Intelligent office area management system and method based on Internet of Things

Through IoT technology, a smart office area management system is established, and data collection and analysis is used to use BIM models and intelligent sensors to realize intelligent management of office areas, solving the problem of low efficiency of existing management solutions and improving operational efficiency and user experience.

CN118940968AInactive Publication Date: 2024-11-12深圳市裕熙科技有限公司

Patent Information

Application Number
CN202411142396.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing office area management plan is not smart enough and inefficient enough to meet the needs of a comfortable, convenient, fast and safe office environment.

Method used

Adopt a smart office area management system based on the Internet of Things, and through the Internet of Things server and cloud service platform, three-dimensional data, design data and function description data are obtained, BIM model is established, intelligent sensors are configured, data is collected in real time, statistical analysis and intelligent control are carried out, Implement intelligent management of environmental parameters and resources.

Benefits of technology

It improves the operation efficiency and user experience of the office area, realizes intelligent adjustment of environmental parameters and efficient allocation of resources, timely identify and handle abnormal events, and improves the intelligent management level of the office area.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940968A_ABST
    Figure CN118940968A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent office area management system and method based on the Internet of Things, and the method comprises the steps: building a BIM model according to the three-dimensional data, design data and function description data of an office area; deploying an intelligent sensor in the office area, collecting area data in real time and transmitting the area data to the cloud service platform; the cloud service platform performs statistical analysis on the data, establishes a digital model, and analyzes an environment parameter state, personnel flow distribution and a resource use state; according to an analysis result, environment facilities are adjusted through intelligent control equipment, and shared resources are intelligently managed, so that efficient utilization is realized; and if the abnormal event is identified, pushing alarm information, and generating an exception handling measure according to the real-time area data and the digital model. Through the scheme of the invention, data acquisition, digital modeling and intelligent management based on the Internet of Things technology are realized, and the operation efficiency and the use experience of an office area are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a smart office area management system and method based on the Internet of Things. Background Art

[0002] The Internet of Things is an important part of the new generation of information technology. It is widely used in the network through intelligent perception, recognition technology and ubiquitous computing. With the development of Internet of Things technology and the advancement of communication technology and people's increasing requirements for the environment, a comfortable, convenient, fast and safe office environment has become people's pursuit; however, the existing office area management solution is not smart enough and has low efficiency. There is an urgent need for an intelligent office area management system based on the Internet of Things. Summary of the invention

[0003] Based on the above problems, the present invention proposes a smart office area management system and method based on the Internet of Things. Through the scheme of the present invention, data collection, digital modeling and intelligent management based on the Internet of Things technology are realized, thereby improving the operating efficiency and user experience of the office area.

[0004] In view of this, one aspect of the present invention proposes a smart office area management system based on the Internet of Things, including: an Internet of Things server and a cloud service platform; wherein, The IoT server is configured as follows: Acquire first three-dimensional data, first design data, and first functional description data of a first office area; Establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data; According to the first BIM model, a plurality of first intelligent sensors are configured in the first office area; Collecting first area data in the first office area in real time through the first intelligent sensor; Transmitting the first regional data to the cloud service platform; The cloud service platform is configured as follows: Performing statistical analysis on the collected data of the first area to establish a first digital model of the first office area; Analyze and identify the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain a first area analysis result; According to the analysis result of the first area, the environmental facilities in the first office area are intelligently controlled and adjusted through the intelligent control device to ensure that the environmental parameters are within the preset range and the various shared resources in the first office area are intelligently managed to achieve efficient allocation and utilization of resources; Identify whether there is an abnormal event in the first area analysis result; If an abnormal event occurs, an alarm message is pushed, and first real-time regional data collected by the first smart sensor is obtained; An exception handling measure is generated according to the first real-time regional data and the first digital model.

[0005] Another aspect of the present invention provides a smart office area management method based on the Internet of Things, comprising: Acquire first three-dimensional data, first design data, and first functional description data of a first office area; Establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data; According to the first BIM model, a plurality of first intelligent sensors are configured in the first office area; Collecting first area data in the first office area in real time through the first intelligent sensor; Transmitting the first regional data to the cloud service platform; The cloud service platform performs statistical analysis on the collected data of the first area to establish a first digital model of the first office area; Analyze and identify the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain a first area analysis result; According to the analysis result of the first area, the environmental facilities in the first office area are intelligently controlled and adjusted through the intelligent control device to ensure that the environmental parameters are within the preset range and the various shared resources in the first office area are intelligently managed to achieve efficient allocation and utilization of resources; Identify whether there is an abnormal event in the first area analysis result; If an abnormal event occurs, an alarm message is pushed, and first real-time regional data collected by the first smart sensor is obtained; An exception handling measure is generated according to the first real-time regional data and the first digital model.

[0006] Optionally, the step of establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data includes: constructing an initial BIM model according to the first three-dimensional data; Establishing an entity object class for each house object and / or facility object according to the name and size in the first design data; Matching and associating the three-dimensional geometric body in the initial BIM model with the entity object class; Inputting the function annotations in the first design data into the initial BIM model, associating correct function attributes for each of the entity object classes, and ensuring that the attribute names and measurement units of each of the entity object classes are consistent with the first design data; Importing the first functional description data into the initial BIM model as a detailed text description of each entity object class; Performing layer management on the initial BIM model to achieve scenario simulation and analysis query; Check whether the initial BIM model is consistent with the design plane in the first design data Figure 1 The information is consistent and complete; If yes, the initial BIM model is used as the first BIM model; If not, the initial BIM model is adjusted according to the design plan in the first design data to obtain the first BIM model.

[0007] Optionally, the step of configuring a plurality of first smart sensors in the first office area according to the first BIM model includes: In the first BIM model, the sensor categories, the number of sensors of each category, the parameter requirements of each sensor and the theoretical layout positions of each sensor are planned according to the functional area division and the equipment layout, and a first corresponding relationship between each layout position and the sensor category, the sensor parameter and the number of sensors is established; In combination with reference office area data based on time series association of other office areas, the first type, the first parameter, the first quantity and the first arrangement position of each first smart sensor are determined according to the sensor category, the number of sensors of each category, the parameter requirements, the theoretical arrangement position and the first corresponding relationship; Installing each of the first smart sensors in the first office area according to the first type, the first parameter, the first quantity, and the first arrangement position, and recording the serial number of each of the first smart sensors and the corresponding identifier of the entity object class in the first BIM model; Acquire real-time data of each of the first smart sensors, and test whether the connection function between the first smart sensor and the house object and / or facility object is normal; If normal, the numbers and parameters of each of the first smart sensors are uploaded through the gateway and written into the corresponding sensor object attributes in the first BIM model to achieve real-time bidirectional synchronous update of the sensor objects and physical sensors in the first BIM model.

[0008] Optionally, the cloud service platform performs statistical analysis on the collected first area data to establish a first digital model of the first office area, including: Arranging the data of the first region and extracting time series parameters and classification features; Establishing a time series analysis model for changes in each indicator of the first office area according to the time series parameters and the classification characteristics; Establishing a first physical model according to the relationship between the object attributes of the first office area described in the first BIM model and the data features of the physical object; Predicting the time-space distribution data of personnel activities and resource utilization in the first office area in different time periods according to the time series analysis model; Extracting sample data from the reference office area data, and training the sample data through a machine learning algorithm to establish a simulation model of the first office area; Integrate and fuse the first physical model, the time-space distribution data and the simulation model to construct a first digital model; The first digital model is tested and the parameters are adjusted to match the real data to a preset matching value.

