A method and system for identifying business district boundaries based on spatial data

Abstract

The present invention discloses a business district boundary recognition method and system based on spatial data, belonging to the technical field of spatial data analysis. It includes collecting business district data, dividing POI data through spatial grid division, constructing a feature matrix, and adjusting feature weights through a time dimension correction factor to identify the initial boundary range of the business district; screening core nodes based on the feature matrix, constructing the basic skeleton structure of the business district, using a density clustering algorithm to fill in the detailed boundaries in the skeleton structure, and performing boundary repair and optimization; setting boundary elastic adjustment, dynamically correcting the business district boundary according to the change trend of pedestrian flow lines and the update situation of commercial facilities, establishing an abnormal warning mechanism, and correspondingly adopting a boundary adjustment strategy. The present invention recognizes the initial boundary range of the business district, making the boundary of the business district more accurate, which is beneficial to business decision-making and market analysis, effectively repairs the boundary breaks caused by data loss, ensures the integrity and connectivity of the business district boundary, and improves the practical application value of the business district.

Description

Technical Field

[0001] The present invention belongs to the technical field of spatial data analysis, and particularly relates to a method and system for identifying business district boundaries based on spatial data. Background Art

[0002] Under the background of the rapid urbanization in today's world, the accurate identification of business district boundaries has become increasingly important for aspects such as commercial planning, market analysis, and resource allocation. Traditional methods for defining business districts mostly rely on empirical judgments or simple spatial analysis means, and these methods often face many limitations. With the rapid development of big data technology, geographic information system (GIS), and spatial analysis methods, the technology for identifying business district boundaries based on spatial data has gradually emerged, forming a quantitative analysis of business districts and their activities. However, most of the current existing technologies are still insufficient in terms of dynamics and flexibility. Traditional methods for identifying business district boundaries mostly rely on static data and cannot reflect the changes in the flow of people, consumer behavior, and business environment in real time, resulting in information lag in business decisions and affecting the sensitivity and response ability to market dynamics.

[0003] Existing technologies for identifying business district boundaries generally have unsatisfactory aspects in terms of data sources, feature extraction, and boundary adjustment. First of all, many methods rely on a single data source, such as only using historical sales data or geographical location information, and cannot fully capture the influence of multi-dimensional information on business district boundaries. At the same time, existing technologies often lack sufficient meticulousness in the construction of feature matrices and cannot comprehensively reflect the interaction relationships between various commercial facilities within the business district and their layout characteristics in space. In addition, the dynamic adjustment ability of existing business district boundaries is weak, and factors such as the trend of the flow of people, seasonal changes, and the update status of surrounding commercial facilities are not fully considered, making it difficult to achieve flexible adaptation of business district boundaries. This has led to insufficient stability and reliability of business district identification results, and further affected the effect of business operations and the optimization of strategic layouts. Summary of the Invention

[0004] In view of the above existing problems, the technical problems solved by the present invention are: solving the core technical problems such as insufficient data integration, inaccurate boundary determination, and insensitivity to dynamic changes in the process of identifying business district boundaries. Specifically, this method collects multi-dimensional business district data, including POI data and basic data, uses spatial grid division and feature matrix construction, dynamically adjusts weights, identifies core business agglomeration areas, and realizes elastic adjustment and abnormal warning of boundaries, thereby improving the accuracy and adaptability of business district boundary identification and ensuring that business district management can respond to market changes in a timely manner.

[0005] To solve the above technical problems, a method for identifying business district boundaries based on spatial data is proposed, including:

[0006] Collect business district data, divide POI data through spatial grid division, construct a feature matrix, and adjust the feature weights through a time dimension correction factor to identify the initial boundary range of the business district; screen core nodes based on the feature matrix, construct the basic skeleton structure of the business district, use the density clustering algorithm to fill in the detailed boundaries in the skeleton structure, and perform boundary repair and optimization; set boundary elastic adjustment, dynamically correct the business district boundary according to the changing trend of pedestrian flow and the update of commercial facilities, establish an anomaly warning mechanism, and correspondingly adopt boundary adjustment strategies.

