Method and device for three-dimensional functional zoning of urban building groups and dynamic floor population distribution

Abstract

The application provides a kind of urban building group three-dimensional function zoning and floor population dynamic distribution method and device, it is related to urban space information processing technical field.The method comprises: based on BERT model and domain-specific vocabulary constructs the semantic feature vector generation fusion data of multi-source POI data;According to three-layer progressive inference structure and inference technology constructs floor position probability distribution model;According to the function coupling strength and the improved spectral clustering algorithm carries out three-dimensional function zoning;Generation building level population statistics data, constructs different attraction model;According to the improved Haaf model, the floor population distribution constraint optimization model is solved to obtain the population dynamic distribution of each floor.The application breaks through the granularity limit of traditional function zoning, realizes the fine three-dimensional function zoning and population dynamic distribution prediction of floor level, provides important decision support for the application such as business site selection, emergency evacuation path planning, public service facility configuration optimization and the like in smart city construction.

Description

Technical Field

[0001] This invention relates to the fields of urban spatial information processing and artificial intelligence technology, and in particular to a method and device for three-dimensional functional zoning of urban building complexes and dynamic distribution of population on each floor. It belongs to the technical field of cross-integration of smart cities, spatial big data analysis, machine learning and urban planning. Background Technology

[0002] The three-dimensional functional zoning and population distribution prediction of urban building complexes are core technical issues in smart city construction, and are of great significance for urban management, emergency response, business planning, and public service optimization. With the accelerated pace of urbanization and the continuous increase in building density, modern urban building complexes exhibit significant characteristics of functional integration, spatial three-dimensionality, and dynamic population flow. Traditional urban spatial analysis methods, mainly based on two-dimensional planar data and static statistical information, are insufficient to accurately reflect the three-dimensional functional distribution characteristics within building complexes, let alone achieve refined population dynamic prediction at the floor level. This technological limitation severely restricts the development level of refined urban management, intelligent decision-making, and personalized services. Therefore, researching methods for three-dimensional functional zoning and dynamic population distribution at different floors of urban building complexes based on multi-source data fusion and artificial intelligence technologies has significant theoretical and practical value for improving the modernization level of urban governance and optimizing resource allocation efficiency.

[0003] In recent years, some progress has been made in research on urban spatial function identification and population distribution prediction. In the field of urban functional identification, scholars have conducted extensive research based on multi-source information such as POI (Point of Interest) data, remote sensing images, and mobile communication data (Liu Yu, Xiao Yu, Gao Song, et al. A review of research on human mobility based on location-aware devices [J]. Acta Geographica Sinica, 2011, 66(10): 1-12; Xue B, Xiao X, Li J, et al. Multi-source data-driven identification of urban functional areas: A case of Shenyang, China [J]. Chinese Geographical Science, 2023, 32: 1-18; Wang J, Gao C, Wang M, et al. Identification of urban functional areas and urban spatial structure analysis by fusing multi-source data features: A case study of Zhengzhou, China [J]. Sustainability, 2023, 15(8): 6505; Wang Y, Li C, Zhang H, et al. Research on multi-source data fusion urban functional area identification method based on random forest model [J]. Sustainability, 2025,17(2): 515).

[0004] In the area of ​​population distribution prediction, researchers have explored population spatial distribution modeling techniques based on machine learning, deep learning, and other methods (Zhao S, Liu Y, Zhang R, et al. China's populationspatialization based on three machine learning models[J]. Journal of CleanerProduction, 2020, 256: 120910; Robinson C, Hohman F, Dilkina B. A deep learning approach for population estimation from satellite imagery[C]. Proceedings of the 1st ACM SIGCAS Conference on Computing and SustainableSocieties, 2017: 1-9; Zhang Y, Zhang Y, Huang B, et al. A hybrid model for high spatial and temporal resolution population distribution prediction[J]. International Journal of Digital Earth, 2022, 15(1): 2155718; Botella C, Joly A, Bonnet P, et al. A deep learning approach to species distribution modelling[M]. Multimedia tools and applications for environmental &biodiversity). informatics. Springer, 2018: 169-199).

[0005] However, these studies mainly focus on two-dimensional functional identification and macro-scale population prediction, lacking analysis of three-dimensional functional zoning within building complexes and population distribution characteristics at the floor level. Furthermore, existing methods often rely on single data sources or simple data overlay, lacking deep semantic understanding and intelligent reasoning capabilities. For the common problem of missing floor location information in POI data, and the spatial correlation and synergistic effects between different functions, existing research has not yet proposed effective solutions, making it difficult to meet the practical needs of refined urban management. Summary of the Invention

[0006] To address the aforementioned technical problems in existing technologies, embodiments of the present invention provide a method and apparatus for three-dimensional functional zoning and dynamic population distribution across floors in urban building complexes. The technical solution is as follows:

[0007] On the one hand, a method for three-dimensional functional zoning and dynamic population distribution of urban building complexes is provided. This method is implemented by equipment for three-dimensional functional zoning and dynamic population distribution of urban building complexes, and includes:

[0008] S1. Obtain multi-source POI data of urban building clusters, construct semantic feature vectors of multi-source POI data based on pre-trained BERT models and domain-specific vocabulary, perform multi-level similarity calculation on semantic feature vectors, and generate fused POI datasets based on similarity calculation results.

[0009] S2. Construct a three-layer progressive reasoning structure based on a large language model. Based on the fused POI dataset, the three-layer progressive reasoning structure, and the Chain-of-Thought reasoning technique, construct a floor location probability distribution model to obtain the POI floor locations.

[0010] S3. Based on the fused POI dataset, functional coupling strength index, and improved spectral clustering algorithm, three-dimensional functional zoning is performed on the interior of the urban building complex to obtain the functional zoning results within the urban building complex; the functional zoning results are optimized based on the simulated annealing algorithm to obtain the optimized functional zoning results.

[0011] S4. Generate building-level population statistics through mobile signaling data processing algorithms, construct a differentiated attraction model based on the population statistics and optimized functional zoning results, and calculate the attraction weight coefficient of each functional zone to the population.

[0012] S5. Establish a floor population allocation constraint optimization model. Based on the population attraction weight coefficient of each floor's functional zoning and the improved Hough model, solve the floor population allocation constraint optimization model to obtain the dynamic population distribution of each floor. Establish a dynamic adjustment mechanism to adjust the dynamic population distribution of each floor in real time.

[0013] S6. Based on the dynamic population distribution of each floor and the optimized functional zoning results, construct a three-dimensional population distribution model of the building and generate a hierarchical population heat map and function-population relationship map of the urban building complex.

