Dynamic updating method and system based on wisdom city data base

Abstract

The application relates to the technical field of dynamic updating of urban data bases, in particular to a dynamic updating method and system based on a smart city data base, which comprises the following steps: obtaining and preprocessing multi-source data from a digital city super-brain station and the city data base; performing feature extraction on the multi-source data to divide core interest and attention areas and construct regional comprehensive updating demand degrees of the core interest and attention areas; and arranging the order of the core interest and attention areas in the next round of incremental updating according to the regional comprehensive updating demand degrees. The application aims to timely adjust the regional priority in the dynamic incremental updating of the updating process of the city data base, improve the dynamic updating efficiency and accuracy of the increment, and timely respond to the changes in the city development.

Description

Technical Field

[0001] This application relates to the field of dynamic update technology for urban data infrastructure, specifically to dynamic update methods and systems based on smart city data infrastructure. Background Technology

[0002] The construction of smart cities aims to achieve intelligent, digital, and real-time urban management through technologies such as the Internet of Things (IoT), cloud computing, and big data. Data collection, storage, analysis, and application are core components in the construction of smart cities for major cities. The data foundation of a smart city refers to a unified data infrastructure platform formed by integrating various data sources (such as IoT sensors, video surveillance, environmental monitoring, and social behavior data), which can be used by multiple parties. This platform can support real-time data collection, storage, updating, processing, and sharing, providing data support for various applications in smart cities (such as traffic management, environmental monitoring, and intelligent security).

[0003] Currently, the smart city industry is committed to improving governance efficiency and service levels through full-domain digital transformation. Its core support lies in building a city data foundation that can integrate multi-source heterogeneous data and achieve dynamic updates.

[0004] The existing urban data infrastructure update model requires manual global comparison of historical and current building patch data to identify increments. This highly manual model results in long update cycles, high costs, and is prone to errors. It also makes it difficult to adjust regional priorities during dynamic incremental updates, and thus cannot support the dynamic real-time update requirements of smart cities for the data infrastructure. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides a dynamic update method and system based on a smart city data foundation, and the specific technical solution adopted is as follows:

[0006] In a first aspect, one embodiment of this application provides a dynamic update method based on a smart city data infrastructure, the method comprising the following steps:

[0007] Data from multiple sources is acquired and preprocessed from the digital city super brain platform and the city data base.

[0008] By utilizing the daily average traffic flow and traffic flow fluctuation characteristics of each intersection within a preset time period, all intersections are clustered to divide the initial interest areas and obtain their initial interest scores using the neighboring intersections within each cluster; the core interest areas and their core interest scores are determined by using the area ratio of overlapping areas in the initial interest areas and their initial interest scores.

[0009] By comparing satellite imagery with standard city maps, the dynamic changes in regional development of each core area of ​​interest are calculated using vector change analysis. The dynamic changes in regional development are then weighted with the core interest levels of the corresponding core areas of interest to construct a joint regional development attention index.

[0010] By utilizing the planning and construction information and release time of the current and adjacent core interest areas published by the resource planning department, the demand performance of construction information for each core interest area is determined; the joint attention to regional construction is weighted by the demand performance of construction information for the corresponding core interest areas to determine the comprehensive regional renewal demand for each core interest area.

[0011] The order in which core interest areas are prioritized for the next round of incremental updates is determined by the level of demand for comprehensive regional updates.

[0012] Preferably, when performing clustering processing on all intersections, the clustering distance is determined by the difference in traffic flow variation between intersections; wherein the traffic flow variation is positively correlated with the daily average traffic flow and traffic flow fluctuation characteristics of the corresponding intersection within a preset time period.

[0013] Preferably, the traffic flow fluctuation characteristics are determined by the standard deviation of the daily traffic flow of each intersection within a preset time period.

[0014] Preferably, the method for dividing the initial region of interest includes:

[0015] For all intersections belonging to the same neighboring intersection within each cluster, obtain the smallest bounding circle on the city map as the initial area of ​​interest.