[0007] As a preferred solution of a business district boundary recognition method based on spatial data according to the present invention, wherein: the business district data includes POI data and basic data;

[0008] The POI data is the interest point data of commercial facilities; the basic data includes that the category attributes of POIs include business types and scale levels, and the spatial positions include longitude and latitude, business hours, passenger flow, surrounding road network density, and historical data;

[0009] The construction of the feature matrix includes dividing the collected POI data according to spatial grids, generating feature vectors for each grid unit, including business density, functional complementarity, and spatial accessibility, and combining the feature vectors into a matrix as the input data for business district recognition.

[0010] As a preferred solution of a business district boundary recognition method based on spatial data according to the present invention, wherein: the identification of the initial boundary range of the business district includes calculating the business association degree of each grid unit according to the historical passenger flow data, performing a functional integrity score through the POI category diversity, evaluating the completeness of the regional commercial function, and dynamically adjusting the weight of each grid unit;

[0011] Combine the weights of all grid units into a dynamic weight matrix and extract the time series of the historical passenger flow data to analyze the passenger flow change rules in different time periods;

[0012] According to the passenger flow change rules, assign a time correction factor to each grid unit to adjust the weight value in the feature matrix;

[0013] Feed the corrected weight value back into the dynamic weight matrix for dynamic optimization in the time dimension, continuously optimize, and identify the initial boundary range of the core commercial agglomeration area;

[0014] Among them, a two-dimensional mechanism is adopted for adjusting the weight value in the feature matrix by the time correction factor, a time limit is set, dimension one is the time decay factor, and dimension two is the time enhancement factor, and the two generate the final correction value through linear superposition;

[0015] For historical data, a time decay factor is adopted, that is, an exponential decay model is used to process the collected historical data. For each additional time period of historical data, the weight decay amplitude is adjusted;

[0016] For the non-historical data collected, a time enhancement factor is adopted, that is, a multiple enhancement model is used for processing. During the time period when the current time is located, a first weight is dynamically assigned; when the current time is on a legal holiday, a second weight is dynamically assigned.

[0017] As a preferred solution of a business district boundary recognition method based on spatial data according to the present invention, wherein: the construction of the basic skeleton structure of the business district includes, based on a dynamic weight matrix, screening out grid cells with weight values higher than a threshold as core nodes, specifically:

[0018] An improved hierarchical clustering algorithm is adopted to cluster the core nodes according to spatial proximity and weight similarity to form the basic skeleton structure of the business district, which consists of a core business district area and main connection paths. Among them, for each completion of hierarchical clustering, the silhouette coefficient of the current clustering result is calculated. When the coefficient < coefficient threshold, the number of clusters is automatically increased by a specified amplitude and recalculated;

[0019] Under the constraint of the skeleton structure, the radiation distance of the core nodes is set. When it is detected that the distance between two core nodes exceeds the radiation distance, an independent sub-business district is automatically generated with the midpoint between the two core nodes as the dividing line, triggering the construction of a secondary skeleton;

[0020] According to the secondary skeleton construction, density clustering algorithm is used to identify secondary business agglomeration areas to form detailed boundaries. All grid cells are traversed, the core point attributes of each cell are calculated, and core nodes are further identified. The identified core points and neighborhood cells are merged to form a detailed boundary area;

[0021] At the same time, for the connection paths connecting the core nodes, the actual travel time is obtained through GIS. When the actual time is more than twice the theoretical time, virtual nodes are inserted to refine the detailed boundary;

[0022] The core business district area formed by the basic skeleton structure and the secondary business area formed by the secondary skeleton are integrated into an initial business district range, and further boundary repair and optimization are carried out.

