Urban update space intelligent planning and evaluation system based on digital twinning

Abstract

The invention belongs to the technical field of urban planning, and provides a digital twinborn-based urban update space intelligent planning and evaluation system, which comprises a data acquisition module for fusing multi-source heterogeneous data in real time, and constructing and updating an urban digital twinborn body; the intelligent planning module generates candidate schemes by combining targets and constraints based on the digital twins and utilizing artificial intelligence; the simulation deduction module performs multi-dimensional dynamic simulation on the candidate scheme, and feeds back and adjusts parameter optimization to generate a planning scheme; the intelligent evaluation module evaluates a planning scheme based on a simulation result through a quantitative index; the monitoring feedback module continuously monitors the actual operation state of the to-be-updated area; according to the invention, through the Internet of Things and the digital twinborn model, the actual condition of a city is dynamically reflected, the integrity and timeliness of data are ensured, and a city updating scheme continuously adapts to city changes.

Description

Technical Field

[0001] The present invention belongs to the field of urban planning technology, and specifically to an urban renewal space intelligent planning and evaluation system based on digital twins. Background Art

[0002] Urban planning requires a large amount of urban planning results, basic data and socio-economic development data indicators; traditional urban planning and renewal rely more on manual research, static data analysis and empirical judgment, lacking real-time monitoring and dynamic adjustment capabilities; mainly relying on manual experience to design planning schemes, there are defects such as low scheme generation efficiency and insufficient multi-objective balancing capabilities. Planners need to spend a lot of time manually adjusting parameters such as land use nature and building indicators, and it is difficult to take into account multi-dimensional goals such as spatial efficiency and environmental quality at the same time, which often leads to traffic congestion, heat island effect and other problems when the planning scheme is actually implemented.

[0003] In terms of simulation verification, traditional technologies often rely on single-dimensional static simulations, lacking the ability to coordinate and analyze spatial environments, traffic flows, socioeconomic factors, and other dimensions. This fragmented simulation approach fails to reflect the holistic nature of urban systems, making it difficult to proactively identify potential risks in planning schemes driven by the interaction of multiple factors. Furthermore, existing technologies often employ qualitative or semi-quantitative assessment methods, lacking a systematic approach to indicator selection and subjectivity in weighting. This makes it difficult to quantify specific indicators such as public service facility coverage and the rate of improvement in living conditions for low-income groups. Furthermore, assessment results are susceptible to subjective biases among experts, resulting in a lack of objective data support for comparing the pros and cons of different schemes.

[0004] At the same time, traditional technologies lack the ability to dynamically track the urban renewal process. During the construction phase, they mainly rely on manual inspections to monitor progress and quality, and are unable to obtain real-time data such as the installation status of building components and on-site environmental parameters. During the operation phase, it is difficult to continuously monitor the actual operating indicators of the renewal area through urban big data, resulting in the inability to timely discover deviations between the planning scheme and the actual effect.

[0005] To this end, technicians in this field have proposed an intelligent planning and evaluation system for urban renewal space based on digital twins, aiming to use the Internet of Things and digital twin models to dynamically reflect the actual situation of the city, ensure the integrity and timeliness of the data, and enable urban renewal plans to continuously adapt to urban changes. Summary of the Invention

[0006] In order to solve the above technical problems, the present invention provides an urban renewal space intelligent planning and evaluation system based on digital twins to solve the problems raised in the background technology.

[0007] The urban renewal space intelligent planning and evaluation system based on digital twins includes:

[0008] Data acquisition module, used to collect and fuse multi-source heterogeneous data in real time, and build and update the city digital twin;

[0009] An intelligent planning module, configured to generate candidate plans using artificial intelligence technology based on the city digital twin, combined with preset planning objectives and constraints;

[0010] A simulation deduction module is used to perform multi-dimensional dynamic simulation deduction based on the candidate solutions to obtain simulation results, and adjust the parameters of the candidate solutions based on the feedback of the simulation results to obtain a planning solution;

[0011] An intelligent evaluation module is used to quantify evaluation indicators and pre-evaluate the planning scheme based on the simulation results to obtain evaluation results; the evaluation indicators include spatial efficiency, environmental quality, social equity, economic vitality, historical and cultural preservation, and resilience and safety;

[0012] The monitoring feedback module is used to continuously monitor the actual operating indicators of the area to be updated in the urban digital twin by utilizing the Internet of Things and urban big data.

