Intelligent management method and system for old community reconstruction based on digital twinborn technology

Abstract

The invention relates to the field of community management, in particular to an old community reconstruction intelligent management method and system based on a digital twin technology. The method comprises the following steps: collecting building information data, geographic space data and demographic data of an old community, constructing a building monomer model, dividing building neighborhood units and neighborhood unit boundaries, and generating a service demand matrix; analyzing the service demand matrix, constructing a supply and demand adaptation matrix, establishing a multi-target configuration function, and generating a resource configuration scheme; analyzing the resource allocation scheme to generate a spatial allocation instruction set, constructing a resident behavior model, analyzing the spatial allocation instruction set, the resident behavior model and the building monomer model, generating a behavior path track and resource use time sequence data, and constructing a behavior disturbance label and a response evaluation matrix; and modifying the resource configuration scheme based on the behavior disturbance label and the response evaluation matrix, and generating an updated resource configuration scheme. The resource utilization rate can be improved.

Description

Technical Field

[0001] This invention relates to the field of community management, specifically to a smart management method and system for the renovation of old communities based on digital twin technology. Background Technology

[0002] Due to their age, older residential communities often suffer from a lack of systematic infrastructure planning, low space utilization efficiency, and inefficient allocation of service resources, making it difficult to meet the increasingly diverse needs of residents for daily life services. With the deepening of the concept of digital urban governance, the systematic and intelligent renovation and management of older residential communities based on digital twin technology has become one of the key issues in the construction of smart cities.

[0003] Chinese Patent Publication No. CN117670629A discloses a smart management method and platform for the renovation of old residential communities. The method includes: determining safety-monitored communities based on the safety risks of renovations in different old residential communities; identifying safety violations in different renovation projects within these communities using monitoring data from surveillance images; determining the monitoring safety risks and potential renovation projects for different renovation projects by combining the monitoring data from these communities with safety violations; determining the potential safety risks of different old residential communities based on the monitoring safety risks and potential renovation projects; determining risk-monitored communities based on the potential safety risks; and monitoring and managing safety violations in both risk-monitored and safety-monitored communities using monitoring data from surveillance images, thereby improving construction safety during the renovation process of old residential communities.

[0004] In existing technologies, the renovation of old residential communities lacks dynamic perception and real-time response mechanisms, making it difficult to accurately match renovation plans with residents' actual needs, resulting in a high rate of resource waste, inability to achieve efficient supply and demand matching, and difficulty in dynamic optimization and adjustment. These are problems that we need to solve. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in the background technology by proposing a smart management method and system for the renovation of old residential communities based on digital twin technology.

[0006] The technical solution of this invention: a smart management method for the renovation of old residential communities based on digital twin technology, comprising the following steps: S1. Collect building information data, geospatial data, and population statistics data of old residential communities, and construct individual building models. Based on the individual building models, analyze the building information data, geospatial data, and population statistics data, divide the building neighborhood units and neighborhood unit boundaries, and generate a service demand matrix. S2. Analyze the service demand matrix, construct the supply and demand matching matrix, and establish a multi-objective configuration function to generate a resource configuration scheme; S3. Analyze the resource allocation scheme to generate a spatial allocation instruction set and build a resident behavior model. Analyze the spatial allocation instruction set, resident behavior model and building unit model to generate behavior path trajectory and resource usage time series data, and build behavior disturbance labels and response evaluation matrix. S4. Modify the resource allocation scheme based on behavioral disturbance labels and response evaluation matrix to generate an updated resource allocation scheme, and then manage the renovation of old residential areas through the updated resource allocation scheme.

[0007] Preferably, the process of collecting building information data, geospatial data, and population statistics of old residential communities, and constructing individual building models includes: Building information data includes structural type, number of floors, functional parameters, and occupancy parameters of buildings in old residential communities; geospatial data includes geospatial coordinates, relative spacing, height information, passageway connections, building number, and house number of buildings in old residential communities; demographic data includes resident population, age structure, family structure, occupation type, and service preference information. Using digital twin technology, a three-dimensional twin model of an old residential community is constructed based on its geographic spatial coordinates, height information, and relative spacing. The number of floors, structural type, and functional parameters of the old residential community buildings are then embedded into the corresponding parts of the three-dimensional twin model to construct a building model of the individual buildings in the old residential community. Based on the geographic spatial location and passageway connection relationship of adjacent old residential community buildings, the spatial adjacency relationship between the corresponding building models is constructed.