[0023] As a preferred solution of a business district boundary recognition method based on spatial data according to the present invention, wherein: the boundary repair and optimization include, through spatial adjacency connectivity constraints, repairing the boundary breaks caused by data loss;

[0024] The adjacency connectivity constraint is that each boundary area must be directly adjacent to at least two core nodes;

[0025] When the boundary area is only connected to one core node, the connection path is completed through a path search algorithm;

[0026] Detect the broken boundary, mark all isolated areas that do not meet the adjacency connectivity constraint, generate a minimum spanning tree based on the road network data, and complete the missing connections between core nodes;

[0027] Generate a set buffer for the repaired boundary and establish a repair record database to record the parameters of each repair operation and the effect evaluation index.

[0028] As a preferred solution of a business district boundary recognition method based on spatial data according to the present invention, wherein: the boundary elastic adjustment includes real-time monitoring of the change trend of the pedestrian flow line and the update situation of commercial facilities, performing boundary elastic adjustment, and calculating the boundary adjustment amplitude ;

[0029] Dynamically correct the business district boundary according to the adjustment amplitude to ensure that the boundary shape is consistent with the actual business activities. Specifically: when the first correction threshold < ≤ the second correction threshold, only adjust the boundary point coordinates, and the maximum offset distance does not exceed the expansion threshold range of the original boundary;

[0030] When the second correction threshold < the third correction threshold, adjust the boundary in the direction, and the amplitude is ;

[0031] When > the third correction threshold, trigger the warning mode, freeze the automatic correction, trigger manual review and start regional reconstruction.

[0032] As a preferred solution of a business district boundary recognition method based on spatial data according to the present invention, wherein: the abnormal warning mechanism includes establishing an abnormal warning mechanism. When the third correction threshold < ≤ the fourth correction threshold, perform regional reconstruction, keep the skeleton structure unchanged, re-execute the density clustering algorithm to identify secondary commercial agglomeration areas, form a detailed boundary, and perform manual review and correction;

[0033] When > the fourth correction threshold, cancel the original skeleton structure and trigger the initial boundary range of the core commercial agglomeration area re-identified.

[0034] Another object of the present invention is to provide a business district boundary recognition system based on spatial data. Through efficient data processing and dynamic adjustment, the present invention accurately identifies and maintains the boundaries of business districts to support business decisions and urban development planning. The system aims to achieve the following key objectives: First, the data adjustment module is used to collect and process multi-dimensional POI and basic data, construct an accurate feature matrix, and lay a solid foundation for the recognition of business district boundaries; Second, through the boundary generation module, based on the feature matrix, core nodes are screened out, the skeleton structure of the business district is established, and density clustering is used to optimize the detailed boundaries to ensure the integrity and accuracy of the boundaries; Finally, the self-correction module can monitor the changes in the flow of people and commercial facilities in real time, dynamically adjust the boundaries, and trigger an alarm in case of abnormalities to ensure that the boundaries of the business district always adapt to the actual business activities.

[0035] As a preferred solution of a business district boundary recognition system based on spatial data according to the present invention, it includes a data adjustment module, a boundary generation module, and a self-correction module;

[0036] The data adjustment module collects and processes the original data and adjusts the feature weights according to the time dimension correction factor;

[0037] The boundary generation module constructs the basic skeleton structure of the business district based on the feature matrix and uses the density clustering algorithm for boundary filling and repair;

[0038] The self-correction module performs dynamic correction and optimization according to the business district boundary provided by the boundary generation module, performs boundary elastic adjustment, establishes an abnormal warning mechanism, and triggers manual review and regional reconstruction.

[0039] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of a business district boundary recognition method based on spatial data as described above are implemented.

[0040] A computer-readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of a business district boundary recognition method based on spatial data as described above are implemented.

[0041] The beneficial effects of the present invention: By collecting business district data and spatially grid-dividing POI data, the present invention constructs a feature matrix and realizes the recognition of the initial boundary range of the business district. It is of great significance for the functional division and agglomeration area recognition of the business district, making the boundaries of the business district more accurate and conducive to business decisions and market analysis.