[0013] Preferably, the data acquisition module further includes:

[0014] The multi-source heterogeneous data includes air-ground integrated surveying and mapping data, real-time data from IoT sensors, social perception big data, and historical planning document data; the social perception big data includes mobile phone signaling data, traffic checkpoint data, social platform geo-tag data, and point of interest data;

[0015] Constructing a three-dimensional model of the current state of the city based on the integrated air-ground mapping data, and identifying and extracting elements of buildings, roads, green spaces, and facilities;

[0016] Based on the real-time data of the Internet of Things sensor, dynamically associate and map it to the corresponding spatial objects in the three-dimensional model of the current city to obtain a dynamic data mapping result;

[0017] The city digital twin includes the current three-dimensional model of the city and dynamic data mapping results.

[0018] Preferably, the intelligent planning module further includes:

[0019] The city digital twin is discretized into N decision-making units, and the state vector of each unit is:

[0020]

[0021] Among them, z i For land use nature, u i is the volume ratio, v i is the building height, τ i It is the transportation connection topology;

[0022] Construct a multi-objective reward function based on the preset planning target φ:

[0023]

[0024] Among them, r(X) represents the total reward value of the objective function, X is the decision state, k is the number of targets, φ j (X) is the function value of the j-th target on the decision state X, ω j is the weight of the j-th target;

[0025] Constructing constraint sets based on constraint conditions According to the constraint set Define the constraint cost function:

[0026]

[0027] Where C(X) is the constraint cost function, m is the total number of constraints, g l (X) represents the lth constraint function, giving the value of the constraint under the current decision state X, and ||…||2 represents the L2 norm of the vector;

[0028] Using constrained multi-objective reinforcement learning, the optimization objective is expressed as:

[0029]

[0030] in, It means finding the strategy that maximizes the target expectation in all strategy spaces, E[…] represents the expected value, represents the discounted reward accumulated at time step t, with a discount factor of γ, s t Indicates the current solution X t The spatial characteristics in the digital twin of the city, a t Indicates the modification of the unit state vector x i operation, r is the increment of the objective function, which indicates the change of the objective function; under the premise of satisfying the constraints, find the optimal strategy π * To maximize the expected cumulative reward; constrain stE[C(s t ,a t )]≤η corresponds to the constraint cost C(s t ,a t ) does not exceed the threshold η;

[0031] Final output candidate solution set Each solution corresponds to a trade-off solution for different objectives.

[0032] Preferably, the simulation deduction module further includes:

[0033] According to the candidate Perform multi-dimensional dynamic simulation, including spatial environment simulation, traffic flow simulation, and socio-economic simulation;

[0034] A deviation function is constructed based on the simulation results and the planning target, which is expressed as:

[0035]

[0036] Among them, w k is the indicator weight, is the simulation index value, is the target value;

[0037] Based on the parameter optimization method of gradient descent, the parameters of the candidate solutions are feedback-adjusted to obtain a planning solution.

[0038] Preferably, the intelligent evaluation module further includes:

[0039] Based on the simulation results, the planning scheme is quantitatively evaluated through a multi-dimensional indicator system and a weight system to obtain an evaluation result;

[0040] The evaluation indicators include spatial efficiency, environmental quality, social equity, economic vitality, historical and cultural protection, and resilience and safety. The following multi-dimensional comprehensive evaluation formula is used to obtain the comprehensive score CS:

[0041]

[0042] Among them, θ d is the weight corresponding to the evaluation index, Score d is the standardized score of each dimension;

[0043] When the comprehensive score CS is lower than the preset threshold, the following formula is used to trigger parameter adjustment:

[0044]

[0045] Among them, ΔP is the adjustment amount of planning parameters, α is the iteration step coefficient, To evaluate the gradient of the function with respect to the parameters, the parameters are optimized by gradient descent until CS ≥ TS;

[0046] The weight system is determined by using the tomographic analysis method combined with the entropy weight method, and the comprehensive weight is:

[0047]

[0048] Among them, β is the adjustment parameter, is the subjective weight of the tomographic analysis method, is the objective weight of the entropy weight method, ω i is the final comprehensive indicator weight.