[0014] Optionally, in S1, a semantic feature vector of multi-source POI data is constructed based on a pre-trained BERT model combined with domain-specific vocabulary. Multi-level similarity calculations are performed on the semantic feature vectors, and a fused POI dataset is generated based on the similarity calculation results, including:

[0015] S11. Construct semantic feature vectors for multi-source POI data based on multi-source POI data, pre-trained BERT models, and domain-specific vocabulary.

[0016] S12. Perform multi-level similarity calculation on the semantic feature vector based on semantic similarity, geographical similarity, and attribute similarity to obtain the similarity calculation results.

[0017] S13. Based on the data source credibility and historical accuracy of multi-source POI data, establish a dynamic adjustment mechanism for the adaptive fusion threshold of POI.

[0018] The formula for calculating the POI adaptive fusion threshold is shown in equation (1) below:

[0019] (1)

[0020] In the formula, Indicates the POI adaptive fusion threshold. Indicates the basic threshold. Indicates the adjustment factor. This indicates the metrics for evaluating the quality of the data source.

[0021] S14. Based on the similarity calculation results and the POI adaptive fusion threshold, perform multi-source POI data fusion to generate a fused POI dataset.

[0022] Optionally, in S11, constructing semantic feature vectors for multi-source POI data based on multi-source POI data, a pre-trained BERT model, and domain-specific vocabulary includes:

[0023] S111. Establish a POI domain-specific dictionary that includes business terms, geographical terms, and domain-specific vocabulary.

[0024] S112. Based on the POI domain-specific dictionary, the BERT model is further pre-trained on multi-source POI data to obtain a pre-trained BERT model.

[0025] S113. Calculate the semantic feature vector of multi-source POI data based on the pre-trained BERT model and the multi-granularity feature fusion strategy.

[0026] Optionally, S2 constructs a three-layer progressive inference structure based on a large language model. Based on the fused POI dataset, the three-layer progressive inference structure, and Chain-of-Thought inference technology, a floor location probability distribution model is built to obtain the POI floor locations, including:

[0027] S21. Construct a three-layer progressive reasoning structure based on a large language model; wherein the three-layer progressive reasoning structure includes a basic information reasoning layer, a related information reasoning layer, and a logical verification reasoning layer.

[0028] S22. The basic information reasoning layer performs explicit information analysis on the fused POI dataset to generate a preliminary floor judgment; the association information reasoning layer performs implicit information analysis on the fused POI dataset to correct the floor judgment; the logical verification reasoning layer verifies the logical consistency and realistic rationality of the reasoning results and outputs the floor location probability.

[0029] S23. Based on the initial floor judgment, the revised floor judgment, and the floor location probability, the context information is obtained through Chain-of-Thought reasoning techniques.

[0030] S24. Construct a floor location probability distribution model based on contextual information, and obtain the floor location inference result based on the floor location probability distribution model.

[0031] S25. Establish a confidence assessment mechanism to score the credibility of the floor location reasoning results and obtain the POI floor location and confidence level.

[0032] Optionally, in S3, the internal functional zoning of the urban building complex is performed based on the fused POI dataset, the functional coupling strength index, and the improved spectral clustering algorithm to obtain the functional zoning results within the urban building complex; the functional zoning results are then optimized based on the simulated annealing algorithm to obtain optimized functional zoning results, including:

[0033] S31. Calculate the functional coupling strength index based on the spatial proximity, business relevance, and pedestrian interaction of the fused POI dataset.

[0034] S32. Construct a floor adjacency matrix based on the fused POI dataset, and obtain the Laplacian matrix based on the floor adjacency matrix.

[0035] S33. Based on the functional coupling strength index and the Laplace matrix, an improved spectral clustering algorithm is used to perform three-dimensional functional zoning within the urban building complex, resulting in functional zoning results within the urban building complex. The improved spectral clustering algorithm introduces floor connectivity constraints and functional similarity weights.

[0036] S34. The partition boundaries in the functional partitioning results are optimized based on the simulated annealing algorithm to obtain the optimized functional partitioning results.

[0037] Optionally, in S4, building-level demographic data is generated using mobile signaling data processing algorithms. A differentiated attractiveness model is constructed based on the demographic data and the optimized functional zoning results. The attractiveness weight coefficients for each functional zoning area are calculated, including:

[0038] S41. Obtain mobile signaling data, extract the number of mobile phone users within the boundaries of each building in the urban building complex through mobile signaling data processing algorithms, and generate building-level population statistics based on the number of mobile phone users.

[0039] S42. Based on demographic data and optimized functional zoning results, construct a differentiated attractiveness model; wherein, the differentiated attractiveness model includes multiple time-dynamic models, each of which includes basic attractiveness and time-dynamic attractiveness; the multiple time-dynamic models include a commercial function attractiveness model, a residential function attractiveness model, an educational function attractiveness model, a medical function attractiveness model, an office function attractiveness model, and a comprehensive function attractiveness model.

[0040] S43. Based on the differentiated attraction model, calculate the attraction weight coefficient of each floor's functional zones to the population.

[0041] Optionally, in S5, a floor-level population allocation constraint optimization model is established. Based on the population attraction weight coefficients of each floor's functional zones and the improved Hough model, the floor-level population allocation constraint optimization model is solved to obtain the dynamic population distribution of each floor. A dynamic adjustment mechanism is established to adjust the dynamic population distribution of each floor in real time, including:

[0042] S51. Establish a floor population allocation constraint optimization model.

[0043] S52. Based on the population attraction weight coefficient of each floor's functional zoning, the improved Hough model is used to solve the floor population allocation constraint optimization model to obtain the dynamic population distribution of each floor; among them, the improved Hough model introduces floor capacity constraints and functional matching degree constraints.

[0044] S53. Establish a dynamic adjustment mechanism to adjust the dynamic population distribution of each floor in real time based on real-time acquired mobile phone signaling data and the dynamic adjustment mechanism; wherein, the dynamic adjustment mechanism includes designing a sliding window data update strategy and using a weighted average method to update the attraction weight coefficient; the length of the sliding window is adaptively adjusted according to the frequency of data changes.

[0045] On the other hand, a device for three-dimensional functional zoning and dynamic population distribution of urban building complexes is provided. This device is applied to the method of three-dimensional functional zoning and dynamic population distribution of urban building complexes. The device includes:

[0046] The data fusion module is used to acquire multi-source POI data of urban building clusters. Based on the pre-trained BERT model and combined with domain-specific vocabulary, it constructs semantic feature vectors of multi-source POI data, performs multi-level similarity calculation on the semantic feature vectors, and generates the fused POI dataset based on the similarity calculation results.