[0042] By screening core nodes and filling the boundaries using density clustering algorithms, the boundary breaks caused by data loss can be effectively repaired, ensuring the integrity and connectivity of the business district boundaries and enhancing the practical application value of the business districts. In addition, through a dynamic boundary elasticity adjustment mechanism, according to the changing trends of pedestrian flow lines and the updates of commercial facilities, the business district boundaries can be corrected in real time to ensure that the boundary shapes are highly consistent with commercial activities, thus adapting to market demands and enhancing business vitality.

[0043] Establish an abnormal warning mechanism and quickly take regional reconstruction measures under certain threshold conditions to effectively respond to sudden changes and improve the flexibility and response speed of business district management. These steps together promote the accuracy and practicality of business district boundary recognition, providing data support and decision-making basis for urban commercial development. Brief Description of the Drawings

[0044] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings, where:

[0045] Figure 1 It is the overall flowchart of a business district boundary recognition method based on spatial data provided by an embodiment of the present invention.

[0046] Figure 2 It is the system scheme module diagram of a business district boundary recognition system based on spatial data provided by an embodiment of the present invention. Detailed Embodiments

[0047] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0048] Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0049] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they embodiments that are mutually exclusive of other embodiments individually or selectively.

[0050] The present invention will be described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views showing the device structure will be enlarged locally in a non-general proportion, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0051] At the same time, in the description of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "upper, lower, inner, and outer" is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation of the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0052] Unless otherwise clearly defined and limited in the present invention, the terms "installed, connected, and coupled" shall be understood in a broad sense. For example: it can be a fixed connection, a detachable connection, or an integral connection; it can also be a mechanical connection, an electrical connection, or a direct connection, and can also be indirectly connected through an intermediate medium, or can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0053] Example 1, referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a method for identifying business district boundaries based on spatial data, including:

[0054] S1: Collect business district data, divide POI data through spatial grids, construct a feature matrix, and adjust the feature weights through a time dimension correction factor to identify the initial boundary range of the business district.

[0055] It should be noted that the business district data includes POI data and basic data;

[0056] The POI data is the interest point data of commercial facilities, including but not limited to shopping malls, restaurants, office buildings, transportation hubs, etc.;

[0057] The basic data includes the category attributes of POIs, including business types and scale levels, spatial positions including longitude and latitude, business hours, passenger flow, surrounding road network density, and historical data.

[0058] Clean the collected data, call the GIS data of the city's geographical scope for the POI data, and delete isolated POI points that exceed the actual geographical scope of the city;

[0059] The historical passenger flow data is smoothed using the sliding window method with a window size of 7 days to eliminate abnormal fluctuations in a single day;

[0060] A POI status monitoring table is established to automatically mark POIs with zero passenger flow for 30 consecutive days as "invalid" and set their business density value to zero in the feature matrix.

[0061] The constructing of the feature matrix includes dividing the collected POI data into spatial grids, and generating a feature vector for each grid unit, including business density, functional complementarity, and spatial accessibility;

[0062] The business density is the percentage of any type of POI;

[0063] The functional complementarity is the spatial proximity of POIs of different business formats;

[0064] The spatial accessibility is the shortest path distance based on the road network, that is, walking distance rather than straight-line distance;

[0065] The feature vectors are combined into a matrix as input data for business district identification.

[0066] Furthermore, the business type correlation of each grid unit is calculated based on the historical passenger flow data to reflect the synergy between different business types; the functional completeness score is calculated through the diversity of POI categories to evaluate the completeness of regional commercial functions.