[0049] Preferably, the monitoring feedback module further includes:

[0050] Leveraging the Internet of Things and city big data, the following formula is used to update the status of the city digital twin:

[0051] X t =f(X t-1 ,U t ,Z t ,Θ,Ω t )+ε t

[0052] Among them, X t is the state vector of the digital twin at time t, X t-1 is the state vector of the digital twin at time t-1, U t is the external input vector at time t, Z t is the observation data vector at time t, Θ is the model parameter set, Ω t is the environmental interference vector at time t, representing unpredictable external factors, ε t is the random error term in the state update process, f(·) is the state transition function;

[0053] Based on the status update of the city digital twin, the following formula is used to monitor the actual operating indicators of the area to be updated:

[0054] Z t =h(X t ,V t )

[0055] Where h(·) is the observation function, which represents the mapping relationship between real-world data and the state of the digital twin. t is the observation noise vector, reflecting the error in the data acquisition process.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. This invention forms a complete closed loop from data collection to monitoring feedback, realizes automated iteration, and effectively improves the efficiency and scientificity of urban renewal. Through multi-objective planning, multi-dimensional simulation and multi-indicator evaluation, it comprehensively considers multiple factors in urban renewal and effectively avoids the global imbalance caused by single-dimensional optimization.

[0058] 2. The present invention integrates real-time updates of digital twins with IoT data, enabling the system to adapt to dynamic changes in the city and achieve accurate calibration and dynamic adjustment of planning schemes.

[0059] 3. This invention replaces traditional empirical judgments with quantitative indicators and evaluation models, reduces human decision-making bias, and provides objective and scientific decision-making support for urban managers. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a block diagram of the urban renewal space intelligent planning and evaluation system based on digital twins of the present invention. DETAILED DESCRIPTION

[0061] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0062] As attached Figure 1 As shown:

[0063] Embodiment: The present invention provides an urban renewal space intelligent planning and evaluation system based on digital twins, comprising:

[0064] The data acquisition module is used to collect and fuse multi-source heterogeneous data in real time to build and update the city digital twin. Multi-source heterogeneous data includes integrated air-ground mapping data, real-time data from IoT sensors, social perception big data, and historical planning document data. Social perception big data includes mobile phone signaling data, traffic checkpoint data, social platform geo-tag data, and point of interest data.

[0065] Build a 3D model of the city's current state based on integrated air-ground mapping data, and identify and extract elements such as buildings, roads, green spaces, and facilities;

[0066] Based on the real-time data of IoT sensors, dynamic association is mapped to the corresponding spatial objects in the current 3D model of the city to obtain dynamic data mapping results;

[0067] The city digital twin contains a three-dimensional model of the city’s current status and dynamic data mapping results.

[0068] Based on surveying and mapping data, a three-dimensional model of the city’s current state is constructed to identify elements such as buildings and roads. The IoT data is then mapped to the three-dimensional model to form a dynamic data mapping result, thereby ensuring that the digital twin can accurately reflect the spatial form and real-time dynamics of the physical city.

[0069] The intelligent planning module is used to generate candidate solutions based on the city digital twin, combined with preset planning goals and constraints, using artificial intelligence technology; the city digital twin is discretized into N decision-making units, and the state vector of each unit is:

[0070]

[0071] Among them, z i For land use nature, u iis the volume ratio, v i is the building height, τ i It is the transportation connection topology;

[0072] Construct a multi-objective reward function based on the preset planning target φ:

[0073]

[0074] Among them, r(X) represents the total reward value of the objective function, X is the decision state, k is the number of targets, φ j (X) is the function value of the j-th target on the decision state X, ω j is the weight of the j-th target;

[0075] Constructing constraint sets based on constraint conditions According to the constraint set Define the constraint cost function:

[0076]

[0077] Where C(X) is the constraint cost function, m is the total number of constraints, g l (X) represents the lth constraint function, giving the value of the constraint under the current decision state X, and ||…||2 represents the L2 norm of the vector;

[0078] Using constrained multi-objective reinforcement learning, the optimization objective is expressed as:

[0079]

[0080] in, It means finding the strategy that maximizes the target expectation in all strategy spaces, E[…] represents the expected value, represents the discounted reward accumulated at time step t, with a discount factor of γ, s t Indicates the current solution X t Spatial characteristics in the city digital twin, a t Indicates the modification of the unit state vector x i operation, r is the increment of the objective function, which indicates the change of the objective function; under the premise of satisfying the constraints, find the optimal strategy π * To maximize the expected cumulative reward; constrain stE[C(s t ,a t )]≤η corresponds to the constraint cost C(s t ,a t ) does not exceed the threshold η;

[0081] Final output candidate solution set Each solution corresponds to a trade-off solution for different objectives.