[0016] The initial interest level of the initial interest focus area is assigned the average value of the traffic flow variation of all intersections in its cluster.

[0017] Preferably, the method for obtaining the initial interest level is as follows: the average value of the traffic flow variation of all intersections within the cluster to which the initial interest level belongs is used as the initial interest level of the initial interest level.

[0018] Preferably, the method for determining the core interest focus area and its core interest focus degree is as follows:

[0019] Obtain several overlapping regions from all initial areas of interest;

[0020] The area ratio of the current overlapping region in each of its respective initial interest regions is weighted and summed with the initial interest degree of each of its respective initial interest regions to obtain the core interest degree of the current overlapping region as the core interest region.

[0021] The initial region of interest after removing overlapping areas is taken as the core region of interest, and its core interest score is obtained; the core interest score is the initial interest score of the initial region of interest before removing overlapping areas.

[0022] Preferably, the method for calculating the dynamic changes in regional construction is as follows: using the vector change analysis method to compare satellite imagery with a standard urban map, summing the lengths of the change vectors of all pixels within each core area of ​​interest, and normalizing to obtain the dynamic changes in regional construction for each core area of ​​interest.

[0023] Preferably, the method for determining the representation degree of construction information demand is as follows:

[0024] The total number of areas of interest mentioned in the planning and construction information after the last incremental update is counted.

[0025] The average time interval between the current time and all published information on planning and construction in the core area of ​​interest since the last incremental update is calculated.

[0026] Multiply the normalized value of the total number by 1 plus the normalized value of the average time interval to obtain the initial update demand of regional interest for each core interest area.

[0027] The initial update demand for regional interest in each core interest area is weighted by the average of the initial update demand for regional interest in all adjacent areas of each core interest area, in order to determine the performance of construction information demand in each core interest area.

[0028] Preferably, the multi-source data includes: urban traffic flow data, urban maps, satellite imagery, and planning and construction information and release time published by resource planning departments.

[0029] Secondly, another embodiment of this application also provides a dynamic update system based on a smart city data foundation, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the dynamic update method based on the smart city data foundation described above.

[0030] This application has at least the following beneficial effects:

[0031] 1. This application transforms "intersection traffic flow data" into "regional interest values" and filters core interest areas, calculates core interest levels, that is, by identifying which areas in the city are more dynamic and have more attention value in terms of traffic, it reduces blind full-area updates and provides basic regional units and initial weights for subsequent weighting.

[0032] 2. This application uses satellite imagery analysis to correct core interest levels and simultaneously captures the real-time coupling relationship between urban spatial supply and traffic demand response, avoiding misjudgment of regional potential based solely on historical traffic flow.

[0033] 3. This application introduces the "policy timeline + neighborhood diffusion" level to reflect the actual data update needs of the region due to policy-driven and surrounding construction activities, quantify the urgency of policy-driven updates, solve the problem of delayed identification of engineering planning and construction, and ensure that policy benefit areas are not overlooked.

[0034] 4. This application combines "supply and demand coupling strength" and "policy urgency" into a single score, which directly corresponds to the update priority. This score is used to determine the order in which each core interest area is collected, verified and stored in the next round of incremental updates. The higher the score, the higher the priority for collection, verification and storage. This achieves the goal of precise and dynamic updates that prioritize areas where changes are most drastic and policies are most urgent.

[0035] 5. This application aims to update and improve the data in a timely manner in accordance with the priority of areas in the urban data foundation where data is dynamically changing, thereby improving the efficiency and accuracy of incremental dynamic updates and responding promptly to changes in urban development. Attached Figure Description

[0036] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart illustrating a dynamic update method based on a smart city data platform, provided as an embodiment of this application. Detailed Implementation

[0038] Example 1

[0039] This application provides a dynamic update method based on a smart city data infrastructure according to one embodiment, which can be found in the following document. Figure 1 The method includes the following steps:

[0040] Step 1: Obtain multi-source data from the digital city super brain platform and the city data base and perform preprocessing.

