor, a calculation unit, a software algorithm module, etc.

[0190] The judgment module 203 is a unit for analyzing schedule information and personnel entry and exit records and identifying the nature of current activities in the functional area. It can be implemented using a logic judgment unit, a data analysis module, a software program, etc.

[0191] The matching module 204 is a unit for selecting a suitable environment control strategy from a preset library according to the density level and activity type, and can be implemented by a lookup table, a rule engine, a decision module, etc.

[0192] The adjustment module 205 is a unit for converting the matched strategy into a control instruction and sending it to the building automation subsystem, and can be implemented by a communication interface, a protocol converter, a control signal generator, etc.

[0193] This system achieves dynamic control of the functional area environment by decomposing the smart park IBMS integration method into a series of modules with clear functions.

[0194] First, the acquisition module 201 continuously collects personnel activity data from multiple sources such as access control, conference booking, and visitor management. These raw data are sent to the division module 202, which performs aggregation calculations to obtain the number and density of people in the area and determines the personnel density level based on a preset threshold. At the same time, the judgment module 203 analyzes the schedule information and personnel entry and exit records in the activity data to identify the type of activity being carried out in the current area. Subsequently, the matching module 204 receives the personnel density level and activity type information and searches the preset policy library for the environmental control policy template that best suits the current scenario. Finally, the adjustment module 205 generates control instructions that can be recognized by the building automation subsystem based on the matched policy template and sends them out to adjust the temperature, lighting, fresh air and other environmental parameters of the functional area in real time.

[0195] This modular system design enables complex data processing, state judgment, strategy matching and instruction sending processes to be executed efficiently and reliably, providing a solid system foundation for dynamic environmental control based on multi-source personnel activity data, and overcoming the difficulties encountered by existing general IBMS systems in achieving such refined control.

[0196] In a specific embodiment, the IBMS integrated system of the smart park can be deployed on a distributed computing platform. The acquisition module 201 can implement a set of data acquisition services, connect with the access control system, conference reservation system, visitor management system, etc. through a standard API or data bus, and pull or receive data streams in real time. The division module 202 and the judgment module 203 can be implemented as data processing services, running on the computing node, receiving the data transmitted by the acquisition module, and executing algorithms for aggregation calculation, density division and activity type judgment. The matching module 204 can be implemented as a policy engine service, maintaining a scenario-based environment control policy template library, and executing matching logic based on the received density level and activity type information. The adjustment module 205 can be implemented as a control instruction generation and sending service, parsing the matched policy template into a control instruction that complies with the building automation subsystem communication protocol (such as BACnet, Modbus, etc.), and sending it to the corresponding building automation device controller through the network interface. These services can communicate asynchronously through message queues to ensure smooth data flow and system responsiveness.

[0197] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0198] The foregoing is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Persons skilled in the art will readily appreciate that the present application may be modified and altered in various ways. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A smart park IBMS integration method, characterized in that: The method comprises the steps of: S1: Acquire multi-source personnel activity data in functional areas; S2: Based on the multi-source personnel activity data, aggregate and calculate the number and density of personnel in the functional area, and divide the personnel density levels; S3: Determine the activity type of the functional area by combining the schedule information and personnel entry and exit records in the multi-source personnel activity data; S4: matching a scenario-based environment control strategy template according to the personnel density level and the activity type; S5: Based on the matching scenario-based environmental control strategy template, control instructions are sent to the building automation subsystem to adjust the environmental parameters of the functional area, including temperature, lighting, and fresh air.

2. A smart park IBMS integration method according to claim 1, characterized in that: Step S1 includes: S11: collecting initial multi-source personnel activity data from the access control system, conference booking system, and visitor management system in real time at preset time intervals; S12: performing a cleaning process on the initial multi-source personnel activity data to remove duplicate data and filter out invalid data; S13: performing unified format conversion on the cleaned initial multi-source personnel activity data, converting data from different sources into a unified data structure, and obtaining the multi-source personnel activity data.

3. The smart park IBMS integration method according to claim 1, characterized in that: Step S2 includes: S21: Constructing a personnel density calculation model, using the multi-source personnel activity data as input, to calculate the number of personnel in the functional area; S22: Calculate the personnel density based on the area of ​​the functional area and the number of personnel, where personnel density = number of personnel / area of ​​the functional area; S23: Obtain a preset threshold for dividing the population density level, and divide the population density level into low density, medium density and high density according to the preset threshold for dividing the population density level and the population density.