[0009] Optionally, the step of analyzing and identifying the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain the first area analysis result includes: Setting an analysis index system for each region in the first digital model; Obtaining statistical distribution data of each indicator in the analysis indicator system according to the historical data algorithm built into the first digital model; The statistical distribution data is respectively compared with a first preset standard corresponding to the environmental parameter state, a second preset standard corresponding to the personnel flow distribution, and a third preset standard corresponding to the resource usage state to determine abnormal values ​​of environmental indicators and environmental development trends, abnormal values ​​of personnel flow indicators and personnel flow development trends, and abnormal values ​​of resource usage and resource usage trends; Based on the abnormal values ​​of environmental indicators and environmental development trends, the abnormal values ​​of human flow indicators and human flow development trends, and the abnormal values ​​of resource use and resource use trends, the first regional analysis results are generated to mark problem points and optimization suggestions.

[0010] Optionally, the step of intelligently controlling and adjusting environmental facilities in the first office area through intelligent control equipment to ensure that environmental parameters are within a preset range and intelligently managing various shared resources in the first office area to achieve efficient resource allocation and utilization includes: Determine potential problem areas of environment and resource utilization efficiency based on the first area analysis results, and generate corresponding tuning suggestions for the potential problem areas; Sending the tuning suggestions to the intelligent control device via the Internet of Things; The intelligent control device adjusts the parameters of the environmental facilities in the potential problem area according to the tuning suggestion; Acquire real-time monitoring data of the first intelligent sensor; Determining whether environmental parameters are within a preset range and / or whether various shared resources in the first office area meet preset usage rates according to the real-time monitoring data; If the environmental parameters are not within a preset range and / or the various shared resources in the first office area do not meet the preset usage rate, the management measures of the first office area are continuously optimized through the intelligent control device.

[0011] Optionally, the step of identifying whether there is an abnormal event in the first region analysis result includes: Extracting historical abnormal event data from the reference office area data; Establishing an anomaly recognition model based on the historical abnormal event data; Preprocessing the first region analysis result to extract a first characteristic parameter; Using a machine learning classifier stored in the abnormality recognition model, comparing the first feature parameter with the abnormal feature parameter in the abnormality recognition model; The machine learning classifier gives a probability score for each abnormal event and issues a warning for the type and level of the abnormal event with the highest probability value.

[0012] Optionally, the step of generating an exception handling measure according to the first real-time regional data and the first digital model includes: Determining a real-time status of an abnormal event from the first real-time regional data according to the abnormality recognition model; determining a first office area real-time status of the first office area according to the first real-time area data; Retrieving a common processing flow for the abnormal event in a preset knowledge base; According to the real-time status of the abnormal event and the real-time status of the first office area, the specific operation steps in the general processing flow are revised to obtain the abnormal processing measures.

[0013] Optionally, the step of revising specific operation steps in the general processing flow according to the real-time status of the abnormal event and the real-time status of the first office area to obtain the abnormal processing measures includes: Determine the current state of the abnormal event and the development trend of the abnormal event according to the real-time state of the abnormal event; Determine the current abnormal state and current personnel evacuation state of the first office area according to the real-time state of the first office area; According to the current state of the abnormal event, the development trend of the abnormal event, the current abnormal state and the current personnel evacuation state, evaluate the potential impact of the abnormal event on the first office area, and identify the abnormal areas and abnormal problems that need to be handled with priority; According to the potential impact, the abnormal area and the abnormal problem, adjust the evacuation route, avoid high-risk areas, optimize resource allocation, and update the emergency response level; Formulate detailed implementation steps, clarify the division of responsibilities of each department and personnel, set key nodes and completion deadlines, and obtain the aforementioned exception handling measures; Adjust processing measures in real time according to the latest status, evaluate the effectiveness of the measures, and make corresponding corrections.

[0014] According to the technical solution of the present invention, the smart office area management method based on the Internet of Things includes: obtaining first three-dimensional data, first design data and first functional description data of a first office area; establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data; configuring a plurality of first intelligent sensors in the first office area according to the first BIM model; collecting first regional data in the first office area in real time through the first intelligent sensor; transmitting the first regional data to a cloud service platform; the cloud service platform statistically analyzes the collected first regional data to establish a first digital model of the first office area; analyzing and identifying the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain a first regional analysis result; according to the first regional analysis result, intelligently controlling and adjusting the environmental facilities in the first office area through an intelligent control device to ensure that the environmental parameters are within a preset range and intelligently managing various shared resources in the first office area to achieve efficient resource allocation and utilization; identifying whether there is an abnormal event in the first regional analysis result; if there is an abnormal event, pushing an alarm message, and obtaining the first real-time regional data collected by the first intelligent sensor; generating an abnormality handling measure according to the first real-time regional data and the first digital model. Through the solution of the present invention, data collection, digital modeling and intelligent management based on the Internet of Things technology are realized, and the operating efficiency and user experience of the office area are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic block diagram of a smart office area management system based on the Internet of Things provided by an embodiment of the present invention; Figure 2 It is a flow chart of a smart office area management method based on the Internet of Things provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0019] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] Refer to the following Figure 1 to Figure 2 To describe a smart office area management system and method based on the Internet of Things provided according to some embodiments of the present invention.

[0021] like Figure 1 As shown, an embodiment of the present invention provides a smart office area management system based on the Internet of Things, including: an Internet of Things server and a cloud service platform; wherein, The IoT server is configured as follows: Acquire first three-dimensional data, first design data, and first functional description data of a first office area; Establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data; According to the first BIM model, a plurality of first intelligent sensors are configured in the first office area; Collecting first area data in the first office area in real time through the first intelligent sensor; Transmitting the first regional data to the cloud service platform; The cloud service platform is configured as follows: Performing statistical analysis on the collected data of the first area to establish a first digital model of the first office area; Analyze and identify the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain a first area analysis result; According to the analysis result of the first area, the environmental facilities in the first office area are intelligently controlled and adjusted through the intelligent control device to ensure that the environmental parameters are within the preset range and the various shared resources in the first office area are intelligently managed to achieve efficient allocation and utilization of resources; Identify whether there is an abnormal event in the first area analysis result; If an abnormal event occurs, an alarm message is pushed, and first real-time regional data collected by the first smart sensor is obtained; An exception handling measure is generated according to the first real-time regional data and the first digital model.

[0022] It should be known that Figure 1 The block diagram of the IoT-based smart office management system is for illustration only, and the number of modules shown does not limit the protection scope of the present invention.

[0023] See also Figure 2 Another embodiment of the present invention provides a smart office area management method based on the Internet of Things, comprising: Acquire first three-dimensional data, first design data, and first functional description data of a first office area; In this step, the first office area is 3D scanned to obtain the 3D point cloud data of all the house structures and equipment layouts in the area; the scanning results are carefully processed to extract the 3D model file data of each house and equipment; according to the original design drawings, the structural design parameters such as personnel planning and area design in the area are restored; through the original design requirements, design materials, field observations and interviews, the functional use description of each area in the area is determined and recorded or marked; the above 3D model data, design data and functional description data are stored in the cloud database. The data collected in this step can build the first digital twin of the first office area and truly restore the first physical space; it can provide the first fine 3D model to support a new round of design work; it can enter the first metadata to build the first foundation of intelligent management; it can realize the first data mobile phone access to support remote visual management; and it can lay the first intelligent work foundation and lay the foundation for intelligent operation.