[0041] The data obtained from the digital city super brain platform and urban data base includes: urban traffic flow data, urban maps, satellite imagery, and planning and construction information (demolition, renovation or new construction permits) and release time issued by resource planning departments.

[0042] The above multi-source data are subjected to unified coordinates, unified encoding, and unified temporal annotation, and denoising, missing data completion, and format conversion are completed to form a standardized dataset that can be directly used later.

[0043] Step 2: Extract features from multi-source data to delineate core interest areas and construct a comprehensive update demand for these core interest areas.

[0044] Even in previously standardized multi-source data, redundancy or conflicts may still exist. To extract valuable information, data fusion can enhance the integrity and accuracy of the data. Especially for smart city data, correlation classification, data fusion, and key data extraction can identify core points of interest (i.e., locations or facilities that have a critical impact on city operations, residents' quality of life, traffic flow, and business activities) and detect urban changes, providing priority target areas for dynamic incremental updates.

[0045] Different areas of a city have different attributes, such as commercial areas, residential areas, and industrial areas. As a result, there will be significant differences in traffic flow data between different areas, and these differences will lead to different regional interest expressions. In particular, areas with significant traffic flow data will show significantly higher regional interest expressions than areas with low traffic flow data.

[0046] In this context, significant differences in traffic flow data lead to variations in interest across different areas. Areas with noticeably fluctuating or high-flow traffic should exhibit stronger interest. The dynamic changes in high-flow areas indicate more complex and volatile traffic conditions, resident activities, and business operations. Therefore, these areas should receive greater attention and resource allocation within smart city management systems to respond promptly to their dynamic changes, optimize traffic management, alleviate congestion, and improve overall service quality. Conversely, areas with relatively low flow may be more stable, with lower interest and update needs, requiring adjusted management focus accordingly.

[0047] (1) Accordingly, in order to obtain the core interest area in the city, this application uses the daily average traffic flow and traffic flow fluctuation characteristics of each intersection within a preset time period to perform clustering processing on all intersections, so as to divide the initial interest area by using the neighboring intersections in each cluster and obtain its initial interest degree; and uses the area ratio of the overlapping area in the initial interest area and its initial interest degree to determine the core interest area and its core interest degree.

[0048] When clustering all intersections, the clustering distance is determined by the difference in traffic flow variation between intersections; wherein the traffic flow variation is positively correlated with the daily average traffic flow and traffic flow fluctuation characteristics of the corresponding intersection within a preset time period.

[0049] Specifically, in this embodiment, the traffic flow data of each intersection in the recent period (in this embodiment, the historical period of one month prior to the current day is selected as the recent preset time period) is obtained based on the digital city super brain platform. In this embodiment, the traffic flow data of each intersection is obtained based on the daily vehicle flow data.

[0050] The daily traffic flow data in the recent period is accumulated and averaged to obtain the daily average traffic flow of each intersection within a preset time period; and the daily traffic flow data in the recent period is further calculated to calculate the traffic flow fluctuation characteristics, wherein the traffic flow fluctuation characteristics are determined by the standard deviation of the daily traffic flow of each intersection within the preset time period.

[0051] Furthermore, the normalized value of the average daily traffic flow at each intersection in the recent period is calculated as the first normalized value. The normalized value of the standard deviation of the daily traffic flow at each intersection in the recent period is calculated and summed with 1. The product of the first normalized value and the sum is normalized to obtain the traffic flow variation of each intersection. This is used to evaluate whether the traffic flow at each intersection has significant fluctuations in historical traffic flow, so as to determine whether the area where the intersection is located is a high-flow area.

[0052] At this point, the degree of traffic flow variation at each intersection can be determined.