[0008] Preferably, the process of analyzing building information data, geospatial data, and demographic data based on individual building models, dividing building neighborhood units and neighborhood unit boundaries, and generating a service demand matrix includes: Based on age structure, family structure, occupation type, and service preference information in demographic data, data of similar attributes within individual building models are merged and statistically analyzed. Demographic data is then categorized into population hierarchies to obtain population classification results. These population classification results are then correlated with individual building models to construct hierarchical labels for population attributes. Based on population attribute hierarchical labels, spatial adjacency relationships, and channel connection relationships, a density-based clustering algorithm is used to aggregate and group individual building models, identify neighborhood unit clusters, construct building neighborhood units and neighborhood unit boundaries, and number the building neighborhood units to obtain unit numbers and corresponding range coordinates. Based on the unit number, population attribute hierarchical labels, range coordinates, service preference information, capacity parameters, number of permanent residents, and corresponding building information data of each building neighborhood unit, a neighborhood unit index table is constructed. Based on the neighborhood unit index table, the service category and corresponding service preference intensity value of each building neighborhood unit are extracted by analyzing the correspondence between population attribute hierarchical labels and service preference information. The service capacity value and expected service radius value of each building neighborhood unit are obtained. The service category, service capacity value, service preference intensity value and expected service radius value of each building neighborhood unit are normalized to construct a service supply and demand field set. The data is then summarized by unit number to generate a service demand matrix.

[0009] Preferably, the process of analyzing the service demand matrix, constructing a supply-demand matching matrix, and establishing a multi-objective configuration function to generate a resource allocation scheme includes: Obtain the service supply and demand field set corresponding to each building neighborhood unit in the service demand matrix, and combine it with the unit number, population attribute hierarchical label, accommodating capacity parameter and permanent population recorded in the neighborhood unit index table to construct a population service demand profile for the building neighborhood unit; according to the service category of each building neighborhood unit, obtain the corresponding service resource list in the old community building and establish a service resource table. The population service demand profile is correlated with the resource data in the service resource table. According to the set matching constraints, a supply and demand adaptation model is constructed and a supply and demand adaptation matrix is ​​generated. Based on the supply and demand adaptation matrix, the minimum resource waste rate, the maximum population service satisfaction, and the resource distribution balance are set as objective functions to construct a multi-objective configuration function. The mapping relationship between each building neighborhood unit and service resources is solved based on the multi-objective optimization algorithm to obtain the optimal resource configuration combination. Based on the optimal resource allocation combination, a resource allocation scheme for the renovation of old residential communities is generated. The resource allocation scheme includes the location of each service resource, the service radius coverage map of the neighborhood unit, the service satisfaction score of the population group, and the service suitability score.

[0010] Preferably, the process of analyzing resource allocation schemes to generate spatial allocation instruction sets, constructing resident behavior models, and analyzing spatial allocation instruction sets, resident behavior models, and individual building models to generate behavioral path trajectories and resource usage time series data is as follows: The service resource deployment location, service radius coverage map, population group service satisfaction score and service adaptability score recorded in the resource allocation scheme are used as spatial configuration parameters and injected into the building unit model composed of the neighborhood unit index table and the building unit twin model to generate a spatial configuration instruction set. A resident behavior model is constructed based on demographic data. The spatial configuration instruction set and the resident behavior model are synchronously input into the building unit model. Based on the building information data, geospatial data and service resource list in the building unit model, a spatial resource set is constructed. Based on the basic service function areas defined by the building neighborhood units and neighborhood unit boundaries in the building unit model, spatial resource units are constructed. The central location of the spatial resource unit is extracted as a resource node using a spatial indexing method. The residents within the building neighborhood unit are simulated using a multi-agent simulation method to generate the simulated crowd's behavior path trajectory and resource usage time series data. Density clustering of the behavior path trajectory is then performed to obtain the crowd's concentrated path.