[0067] Dynamically adjust the weight of each grid unit to ensure that the weight of the core commercial agglomeration area increases:

[0068] ;

[0069] in, For the The weight value of the grid cell, and are adjustment factors, respectively controlling the impact of business density and functional complementarity. For the The number of POIs of a certain type in a grid cell, is the total number of POIs in the area, For the The business type correlation of each grid unit, For the The functional integrity score of each grid cell;

[0070] Combine the weights of all grid cells into a dynamic weight matrix and extract the time series of passenger flow historical data. Analyze the passenger flow change rules in different time periods. According to the passenger flow change rules, assign a time correction factor to each grid cell, adjust the weight values in the feature matrix, and feedback the corrected weight values to the dynamic weight matrix for dynamic optimization in the time dimension. Continuously optimize to identify the initial boundary range of the core business agglomeration area;

[0071] Among them, a two-dimensional mechanism is adopted to adjust the weight values in the feature matrix by the time correction factor. The time period is set to 1 month. Dimension one is the time decay factor, and dimension two is the time enhancement factor. The two generate the final correction value through linear superposition;

[0072] Specifically, for historical data, the time decay factor is adopted, that is, the collected historical data is processed by an exponential decay model. For each additional time period of historical data, the adjusted weight decays by 15%;

[0073] For the non-historical data collected, the time enhancement factor is adopted, that is, a multiple enhancement model is used for processing. During the time period where the current time is located, a weight of 1.3 times is dynamically assigned; when it is a legal holiday at the current time, a weight of 2 times is dynamically assigned.

[0074] S2: Screen core nodes based on the feature matrix, construct the basic skeleton structure of the business district, use the density clustering algorithm to fill in the detailed boundaries in the skeleton structure, and perform boundary repair and optimization.

[0075] Furthermore, based on the dynamic weight matrix, screen out the grid cells with weight values higher than the threshold as core nodes. Specifically:

[0076] Use an improved hierarchical clustering algorithm to cluster the core nodes according to spatial proximity and weight similarity to form the basic skeleton structure of the business district, which consists of the core business district area and the main connection paths. Among them, for each completion of hierarchical clustering, calculate the silhouette coefficient of the current clustering result. When the coefficient < coefficient threshold, automatically increase the number of clusters by 20% and recalculate;

[0077] Under the constraint of the skeleton structure, identify secondary business agglomeration areas through the density clustering algorithm to form detailed boundaries, traverse all grid cells, and calculate the core point attributes of each cell:

[0078] ;

[0079] Among them, To judge whether the grid cell is a core point, is the set of neighborhood grid cells of is the weight value of the neighborhood grid cell, is the spatial distance from ; is the distance attenuation coefficient, is the core point determination threshold, , is the mean of the dynamic weight matrix, is the standard deviation of the dynamic weight matrix;

[0080] Merge the identified core points and neighborhood cells to form a detailed boundary region.

[0081] Meanwhile, under the constraint of the skeleton structure, set the radiation distance of the core nodes. When the distance between two core nodes exceeds the radiation distance, automatically generate an independent sub-business district with the midpoint between the two core nodes as the dividing line, triggering the construction of the secondary skeleton;

[0082] According to the construction of the secondary skeleton, identify the secondary business agglomeration areas through the density clustering algorithm to form detailed boundaries. Traverse all grid cells, calculate the core point attributes of each cell, further identify the core nodes, and merge the identified core points and neighborhood cells to form a detailed boundary region;

[0083] Meanwhile, for the connection paths connecting the core nodes, obtain the actual travel time through GIS. When the actual time is more than twice the theoretical time, insert virtual nodes to refine the detailed boundaries;

[0084] Integrate the core business district area formed by the basic skeleton structure and the secondary business areas formed by the secondary skeleton into an initial business district scope, and further perform boundary repair and optimization.