[0053] Specifically, in this embodiment, the clustering algorithm uses the DBSCAN clustering method to cluster the traffic flow variation of all intersections, thereby obtaining several clusters, in which the traffic flow variation of intersections within each cluster maintains similar performance. The DBSCAN clustering method is a well-known technology and will not be described in detail here.

[0054] The method for dividing the initial interest area includes: obtaining the smallest circumcircle on the city map for all intersections belonging to the same neighboring intersection within each cluster, which is used as the initial interest area; and assigning the initial interest degree of the initial interest area to the average of the traffic flow change degree of all intersections in its cluster.

[0055] Specifically, in this embodiment, the average traffic flow variation of all intersections within each cluster is calculated to determine the interest value of each cluster.

[0056] Meanwhile, for each cluster, based on the location information of each intersection, the intersections that belong to the same neighboring intersection (i.e., the intersections are consecutively adjacent) are used to construct a neighboring intersection set, so that several neighboring intersection sets can be obtained for each cluster.

[0057] For each set of neighboring intersections, the minimum circumcircle of the intersections contained therein is processed on the city map to determine the urban area covered by the set of neighboring intersections, i.e. the initial region of interest. In this way, based on several sets of neighboring intersections of several clusters, the urban areas covered by several sets of neighboring intersections can be divided on the city map, thus obtaining several initial regions of interest.

[0058] Meanwhile, for each initial interest focus area, the interest focus value of the cluster class to which the set of neighboring intersections that constitutes the area belongs is used as the initial interest focus degree of each initial interest focus area;

[0059] Thus, several initial areas of interest and their corresponding initial levels of interest can be identified, serving as quantitative indicators to measure the traffic activity level of these areas and reflecting the "intensity of interest" at the traffic flow level.

[0060] However, considering that there will be overlap between different initial interest areas under the above processing method, and since this overlap will lead to repeated analysis and calculation of the area, the overlapping part of all the above initial interest areas is segmented separately to obtain several overlapping areas.

[0061] For each overlapping region, the corresponding initial interest level is affected by various factors from different initial interest areas, resulting in deviations. Therefore, the influence on the overlapping region can be analyzed based on the several initial interest areas that constitute the overlapping region. Specifically, the higher the regional coverage correlation between the overlapping region and a certain initial interest area, the more the overlapping region conforms to the characteristics (i.e., initial interest level) of that initial interest area.

[0062] Accordingly, for each overlapping region, all initial interest regions to which that overlapping region belongs are obtained. The area of ​​each overlapping region is compared with the area of ​​each of its constituent initial interest regions to determine the regional coverage correlation between the overlapping region and each of its constituent initial interest regions. Furthermore, this application performs a weighted summation of the area ratio of the current overlapping region in each of its constituent initial interest regions with the initial interest scores of each of its constituent initial interest regions to obtain the core interest score of the current overlapping region as the core interest region.

[0063] Specifically, in this embodiment, the formula for calculating the core interest attention Q of the currently overlapping region as the core interest attention region is as follows:

[0064]

[0065] Where Q represents the core interest attention level of the current overlapping region as a core interest attention region; M represents the number of initial interest attention regions constituting the current overlapping region. This indicates the area ratio of the current overlapping region within its m-th initial region of interest; This indicates the initial interest level of the m-th initial interest region to which the current overlapping region belongs; express A function that ensures that each element is between 0 and 1, and that the sum of all elements is 1, thus guaranteeing... As When weighted, the sum of all weights is 1.

[0066] In this way, the core interest level of each overlapping region can be determined as the core interest focus region.

[0067] Meanwhile, for each initial interest focus area, the remaining area after removing the overlapping areas is taken as the core interest focus area, and the initial interest focus of each initial interest focus area before removing the overlapping areas is taken as the core interest focus of each core interest focus area.