[0047] The AI ​​reasoning module is used to construct a three-layer progressive reasoning structure based on a large language model. It constructs a floor location probability distribution model based on the fused POI dataset, the three-layer progressive reasoning structure, and the Chain-of-Thought reasoning technology to obtain the POI floor location.

[0048] The functional zoning module is used to perform three-dimensional functional zoning of the urban building complex based on the fused POI dataset, functional coupling strength index and improved spectral clustering algorithm to obtain the functional zoning results of the urban building complex; the functional zoning results are optimized based on the simulated annealing algorithm to obtain the optimized functional zoning results.

[0049] The attraction modeling module is used to generate building-level demographic data through mobile signaling data processing algorithms, construct differentiated attraction models based on demographic data and optimized functional zoning results, and calculate the attraction weight coefficients of each functional zone for the population.

[0050] The population allocation optimization module is used to establish a floor-level population allocation constraint optimization model. Based on the population attraction weight coefficient of each floor's functional zoning and the improved Hough model, the module solves the floor-level population allocation constraint optimization model to obtain the dynamic population distribution of each floor. A dynamic adjustment mechanism is established to adjust the dynamic population distribution of each floor in real time.

[0051] The visualization module is used to construct a three-dimensional population distribution model of a building based on the dynamic population distribution of each floor and the optimized functional zoning results, and to generate a layered population heat map and a function-population relationship map of the urban building complex.

[0052] Optionally, the data fusion module is further used for:

[0053] S11. Construct semantic feature vectors for multi-source POI data based on multi-source POI data, pre-trained BERT models, and domain-specific vocabulary.

[0054] S12. Perform multi-level similarity calculation on the semantic feature vector based on semantic similarity, geographical similarity, and attribute similarity to obtain the similarity calculation results.

[0055] S13. Based on the data source credibility and historical accuracy of multi-source POI data, establish a dynamic adjustment mechanism for the adaptive fusion threshold of POI.

[0056] The formula for calculating the POI adaptive fusion threshold is shown in equation (1) below:

[0057] (1)

[0058] In the formula, Indicates the POI adaptive fusion threshold. Indicates the basic threshold. Indicates the adjustment factor. This indicates the metrics for evaluating the quality of the data source.

[0059] S14. Based on the similarity calculation results and the POI adaptive fusion threshold, perform multi-source POI data fusion to generate a fused POI dataset.

[0060] Optionally, the data fusion module is further used for:

[0061] S111. Establish a POI domain-specific dictionary that includes business terms, geographical terms, and domain-specific vocabulary.

[0062] S112. Based on the POI domain-specific dictionary, the BERT model is further pre-trained on multi-source POI data to obtain a pre-trained BERT model.

[0063] S113. Calculate the semantic feature vector of multi-source POI data based on the pre-trained BERT model and the multi-granularity feature fusion strategy.

[0064] Optionally, the AI ​​inference module is further used for:

[0065] S21. Construct a three-layer progressive reasoning structure based on a large language model; wherein the three-layer progressive reasoning structure includes a basic information reasoning layer, a related information reasoning layer, and a logical verification reasoning layer.

[0066] S22. The basic information reasoning layer performs explicit information analysis on the fused POI dataset to generate a preliminary floor judgment; the association information reasoning layer performs implicit information analysis on the fused POI dataset to correct the floor judgment; the logical verification reasoning layer verifies the logical consistency and realistic rationality of the reasoning results and outputs the floor location probability.

[0067] S23. Based on the initial floor judgment, the revised floor judgment, and the floor location probability, the context information is obtained through Chain-of-Thought reasoning techniques.

[0068] S24. Construct a floor location probability distribution model based on contextual information, and obtain the floor location inference result based on the floor location probability distribution model.

[0069] S25. Establish a confidence assessment mechanism to score the credibility of the floor location reasoning results and obtain the POI floor location and confidence level.

[0070] Optionally, the function partition module is further used for:

[0071] S31. Calculate the functional coupling strength index based on the spatial proximity, business relevance, and pedestrian interaction of the fused POI dataset.

[0072] S32. Construct a floor adjacency matrix based on the fused POI dataset, and obtain the Laplacian matrix based on the floor adjacency matrix.

[0073] S33. Based on the functional coupling strength index and the Laplace matrix, an improved spectral clustering algorithm is used to perform three-dimensional functional zoning within the urban building complex, resulting in functional zoning results within the urban building complex. The improved spectral clustering algorithm introduces floor connectivity constraints and functional similarity weights.

[0074] S34. The partition boundaries in the functional partitioning results are optimized based on the simulated annealing algorithm to obtain the optimized functional partitioning results.

[0075] Optionally, the attraction modeling module is further used for:

[0076] S41. Obtain mobile signaling data, extract the number of mobile phone users within the boundaries of each building in the urban building complex through mobile signaling data processing algorithms, and generate building-level population statistics based on the number of mobile phone users.

[0077] S42. Based on demographic data and optimized functional zoning results, construct a differentiated attractiveness model; wherein, the differentiated attractiveness model includes multiple time-dynamic models, each of which includes basic attractiveness and time-dynamic attractiveness; the multiple time-dynamic models include a commercial function attractiveness model, a residential function attractiveness model, an educational function attractiveness model, a medical function attractiveness model, an office function attractiveness model, and a comprehensive function attractiveness model.

[0078] S43. Based on the differentiated attraction model, calculate the attraction weight coefficient of each floor's functional zones to the population.

[0079] Optionally, the population allocation optimization module is further used for:

[0080] S51. Establish a floor population allocation constraint optimization model.

[0081] S52. Based on the population attraction weight coefficient of each floor's functional zoning, the improved Hough model is used to solve the floor population allocation constraint optimization model to obtain the dynamic population distribution of each floor; among them, the improved Hough model introduces floor capacity constraints and functional matching degree constraints.

[0082] S53. Establish a dynamic adjustment mechanism to adjust the dynamic population distribution of each floor in real time based on real-time acquired mobile phone signaling data and the dynamic adjustment mechanism; wherein, the dynamic adjustment mechanism includes designing a sliding window data update strategy and using a weighted average method to update the attraction weight coefficient; the length of the sliding window is adaptively adjusted according to the frequency of data changes.

[0083] On the other hand, a device for three-dimensional functional zoning of urban building complexes and dynamic distribution of population per floor is provided. The device includes: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the methods described above for three-dimensional functional zoning of urban building complexes and dynamic distribution of population per floor is implemented.

[0084] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-mentioned methods for three-dimensional functional zoning of urban building complexes and dynamic distribution of population per floor.