[0011] Preferably, the process of constructing behavioral perturbation labels and response evaluation matrices is as follows: Based on the simulated behavioral path trajectories and resource usage time series data, a behavioral response logic chain is constructed. Based on the behavioral response logic chain, behavioral inflection points and abnormal resource occupancy locations in the concentrated paths of the crowd are analyzed. The spatial locations of abnormal fluctuations in resource usage are identified, and the corresponding spatial resource units are determined as sensitive nodes and marked as behavioral disturbance labels. Based on the behavioral disturbance labels, each resource node in the building unit model is analyzed, behavioral evaluation parameters are calculated, and a response evaluation matrix is ​​generated.

[0012] Preferably, the process of modifying the resource allocation scheme based on behavioral disturbance labels and response evaluation matrices to generate an updated resource allocation scheme, and then managing the renovation of old residential areas through the updated resource allocation scheme, includes: The system acquires spatial resource units marked by behavioral disturbance tags and locates the corresponding resource nodes in the building unit model. Based on the behavioral evaluation parameters recorded in the response evaluation matrix, it analyzes the operating status of the resource nodes, sets behavioral evaluation thresholds, analyzes the behavioral evaluation parameters through the behavioral evaluation thresholds, and generates anomaly judgment results. Based on the anomaly judgment results, it adjusts the resource configuration scheme and generates an updated resource configuration scheme. The updated resource configuration scheme is injected into the building unit model to synchronously update the spatial location and operating status of each service resource.

[0013] This invention also discloses a smart management system for the renovation of old residential communities based on digital twin technology, including a management center, which is communicatively connected to a data acquisition module, a resource configuration module, a resource analysis module, and a renovation management module. The data acquisition module is used to collect building information data, geospatial data, and population statistics data of old residential communities, and to construct individual building models. Based on the individual building models, the module analyzes the building information data, geospatial data, and population statistics data, divides the building neighborhood units and neighborhood unit boundaries, and generates a service demand matrix. The resource configuration module is used to analyze the service demand matrix, construct the supply and demand matching matrix, establish a multi-objective configuration function, and generate a resource configuration scheme. The resource analysis module is used to analyze resource allocation schemes, generate spatial allocation instruction sets, and build resident behavior models. It analyzes spatial allocation instruction sets, resident behavior models, and building unit models to generate behavioral path trajectories and resource usage time series data, and builds behavioral disturbance labels and response evaluation matrices. The renovation management module is used to modify the resource allocation scheme based on behavioral disturbance labels and response evaluation matrix, generate an updated resource allocation scheme, and manage the renovation of old residential areas through the updated resource allocation scheme.

[0014] Compared with the prior art, the above-mentioned technical solution of the present invention has the following beneficial technical effects: by constructing a building unit model and dividing the building neighborhood units, combining population attribute hierarchical labels and service preference information, establishing a service demand matrix and a supply and demand matching matrix, and generating a resource allocation scheme based on a multi-objective configuration function, it is possible to achieve accurate identification and optimal allocation of service resources in old residential areas and improve resource utilization; by constructing a resident behavior model and generating behavior disturbance labels and response evaluation matrices, it is possible to achieve dynamic identification of abnormal resource usage states and retrospective evaluation of spatial resource units, which can support dynamic optimization and real-time adjustment of resource allocation schemes. Attached Figure Description

[0015] Figure 1 This is a flowchart of one embodiment of the present invention. Detailed Implementation

[0016] Example 1, as Figure 1 As shown, the intelligent management method for the renovation of old residential communities based on digital twin technology proposed in this invention includes the following steps: S1. Collect building information data, geospatial data, and population statistics data of old residential communities, and construct individual building models. Based on the individual building models, analyze the building information data, geospatial data, and population statistics data, divide the building neighborhood units and neighborhood unit boundaries, and generate a service demand matrix. S2. Analyze the service demand matrix, construct the supply and demand matching matrix, and establish a multi-objective configuration function to generate a resource configuration scheme; S3. Analyze the resource allocation scheme to generate a spatial allocation instruction set and build a resident behavior model. Analyze the spatial allocation instruction set, resident behavior model and building unit model to generate behavior path trajectory and resource usage time series data, and build behavior disturbance labels and response evaluation matrix. S4. Modify the resource allocation scheme based on behavioral disturbance labels and response evaluation matrix to generate an updated resource allocation scheme, and then manage the renovation of old residential areas through the updated resource allocation scheme.