[0068] Thus, based on the obtained overlapping areas and core interest areas, they are collectively referred to as core interest areas. This is used to classify core interest areas within the city based on urban traffic flow data, ensuring varying degrees of core interest. The core interest intensity of a core interest area serves as a comprehensive "interest intensity" indicator measuring the traffic activity of that area. It combines the traffic flow variation at intersections with the impact of regional overlap, reflecting the prominence of an area in traffic flow. This identifies which areas in the city are more dynamic and valuable in terms of traffic, providing a quantitative basis for subsequent urban monitoring, resource allocation, and data update prioritization.

[0069] In summary, several core interest areas and their corresponding core interest levels can be obtained.

[0070] For each core interest area obtained through the above process, we can consider using image map data (satellite imagery) to capture data on housing changes in each core interest area and make a preliminary comparison with standard maps to obtain the degree of housing construction change in each core interest area.

[0071] (2) Accordingly, this application obtains the latest image map data of urban areas through satellite imagery, compares the satellite imagery with the standard urban map, and calculates the dynamic changes in regional construction of each core area of ​​interest through vector change analysis.

[0072] Specifically, using a standard city map as a reference, images of each core area of ​​interest are compared at different times. The vector change analysis (CVA) method is used to determine the length of the change vector of each pixel. The lengths of the change vectors of all pixels are summed and normalized to determine the dynamic changes in regional construction of each core area of ​​interest. The vector change analysis method is a well-known technology and will not be described in detail here.

[0073] At this point, the dynamic changes in regional development for each core area of ​​interest can be determined.

[0074] The dynamic changes presented by traffic flow data can reflect the pressure and demand of the urban transportation network at different stages of development, thereby revealing the activity level and development potential of a certain region or core area of ​​interest. The dynamic changes in regional construction usually involve the implementation of urban planning and construction strategies, including the planning and construction of new residential areas, commercial areas, and green spaces, and even the renovation and renewal of old urban areas. These changes not only directly affect the urban spatial structure, but also affect the quality of life and frequency of economic activities of residents in the region, thereby further driving changes in traffic demand.

[0075] (3) Accordingly, this application uses the dynamic changes in regional development to weight the core interest attention of the corresponding core interest attention areas to construct the joint attention of regional development.

[0076] Its significance lies in the fact that the joint attention to regional development can simultaneously capture the real-time coupling relationship between "urban space supply" and "traffic demand response". Only by dynamically weighting the development can we quantify the real pressure of "traffic demand that is added or transferred due to spatial renewal", so that the joint attention can directly reflect "the real-time leverage effect of current construction actions on the future transportation network" and avoid misjudging the regional potential based solely on historical traffic.

[0077] Specifically, in this embodiment, the dynamic change of regional construction in each core interest area is multiplied by the core interest attention level and normalized to determine the joint attention level of regional construction in each core interest area.

[0078] Urban planning and construction are dynamically adjusted according to the requirements of relevant departments. Therefore, based on the joint attention to regional construction in the core interest areas analyzed above, there is a lack of timely correlation with information from functional departments. Hence, this analysis will focus on this aspect.

[0079] In urban planning and construction, the process is coordinated and handled by relevant departments. For example, the resource planning department may plan the demolition of some areas, while some adjacent areas may not be in the demolition area for the time being. However, there may be sporadic illegal constructions and other problems in the adjacent areas. Therefore, the scope of dynamic regional interest updates should be carried out in a timely manner for both the planned area and the adjacent areas.

[0080] (4) Accordingly, this application uses the planning and construction information released by the resource planning department and the release time to determine the initial demand for regional interest updates in the current core interest areas, and uses the average value of the initial demand for regional interest updates in adjacent areas to weight it, so as to determine the demand performance of construction information in each core interest area.

[0081] In this way, the joint attention to regional development in the aforementioned core interest areas can be used to analyze whether there is significant regional planning in the near future, and to update the analysis based on the interest needs of each area.

[0082] Here, based on the planning and construction information released by the resource planning department, the demolition, renovation or new construction policies of each core area of ​​interest are marked.