[0085] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0086] This invention provides a method and system for three-dimensional functional zoning and dynamic population distribution of urban building complexes. It can intelligently integrate multi-source POI data and complete missing floor location information, breaking through the granularity limitations of traditional functional zoning, realizing refined three-dimensional functional zoning at the floor level, scientifically calculating the attractiveness of each functional zone to the population, achieving optimized hierarchical distribution of the total population of the building, and providing real-time dynamic adjustments based on a sliding window data update strategy and anomaly detection mechanism. This provides important decision support for key applications in smart city construction such as commercial site selection, emergency evacuation, and facility planning, effectively improving the intelligence and refinement level of urban spatial analysis. Attached Figure Description

[0087] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0088] Figure 1This is a flowchart of a method for three-dimensional functional zoning and dynamic population distribution of urban building complexes provided by an embodiment of the present invention;

[0089] Figure 2 This is a flowchart of POI floor location inference based on a large language model provided in an embodiment of the present invention;

[0090] Figure 3 This is a hierarchical population heat map of urban building clusters provided in an embodiment of the present invention;

[0091] Figure 4 This is a schematic diagram of a three-dimensional functional zoning and dynamic population distribution device for urban building complexes based on AI semantic parsing and multi-source data fusion, provided by an embodiment of the present invention.

[0092] Figure 5 This is a structural schematic diagram of a three-dimensional functional zoning and dynamic population distribution device for urban building complexes provided in an embodiment of the present invention. Detailed Implementation

[0093] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0094] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0095] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0096] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0097] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0098] This invention provides a method for three-dimensional functional zoning and dynamic population distribution of urban building complexes. This method can be implemented using a device for three-dimensional functional zoning and dynamic population distribution of urban building complexes, which can be a terminal or a server. Figure 1 The flowchart shown illustrates a method for three-dimensional functional zoning of urban building complexes and dynamic population distribution per floor. This method's processing flow may include the following steps:

[0099] S1. Obtain multi-source POI data of urban building clusters, construct semantic feature vectors of multi-source POI data based on pre-trained BERT models and domain-specific vocabulary, perform multi-level similarity calculation on semantic feature vectors, and generate fused POI datasets based on similarity calculation results.

[0100] Optionally, in S1, the semantic feature vectors of multi-source POI data are constructed based on a pre-trained BERT model combined with domain-specific vocabulary. Multi-level similarity calculations are then performed on the semantic feature vectors, and the fused POI dataset is generated based on the similarity calculation results. This may include the following steps S11-S14:

[0101] S11. Construct semantic feature vectors of multi-source POI data based on multi-source POI data, pre-trained BERT models, and domain-specific vocabulary to generate a 768-dimensional semantic embedding representation.

[0102] Optionally, step S11 above may include the following steps S111-S113:

[0103] S111. Establish a POI domain-specific dictionary that includes business terms, geographical terms, and domain-specific vocabulary.

[0104] Among them, domain-specific vocabulary refers to industry-specific terms, which are custom-defined and standardized vocabularies. The constructed POI domain-specific dictionary standardizes similar terms from different data sources, eliminating ambiguity caused by polysemous words, thereby enhancing semantic understanding and assisting feature extraction.

[0105] S112. Based on the POI domain-specific dictionary, the masked language model is further pre-trained on multi-source POI data to improve the domain adaptability of the model and obtain a well-trained masked language model.

[0106] Among them, the BERT model belongs to the masked language model. The masked language model learns to predict the masked words from the context text by masking parts of the input text, thereby generating a vector containing semantic information.

[0107] S113. Calculate the semantic feature vector of multi-source POI data based on the trained mask language model and multi-granularity feature fusion strategy.

[0108] The calculation formula for multi-granularity feature fusion is as follows:

[0109] .

[0110] S12. Perform multi-level similarity calculation on the semantic feature vector based on semantic similarity, geographical similarity, and attribute similarity to obtain the similarity calculation results.

[0111] The formula for calculating multi-level similarity is as follows:

[0112] .

[0113] S13. Based on the data source credibility and historical accuracy of multi-source POI data, establish a dynamic threshold adjustment mechanism to adaptively adjust the POI fusion threshold.

[0114] The formula for calculating the POI adaptive fusion threshold is shown in equation (1) below:

[0115] (1)

[0116] In the formula, Indicates the POI adaptive fusion threshold. Indicates the basic threshold. Indicates the adjustment factor. This indicates the metrics for evaluating the quality of the data source.

[0117] S14. Based on the similarity calculation results and the POI adaptive fusion threshold, multi-source POI data are fused to generate a high-quality fused POI dataset.

[0118] S2. Construct a three-layer progressive reasoning structure based on a large language model. Based on the fused POI dataset, the three-layer progressive reasoning structure, and the Chain-of-Thought reasoning technique, construct a floor location probability distribution model to obtain the POI floor locations.

[0119] Optionally, such as Figure 2 As shown, step S2 above may include the following steps S21-S25:

[0120] S21. Construct a three-layer progressive reasoning structure based on a large language model; wherein the three-layer progressive reasoning structure includes a basic information reasoning layer, a related information reasoning layer, and a logical verification reasoning layer.

[0121] S22. The basic information reasoning layer performs explicit information analysis on the fused POI dataset to generate a preliminary floor judgment; the association information reasoning layer performs implicit information analysis on the fused POI dataset to correct the floor judgment; the logical verification reasoning layer verifies the logical consistency and realistic rationality of the reasoning results and outputs the floor location probability.

[0122] In one feasible implementation, the first layer of basic information reasoning involves analyzing explicit information such as POI name, category, and business hours to generate a preliminary floor determination.

[0123] The second layer of related information reasoning: combining implicit information such as the distribution of surrounding POIs, building types, and regional characteristics to correct the floor judgment.

[0124] The third layer of logic verifies the reasoning: it checks the logical consistency and realistic rationality of the reasoning results, and outputs the probability of the final floor position.

[0125] S23. Based on the initial floor judgment, the revised floor judgment, and the floor location probability, the context information is obtained through Chain-of-Thought reasoning techniques.

[0126] One feasible implementation involves analyzing contextual information such as POI business type, surrounding environment, and user reviews based on Chain-of-Thought reasoning technology.

[0127] S24. Construct a floor location probability distribution model based on contextual information, and obtain the floor location inference result based on the floor location probability distribution model.

[0128] The calculation formula for the probability distribution model is as follows:

[0129] (2)

[0130] in, This represents the probability distribution of which floor a given context belongs to. Represents the weight matrix. A semantic feature vector representing the context. This represents the bias vector.

[0131] S25. Establish a confidence assessment mechanism to score the credibility of the floor location reasoning results and obtain the POI floor location and confidence level.

[0132] The formula for calculating confidence level includes:

[0133] (3)

[0134] in, For the first Confidence level of each floor, For the first The weights of each inference factor, For the first The inference factor for the first... The probability of support for each floor This represents the total number of inference factors.