[0024] Establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data; According to the first BIM model, a plurality of first intelligent sensors are configured in the first office area; Collecting first area data (such as environmental data, personnel activity data, resource usage data, etc.) in the first office area in real time through the first intelligent sensor; In this step, the first intelligent sensor automatically collects data regularly according to the parameters, and the data is uploaded to the sensor object in the form of a digital package; the sensor object converts the collected data into the corresponding data standard format and stores it in the corresponding attribute field of the first BIM model; the first BIM model aggregates and integrates the data collected by multiple sensors into data analysis for each area to identify regional change trends; multivariate analysis is performed on the collected environmental data, human flow data, and resource usage data to draw a dynamic map of regional space and time; regional data is transparently displayed to management users, supporting query statistics and visual analysis. Through this step, unified data collection management based on BIM can be achieved, multi-source physical indicators of the region during real operation can be obtained, regional spatial decision-making references based on data analysis can be provided, and supporting evidence for regional resource operations and environmental adjustments can be achieved, laying a data foundation for future intelligent facility control; this step is based on BIM and realizes the full perception of the status within the management area.

[0025] Transmitting the first regional data to the cloud service platform; In this step, the first BIM model encapsulates and integrates the data collected in each first area, selects a safe and reliable communication method, and sends the regional data from the BIM model to the Internet of Things platform; after receiving the data, the Internet of Things platform performs format verification and stores it on the cloud service platform (cloud database server); the cloud service platform associates and integrates the regional physical data with the BIM model information; develops cloud service applications to realize online query and analysis of regional data in the cloud; cloud services support sending analysis results to the management end through the App. In this step, cloud technology is used to realize the centralized storage and management of regional data, solve the capacity limitations of local data storage and reasoning, realize network access query of regional data by any device, provide a uniform and standardized development environment for data applications, and support regional operation decision support based on big data. This step helps the transformation of smart management to cloud services by uploading regional data to the cloud.

[0026] The cloud service platform performs statistical analysis on the collected data of the first area to establish a first digital model of the first office area; Analyze and identify the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain a first area analysis result; Based on the analysis results of the first area, intelligently control and adjust the environmental facilities (such as lighting, ventilation, air conditioning and other equipment) in the first office area through intelligent control equipment to ensure that the environmental parameters are within a preset range and intelligently manage various shared resources (such as conference rooms, multimedia equipment, etc.) in the first office area to achieve efficient resource allocation and utilization; Identify whether there is an abnormal event in the first area analysis result; If an abnormal event occurs, an alarm message is pushed, and first real-time regional data collected by the first smart sensor is obtained; In this step, after the anomaly recognition model recognizes that there is an abnormal event in the first office area, it immediately marks the state of the area as "abnormal" in the cloud; the cloud pushes the abnormal event type and regional location information to the intelligent control terminal via SMS or application, and the intelligent control terminal sends instructions to the relevant first intelligent sensor in the first office area; the relevant first intelligent sensor begins to collect important monitoring parameters in the first office area at a higher sampling frequency; the first intelligent sensor reports the collected first real-time regional data to the cloud at a higher frequency; the cloud saves the first real-time regional data to provide a basis for further analysis and evaluation. In this step, an alarm can be pushed in time when an abnormality occurs. After the alarm, the monitoring frequency is increased to obtain key data, which provides an important reference for subsequent event analysis and processing, timely response and adjustment, and reduction of losses, to achieve automated intelligent management in a digital environment.

[0027] An exception handling measure is generated according to the first real-time regional data and the first digital model.

[0028] According to the technical solution of this embodiment, first three-dimensional data, first design data and first functional description data of a first office area are obtained; a first BIM model of the first office area is established according to the first three-dimensional data, the first design data and the first functional description data; a plurality of first intelligent sensors are configured in the first office area according to the first BIM model; first regional data in the first office area is collected in real time by the first intelligent sensor; the first regional data is transmitted to a cloud service platform; the cloud service platform performs statistical analysis on the collected first regional data to establish a first digital model of the first office area; the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area are analyzed and identified according to the first digital model to obtain a first regional analysis result; according to the first regional analysis result, environmental facilities in the first office area are intelligently controlled and adjusted by an intelligent control device to ensure that the environmental parameters are within a preset range and various shared resources in the first office area are intelligently managed to achieve efficient resource allocation and utilization; it is identified whether there is an abnormal event in the first regional analysis result; if there is an abnormal event, an alarm message is pushed, and the first real-time regional data collected by the first intelligent sensor is obtained; and abnormal handling measures are generated according to the first real-time regional data and the first digital model. Through the scheme of the present invention, data collection, digital modeling and intelligent management based on the Internet of Things technology are realized, and the operating efficiency and user experience of the office area are improved. The scheme of this embodiment realizes data collection, digital modeling and intelligent management based on the Internet of Things technology, and improves the operating efficiency and user experience of the office area.

[0029] In some possible implementations of the present invention, the step of establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data includes: constructing an initial BIM model according to the first three-dimensional data; Establishing an entity object class for each house object and / or facility object according to the name and size in the first design data; In this step, the name, type, size and other attribute information of each house or facility object is extracted from the first design data; in the BIM software, the corresponding standard object template is selected for each object according to the object type library; according to the attribute information, the name and type attribute values ​​are specified for each object template; according to the position and orientation information specified in the design document, the position and direction of the object template in the three-dimensional space are adjusted; the length, width and depth of the object are input according to the actual size; the material and surface attributes are assigned to the object according to the design requirements; the object attribute values ​​are checked to see if they are consistent with the design documents and saved as object classes. Through this step, an object class system that corresponds to the actual design and has complete information can be constructed, providing a standardized object classification system for information management and statistical calculations, and providing location and topology information for future maintenance and embedded IoT devices.

[0030] Matching and associating the three-dimensional geometric body in the initial BIM model with the entity object class; In this step, the established object classes are exported as three-dimensional geometric bodies of different colors, the initial model geometric bodies in the initial BIM model are classified, and different colors are used to represent different object types; the object class geometric bodies are placed one by one into the initial model geometric bodies of the corresponding type and position; the consistency of the object class geometric bodies and the initial model geometric bodies in position, shape and direction is checked; the topological relationship between the object class and the initial model geometric bodies is established; check whether all geometric bodies are matched, and correct the necessary matching relationship; write the matching relationship into the object attributes to optimize the BIM model structure organization. Through this step, the integration between the initial geometric information and the object attributes can be realized, and the corresponding relationship between the various parts of the model and the object attribute parameters can be established, providing a unified framework for information query, statistics and management.