[0017] It needs further explanation that, in the specific implementation process, the following steps are taken: collecting building information data, geospatial data, and demographic data of old residential communities; constructing individual building models; analyzing the building information data, geospatial data, and demographic data based on the individual building models; dividing building neighborhood units and neighborhood unit boundaries; and generating a service demand matrix. The system collects building information data, geospatial data, and demographic data for old residential communities. The building information data includes the structural type, number of floors, functional parameters, and occupancy parameters of the buildings in the old residential communities. The geospatial data includes the geospatial coordinates, relative spacing, height information, passageway connections, building numbers, and house numbers of the buildings in the old residential communities. The demographic data includes the number of permanent residents, age structure, family structure, occupation type, and service preference information. The service preference information is obtained through questionnaires or statistical analysis of historical usage records. Using digital twin technology, a three-dimensional twin model of an old residential community is constructed based on its geographic spatial coordinates, height information, and relative spacing. The number of floors, structural type, and functional parameters of the old residential community buildings are then embedded into the corresponding parts of the three-dimensional twin model to construct a building model of the individual buildings in the old residential community. Based on the geographic spatial location and passageway connection relationship of adjacent old residential community buildings, the spatial adjacency relationship between the corresponding building models is constructed.

[0018] Based on age structure, family structure, occupation type, and service preference information in demographic data, data of similar attributes within the building unit model are merged and statistically analyzed. The demographic data is then classified into population hierarchical categories to obtain population classification results. These population hierarchical categories include, but are not limited to, the elderly, young and middle-aged people, families with children, and single people. The population classification results are then associated with the building unit model to construct hierarchical labels for population attributes. Based on population attribute hierarchical labels, spatial adjacency relationships, and channel connection relationships, the density-based DBSCAN clustering algorithm is used to aggregate and group building unit models, identify neighborhood unit clusters, construct building neighborhood units and neighborhood unit boundaries, and number the building neighborhood units to obtain unit numbers and corresponding range coordinates. Based on the unit number, population attribute hierarchical labels, range coordinates, service preference information, capacity parameters, number of permanent residents, and corresponding building information data of each building neighborhood unit, a neighborhood unit index table is constructed. Based on the unit number, population attribute hierarchical labels, corresponding building information data, and service preference information of each building neighborhood unit recorded in the neighborhood unit index table, the service category and corresponding service preference intensity value of each building neighborhood unit are extracted by analyzing the correspondence between population attribute hierarchical labels and service preference information. The service preference intensity value is obtained through questionnaire surveys or historical usage records. The service capacity value and expected service radius value of each building neighborhood unit are obtained. The service capacity value is the total number of service visits that existing service resources within the neighborhood unit can provide. The expected service radius value is the target spatial coverage radius for residents of the building neighborhood unit to access service resources, which is set according to the service radius recommended by the planning of old residential areas. The service category, service capacity value, service preference intensity value, and expected service radius value of each building neighborhood unit are normalized to construct a service supply and demand field set. The data is then summarized according to the unit number to generate a service demand matrix. The service demand matrix consists of a two-dimensional structure of unit number and service supply and demand field set.

[0019] It should be further explained that, in the specific implementation process, the process of analyzing the service demand matrix, constructing the supply and demand matching matrix, establishing a multi-objective configuration function, and generating a resource allocation scheme is as follows: Obtain the set of service supply and demand fields corresponding to each building neighborhood unit in the service demand matrix, and combine them with the unit number, population attribute hierarchical label, accommodating capacity parameter and permanent population recorded in the neighborhood unit index table to construct a population service demand profile for the building neighborhood unit. Based on the service categories of each building neighborhood unit, obtain the corresponding service resource list within the old residential buildings. The service resource list includes information on spatial service resources such as community health, elderly care facilities, children's activity spaces, cultural and educational services, and commercial outlets. The information includes the available capacity, service coverage radius, resource utilization rate, service operation and maintenance status, and resource type code of the service resources. Establish a service resource table. The population service demand profile is associated with various resource data in the service resource table. According to the set matching constraints, including spatial distance constraints, service category matching constraints, population attribute preference adaptation constraints, and service capacity reachability constraints, a supply and demand adaptation model is constructed. The supply and demand adaptation model is based on the bidirectional mapping relationship between building neighborhood units and service resources, and a supply and demand adaptation matrix is ​​generated. The supply and demand adaptation matrix is ​​composed of a two-dimensional structure of building neighborhood units and the supply and demand adaptation model. Specifically, the spatial distance constraint is calculated based on the Euclidean distance between the coordinates of the neighborhood unit range and the geographic spatial coordinates of the service resource; the service category matching constraint is based on the service category field in the service supply and demand field set; the population attribute preference adaptation constraint is based on the association between the population attribute hierarchical labels of the neighborhood unit and the service preference information; and the service capacity reachability constraint is based on the correspondence analysis between the service capacity field in the service resource table and the accommodating number of people parameter of the neighborhood unit.