[0082] The digital twin is discretized into decision-making units, each of which contains state vectors such as land use nature, floor area ratio, and building height; combined with preset planning goals and constraints, a multi-objective reward function and constraint cost function are constructed, and a constrained multi-objective reinforcement learning algorithm is used to generate candidate solutions. Through artificial intelligence technology, candidate solutions that take into account multiple objectives such as spatial efficiency and environmental quality are automatically generated, solving the problems of strong reliance on manual experience and low solution generation efficiency in traditional planning, thereby improving the scientific nature and diversity of planning.

[0083] The simulation deduction module is used to perform multi-dimensional dynamic simulation deduction based on candidate solutions to obtain simulation results, and adjust the parameters of the candidate solutions based on the simulation results to obtain a planning solution; Conduct multi-dimensional dynamic simulation, including spatial environment simulation, traffic flow simulation and socio-economic simulation;

[0084] According to the simulation results and planning objectives, a deviation function is constructed, which is expressed as:

[0085]

[0086] Among them, w k is the indicator weight, is the simulation index value, is the target value;

[0087] Based on the parameter optimization method of gradient descent, the parameters of the candidate solutions are fed back and adjusted to obtain the planning solution.

[0088] Conduct dynamic simulations of candidate plans in multiple dimensions, including spatial environment, traffic flow, and social economy. Build a deviation function between the simulation results and the planning objectives. Adjust the plan parameters based on the gradient descent method to form the final planning plan. This will verify the feasibility of the planning plan in actual scenarios in advance, quantitatively assess potential problems, and improve the rationality of the plan through iterative parameter optimization, thereby reducing the risk of actual implementation.

[0089] The intelligent evaluation module is used to quantify the evaluation indicators and pre-evaluate the planning scheme based on the simulation results to obtain the evaluation results. Based on the simulation results, the planning scheme is quantitatively evaluated through a multi-dimensional indicator system and weight system to obtain the evaluation results.

[0090] The evaluation indicators include spatial efficiency, environmental quality, social equity, economic vitality, historical and cultural preservation, and resilience and safety. The following multi-dimensional comprehensive evaluation formula is used to obtain the comprehensive score CS:

[0091]

[0092] Among them, θ dis the weight corresponding to the evaluation index, Score d is the standardized score of each dimension;

[0093] When the comprehensive score CS is lower than the preset threshold, the following formula is used to trigger parameter adjustment:

[0094]

[0095] Among them, ΔP is the adjustment amount of planning parameters, α is the iteration step coefficient, To evaluate the gradient of the function with respect to the parameters, the parameters are optimized by gradient descent until CS ≥ TS;

[0096] The weight system is determined by combining the tomographic analysis method with the entropy weight method, and the comprehensive weight is:

[0097]

[0098] Among them, β is the adjustment parameter, is the subjective weight of the tomographic analysis method, is the objective weight of the entropy weight method, ω i is the final comprehensive indicator weight.

[0099] Based on the simulation results, an indicator system was established from six dimensions, and the hierarchical analysis method and entropy weight method were used to determine the weights. The scores were calculated through a comprehensive evaluation formula, and parameter adjustments were triggered when the scores were below the threshold. This quantitatively evaluated the comprehensive benefits of the planning scheme, provided decision makers with a data-driven decision-making basis, and ensured the balance and optimality of the scheme under multi-dimensional objectives.

[0100] A monitoring and feedback module, which uses the Internet of Things and urban big data to continuously monitor the actual operating indicators of the areas to be updated in the city's digital twin;

[0101] Leveraging the Internet of Things and urban big data, the following formula is used to update the status of the city digital twin:

[0102] X t =f(X t-1 ,U t ,Z t ,Θ,Ω t )+ε t

[0103] Among them, X t is the state vector of the digital twin at time t, X t-1 is the state vector of the digital twin at time t-1, U t is the external input vector at time t, Z t is the observation data vector at time t, Θ is the model parameter set, Ω tis the environmental interference vector at time t, representing unpredictable external factors, ε t is the random error term in the state update process, f(·) is the state transition function;

[0104] Based on the status update of the city digital twin, the following formula is used to monitor the actual operating indicators of the area to be updated:

[0105] Z t =h(X t ,V t )

[0106] Where h(·) is the observation function, which represents the mapping relationship between real-world data and the state of the digital twin. t is the observation noise vector, reflecting the error in the data acquisition process.