[0135] This invention uses a contextual reasoning mechanism based on a large language model to extract the implicit floor location information of POIs and generate a floor location probability distribution.

[0136] S3. Based on the fused POI dataset, functional coupling strength index, and improved spectral clustering algorithm, three-dimensional functional zoning is performed on the interior of the urban building complex to obtain the functional zoning results within the urban building complex; the functional zoning results are optimized based on the simulated annealing algorithm to obtain the optimized functional zoning results.

[0137] Optionally, step S3 above may include the following steps S31-S34:

[0138] S31. Calculate the functional coupling strength index based on the spatial proximity, business relevance, and pedestrian interaction of the fused POI dataset.

[0139] The formula for calculating the functional coupling strength is as follows: Functional partitioning is based on the functional coupling strength index.

[0140] S32. Construct a floor adjacency matrix based on the fused POI dataset, and obtain the Laplacian matrix based on the floor adjacency matrix.

[0141] In one feasible implementation, a floor adjacency matrix is ​​constructed. Modify the Laplacian matrix; calculate the eigenvectors of the Laplacian matrix. The formula for calculating the Laplacian matrix includes:

[0142] (4)

[0143] in, This represents the modified Laplace matrix. Represents the Laplace matrix, This represents the topological constraint weights. The spatial relationships between various functional units are expressed mathematically using the Laplace matrix, providing a foundation for subsequent automated partitioning.

[0144] S33. Based on the functional coupling strength index and the Laplace matrix, an improved spectral clustering algorithm is used to perform three-dimensional functional zoning within the urban building complex, resulting in functional zoning results within the urban building complex. The improved spectral clustering algorithm introduces floor connectivity constraints and functional similarity weights.

[0145] Compared with existing spectral clustering algorithms, the improved spectral clustering algorithm of this invention achieves fusion modeling and constraint optimization of multi-source heterogeneous data by introducing functional coupling strength indicators, spatial connectivity constraints, and functional similarity weights. This improved algorithm effectively solves the problems of existing methods that rely solely on spatial adjacency and ignore spatial topology and functional heterogeneity. It significantly improves the scientific rigor and automation level of spatial functional zoning.

[0146] S34. Based on the simulated annealing algorithm, optimize the partition boundaries in the functional partitioning results to minimize the functional conflict within the partitions and obtain the optimized functional partitioning results.

[0147] S4. Generate building-level population statistics through mobile signaling data processing algorithms, construct a differentiated attraction model based on the population statistics and optimized functional zoning results, and calculate the attraction weight coefficient of each functional zone to the population.

[0148] Optionally, step S4 above may include the following steps S41-S43:

[0149] S41. Obtain mobile signaling data, extract the number of mobile phone users within the boundaries of each building in the urban building complex through mobile signaling data processing algorithms, and generate building-level population statistics based on the number of mobile phone users.

[0150] S42. Based on demographic data and optimized functional zoning results, construct a differentiated attractiveness model; wherein, the differentiated attractiveness model includes multiple time-dynamic models, each of which includes basic attractiveness and time-dynamic attractiveness; the multiple time-dynamic models include a commercial function attractiveness model, a residential function attractiveness model, an educational function attractiveness model, a medical function attractiveness model, an office function attractiveness model, and a comprehensive function attractiveness model.

[0151] In one feasible implementation, the differentiated attractiveness model includes a commercial function attractiveness model, a residential function attractiveness model, an educational function attractiveness model, a medical function attractiveness model, an office function attractiveness model, and a comprehensive function attractiveness model. Each model is a time-dynamic model, consisting of two components: basic attractiveness and time attractiveness.

[0152] Specifically, the business function attractiveness model is as follows: ;

[0153] in, ;

[0154] .

[0155] The residential function attractiveness model is as follows: ;

[0156] in, ;

[0157] .

[0158] The educational function attractiveness model is as follows: ;

[0159] in, ;

[0160] .

[0161] The medical function attractiveness model is as follows: ;

[0162] in, ;

[0163] .

[0164] The attractiveness model for office functions is as follows: ;

[0165] in, ;

[0166] .

[0167] The comprehensive functional attractiveness model is as follows: ;in, .

[0168] S43. Based on the differentiated attraction model, calculate the attraction weight coefficient of each floor's functional zoning on the population. Use the attraction weight coefficient as the input parameter of the Hough model—the attraction factor.

[0169] S5. Establish a floor population allocation constraint optimization model. Based on the population attraction weight coefficient of each floor's functional zoning and the improved Hough model, solve the floor population allocation constraint optimization model to obtain the dynamic population distribution of each floor. Establish a dynamic adjustment mechanism to adjust the dynamic population distribution of each floor in real time.

[0170] Optionally, step S5 above may include the following steps S51-S53:

[0171] S51. Establish a floor population allocation constraint optimization model.

[0172] S52. Based on the population attraction weight coefficient of each floor's functional zoning, the improved Hough model is used to solve the floor population allocation constraint optimization model to obtain the dynamic population distribution of each floor; among them, the improved Hough model introduces floor capacity constraints and functional matching degree constraints.

[0173] In one feasible implementation, the total population of the building is allocated hierarchically according to the attractiveness weight of the functional zones on each floor, generating a dynamic population distribution for each floor. An improved Hough model is used to solve the population floor allocation scheme.

[0174] Among them, an optimization model for population allocation constraints on each floor is established: The constraints are: .

[0175] Furthermore, a floor capacity constraint processing mechanism is designed to ensure that the allocated population does not exceed the maximum carrying capacity of each floor. The maximum carrying capacity is calculated based on the floor area, functional type, and safety specifications.

[0176] Introducing a smoothness constraint between floors to minimize abrupt changes in population density between adjacent floors, the constraint formula is as follows: .

[0177] Traditional models mostly consider only static attractiveness, ignoring the time-varying nature of population flow, and lack constraints on floor-level capacity, which may lead to floor overload. This invention introduces a differentiated attractiveness model to provide attractiveness factors as input for the improved Hough model, solving the problem that the static, single attractiveness of traditional models cannot reflect the actual population flow patterns. At the same time, the introduction of floor-level capacity constraints solves the problem that traditional models have no constraints on allocation and are prone to overload.

[0178] S53. Establish a dynamic adjustment mechanism to adjust the dynamic population distribution of each floor in real time based on real-time acquired mobile phone signaling data and the dynamic adjustment mechanism; wherein, the dynamic adjustment mechanism includes designing a sliding window data update strategy and using a weighted average method to update the attraction weight coefficient; the length of the sliding window is adaptively adjusted according to the frequency of data changes.