[0020] Based on the supply and demand matching matrix, the minimum resource waste rate, the maximum population service satisfaction, and the resource distribution balance are set as objective functions to construct a multi-objective configuration function. The mapping relationship between each building neighborhood unit and service resources is solved based on the NSGA-II multi-objective optimization algorithm to obtain the optimal resource configuration combination. Based on the optimal resource allocation combination, a resource allocation scheme for the renovation of old residential communities is generated. The resource allocation scheme includes the deployment location of each service resource, the service radius coverage map of the neighborhood unit, the service satisfaction score of the population group, and the service adaptability score. The service satisfaction score and the service adaptability score are statistically generated based on the supply and demand adaptation model and the output results of the multi-objective configuration function.

[0021] It should be further explained that, in the specific implementation process, the process of analyzing the resource allocation scheme to generate a spatial allocation instruction set, constructing a resident behavior model, analyzing the spatial allocation instruction set, resident behavior model, and building unit model to generate behavioral path trajectories and resource usage time series data, and constructing behavioral disturbance labels and response evaluation matrices is as follows: The service resource deployment location, service radius coverage map, population group service satisfaction score and service adaptability score recorded in the resource allocation scheme are used as spatial configuration parameters and injected into the building unit model composed of the neighborhood unit index table and the building unit twin model to generate a spatial configuration instruction set. The spatial configuration instruction set is used to indicate the deployment location and operation parameters of each service resource in the building unit model. A resident behavior model is constructed, which is based on the family structure, occupation type, age structure and service preference information of the demographic data, and combined with the daily travel time distribution data and historical trajectory database to generate resident behavior sequence templates. The resident behavior model models the activity trajectory of residents between different service resources according to the time dimension and the spatial dimension. The spatial configuration instruction set and resident behavior model are synchronously input into the building unit model. Based on the building information data, geospatial data and service resource list in the building unit model, a spatial resource set is constructed. Based on the basic service function areas defined by the building neighborhood units and neighborhood unit boundaries in the building unit model, spatial resource units are constructed. The central location of the spatial resource unit is extracted as a resource node using a spatial indexing method. Based on a multi-agent simulation method, the behavior processes of residents in the building neighborhood unit, such as travel paths, stay time and resource usage intensity, are simulated to generate simulated crowd behavior path trajectories and resource usage time series data. Density clustering of the behavior path trajectories is then used to obtain the concentrated paths of the crowd. Specifically, the resource usage intensity refers to the sum of the average access frequency and the duration of occupation of resource nodes per unit time.

[0022] Based on the simulated behavioral path trajectories and resource usage time-series data, a behavioral response logic chain is constructed. The behavioral response logic chain is a mapping relationship chain between population behavior and dynamic resource status established based on the simulation data. The transmission path of the behavioral response logic chain is, in sequence, population behavior change, service space response, and usage load evolution. The population behavior change corresponds to the travel and stay changes output by the resident behavior model. The service space response corresponds to the resource node occupancy change response. The usage load evolution corresponds to the time-series characteristics of the resource node occupancy rate and traffic change curves. Based on the behavioral response logic chain analysis, behavioral inflection points and abnormal resource usage locations in the concentrated path of the crowd are identified, the spatial locations of abnormal fluctuations in resource usage are identified, the corresponding spatial resource units are determined as sensitive nodes, and marked as behavioral disturbance labels to indicate the spatial locations of abnormal fluctuations in resource usage. Based on behavioral disturbance labels, the resource nodes in the building unit model are analyzed, and behavioral evaluation parameters are calculated. These behavioral evaluation parameters include behavioral load volatility, crowd gathering index, resource occupancy rate change value and offset response time. A response evaluation matrix is ​​generated as the feedback basis for subsequent dynamic optimization and adjustment. It should be noted that the behavioral load volatility refers to the magnitude and frequency of changes in resource node access volume or occupancy rate within a set time window, used to reflect the stability of service usage; the crowd aggregation index is based on resident behavior models and behavioral path trajectories, recording the crowd aggregation density per unit area, used to identify high-density areas or potential congestion points; the resource occupancy rate change value is the relative increase or decrease in the occupancy ratio of resource nodes within the simulation period, reflecting the trend of service supply and demand balance; the offset response time is the time difference between the occurrence of behavioral anomalies and changes in resource status; the response evaluation matrix is ​​composed of a two-dimensional structure of resource nodes and behavioral evaluation parameters; The triggering rules for dynamic adjustment of service configuration are set according to the response evaluation matrix. The triggering rules include sensitive node resource occupancy exceeding the threshold, continuous increase in crowd gathering index, abnormal frequency of resource usage path conflict, etc., and are marked in the corresponding position in the building unit model.