[0107] By leveraging the Internet of Things and urban big data, the digital twin is dynamically calibrated through state update equations, and the actual operating indicators of the area to be updated are monitored in real time. These indicators are then fed back to the digital twin to achieve closed-loop optimization. This enables real-time interaction between the physical city and the digital twin, dynamically monitors the construction process and operating status, and promptly identifies and adjusts deviations to ensure the accurate implementation and continuous optimization of the planning scheme.

[0108] Application scenarios:

[0109] Construction progress calibration: Reading component installation time Z through IoT RFID tags t , and BIM model preset progress X t-1 By contrast, f(·) is used to adjust the time parameter U of the subsequent process t , update X t The duration status in .

[0110] Dynamic assessment of environmental quality: PM2.5 concentration Z collected by sensors t Input the observation function h(·) to modify the atmospheric diffusion model parameter Θ in the digital twin, and then update X t Environmental quality indicators in.

[0111] From the above, we can see that by taking digital twins as the basis for planning and simulation, combined with reinforcement learning and multi-objective optimization methods, the automatic generation and parameter optimization of candidate solutions can be realized, breaking through the limitations of manual design in traditional planning; and by integrating multi-source heterogeneous information such as surveying and mapping data, Internet of Things data, and social big data, a high-fidelity digital twin is constructed, which more comprehensively reflects the real state of the city than the traditional single data source; at the same time, a simulation and evaluation model covering multiple dimensions is established, and the indicators and comprehensive benefits of each dimension are quantified to achieve comprehensive solution verification; in addition, the real-time monitoring data of the Internet of Things and the state update equation of the digital twin are used to form a closed loop, so that the planning scheme can be continuously iterated according to the actual operation situation, which is different from the traditional one-time planning model.

[0112] It is important to note that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are merely illustrative. Although only a few embodiments are described in detail in this disclosure, it will be readily understood by those who consult this disclosure that many modifications are possible without departing substantially from the novel teachings and advantages of the subject matter described in this application. Other substitutions, changes, and omissions may be made in the design, operating conditions, and arrangement of the exemplary embodiments without departing from the scope of the present invention. Therefore, the present invention is not limited to specific embodiments, but extends to a variety of modifications that still fall within the scope of the appended claims.

[0113] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (i.e., those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The urban renewal space intelligent planning and evaluation system based on digital twin is characterized by: include: Data acquisition module, used to collect and fuse multi-source heterogeneous data in real time, and build and update the city digital twin; An intelligent planning module, configured to generate candidate plans using artificial intelligence technology based on the city digital twin, combined with preset planning objectives and constraints; A simulation deduction module is used to perform multi-dimensional dynamic simulation deduction based on the candidate solutions to obtain simulation results, and adjust the parameters of the candidate solutions based on the feedback of the simulation results to obtain a planning solution; An intelligent evaluation module is used to quantify evaluation indicators and pre-evaluate the planning scheme based on the simulation results to obtain evaluation results; the evaluation indicators include spatial efficiency, environmental quality, social equity, economic vitality, historical and cultural preservation, and resilience and safety; The monitoring feedback module is used to continuously monitor the actual operating indicators of the area to be updated in the urban digital twin by utilizing the Internet of Things and urban big data.

2. The urban renewal space intelligent planning and evaluation system based on digital twins as claimed in claim 1 is characterized in that: The data acquisition module also includes: The multi-source heterogeneous data includes air-ground integrated surveying and mapping data, real-time data from IoT sensors, social perception big data, and historical planning document data; the social perception big data includes mobile phone signaling data, traffic checkpoint data, social platform geo-tag data, and point of interest data; Constructing a three-dimensional model of the current state of the city based on the integrated air-ground mapping data, and identifying and extracting elements of buildings, roads, green spaces, and facilities; Based on the real-time data of the Internet of Things sensor, dynamically associate and map it to the corresponding spatial objects in the three-dimensional model of the current city to obtain a dynamic data mapping result; The city digital twin includes the current three-dimensional model of the city and dynamic data mapping results.