[0179] In one feasible implementation, a sliding window data update strategy is designed to maintain the most recent... The mobile signaling observation data for each time period are used, and the sliding window length is adaptively adjusted according to the frequency of data changes.

[0180] Furthermore, the attraction weight parameters are updated using a weighted average method, and the parameter update formula is as follows: ,in The learning rate parameter;

[0181] Furthermore, an anomaly detection mechanism is established so that when the deviation between real-time observation data and prediction results exceeds a set threshold, the weight parameters are automatically recalibrated.

[0182] S6. Based on the dynamic population distribution of each floor and the optimized functional zoning results, construct a three-dimensional population distribution model of the building and generate a hierarchical population heat map and function-population relationship map of the urban building complex.

[0183] In one feasible implementation, a three-dimensional population distribution model of a building is constructed based on the floor population allocation results and functional zoning information, generating a layered population heat map and a function-population relationship map of the urban building complex.

[0184] Specifically, a three-dimensional functional distribution map of urban building clusters and a floor population density heat map are generated based on the prediction results;

[0185] Construct a layered population heat map to visually display the population density distribution on each floor, such as... Figure 3 As shown;

[0186] Generate a functional-population relationship map to reveal the relationship between different functional zones and population distribution;

[0187] It provides decision support for different application scenarios, including business site selection recommendations, emergency evacuation route planning, and optimization of public service facility configuration.

[0188] In this embodiment of the invention, semantic feature vectors of POIs are constructed based on a pre-trained BERT model combined with domain-specific vocabulary, and a high-quality POI dataset is generated through multi-level similarity calculation. Based on a three-layer progressive reasoning structure of a large language model, Chain-of-Thought reasoning technology is used to extract implicit floor location information of POIs and generate floor location probability distributions. Three-dimensional functional zoning of building complexes is performed based on functional coupling degree and an improved spectral clustering algorithm. The total population of buildings is obtained based on mobile phone signaling data, and six differentiated floor attraction models are constructed, each of which is a time-dynamic model. Based on an improved Hough model, a floor population allocation optimization algorithm is introduced, which introduces floor capacity constraints and smoothness constraints, and allocates the total population of buildings hierarchically according to the attraction weight of each floor's functional zoning. A dynamic adjustment mechanism based on a sliding window data update strategy and an anomaly detection mechanism is established.

[0189] Figure 4 This is a block diagram illustrating a device for three-dimensional functional zoning and dynamic population distribution of urban building complexes according to an exemplary embodiment. This device is used in a method for three-dimensional functional zoning and dynamic population distribution of urban building complexes. (Refer to...) Figure 4 The device includes a data fusion module 10, an AI inference module 20, a functional zoning module 30, an attraction modeling module 40, a population allocation optimization module 50, and a visualization module 60. Among them:

[0190] The data fusion module 10 is used to acquire multi-source POI data of urban building clusters, construct semantic feature vectors of multi-source POI data based on a pre-trained BERT model combined with domain-specific vocabulary, perform multi-level similarity calculation on the semantic feature vectors, and generate a fused POI dataset based on the similarity calculation results.

[0191] AI reasoning module 20 is used to construct a three-layer progressive reasoning structure based on a large language model. It constructs a floor location probability distribution model based on the fused POI dataset, the three-layer progressive reasoning structure, and the Chain-of-Thought reasoning technology to obtain the POI floor location.

[0192] The functional zoning module 30 is used to perform three-dimensional functional zoning of the urban building complex based on the fused POI dataset, functional coupling strength index and improved spectral clustering algorithm to obtain the functional zoning results of the urban building complex; and to optimize the functional zoning results based on the simulated annealing algorithm to obtain the optimized functional zoning results.

[0193] The attraction modeling module 40 is used to generate building-level demographic data through mobile signaling data processing algorithms, construct a differentiated attraction model based on the demographic data and the optimized functional zoning results, and calculate the attraction weight coefficient of each functional zoning to the population.

[0194] The population allocation optimization module 50 is used to establish a floor population allocation constraint optimization model. Based on the population attraction weight coefficient of each floor's functional zoning and the improved Hough model, the floor population allocation constraint optimization model is solved to obtain the dynamic population distribution of each floor; a dynamic adjustment mechanism is established to adjust the dynamic population distribution of each floor in real time.

[0195] The visualization module 60 is used to construct a three-dimensional population distribution model of a building based on the dynamic population distribution of each floor and the optimized functional zoning results, and to generate a hierarchical population heat map and a function-population relationship map of the urban building complex.

[0196] The present invention includes a data fusion module for intelligent fusion processing of multi-source POI data; an AI inference module for floor location inference based on a large language model; a functional zoning module for three-dimensional functional zoning based on improved spectral clustering; an attractiveness modeling module for constructing and calculating differentiated floor attractiveness models based on functional zoning types; a population allocation optimization module for calculating and generating dynamic population distribution based on optimization algorithms; and a visualization platform that provides interactive display functions for building three-dimensional population distribution models, hierarchical population heat maps, and function-population relationship diagrams based on Web services.

[0197] Specifically, the data fusion module 10 includes a data acquisition unit, a preprocessing unit, a semantic feature extraction unit, and a fusion processing unit, which are used to achieve high-quality fusion of multi-source POI data.

[0198] The AI ​​inference module 20 includes a three-layer inference unit, a chain-of-thought inference unit, a probability distribution calculation unit, and a confidence assessment unit, which are used to accurately infer the POI floor location information.

[0199] The functional zoning module 30 includes a coupling degree calculation unit, a spectral clustering unit, a constraint optimization unit, and a zoning result generation unit, which are used to realize the three-dimensional functional zoning of the building complex.

[0200] The attraction modeling module 40 includes six types of attraction model building units, corresponding to commercial, residential, educational, medical, office and comprehensive functions, respectively. Each unit supports dynamic modeling over time.

[0201] The population allocation optimization module 50 includes a constraint optimization unit, a Hough model solving unit, a capacity constraint processing unit, and a smoothness constraint unit, which are used to achieve optimal floor population allocation.

[0202] The visualization module 60 includes a 3D rendering unit, a heatmap generation unit, a correlation diagram generation unit, and an interactive query unit, providing comprehensive result display and analysis functions.

[0203] Furthermore, the device also includes:

[0204] A distributed data processing engine that supports parallel processing and real-time updates of large-scale POI data and mobile signaling data;

[0205] The high-speed caching system enables efficient storage and fast access to model parameters, intermediate calculation results, and historical data;

[0206] An automated operation and maintenance mechanism dynamically adjusts resource allocation based on computing load to ensure stable system operation.