[0023] It should be further explained that, in the specific implementation process, the resource allocation scheme is modified based on behavioral disturbance labels and response evaluation matrices to generate an updated resource allocation scheme. The process of renovating and managing old residential areas through the updated resource allocation scheme is as follows: The system acquires spatial resource units marked by behavioral disturbance tags and locates corresponding resource nodes in the building unit model. Based on the behavioral evaluation parameters recorded in the response evaluation matrix, it analyzes the operating status of resource nodes and sets behavioral evaluation thresholds, including volatility threshold, aggregation threshold, occupancy threshold, and offset threshold. When the behavioral load volatility exceeds the volatility threshold, it is determined to be an area with unstable service demand. When the crowd aggregation index is higher than the aggregation threshold and the resource occupancy rate is higher than the occupancy threshold, it is determined to be an area with service shortage. When the resource occupancy rate of a resource node is lower than the occupancy threshold, it is determined to be an area with service redundancy. When the offset response time is higher than the offset threshold, it is determined to be a service deployment offset. The service deployment offset refers to a significant spatial deviation between the actual service resource deployment location and the residents' high-frequency behavioral paths or service preference aggregation areas, resulting in reduced service resource utilization efficiency, inconvenience for residents to obtain services, or service coverage blind spots. Areas with unstable service demand, service shortage, service redundancy, and service deployment offset are recorded as abnormal judgment results. Based on the anomaly detection results, the deployment location, service radius, or service capacity fields in the resource configuration scheme are adjusted accordingly to generate an updated resource configuration scheme; The updated resource configuration scheme is injected into the building unit model, and the spatial location and operational status of each service resource are updated synchronously. Based on the updated resource configuration scheme and combined with the behavior response logic chain, the crowd concentration path and resource node occupancy are retrospectively analyzed to verify the mitigation effect of the optimized scheme on abnormal fluctuations, which serves as the basis for subsequent renovation management.

[0024] Example 2: The smart management system for the renovation of old residential communities based on digital twin technology proposed in this invention is applied to the smart management method for the renovation of old residential communities based on digital twin technology described in Example 1. Specifically, it includes a management center, which is communicatively connected to a data acquisition module, a resource configuration module, a resource analysis module, and a renovation management module. The data acquisition module is used to collect building information data, geospatial data, and population statistics data of old residential communities, and to construct individual building models. Based on the individual building models, the module analyzes the building information data, geospatial data, and population statistics data, divides the building neighborhood units and neighborhood unit boundaries, and generates a service demand matrix. The resource configuration module is used to analyze the service demand matrix, construct the supply and demand matching matrix, establish a multi-objective configuration function, and generate a resource configuration scheme. The resource analysis module is used to analyze resource allocation schemes, generate spatial allocation instruction sets, and build resident behavior models. It analyzes spatial allocation instruction sets, resident behavior models, and building unit models to generate behavioral path trajectories and resource usage time series data, and builds behavioral disturbance labels and response evaluation matrices. The renovation management module is used to modify the resource allocation scheme based on behavioral disturbance labels and response evaluation matrix, generate an updated resource allocation scheme, and manage the renovation of old residential areas through the updated resource allocation scheme.