[0031] Inputting the function annotations in the first design data into the initial BIM model, associating correct function attributes for each of the entity object classes, and ensuring that the attribute names and measurement units of each of the entity object classes are consistent with the first design data; In this step, extract the functional annotation of each object from the first design data, such as "office", "conference room", etc.; prepare the corresponding functional attribute field for each object class in the BIM object classification system; input the functional annotation of the corresponding object in the design file into the functional attribute field in the object class; check whether all attribute names, attribute types, and units of the object class match the attributes defined in the design document; if there are any inconsistencies, modify them to keep the attributes consistent; repeat the above steps for all objects until the functional attribute annotation and association of all objects are completed. Through this step, the consistency of object attributes and design requirements can be achieved, providing standardized data reference for information extraction and management, effectively associating objects with their attribute definitions, and providing guarantees for subsequent management.

[0032] Importing the first functional description data into the initial BIM model as a detailed text description of each entity object class; In this step, in the BIM model management software, prepare a detailed description attribute field for each entity object; extract the detailed functional description text of each object from the first functional description data, and import the text information into the detailed description attribute field of the corresponding object. Repeat the above steps until all objects have imported relevant descriptions, check whether the detailed descriptions of all objects are correctly imported, unify the format and supplement the information to ensure the quality of the description. In this step, add rich functional background information to the object attribute information; effectively use the information collected in the design phase to enrich the BIM model; provide reference for future operators and managers to improve work efficiency; establish a high-quality digital twin model to meet the needs of the entire life cycle.

[0033] Performing layer management on the initial BIM model to achieve scenario simulation and analysis query; Check whether the initial BIM model is consistent with the design plane in the first design data Figure 1 The information is consistent and complete; If yes, the initial BIM model is used as the first BIM model; If not, the initial BIM model is adjusted according to the design plan in the first design data to obtain the first BIM model.

[0034] In this embodiment, a truly manageable digital first BIM model can be constructed, providing data content with rich object attributes, describing in detail the functional area division and equipment layout, realizing integrated query of three-dimensional data and attribute information, providing a reliable basis for the periodic management and transformation of office areas, and laying a professional and technical guarantee for fine-tuning management; constructing a high-quality first BIM model is the foundation of digital management.

[0035] In some possible implementations of the present invention, the step of configuring a plurality of first smart sensors in the first office area according to the first BIM model includes: In the first BIM model, the sensor categories, the number of sensors of each category, the parameter requirements of each sensor and the theoretical layout positions of each sensor are planned according to the functional area division and the equipment layout, and a first corresponding relationship between each layout position and the sensor category, the sensor parameter and the number of sensors is established; In this step, the division of different functional areas is obtained from the first BIM model, and the types of sensors that need to be monitored (such as temperature, humidity, smoke, etc.) are planned according to the functional requirements of different areas; the theoretical number of sensors of each type is planned according to the area and importance of the area; the parameter items and accuracy requirements of each type of sensor monitoring are determined according to the sensor model specifications; in the BIM model, the theoretical installation position of each sensor is determined according to the layout and monitoring requirements; the sensor class is established in the BIM object attributes, and the attributes such as type, parameter, and quantity are recorded; and the relationship attributes are established between each theoretical position and the corresponding sensor class. In this step, the reasonable layout of the sensor network is planned, and the corresponding relationship between BIM and sensor attributes is established to provide a standard reference for installation and monitoring, and the layout optimization is implemented to realize the closed-loop management of intelligent monitoring, ensuring the fine matching of the BIM closed loop and the monitoring implementation.

[0036] Combined with the reference office area data based on time series association of other office areas (historical environment data, historical operation data, historical traffic data, historical inspection and maintenance data, space layout / construction data, sensor layout data and sensor working data, etc.), determine the first type, first parameter, first quantity and first layout position of each first intelligent sensor (such as temperature sensor, humidity sensor, light sensor, micro-motion sensor, camera sensor, etc.) according to the sensor category, the number of sensors of each category, the parameter requirements, the theoretical layout position and the first corresponding relationship; In this step, the sensor type, parameter setting, and quantity planning of the historical similar areas are extracted from the reference office area data; sensor reference data is selected according to the similarity between the first office area and the reference area in terms of function, scale, structure, etc.; the type requirements (i.e., the first type) of the corresponding sensors of the first office area are determined in combination with the sensor category by referring to the type specifications of the same sensors in the sensor reference data; the number setting of the corresponding sensors of the first office area (i.e., the number of sensors of each category) is adjusted to obtain the first quantity by referring to the average value of the number of the same sensors in the sensor reference data; the preliminary parameters of the corresponding sensors of the first office area are determined according to the common parameter settings of the same sensors in the sensor reference data and the parameter requirements; the parameters are adjusted in combination with the actual situation of the first office area to make them more finely adapted to obtain the first parameters; according to the first corresponding relationship, the type, quantity, and parameters are refined and configured to the corresponding sensor position (i.e., the first layout position) in the first BIM model. Through this step, the design accuracy can be improved, the design cycle can be shortened; repeated omissions can be avoided, and the design quality can be improved; similar case experience can be fully utilized to lower the application threshold; the intelligent process can be promoted to the standardized finalization stage; data-derived design can be used to improve intelligent monitoring capabilities.

[0037] Installing each of the first smart sensors in the first office area according to the first type, the first parameter, the first quantity, and the first arrangement position, and recording the serial number of each of the first smart sensors and the corresponding identifier of the entity object class in the first BIM model; Acquire real-time data of each of the first smart sensors, and test whether the connection function between the first smart sensor and the house object and / or facility object is normal; If normal, the numbers and parameters of each of the first smart sensors are uploaded through the gateway and written into the corresponding sensor object attributes in the first BIM model to achieve real-time bidirectional synchronous update of the sensor objects and physical sensors in the first BIM model.

[0038] Through this embodiment, intelligent sensors are accurately deployed according to the BIM model, forming a digital twin entity-digital mapping relationship, realizing a unified intelligent management platform based on BIM, laying the foundation for information collection, and carrying out visual decision support; the Internet of Things sensors are correctly deployed according to the BIM model, realizing a closed loop of intelligent monitoring.

[0039] In some possible implementations of the present invention, the cloud service platform performs statistical analysis on the collected first area data to establish a first digital model of the first office area, including: Arranging the data of the first region and extracting time series parameters and classification features; In this step, the sensor data can be arranged in the order of monitoring time to construct a time series data framework; time series analysis can be performed on the corresponding indicators of each sensor to extract periodicity, trend and other parameters; various environmental influencing factors in the region (such as human flow, equipment usage, etc.) can be classified and coded; according to the occurrence time of the influencing factors, the classification code can be bound to the corresponding time span; the environmental parameters and classification influencing factors can be analyzed in association to identify the characteristic influencing rules; and the time series parameters and classification features can be tested to see whether they fully represent the original data characteristics. In this step, the essential characteristics of the data can be extracted, the data scale can be reduced, basic variables can be provided for subsequent modeling and management, important laws of regional operation can be mastered, and the efficiency of model establishment and decision-making can be improved. Data mining is the basis for a deep understanding of regional operation.

[0040] Establishing a time series analysis model for changes in each indicator of the first office area according to the time series parameters and the classification characteristics; In this step, the extracted time series parameters and classification features are imported into the time series analysis model template. According to the indicator type (such as temperature and humidity, etc.), the appropriate time series analysis method (ARIMA, prophet, etc.) is selected; the time series parameters are input to train the model to learn the change law of the indicator; the classification features are input to incorporate the influencing factors into the establishment of the model relationship; the model hyperparameters are tuned to optimize the fitting residuals and prediction performance; the above steps are repeated for each indicator to establish its own time series model; the evaluation indicators of each model are counted to evaluate the overall modeling quality. In this step, the dynamic change law of each indicator can be quantitatively described and predicted, the impact of complex factors can be decomposed, decision support and risk warning capabilities can be provided, data-driven management decisions can be supported, and time series modeling can extract deep relationships to help smart decision-making.