[0207] This invention provides a method and system for three-dimensional functional zoning and dynamic population distribution of urban building complexes. It constructs POI semantic feature vectors by combining a pre-trained BERT model with domain-specific vocabulary, and achieves high-quality data fusion based on multi-level similarity calculation. A three-layer progressive inference structure using a large language model is employed to accurately extract floor location information. Three-dimensional functional zoning is implemented based on functional coupling degree and an improved spectral clustering algorithm. Six differentiated time-dynamic attraction models are constructed. A reasonable allocation of floor population is achieved through an improved Hough model and constraint optimization. Dynamic adjustment functionality is provided based on a sliding window and anomaly detection mechanism. This method enables intelligent, refined, and dynamic analysis of three-dimensional functional zoning and dynamic population distribution of urban building complexes, providing important technical support for smart city construction.

[0208] Figure 5 This is a structural schematic diagram of a three-dimensional functional zoning and dynamic population distribution device for urban building complexes provided in an embodiment of the present invention, such as... Figure 5 As shown, the three-dimensional functional zoning and dynamic population distribution equipment for urban building complexes can include the above-mentioned features. Figure 4 The illustrated device is a three-dimensional functional zoning and dynamic population distribution system for urban building complexes. Optionally, the device 410 for three-dimensional functional zoning and dynamic population distribution of urban building complexes may include a first processor 2001.

[0209] Optionally, the urban building complex three-dimensional functional zoning and floor population dynamic distribution equipment 410 may also include a memory 2002 and a transceiver 2003.

[0210] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0211] The following is combined Figure 5 A detailed description is provided of each component of the urban building complex three-dimensional functional zoning and floor-level population dynamic distribution equipment 410:

[0212] The first processor 2001 is the control center of the urban building complex three-dimensional functional zoning and floor population dynamic distribution equipment 410. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), or application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0213] Optionally, the first processor 2001 can execute various functions of the urban building complex three-dimensional functional zoning and floor population dynamic distribution device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0214] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 5 CPU0 and CPU1 are shown in the diagram.

[0215] In a specific implementation, as one example, the urban building complex three-dimensional functional zoning and floor population dynamic distribution device 410 may also include multiple processors, such as... Figure 5The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, a processor can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0216] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0217] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or exist independently, and may be connected via the interface circuit of the urban building complex three-dimensional functional zoning and floor population dynamic distribution device 410. Figure 5 (Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0218] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0219] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 5 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0220] Optionally, the transceiver 2003 can be integrated with the first processor 2001 or exist independently, and can be connected to the interface circuit of the urban building complex three-dimensional functional zoning and floor population dynamic distribution equipment 410. Figure 5(Not shown in the image) is coupled to the first processor 2001, and this embodiment of the invention does not specifically limit this.

[0221] It should be noted that, Figure 5 The structure of the three-dimensional functional zoning and dynamic population distribution device 410 shown in the diagram does not constitute a limitation on the router. The actual knowledge structure identification device may include more or fewer components than shown in the diagram, or combine certain components, or have different component arrangements.

[0222] Furthermore, the technical effects of the three-dimensional functional zoning and dynamic population distribution equipment 410 for urban building complexes can be referred to the technical effects of the three-dimensional functional zoning and dynamic population distribution method for urban building complexes described in the above method embodiments, and will not be repeated here.

[0223] It should be understood that the first processor 2001 in the embodiments of the present invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0224] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0225] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0226] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0227] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0228] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0229] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0230] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0231] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0232] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0233] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0234] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0235] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for three-dimensional functional zoning and dynamic population distribution of urban building complexes, characterized in that, The method includes: S1. Obtain multi-source POI data of urban building clusters, construct semantic feature vectors of multi-source POI data based on pre-trained BERT model combined with domain-specific vocabulary, perform multi-level similarity calculation on semantic feature vectors, and generate fused POI dataset based on similarity calculation results. S2. Construct a three-layer progressive reasoning structure based on a large language model. Based on the fused POI dataset, the three-layer progressive reasoning structure, and the Chain-of-Thought reasoning technique, construct a floor location probability distribution model to obtain the POI floor location. S3. Based on the fused POI dataset, functional coupling strength index, and improved spectral clustering algorithm, three-dimensional functional zoning is performed on the interior of the urban building complex to obtain the functional zoning results within the urban building complex; the functional zoning results are optimized based on the simulated annealing algorithm to obtain the optimized functional zoning results. S4. Generate building-level population statistics through mobile signaling data processing algorithms, construct a differentiated attraction model based on the population statistics and optimized functional zoning results, and calculate the attraction weight coefficient of each functional zone to the population. S5. Establish a floor population allocation constraint optimization model. Based on the population attraction weight coefficient of each floor's functional zoning and the improved Hough model, solve the floor population allocation constraint optimization model to obtain the dynamic population distribution of each floor. Establish a dynamic adjustment mechanism to adjust the dynamic population distribution of each floor in real time. S6. Based on the dynamic population distribution of each floor and the optimized functional zoning results, construct a three-dimensional population distribution model of the building and generate a hierarchical population heat map and function-population relationship map of the urban building complex. The construction in S2 is based on a three-layer progressive reasoning structure using a large language model. Based on the fused POI dataset, the three-layer progressive reasoning structure, and Chain-of-Thought reasoning technology, a floor location probability distribution model is constructed to obtain the POI floor locations, including: S21. Construct a three-layer progressive reasoning structure based on a large language model; wherein the three-layer progressive reasoning structure includes a basic information reasoning layer, a related information reasoning layer, and a logical verification reasoning layer; S22. The basic information reasoning layer performs explicit information analysis on the fused POI dataset to generate a preliminary floor judgment; the association information reasoning layer performs implicit information analysis on the fused POI dataset to correct the floor judgment; the logical verification reasoning layer verifies the logical consistency and realistic rationality of the reasoning results and outputs the floor location probability. S23. Based on the initial floor judgment, the revised floor judgment, and the floor location probability, the context information is obtained through Chain-of-Thought reasoning techniques. S24. Construct a floor location probability distribution model based on contextual information, and obtain the floor location inference result based on the floor location probability distribution model; S25. Establish a confidence assessment mechanism to score the credibility of the floor location reasoning results and obtain the POI floor location and confidence level.