3. The urban renewal space intelligent planning and evaluation system based on digital twins according to claim 1 is characterized in that: The intelligent planning module also includes: The city digital twin is discretized into N decision-making units, and the state vector of each unit is: Among them, z i For land use nature, u i is the volume ratio, v i is the building height, τ i It is the transportation connection topology; Construct a multi-objective reward function based on the preset planning target φ: Among them, r(X) represents the total reward value of the objective function, X is the decision state, k is the number of targets, φ j (X) is the function value of the j-th target on the decision state X, ω j is the weight of the j-th target; Constructing constraint sets based on constraint conditions According to the constraint set Define the constraint cost function: Where C(X) is the constraint cost function, m is the total number of constraints, g l (X) represents the lth constraint function, giving the value of the constraint under the current decision state X, and ||…||2 represents the L2 norm of the vector; Using constrained multi-objective reinforcement learning, the optimization objective is expressed as: in, It means finding the strategy that maximizes the target expectation in all strategy spaces, E[…] represents the expected value, represents the discounted reward accumulated at time step t, with a discount factor of γ, s t Indicates the current solution X t The spatial characteristics in the digital twin of the city, a t Indicates the modification of the unit state vector x i operation, r is the increment of the objective function, which indicates the change of the objective function; under the premise of satisfying the constraints, find the optimal strategy π * To maximize the expected cumulative reward; constrain stE[C(s t ,a t )]≤η corresponds to the constraint cost C(s t ,a t ) does not exceed the threshold η; Final output candidate solution set Each solution corresponds to a trade-off solution for different objectives.

4. The urban renewal space intelligent planning and evaluation system based on digital twins according to claim 1 is characterized in that: The simulation deduction module also includes: According to the candidate Perform multi-dimensional dynamic simulation, including spatial environment simulation, traffic flow simulation, and socio-economic simulation; A deviation function is constructed based on the simulation results and the planning target, which is expressed as: Among them, w k is the indicator weight, is the simulation index value, is the target value; Based on the parameter optimization method of gradient descent, the parameters of the candidate solutions are feedback-adjusted to obtain a planning solution.

5. The urban renewal space intelligent planning and evaluation system based on digital twins as claimed in claim 1 is characterized in that: The intelligent evaluation module further includes: Based on the simulation results, the planning scheme is quantitatively evaluated through a multi-dimensional indicator system and a weight system to obtain an evaluation result; The evaluation indicators include spatial efficiency, environmental quality, social equity, economic vitality, historical and cultural protection, and resilience and safety. The following multi-dimensional comprehensive evaluation formula is used to obtain the comprehensive score CS: Among them, θ d is the weight corresponding to the evaluation index, Score d is the standardized score of each dimension; When the comprehensive score CS is lower than the preset threshold, the following formula is used to trigger parameter adjustment: Among them, ΔP is the adjustment amount of planning parameters, α is the iteration step coefficient, To evaluate the gradient of the function with respect to the parameters, the parameters are optimized by gradient descent until CS ≥ TS; The weight system is determined by using the tomographic analysis method combined with the entropy weight method, and the comprehensive weight is: Among them, β is the adjustment parameter, is the subjective weight of the tomographic analysis method, is the objective weight of the entropy weight method, ω i is the final comprehensive indicator weight.

6. The urban renewal space intelligent planning and evaluation system based on digital twins as claimed in claim 1, characterized in that: The monitoring feedback module also includes: Leveraging the Internet of Things and city big data, the following formula is used to update the status of the city digital twin: X t =f(X t-1 ,U t ,Z t ,Θ,Ο t )+e t Among them, X t is the state vector of the digital twin at time t, X t-1 is the state vector of the digital twin at time t-1, U t is the external input vector at time t, Z t is the observation data vector at time t, Θ is the model parameter set, Ω t is the environmental interference vector at time t, representing unpredictable external factors, ε t is the random error term in the state update process, f(·) is the state transition function; Based on the status update of the city digital twin, the following formula is used to monitor the actual operating indicators of the area to be updated: Z t =h(X t ,V t ) Where h(·) is the observation function, which represents the mapping relationship between real-world data and the state of the digital twin. t is the observation noise vector, reflecting the error in the data acquisition process.

Images