[0083] For each core interest area, the total number of planning and construction information related to that core interest area after the last incremental update is counted, and the average time interval between all the times published in the planning and construction information related to that core interest area after the last incremental update and the current time is also counted. The initial demand for regional interest updates for each core interest area is determined using the total number and the average time interval. The initial demand for regional interest updates is positively correlated with the total number and the average time interval, respectively.

[0084] Specifically, in this embodiment, the normalized value of the total number is multiplied by 1 plus the normalized value of the average time interval (in days) to obtain the initial update demand of regional interest for each core interest area.

[0085] Meanwhile, considering the sequential nature of planning, and the potential for information delays due to updates from various functional departments or manual verification, the impact of adjacent areas on each core area of ​​interest is considered based on regional proximity.

[0086] Obtain the adjacent regions for each core area of ​​interest;

[0087] Based on the neighboring regions of each core interest region, calculate the average value of the initial update demand of regional interests in all its neighboring regions to determine the potential impact of neighborhood construction for each core interest region.

[0088] Therefore, in this application, the potential impact of neighborhood construction in each core interest area is used as the weight of the initial demand for regional interest in each core interest area. The initial demand for regional interest in each core interest area is weighted to determine the performance of construction information demand in each core interest area.

[0089] Specifically, in this embodiment, the normalized value of the potential impact of neighborhood construction in each core interest area is multiplied by the initial demand degree of regional interest in each core interest area to obtain the construction information demand performance degree of each core interest area.

[0090] The Construction Information Demand Performance Index (CDI) serves as a comprehensive indicator measuring the "urgency of updates" arising from planning and construction information and its surrounding influence in a given region. It is used to quantitatively determine whether a region should be prioritized in the next data update. This CDI integrates the number of planning events within the region, the time decay effect, and the potential impact of neighboring areas. It reflects the actual data update needs of the region driven by policy and surrounding construction activities, and serves as a direct basis for prioritizing incremental data updates.

[0091] In this application, the joint attention to regional construction in each core interest area is used as the weight of the performance of construction information demand in each core interest area. The performance of construction information demand in each core interest area is weighted to determine the comprehensive update demand in each core interest area.

[0092] Specifically, in this embodiment, the product of the joint attention to regional construction and the performance of construction information demand for each core interest area is used as the comprehensive update demand for each core interest area.

[0093] The regional comprehensive update demand index combines the supply and demand coupling strength of "transportation-construction" (regional construction joint attention) with the time urgency of "policy-neighborhood" (construction information demand performance) into a single quantitative value, which is used to prioritize the core interest areas in the next round of incremental updates. The higher the value, the higher the priority for collection, verification and storage, so as to achieve the precise and dynamic update goal of "updating the areas where changes are most drastic and policies are most urgent first".

[0094] In this application, all methods involving normalization can employ methods such as max-min normalization or standard deviation normalization to limit the range of values ​​before normalization to 0 to 1. The specific normalization method can be set by the implementer based on the actual situation.

[0095] Step 3: Based on the level of demand for comprehensive regional updates, the order in which each core interest area will be prioritized in the next round of incremental updates will be determined.

[0096] Here, the overall regional update demand of each core interest area is used as the priority for data updates in different areas. The higher the value, the higher the priority of data updates in the corresponding area of ​​the city data base.

[0097] Therefore, when updating data for each core area of ​​interest, an incremental update approach is adopted to update the city data base; that is, the higher the priority, the more incremental updates are performed on the corresponding area in the city data base. This improves the overall efficiency of data updates, allowing for timely updates and improvements to areas within the city data base experiencing dynamic data changes according to their priority.

[0098] Example 2

[0099] Another embodiment of this application provides a dynamic update system based on a smart city data foundation, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the dynamic update method based on the smart city data foundation described above.

[0100] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not invented in this application.