2. The method for three-dimensional functional zoning of urban building complexes and dynamic population distribution per floor according to claim 1, characterized in that, S1 involves constructing semantic feature vectors from multi-source POI data using a pre-trained BERT model combined with domain-specific vocabulary, performing multi-level similarity calculations on these semantic feature vectors, and generating a fused POI dataset based on the similarity calculation results. This dataset includes: S11. Construct semantic feature vectors for multi-source POI data based on multi-source POI data, pre-trained BERT models, and domain-specific vocabulary. S12. Perform multi-level similarity calculation on the semantic feature vector based on semantic similarity, geographical similarity, and attribute similarity to obtain the similarity calculation results; S13. Based on the data source credibility and historical accuracy of multi-source POI data, establish a dynamic adjustment mechanism for the adaptive fusion threshold of POI. The formula for calculating the POI adaptive fusion threshold is shown in equation (1) below: （1） In the formula, Indicates the POI adaptive fusion threshold. Indicates the basic threshold. Indicates the adjustment factor. Indicates the data source quality assessment metrics; S14. Based on the similarity calculation results and the POI adaptive fusion threshold, perform multi-source POI data fusion to generate a fused POI dataset.

3. The method for three-dimensional functional zoning of urban building complexes and dynamic distribution of population per floor according to claim 2, characterized in that, The step S11, which involves constructing semantic feature vectors for multi-source POI data based on multi-source POI data, a pre-trained BERT model, and domain-specific vocabulary, includes: S111. Establish a POI-specific dictionary that includes business terms, geographical terms, and domain-specific vocabulary; S112. Based on the POI domain-specific dictionary, the BERT model is further pre-trained on multi-source POI data to obtain the pre-trained BERT model. S113. Calculate the semantic feature vector of multi-source POI data based on the pre-trained BERT model and the multi-granularity feature fusion strategy.

4. The method for three-dimensional functional zoning and dynamic population distribution of urban building complexes according to claim 1, characterized in that, In step S3, the three-dimensional functional zoning of the urban building complex is performed based on the fused POI dataset, the functional coupling strength index, and the improved spectral clustering algorithm to obtain the functional zoning results of the urban building complex. The functional partitioning results are optimized based on the simulated annealing algorithm, resulting in optimized functional partitioning results, including: S31. Calculate the functional coupling strength index based on the spatial proximity, business relevance, and pedestrian interaction of the fused POI dataset; S32. Construct a floor adjacency matrix based on the fused POI dataset, and obtain the Laplacian matrix based on the floor adjacency matrix; S33. Based on the functional coupling strength index and the Laplace matrix, an improved spectral clustering algorithm is used to perform three-dimensional functional zoning within the urban building complex, resulting in functional zoning results within the urban building complex. The improved spectral clustering algorithm introduces floor connectivity constraints and functional similarity weights. S34. The partition boundaries in the functional partitioning results are optimized based on the simulated annealing algorithm to obtain the optimized functional partitioning results.

5. The method for three-dimensional functional zoning and dynamic population distribution of urban building complexes according to claim 1, characterized in that, In step S4, building-level population statistics are generated using a mobile signaling data processing algorithm. A differentiated attractiveness model is constructed based on the population statistics and the optimized functional zoning results. The attraction weight coefficients for each functional zone are calculated, including: S41. Obtain mobile signaling data, extract the number of mobile phone users within the boundaries of each building in the urban building complex through mobile signaling data processing algorithms, and generate building-level population statistics based on the number of mobile phone users. S42. Based on demographic data and optimized functional zoning results, construct a differentiated attractiveness model; wherein, the differentiated attractiveness model includes multiple time-dynamic models, each of which includes basic attractiveness and time-dynamic attractiveness; the multiple time-dynamic models include a commercial function attractiveness model, a residential function attractiveness model, an educational function attractiveness model, a medical function attractiveness model, an office function attractiveness model, and a comprehensive function attractiveness model; S43. Based on the differentiated attraction model, calculate the attraction weight coefficient of each floor's functional zones to the population.

6. The method for three-dimensional functional zoning and dynamic population distribution of urban building complexes according to claim 1, characterized in that, The S5 step establishes a floor population allocation constraint optimization model. Based on the population attraction weight coefficient of each floor's functional zoning and the improved Hough model, the floor population allocation constraint optimization model is solved to obtain the dynamic population distribution of each floor. Establish a dynamic adjustment mechanism to adjust the dynamic distribution of population on each floor in real time, including: S51. Establish a floor population allocation constraint optimization model; S52. Based on the population attraction weight coefficient of each floor's functional zoning, the improved Hough model is used to solve the floor population allocation constraint optimization model to obtain the dynamic population distribution of each floor; among them, the improved Hough model introduces floor capacity constraints and functional matching degree constraints. S53. Establish a dynamic adjustment mechanism to adjust the dynamic population distribution of each floor in real time based on real-time acquired mobile phone signaling data and the dynamic adjustment mechanism; wherein, the dynamic adjustment mechanism includes designing a sliding window data update strategy and using a weighted average method to update the attraction weight coefficient; the length of the sliding window is adaptively adjusted according to the frequency of data changes.

7. A device for three-dimensional functional zoning and dynamic population distribution of urban building complexes, wherein the device is used to implement the method for three-dimensional functional zoning and dynamic population distribution of urban building complexes as described in any one of claims 1-6, characterized in that, The device includes: The data fusion module is used to acquire multi-source POI data of urban building clusters, construct semantic feature vectors of multi-source POI data based on a pre-trained BERT model and domain-specific vocabulary, perform multi-level similarity calculation on the semantic feature vectors, and generate a fused POI dataset based on the similarity calculation results. The AI ​​reasoning module is used to construct a three-layer progressive reasoning structure based on a large language model. Based on the fused POI dataset, the three-layer progressive reasoning structure, and the Chain-of-Thought reasoning technology, a floor location probability distribution model is constructed to obtain the POI floor location. The functional zoning module is used to perform three-dimensional functional zoning of the urban building complex based on the fused POI dataset, functional coupling strength index and improved spectral clustering algorithm to obtain the functional zoning results of the urban building complex; the functional zoning results are optimized based on simulated annealing algorithm to obtain the optimized functional zoning results. The attraction modeling module is used to generate building-level demographic data through mobile signaling data processing algorithms, construct differentiated attraction models based on demographic data and optimized functional zoning results, and calculate the attraction weight coefficients of each functional zone for the population. The population allocation optimization module is used to establish a floor-level population allocation constraint optimization model. Based on the population attraction weight coefficient of each floor's functional zoning and the improved Hough model, the module solves the floor-level population allocation constraint optimization model to obtain the dynamic population distribution of each floor. A dynamic adjustment mechanism is established to adjust the dynamic population distribution of each floor in real time. The visualization module is used to construct a three-dimensional population distribution model of a building based on the dynamic population distribution of each floor and the optimized functional zoning results, and to generate a layered population heat map and a function-population relationship map of the urban building complex.

8. A device for three-dimensional functional zoning and dynamic population distribution on different floors of an urban building complex, characterized in that, The urban building complex's three-dimensional functional zoning and floor-level dynamic population distribution equipment includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains program code that can be invoked by a processor to execute the method as described in any one of claims 1 to 6.

Images