4. A smart park IBMS integration method according to claim 3, characterized in that: Step S21 includes: S211: Analyzing the characteristics of the multi-source personnel activity data based on the multi-source personnel activity data to determine the contribution of each type of data to the personnel quantity calculation; wherein the contribution of the conference reservation system data is greater than or equal to the contribution of the access control system data, which is greater than or equal to the contribution of the visitor management system data; S222: According to the contribution of each type of data to the personnel calculation, combined with historical data statistical analysis, corresponding weight coefficients are set; wherein the weight coefficient of the conference reservation system data is α, the weight coefficient of the access control system data is β, and the weight coefficient of the visitor management system data is γ, and α>β>γ, α+β+γ=1; S223: Based on the data characteristics and weight coefficients, the personnel density calculation model is constructed; the number of personnel = α * the number of participants in the conference reservation system + β * (the number of people entering the gate - the number of people leaving the gate) + γ * the number of people registered in the visitor management system.

5. The smart park IBMS integration method according to claim 1, characterized in that: Step S3 includes: S31: extracting schedule information from multi-source personnel activity data and determining whether schedule information exists; S32: If it does not exist, count the number of people entering and leaving the functional area per unit time based on the personnel entry and exit records of the access control system, and calculate the personnel flow rate; S33: If not, extract the conference theme information and determine whether the conference theme information exists. If the conference theme information exists, determine the activity type by combining the conference theme information with a preset activity type knowledge base. S34: If the conference theme information does not exist, determining the activity type according to the personnel turnover rate and a preset activity type knowledge base.

6. The smart park IBMS integration method according to claim 5, characterized in that: Step S34 includes: S341: Constructing the preset activity type knowledge base, wherein the preset activity type knowledge base includes a mapping relationship between conference theme keywords and activity types, and a mapping relationship between staff turnover rate thresholds and activity types; S342: If the conference topic information does not exist, compare the personnel turnover rate with the personnel turnover rate threshold corresponding to each activity type in the activity type knowledge base, and select the activity type corresponding to the threshold range to which the personnel turnover rate belongs.

7. The smart park IBMS integration method according to claim 1, characterized in that: Step S4 includes: S41: Building an environmental parameter history database; the environmental parameter history database records historical environmental parameters of functional areas in different time periods; S42: Preliminarily screening candidate policy templates from a preset scenario-based environment control policy template library based on the personnel density level and the activity type; S43: Predicting, based on the historical data, the change trend and fluctuation range of the current environmental parameters after adopting each of the candidate strategy templates; S44: According to the change trend and fluctuation range, a candidate policy template that makes the current environmental parameter approach the target value as quickly as possible and has the smallest fluctuation range is selected as the scenario-based environmental control policy template to be finally matched.

8. The smart park IBMS integration method according to claim 7, characterized in that: Step S43 includes: S431: Using historical environmental parameters in the environmental parameter history database as a training set, construct a temperature prediction model, a lighting prediction model, and a fresh air prediction model; S432: Inputting the current environmental parameters into the temperature prediction model, the lighting prediction model, and the fresh air prediction model, and predicting the change trend of the current environmental parameters after adopting each candidate strategy template; S433: Calculate the variance between the predicted environmental parameter and the historical environmental parameter based on the change trend to obtain the fluctuation amplitude.

9. The smart park IBMS integration method according to claim 1, characterized in that: Step S5 includes: S51: monitor the operating status of the building automation subsystem in real time to determine whether the building automation subsystem is operating normally; if the building automation subsystem is operating abnormally, generate an alarm message and send it to the management platform; S52: If the building automation subsystem operates normally, the matching scenario-based environment control strategy template is parsed into a control instruction set recognizable by the building automation subsystem; S53: Evaluate the adjustment effect of the environmental parameters based on the real-time environmental parameters fed back by the building automation subsystem. If the environmental parameters do not reach the target values, adjust the control instructions based on the fed-back real-time environmental parameters and resend them to the building automation subsystem until the environmental parameters reach the target values.

10. A smart park IBMS integrated system, characterized by: In the steps of the method according to any one of claims 1 to 9 above, the system comprises: Acquisition module: acquires multi-source personnel activity data of functional areas; Division module: Based on the multi-source personnel activity data, aggregate and calculate the number and density of personnel in the functional area, and divide the personnel density levels; Determination module: combining the schedule information and personnel entry and exit records in the multi-source personnel activity data to determine the activity type of the functional area; Matching module: matching scenario-based environment control strategy template according to the personnel density level and the activity type; Adjustment module: Based on the matching scenario-based environmental control strategy template, it sends control instructions to the building automation subsystem to adjust the environmental parameters of the functional area, including temperature, lighting and fresh air.

Images