[0025] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A smart management method for the renovation of old residential communities based on digital twin technology, characterized in that: Includes the following steps: S1. Collect building information data, geospatial data, and population statistics data of old residential communities, and construct individual building models. Based on the individual building models, analyze the building information data, geospatial data, and population statistics data, divide the building neighborhood units and neighborhood unit boundaries, and generate a service demand matrix. S2. Analyze the service demand matrix, construct the supply and demand matching matrix, and establish a multi-objective configuration function to generate a resource configuration scheme; S3. Analyze the resource allocation scheme to generate a spatial allocation instruction set and build a resident behavior model. Analyze the spatial allocation instruction set, resident behavior model and building unit model to generate behavior path trajectory and resource usage time series data, and build behavior disturbance labels and response evaluation matrix. S4. Modify the resource allocation scheme based on behavioral disturbance labels and response evaluation matrix to generate an updated resource allocation scheme, and then manage the renovation of old residential areas through the updated resource allocation scheme.

2. The intelligent management method for the renovation of old residential communities based on digital twin technology according to claim 1, characterized in that, The process of collecting building information data, geospatial data, and population statistics for old residential communities, and constructing individual building models, includes: Building information data includes structural type, number of floors, functional parameters, and occupancy parameters of buildings in old residential communities; geospatial data includes geospatial coordinates, relative spacing, height information, passageway connections, building number, and house number of buildings in old residential communities; demographic data includes resident population, age structure, family structure, occupation type, and service preference information. Using digital twin technology, a three-dimensional twin model of an old residential community is constructed based on its geographic spatial coordinates, height information, and relative spacing. The number of floors, structural type, and functional parameters of the old residential community buildings are then embedded into the corresponding parts of the three-dimensional twin model to construct a building model of the individual buildings in the old residential community. Based on the geographic spatial location and passageway connection relationship of adjacent old residential community buildings, the spatial adjacency relationship between the corresponding building models is constructed.

3. The intelligent management method for the renovation of old residential communities based on digital twin technology according to claim 2, characterized in that, The process of analyzing building information data, geospatial data, and demographic data based on individual building models, dividing building neighborhood units and their boundaries, and generating a service demand matrix includes: Based on age structure, family structure, occupation type, and service preference information in demographic data, data of similar attributes within individual building models are merged and statistically analyzed. Demographic data is then categorized into population hierarchies to obtain population classification results. These population classification results are then correlated with individual building models to construct hierarchical labels for population attributes. Based on population attribute hierarchical labels, spatial adjacency relationships, and channel connection relationships, a density-based clustering algorithm is used to aggregate and group individual building models, identify neighborhood unit clusters, construct building neighborhood units and neighborhood unit boundaries, and number the building neighborhood units to obtain unit numbers and corresponding range coordinates. Based on the unit number, population attribute hierarchical labels, range coordinates, service preference information, capacity parameters, number of permanent residents, and corresponding building information data of each building neighborhood unit, a neighborhood unit index table is constructed. Based on the neighborhood unit index table, the service category and corresponding service preference intensity value of each building neighborhood unit are extracted by analyzing the correspondence between population attribute hierarchical labels and service preference information. The service capacity value and expected service radius value of each building neighborhood unit are obtained. The service category, service capacity value, service preference intensity value and expected service radius value of each building neighborhood unit are normalized to construct a service supply and demand field set. The data is then summarized by unit number to generate a service demand matrix.

4. The intelligent management method for the renovation of old residential communities based on digital twin technology according to claim 3, characterized in that, The process of analyzing the service demand matrix, constructing a supply-demand matching matrix, and establishing a multi-objective configuration function to generate a resource allocation scheme includes: Obtain the service supply and demand field set corresponding to each building neighborhood unit in the service demand matrix, and combine it with the unit number, population attribute hierarchical label, accommodating capacity parameter and permanent population recorded in the neighborhood unit index table to construct a population service demand profile for the building neighborhood unit; according to the service category of each building neighborhood unit, obtain the corresponding service resource list in the old community building and establish a service resource table. The population service demand profile is correlated with the resource data in the service resource table. According to the set matching constraints, a supply and demand adaptation model is constructed and a supply and demand adaptation matrix is ​​generated. Based on the supply and demand adaptation matrix, the minimum resource waste rate, the maximum population service satisfaction, and the resource distribution balance are set as objective functions to construct a multi-objective configuration function. The mapping relationship between each building neighborhood unit and service resources is solved based on the multi-objective optimization algorithm to obtain the optimal resource configuration combination. Based on the optimal resource allocation combination, a resource allocation scheme for the renovation of old residential communities is generated. The resource allocation scheme includes the location of each service resource, the service radius coverage map of the neighborhood unit, the service satisfaction score of the population group, and the service suitability score.