[0041] Establishing a first physical model according to the relationship between the object attributes of the first office area described in the first BIM model and the data features of the physical object; In this step, the attributes of each object (such as name, location, etc.) can be extracted from the first BIM model, and the classification characteristics of the influencing factors of each object can be extracted from data mining to determine the object type (such as people, equipment, etc.) that needs to be modeled in the physical model; in the physical model software, use the object attributes to create instances for each object that needs to be modeled; define the classification characteristics as different physical attributes and assign corresponding object instances; adjust the position of the object instance in the physical space according to the object position relationship in the BIM model; establish interaction rules between object instances, such as crowd behavior rules; set up and run the physical simulation scene, and debug the processing rules. Through this step, the object relationship in the BIM model can be reflected, the real operation status of the area can be restored, the design of supporting equipment and crowd reporting can be supported, and the next step of physical construction and operation can be guided. Physical modeling helps smart operation planning and verification.

[0042] Predicting the time-space distribution data of personnel activities and resource utilization in the first office area in different time periods according to the time series analysis model; In this step, according to the time series model of each indicator, the predicted environmental parameter values ​​at different time points (such as rush hour on weekdays) are predicted; the predicted environmental parameters are input into the physical model to simulate the environmental scenes at different time points; the physical model is run to consider the behavior rules of personnel and environmental impacts to predict the distribution of human flow; the spatial activity intensity of personnel at different times is predicted, such as the distribution of human flow density in a certain area; the resource attributes of the BIM model are combined to further predict the distribution of resource utilization at different times; the prediction results are compared with the real data, the prediction accuracy is evaluated and the model is improved. Through this step, the distribution of human flow and resource use in important time periods can be predicted, which provides support for operational scheduling and scenario simulation decisions, effectively prevents congestion and resource shortages in key areas, improves regional operational efficiency and user experience, and supports full-process data-driven management decisions. For crowd flow analysis, it can include: human body model creation, that is, using 3D modeling software to create standard human digital models of different types (such as male, female, etc.) based on human body size statistics; behavioral rule design, that is, formulating behavioral rule parameters such as human walking speed, visual range, avoidance distance, etc. to describe the movement characteristics of crowds in different scenarios; path planning algorithm, that is, using Jackson algorithm, A* algorithm, etc. to select the optimal path to plan the walking route of crowds; crowd flow import, that is, according to the actual flow of people in the office scene, input the corresponding number of digital human models into the 3D scene; dynamic simulation, that is, based on the set behavioral rules, the crowd flow model is simulated in real time to visualize the movement trajectory of people; parameter tuning, that is, adjusting the behavioral parameters according to the experimental results, such as increasing the avoidance distance to simulate the crowd behavior in crowded scenes; analysis and identification, that is, counting the number of people passing through different areas per unit time, identifying the crowd flow time and possible congestion points; feedback optimization, that is, feeding back the analysis results to the scene configuration, redesigning the diversion area, etc. for verification and optimization; repeated simulation, that is, repeated simulation to test whether the crowd flow is smooth under different design schemes.

[0043] Extracting sample data from the reference office area data, and training the sample data through a machine learning algorithm to establish a simulation model of the first office area; In this step, sample data with similar design parameters to the first office area is extracted from the reference office area; the sample data is divided into input factors (such as traffic, environmental parameters, etc.) and output results (resource utilization, etc.); a suitable machine learning algorithm is selected, such as a decision tree or a neural network; the input factors and output results are imported into the machine learning algorithm for training; part of the sample data is used for training, and the remaining data is used to verify the model effect; hyperparameters are adjusted, and training and verification are repeated to optimize model performance, and a simulation model of the first office area is established. In this step, the model's scalability and generalization capabilities can be guaranteed, providing support for future real-time simulation and scheduling decisions, realizing data-driven digital management, continuously improving simulation capabilities and management levels, and enabling machine learning modeling to help full-process smart operations.

[0044] Integrate and fuse the first physical model, the time-space distribution data and the simulation model to construct a first digital model; In this step, the first physical model can be imported into the digital twin simulation platform; the time-space distribution data can be imported into the physical model as the environment input and weight constraint; the simulation model can be imported into the platform as the rule core and decision engine; the data transmission interface between the three can be integrated, the simulation scenario rules can be set to drive the physical behavior, the integrated model can be run on the platform, and debugging and verification can be performed; the abnormal results can be analyzed to further optimize the model. In this step, the real operation scenario and behavior rules can be restored, the simulation accuracy can be improved and the application scope can be expanded, the full process digital management and decision support can be realized, resource scheduling and event response optimization can be promoted, and the continuous improvement of intelligent operation capabilities can be supported. Digital twin fusion modeling can realize resource integration management.

[0045] The first digital model is tested and the parameters are adjusted to match the real data to a preset matching value.

[0046] In this embodiment, a panoramic digital description of the operation of the first office area is achieved, statistical analysis reports of various indicators of the first office area are provided, the future dynamic changes of the first office area are predicted, and a comprehensive digital description of the status of the first office area is achieved, laying the foundation for future management level.

[0047] In some possible implementations of the present invention, the step of analyzing and identifying the environmental parameter status, personnel flow distribution, and resource usage status of each area in the first office area according to the first digital model to obtain the first area analysis result includes: Setting an analysis index system for each region in the first digital model; In this step, based on the functional characteristics and management needs of the region, preliminarily determine the types of indicators that may need to be analyzed (such as environmental indicators, safety indicators, etc.); further subdivide each indicator type and determine specific indicator items (such as temperature, light intensity, etc.); compare reference data / cases to confirm the specific measurement content and calculation method of each indicator; design the indicator system data receiving interface to connect with the sensor data contained in the model; establish corresponding attribute fields for each region in the model to correspond to each indicator; standardize the indicator statistical cycle and set the threshold parameter range; after the system is built, review whether each indicator is complete and reasonable. In this step, a standard system can be provided for subsequent regional evaluations, and analysis dimensions can be customized for each functional area to guide the intelligent management work guide, so as to achieve refined operations under data guidance. Establishing an indicator system is the basis for digital management.

[0048] Obtaining statistical distribution data of each indicator in the analysis indicator system according to the historical data algorithm built into the first digital model; In this step, the historical data algorithm can be: time series analysis algorithm (using the autocorrelation function of time series data to analyze the time series relationship of variables and identify cyclic patterns and trend change laws), cluster analysis algorithm (unsupervised clustering of historical data samples according to feature dimensions to identify the intrinsic classification pattern of data), anomaly detection algorithm (establishing a normal value range through statistical learning of historical data, and giving indicator thresholds to identify abnormal value points in new data), prediction algorithm (such as ARIMA, Holt-Winters and other algorithms to train historical data models for short-term prediction of time series), correlation analysis algorithm (analyzing the strength of correlation between indicators by calculating correlation coefficients or mutual information), distribution fitting algorithm (using probability distribution functions such as normal distribution and skewed distribution to fit the probability distribution of indicator values), feature extraction algorithm (extracting data principal components based on dimensionality reduction methods to grasp core features), etc.; the historical data algorithm obtains the statistical distribution pattern and management law of indicators by training historical collected data.