[0101] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A dynamic update method based on a smart city data foundation, characterized in that, The method includes the following steps: Data from multiple sources is acquired and preprocessed from the digital city super brain platform and the city data base. By utilizing the daily average traffic flow and traffic flow fluctuation characteristics of each intersection within a preset time period, all intersections are clustered to divide the initial interest areas and obtain their initial interest scores using the neighboring intersections within each cluster; the core interest areas and their core interest scores are determined by using the area ratio of overlapping areas in the initial interest areas and their initial interest scores. By comparing satellite imagery with standard city maps, the dynamic changes in regional development of each core area of ​​interest are calculated using vector change analysis. The dynamic changes in regional development are then weighted with the core interest levels of the corresponding core areas of interest to construct a joint regional development attention index. By utilizing the planning and construction information and release time of the current and adjacent core interest areas published by the resource planning department, the demand performance of construction information for each core interest area is determined; the joint attention to regional construction is weighted by the demand performance of construction information for the corresponding core interest areas to determine the comprehensive regional renewal demand for each core interest area. The order in which each core interest area will be prioritized for the next round of incremental updates will be determined based on the level of demand for comprehensive regional updates. The method for determining the core interest focus area and its core interest focus degree is as follows: obtain several overlapping areas among all initial interest focus areas; The area ratio of the current overlapping region in each of its respective initial interest regions is weighted and summed with the initial interest degree of each of its respective initial interest regions to obtain the core interest degree of the current overlapping region as the core interest region. The initial interest region after removing overlapping regions is taken as the core interest region and its core interest score is obtained; the core interest score is the initial interest score of the initial interest region before removing overlapping regions. The method for determining the expressiveness of construction information demand is as follows: count the total number of core interest areas involved in the planning and construction information after the last incremental update; The average time interval between the current time and all published information on planning and construction in the core area of ​​interest since the last incremental update is calculated. Multiply the normalized value of the total number by the result of 1 plus the normalized value of the average time interval to obtain the initial update demand of regional interest for each core interest area. The initial update demand for regional interest in each core interest area is weighted by the average of the initial update demand for regional interest in all adjacent areas of each core interest area, in order to determine the performance of construction information demand in each core interest area.

2. The dynamic update method based on a smart city data foundation as described in claim 1, characterized in that, When clustering all intersections, the clustering distance is determined by the difference in traffic flow variation between intersections; wherein the traffic flow variation is positively correlated with the daily average traffic flow and traffic flow fluctuation characteristics of the corresponding intersection within a preset time period.

3. The dynamic update method based on a smart city data foundation as described in claim 2, characterized in that, The traffic flow fluctuation characteristics are determined by the standard deviation of the daily traffic flow at each intersection within a preset time period.

4. The dynamic update method based on a smart city data foundation as described in claim 2, characterized in that, The method for dividing the initial region of interest includes: For all intersections belonging to the same neighboring intersection within each cluster, obtain the smallest bounding circle on the city map as the initial area of ​​interest. The initial interest level of the initial interest focus area is assigned the average value of the traffic flow variation of all intersections in its cluster.

5. The dynamic update method based on a smart city data foundation as described in claim 4, characterized in that, The method for obtaining the initial interest level is as follows: the average value of the traffic flow change of all intersections within the cluster to which the initial interest level belongs is used as the initial interest level of the initial interest level.

6. The dynamic update method based on a smart city data foundation as described in claim 1, characterized in that, The calculation method for the dynamic changes in regional construction is as follows: the satellite imagery and the city standard map are compared using the vector change analysis method, the lengths of the change vectors of all pixels in each core area of ​​interest are summed, and then normalized to obtain the dynamic changes in regional construction for each core area of ​​interest.

7. The dynamic update method based on a smart city data foundation as described in any one of claims 1-6, characterized in that, The multi-source data includes: urban traffic flow data, city maps, satellite imagery, and planning and construction information and release time published by resource planning departments.

8. A dynamic update system based on a smart city data foundation, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic update method based on the smart city data foundation as described in any one of claims 1-7.

Images