5. The intelligent management method for the renovation of old residential communities based on digital twin technology according to claim 4, characterized in that, The process of analyzing resource allocation schemes to generate spatial allocation instruction sets, constructing resident behavior models, and analyzing spatial allocation instruction sets, resident behavior models, and individual building models to generate behavioral path trajectories and resource usage time series data is as follows: The service resource deployment location, service radius coverage map, population group service satisfaction score and service adaptability score recorded in the resource allocation scheme are used as spatial configuration parameters and injected into the building unit model composed of the neighborhood unit index table and the building unit twin model to generate a spatial configuration instruction set. Resident behavior models are constructed based on demographic data. Spatial configuration instruction sets and resident behavior models are synchronously input into individual building models. Based on building information data, geospatial data and service resource lists in individual building models, spatial resource sets are constructed. Based on the building unit model, the basic service function areas defined by the building neighborhood units and the boundaries of the neighborhood units are used to construct spatial resource units. The central location of a spatial resource unit is extracted as a resource node using a spatial indexing method. The multi-agent simulation method is used to simulate residents in a building neighborhood unit, generate behavioral path trajectories and resource usage time series data of the simulated crowd, and perform density clustering on the behavioral path trajectories to obtain the concentrated paths of the crowd.

6. The intelligent management method for the renovation of old residential communities based on digital twin technology according to claim 5, characterized in that, The process of constructing behavioral perturbation labels and response evaluation matrices is as follows: Based on the simulated behavioral path trajectories and resource usage time series data, a behavioral response logic chain is constructed. Based on the behavioral response logic chain, behavioral inflection points and abnormal resource occupancy locations in the concentrated paths of the crowd are analyzed. The spatial locations of abnormal fluctuations in resource usage are identified, and the corresponding spatial resource units are determined as sensitive nodes and marked as behavioral disturbance labels. Based on the behavioral disturbance labels, each resource node in the building unit model is analyzed, behavioral evaluation parameters are calculated, and a response evaluation matrix is ​​generated.

7. The intelligent management method for the renovation of old residential communities based on digital twin technology according to claim 6, characterized in that, The process of modifying resource allocation schemes based on behavioral disturbance labels and response evaluation matrices to generate updated resource allocation schemes, and then managing the renovation of old residential communities through these updated schemes, includes: The system acquires spatial resource units marked by behavioral disturbance tags and locates the corresponding resource nodes in the building unit model. Based on the behavioral evaluation parameters recorded in the response evaluation matrix, it analyzes the operating status of the resource nodes, sets behavioral evaluation thresholds, analyzes the behavioral evaluation parameters through the behavioral evaluation thresholds, and generates anomaly judgment results. Based on the anomaly judgment results, it adjusts the resource configuration scheme and generates an updated resource configuration scheme. The updated resource configuration scheme is injected into the building unit model to synchronously update the spatial location and operating status of each service resource.

8. A smart management system for the renovation of old residential communities based on digital twin technology, specifically applied to the smart management method for the renovation of old residential communities based on digital twin technology as described in any one of claims 1 to 7, comprising a management center, characterized in that, The management center's communication connections include a data acquisition module, a resource configuration module, a resource analysis module, and a transformation management module. The data acquisition module is used to collect building information data, geospatial data, and population statistics data of old residential communities, and to construct individual building models. Based on the individual building models, the module analyzes the building information data, geospatial data, and population statistics data, divides the building neighborhood units and neighborhood unit boundaries, and generates a service demand matrix. The resource configuration module is used to analyze the service demand matrix, construct the supply and demand matching matrix, establish a multi-objective configuration function, and generate a resource configuration scheme. The resource analysis module is used to analyze resource allocation schemes, generate spatial allocation instruction sets, and build resident behavior models. It analyzes spatial allocation instruction sets, resident behavior models, and building unit models to generate behavioral path trajectories and resource usage time series data, and builds behavioral disturbance labels and response evaluation matrices. The renovation management module is used to modify the resource allocation scheme based on behavioral disturbance labels and response evaluation matrix, generate an updated resource allocation scheme, and manage the renovation of old residential areas through the updated resource allocation scheme.

Images