[0049] The statistical distribution data is respectively compared with a first preset standard corresponding to the environmental parameter state, a second preset standard corresponding to the personnel flow distribution, and a third preset standard corresponding to the resource usage state to determine abnormal values ​​of environmental indicators and environmental development trends, abnormal values ​​of personnel flow indicators and personnel flow development trends, and abnormal values ​​of resource usage and resource usage trends; In this step, based on the statistical distribution data, according to the first preset standard, the environmental parameter data can be judged by threshold, abnormal values ​​can be identified, cluster analysis can be performed on abnormal data, and the trend of environmental parameter changes can be identified; according to the second preset standard, the abnormal values ​​of the crowd distribution data can be judged, and the abnormal crowd data can be analyzed in time series to identify the trend of crowd changes; according to the third standard, the abnormal values ​​of resource usage data can be judged, and the abnormal resource data can be analyzed in association to identify the trend of resource usage. Through this step, the abnormal values ​​of key data can be accurately identified, the potential change patterns of various indicators can be revealed, and a basis can be provided for subsequent risk warnings and adjustment decisions, the level of digital management and response capabilities can be improved, and problem pattern learning and governance capabilities can be promoted; this step is based on normative standards to improve the ability to analyze abnormal events.

[0050] Based on the abnormal values ​​of environmental indicators and environmental development trends, the abnormal values ​​of human flow indicators and human flow development trends, and the abnormal values ​​of resource use and resource use trends, the first regional analysis results are generated to mark problem points and optimization suggestions.

[0051] In this embodiment, by comprehensively evaluating the current operating status of each area of ​​the first office area, providing a basis and reference samples for adjustments to the first office area, identifying potential problems and areas for improvement in the first office area, and playing a guiding role in improving the management level of the first office area, the foundation for intelligent management of the office area is laid.

[0052] In some possible implementations of the present invention, the steps of intelligently controlling and adjusting environmental facilities in the first office area through intelligent control equipment according to the analysis result of the first area to ensure that environmental parameters are within a preset range and intelligently managing various shared resources in the first office area to achieve efficient resource allocation and utilization include: Determine potential problem areas of environment and resource utilization efficiency based on the first area analysis results, and generate corresponding tuning suggestions for the potential problem areas; In this step, find areas where the environmental parameters and resource utilization rates in the first area analysis results are abnormally high or low for a long time (such as exceeding the preset time, and the utilization rate exceeds / is lower than the preset value); judge them as potential problem areas through numerical and time distribution characteristics; detect the corresponding influencing factors (such as changes in traffic flow); refer to other area cases and expert opinions to analyze the causes of the problems; design relevant adjustment plans based on the causes; evaluate the optimization effect of each plan in the model; generate optimization suggestions, including problem description, adjustment measures and expected effects. In this step, efficiency risks can be targeted, resource utilization and environmental quality can be improved, the next period of design and implementation improvements can be guided, the digital management level and service level can be improved, and the intelligent process can be transformed into qualitative control, leading to precise optimization with data and improving management efficiency.

[0053] Sending the tuning suggestions to the intelligent control device via the Internet of Things; The intelligent control device adjusts the parameters of the environmental facilities in the potential problem area (such as lighting brightness, air conditioning temperature setting point) according to the tuning suggestion; Acquire real-time monitoring data of the first intelligent sensor; Determining whether environmental parameters are within a preset range and / or whether various shared resources in the first office area meet preset usage rates according to the real-time monitoring data; If the environmental parameters are not within a preset range and / or the various shared resources in the first office area do not meet the preset usage rate, the management measures of the first office area are continuously optimized through the intelligent control device.

[0054] In this embodiment, precise adjustment of environmental parameters and resource allocation scheduling are achieved, management efficiency is improved and the usage environment is improved, intelligent operation capabilities guided by data are enabled, replicable samples of management experience are provided, and the foundation for improving management levels is laid; through data-driven intelligent management, management efficiency is maximized.

[0055] In some possible implementations of the present invention, the step of identifying whether there is an abnormal event in the first region analysis result includes: Extracting historical abnormal event data from the reference office area data; Establishing an abnormality recognition model based on the historical abnormal event data (the abnormality recognition model can identify abnormal events based on abnormal characteristic parameters such as temperature increase, local light brightness, and smoke density increase during a fire alarm); In this step, relevant indicator data during different types of abnormal events are extracted from the historical abnormal event data, and the data is preprocessed, such as standardization; the event type is marked as a classification feature, the indicator data is used as an input feature, and a suitable machine learning classification algorithm is selected according to the model type (such as decision tree, SVM, etc.); the data is randomly divided into training and test data sets; the model is trained on the training data set to find the optimal hyperparameter combination; the model classification effect, such as accuracy, is evaluated on the test data set; and the model is further optimized based on the evaluation results. Through this step, the type of abnormal event can be identified in real time, the occurrence of abnormal events can be warned in advance, and the efficiency of security response can be improved; new abnormalities can be identified, the model can be improved, and data-driven intelligent management can be realized; the abnormal identification model can effectively improve the level of safety management in the office area.

[0056] Preprocessing the first region analysis result to extract a first characteristic parameter; Using a machine learning classifier stored in the abnormality recognition model, comparing the first feature parameter with the abnormal feature parameter in the abnormality recognition model; In this step, the established abnormality recognition model is activated, and the extracted first characteristic parameter is classified and recognized using the classifier; the first characteristic parameter is input into the classifier for prediction and classification; it is determined whether the prediction result is an abnormal event type; the reliability of the recognition result is determined according to the confidence of the classifier; if there is an abnormality, the abnormal details are extracted to generate a report. Through this step, real-time abnormality monitoring and identification can be achieved, and possible safety incidents can be warned in time, the response efficiency of safe production can be improved, losses can be effectively prevented and reduced, the level of digital security management can be improved, and technical support can be provided for comprehensive operation monitoring.

[0057] The machine learning classifier gives a probability score for each abnormal event and issues a warning for the type and level of the abnormal event with the highest probability value.

[0058] After inputting the feature parameters monitored in real time into the classifier for prediction in the previous step, the classifier will give the probability value of each abnormal event type; find the predicted probability value of each event type and find the largest event type; judge the prediction credibility based on the magnitude of the maximum probability value; classify the credibility through threshold setting and identify the level; give semantic warning information according to the level; record the recognition results for easy reference and analysis later. In this step, the recognition effect can be quantified to reduce the false alarm rate; generate different levels of warning response calls; effectively identify new abnormalities and improve the model; unify data output for easy integration and application; and improve the level of security operation automation.

[0059] In this embodiment, hidden abnormal changes in the area can be discovered in time, and safety hazards and problem points can be warned in advance, which effectively improves the management response efficiency, prevents and mitigates the consequences of abnormal events, and improves the regional operation monitoring and safety assurance capabilities. Regional safety hazards can be identified through digital models to achieve intelligent safety management.

[0060] In some possible implementations of the present invention, the step of generating an exception handling measure according to the first real-time regional data and the first digital model includes: Determining the real-time status of the abnormal event (such as the fire development status, the water depth status, etc.) from the first real-time regional data according to the abnormality recognition model; Determine the real-time status of the first office area of ​​the first office area (such as the degree of damage to the office area, the status of personnel evacuation, etc.) according to the first real-time regional data; Retrieving a common processing flow for the abnormal event in a preset knowledge base; According to the real-time status of the abnormal event and the real-time status of the first office area, the specific operation steps in the general processing flow are revised to obtain the abnormal processing measures.

[0061] In this embodiment, it is possible to generate response plans scientifically based on real data; efficiently use historical experience to design optimal solutions, provide strong reference support for management decisions, minimize the impact of human subjective factors on the solutions, achieve autonomous handling capabilities in digital work scenarios, and generate professional exception handling measures driven by data.

[0062] In some possible implementations of the present invention, the step of revising the specific operation steps in the general processing flow according to the real-time status of the abnormal event and the real-time status of the first office area to obtain the abnormal processing measures includes: Determine the current status of the abnormal event (such as data on fire intensity, water accumulation, etc.) and the development trend of the abnormal event (such as using video analysis and other technologies to evaluate the development trend of the abnormal event) based on the real-time status of the abnormal event; Determine the current abnormal state of the first office area (such as the scope affected by the fire or water accumulation) and the current personnel evacuation state (such as the number of people evacuated, the location of the remaining personnel, etc.) according to the real-time state of the first office area; According to the current state of the abnormal event, the development trend of the abnormal event, the current abnormal state and the current personnel evacuation state, evaluate the potential impact of the abnormal event on the first office area, and identify the abnormal areas and abnormal problems that need to be handled with priority; According to the potential impact, abnormal area and abnormal problem, adjust the evacuation route to avoid high-risk areas, optimize resource allocation (such as dispatching additional firefighting forces to areas with larger fires), and update the emergency response level (such as raising the response level according to the expansion of the fire); Formulate detailed execution steps (such as specific fire extinguishing or drainage operations), clarify the division of responsibilities of each department and personnel, set key nodes and completion deadlines, and obtain the abnormal handling measures; Adjust processing measures in real time according to the latest status, evaluate the effectiveness of the measures, and make corresponding corrections.

[0063] This embodiment can improve the pertinence and effectiveness of emergency response, realize dynamic optimization of treatment measures, enhance flexibility in dealing with emergencies, optimize resource allocation, improve emergency handling efficiency, reduce the risk of casualties and property losses, and provide data support for subsequent optimization of emergency plans. Through the method of this embodiment, the emergency handling process can be flexibly adjusted according to actual conditions, avoiding the lag that may be caused by the implementation of fixed plans, so as to better deal with various sudden abnormal situations.

[0064] Some possible implementations of the present invention include: real-time monitoring of the development status of the event, such as understanding the speed of fire spread / depth of accumulated water, etc.; real-time monitoring of factors such as the scope of the office area affected / degree of evacuation of personnel; comparing real-time data with the general process to evaluate the applicability of measures; adjusting the detailed operations of the process according to the differences between the two: giving priority to evacuating people in a wider area, and selecting drainage / fire extinguishing equipment that is easy to operate and more effective; providing feedback on the modified process, seeking expert review to ensure feasibility; and informing on-site executors to implement the new process. This embodiment fully considers the real-time situation to adjust the processing plan, solves the shortcomings of the general process in actual operation, improves processing efficiency and reduces secondary losses, realizes dynamic optimization of event response measures under digitalization, makes up for the lack of subjective factors in manual judgment, and revises measures in real time with data support to improve response capabilities.

[0065] In some possible implementations of the present invention, the method further includes: using a model to simulate the evacuation route and time of personnel when an abnormal situation occurs, and finding possible bottleneck areas, specifically: In the first digital model, set up safe exits in different areas and compile evacuation routes; According to the crowd density and equipment limitations, set the optimal and suboptimal evacuation routes for each person; According to the attributes of personnel such as gender and age, set evacuation parameters such as walking speed; Simulate each person's evacuation movements and positions according to the path scheduling at certain intervals; Count the remaining density of people in different areas at different time points and identify possible detention points; Find out the reasons for the delay, such as people competing for the right of way or passage obstruction; Propose technical countermeasures such as adding emergency exits or optimizing sign guidance.

[0066] In this embodiment, potential safety hazards can be checked in advance to improve evacuation efficiency; the scientificity and operability of emergency plans can be tested; the protection level of safety facilities can be upgraded in a targeted manner; and the scientificity and clarity of management decisions can be improved.

[0067] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0068] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0069] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0070] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0072] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0073] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0074] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0075] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A smart office area management system based on the Internet of Things, It is characterized in that include: IoT servers and cloud service platforms; among them, The IoT server is configured as follows: Acquire first three-dimensional data, first design data, and first functional description data of a first office area; Establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data; According to the first BIM model, a plurality of first intelligent sensors are configured in the first office area; Collecting first area data in the first office area in real time through the first intelligent sensor; Transmitting the first regional data to the cloud service platform; The cloud service platform is configured as follows: Performing statistical analysis on the collected data of the first area to establish a first digital model of the first office area; Analyze and identify the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain a first area analysis result; Based on the analysis results of the first area, intelligently control and adjust the environmental facilities in the first office area through intelligent control equipment to ensure that the environmental parameters are within a preset range and intelligently manage various shared resources in the first office area to achieve efficient resource allocation and utilization; Identify whether there is an abnormal event in the first area analysis result; If an abnormal event occurs, an alarm message is pushed, and first real-time regional data collected by the first smart sensor is obtained; An exception handling measure is generated according to the first real-time regional data and the first digital model.

2. A smart office area management method based on the Internet of Things, It is characterized in that include: Acquire first three-dimensional data, first design data, and first functional description data of a first office area; Establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data; According to the first BIM model, a plurality of first intelligent sensors are configured in the first office area; Collecting first area data in the first office area in real time through the first intelligent sensor; Transmitting the first regional data to the cloud service platform; The cloud service platform performs statistical analysis on the collected data of the first area to establish a first digital model of the first office area; Analyze and identify the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain a first area analysis result; According to the analysis result of the first area, the environmental facilities in the first office area are intelligently controlled and adjusted through the intelligent control device to ensure that the environmental parameters are within the preset range and the various shared resources in the first office area are intelligently managed to achieve efficient allocation and utilization of resources; Identify whether there is an abnormal event in the first area analysis result; If an abnormal event occurs, an alarm message is pushed, and first real-time regional data collected by the first smart sensor is obtained; An exception handling measure is generated according to the first real-time regional data and the first digital model.

3. According to the method for managing a smart office area based on the Internet of Things according to claim 2, It is characterized in that The step of establishing a first BIM model of the first office area according to the first three-dimensional data, the first design data and the first functional description data comprises: constructing an initial BIM model according to the first three-dimensional data; Establishing an entity object class for each house object and / or facility object according to the name and size in the first design data; Matching and associating the three-dimensional geometric body in the initial BIM model with the entity object class; Inputting the function annotations in the first design data into the initial BIM model, associating correct function attributes for each of the entity object classes, and ensuring that the attribute names and measurement units of each of the entity object classes are consistent with the first design data; Importing the first functional description data into the initial BIM model as a detailed text description of each entity object class; Performing layer management on the initial BIM model to achieve scenario simulation and analysis query; Check whether the initial BIM model is consistent with the design plan in the first design data and whether the information is complete; If yes, the initial BIM model is used as the first BIM model; If not, the initial BIM model is adjusted according to the design plan in the first design data to obtain the first BIM model.

4. According to the method for managing a smart office area based on the Internet of Things according to claim 3, It is characterized in that The step of configuring a plurality of first intelligent sensors in the first office area according to the first BIM model includes: In the first BIM model, the sensor categories, the number of sensors of each category, the parameter requirements of each sensor and the theoretical layout positions of each sensor are planned according to the functional area division and the equipment layout, and a first corresponding relationship between each layout position and the sensor category, the sensor parameter and the number of sensors is established; In combination with reference office area data based on time series association of other office areas, the first type, the first parameter, the first quantity and the first arrangement position of each first smart sensor are determined according to the sensor category, the number of sensors of each category, the parameter requirements, the theoretical arrangement position and the first corresponding relationship; Installing each of the first smart sensors in the first office area according to the first type, the first parameter, the first quantity, and the first arrangement position, and recording the serial number of each of the first smart sensors and the corresponding identifier of the entity object class in the first BIM model; Acquire real-time data of each of the first smart sensors, and test whether the connection function between the first smart sensor and the house object and / or facility object is normal; If normal, the numbers and parameters of each of the first smart sensors are uploaded through the gateway and written into the corresponding sensor object attributes in the first BIM model to achieve real-time bidirectional synchronous update of the sensor objects and physical sensors in the first BIM model.

5. According to the method for managing a smart office area based on the Internet of Things according to claim 4, It is characterized in that The cloud service platform performs statistical analysis on the collected data of the first area to establish a first digital model of the first office area, including: Arranging the data of the first region and extracting time series parameters and classification features; Establishing a time series analysis model for changes in each indicator of the first office area according to the time series parameters and the classification characteristics; Establishing a first physical model according to the relationship between the object attributes of the first office area described in the first BIM model and the data features of the physical object; Predicting the time-space distribution data of personnel activities and resource utilization in the first office area in different time periods according to the time series analysis model; Extracting sample data from the reference office area data, and training the sample data through a machine learning algorithm to establish a simulation model of the first office area; Integrate and fuse the first physical model, the time-space distribution data and the simulation model to construct a first digital model; The first digital model is tested and the parameters are adjusted to match the real data to a preset matching value.

6. According to the method for managing a smart office area based on the Internet of Things according to claim 5, It is characterized in that The step of analyzing and identifying the environmental parameter status, personnel flow distribution and resource usage status of each area in the first office area according to the first digital model to obtain the first area analysis result includes: Setting an analysis index system for each region in the first digital model; Obtaining statistical distribution data of each indicator in the analysis indicator system according to the historical data algorithm built into the first digital model; The statistical distribution data is respectively compared with a first preset standard corresponding to the environmental parameter state, a second preset standard corresponding to the personnel flow distribution, and a third preset standard corresponding to the resource usage state to determine abnormal values ​​of environmental indicators and environmental development trends, abnormal values ​​of personnel flow indicators and personnel flow development trends, and abnormal values ​​of resource usage and resource usage trends; Based on the abnormal values ​​of environmental indicators and environmental development trends, the abnormal values ​​of human flow indicators and human flow development trends, and the abnormal values ​​of resource use and resource use trends, the first regional analysis results are generated to mark problem points and optimization suggestions.

7. According to the method for managing a smart office area based on the Internet of Things according to claim 6, It is characterized in that The step of intelligently controlling and adjusting the environmental facilities in the first office area through the intelligent control device according to the analysis result of the first area to ensure that the environmental parameters are within a preset range and intelligently managing various shared resources in the first office area to achieve efficient resource allocation and utilization includes: Determine potential problem areas of environment and resource utilization efficiency based on the first area analysis results, and generate corresponding tuning suggestions for the potential problem areas; Sending the tuning suggestions to the intelligent control device via the Internet of Things; The intelligent control device adjusts the parameters of the environmental facilities in the potential problem area according to the tuning suggestion; Acquire real-time monitoring data of the first intelligent sensor; Determining whether environmental parameters are within a preset range and / or whether various shared resources in the first office area meet preset usage rates according to the real-time monitoring data; If the environmental parameters are not within a preset range and / or the various shared resources in the first office area do not meet the preset usage rate, the management measures of the first office area are continuously optimized through the intelligent control device.

8. According to the method for managing a smart office area based on the Internet of Things according to claim 7, It is characterized in that The step of identifying whether there is an abnormal event in the first region analysis result includes: Extracting historical abnormal event data from the reference office area data; Establishing an anomaly recognition model based on the historical abnormal event data; Preprocessing the first region analysis result to extract a first characteristic parameter; Using a machine learning classifier stored in the abnormality recognition model, comparing the first feature parameter with the abnormal feature parameter in the abnormality recognition model; The machine learning classifier gives a probability score for each abnormal event and issues a warning for the type and level of the abnormal event with the highest probability value.

9. According to the method for managing a smart office area based on the Internet of Things according to claim 8, It is characterized in that The step of generating an exception handling measure according to the first real-time regional data and the first digital model comprises: Determining a real-time status of an abnormal event from the first real-time regional data according to the abnormality recognition model; determining a first office area real-time status of the first office area according to the first real-time area data; Retrieving a common processing flow for the abnormal event in a preset knowledge base; According to the real-time status of the abnormal event and the real-time status of the first office area, the specific operation steps in the general processing flow are revised to obtain the abnormal processing measures.

10. The method for managing a smart office area based on the Internet of Things according to claim 9, It is characterized in that The step of revising the specific operation steps in the general processing flow according to the real-time status of the abnormal event and the real-time status of the first office area to obtain the abnormal processing measures includes: Determine the current state of the abnormal event and the development trend of the abnormal event according to the real-time state of the abnormal event; Determine the current abnormal state and current personnel evacuation state of the first office area according to the real-time state of the first office area; According to the current state of the abnormal event, the development trend of the abnormal event, the current abnormal state and the current personnel evacuation state, evaluate the potential impact of the abnormal event on the first office area, and identify the abnormal areas and abnormal problems that need to be handled with priority; According to the potential impact, the abnormal area and the abnormal problem, adjust the evacuation route, avoid high-risk areas, optimize resource allocation, and update the emergency response level; Formulate detailed implementation steps, clarify the division of responsibilities of each department and personnel, set key nodes and completion deadlines, and obtain the aforementioned exception handling measures; Adjust processing measures in real time according to the latest status, evaluate the effectiveness of the measures, and make corresponding corrections.

Citation Information

Patent Citations

  • Park asset management system based on artificial intelligence

    CN117495297A

  • Smart city environment monitoring system and method based on 5G communication

    CN118283093A

Cited By

  • Centralized management method and system for water, electricity and gas security and protection in Internet of Things vision field

    CN119130158A

  • Digital office data synchronization and sharing method and system based on cloud computing

    CN119248884A

  • Generation method and device of digital park, storage medium and electronic equipment

    CN119740290A

  • Project intelligent management method and system based on enterprise digital information

    CN120198073A

  • Intelligent parameter optimized central air conditioner protocol conversion gateway and configuration method thereof

    CN120819885A