[0085] It should be noted that through the spatial adjacency connectivity constraint, repair the boundary breaks caused by data loss;

[0086] The adjacency connectivity constraint is that each boundary region must be directly adjacent to at least 2 core nodes (sharing an edge or a corner); when a boundary region is only connected to 1 core node, complete the connection path through the path search algorithm;

[0087] Detect the broken boundaries, mark all isolated regions that do not meet the adjacency connectivity constraint, generate a minimum spanning tree based on the road network data, and complete the missing connections between the core nodes;

[0088] Generate a 50-meter buffer for the repaired boundary, incorporate the areas where the POI density in the buffer is higher than 80% of the original boundary into the formal boundary, establish a repair record database, and record the parameters and effect evaluation indicators of each repair operation.

[0089] S3: Set boundary elastic adjustment, dynamically correct the business district boundary according to the changing trend of the pedestrian flow line and the update situation of commercial facilities, establish an abnormal warning mechanism, and correspondingly adopt boundary adjustment strategies.

[0090] Furthermore, real-time monitor the changing trend of the pedestrian flow line and the update situation of commercial facilities, conduct boundary elastic adjustment, and calculate the boundary adjustment amplitude:

[0091] ;

[0092] Wherein, is the boundary adjustment amplitude, is the elastic coefficient, is the change amount of the pedestrian flow line, is the update amount of commercial facilities, and are respectively the historical maximum values of the pedestrian flow line and commercial facilities;

[0093] Dynamically correct the business district boundary according to the adjustment amplitude to ensure that the boundary form is consistent with the actual business activities. Specifically:

[0094] When , only adjust the boundary point coordinates, and the maximum offset distance does not exceed 5% of the original boundary;

[0095] When , adjust the boundary in the direction, and the amplitude is ;

[0096] When , trigger the warning mode, freeze the automatic correction, trigger manual review and start regional reconstruction;

[0097] Establish an abnormal warning mechanism. When , conduct regional reconstruction, keep the skeleton structure unchanged, and re-execute the density clustering algorithm to identify secondary commercial agglomeration areas to form detailed boundaries;

[0098] When , cancel the original skeleton structure and trigger the initial boundary range for re-identifying the core commercial agglomeration area.

[0099] Wherein, the first correction threshold is 0, the second correction threshold is 0.1, the third correction threshold is 0.3, and the fourth correction threshold is 0.6.

[0100] Embodiment 2, the second embodiment of the present invention, which is different from the previous embodiment in that:

[0101] When the above-mentioned functions are implemented in the form of 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 the present invention, in essence, or the part that contributes to the prior art, or a part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0102] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device.

[0103] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or processing it in other suitable ways if necessary, and then storing it in a computer memory.

[0104] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination of the two: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0105] Example 3, reference Figure 2 , which is the third embodiment of the present invention, and which provides a business district boundary recognition system based on spatial data, including a data adjustment module, a boundary generation module, and a self-correction module;

[0106] The data adjustment module is responsible for collecting and processing raw data, including POI data and basic data. The collected POI data is divided into spatial grids, and each grid unit generates a feature vector, constructs a feature matrix as input data for business district identification, and adjusts the feature weight according to the time dimension correction factor;

[0107] The business type association of each grid unit is calculated based on the historical data of passenger flow, and the functional integrity score is scored through the diversity of POI categories to evaluate the completeness of regional commercial functions. The weight of each grid unit is dynamically adjusted. The time correction factor is used to adjust the weight value in the feature matrix using a two-dimensional mechanism. The time limit is set. Dimension one is the time attenuation factor, and dimension two is the time enhancement factor. The two are linearly superimposed to generate the final correction value, providing the processed feature matrix and initial boundary range for the boundary generation module, laying a data foundation for subsequent boundary identification and optimization;

[0108] The boundary generation module receives the feature matrix provided by the data adjustment module, and based on the dynamic weight matrix, selects the grid cells with weight values ​​higher than the threshold as core nodes to build the basic skeleton structure of the business district. Under the constraints of the skeleton structure, the radiation distance of the core nodes is set. When it is detected that the distance between two core nodes exceeds the radiation distance, an independent sub-business district is automatically generated with the middle point of the two core nodes as the dividing line, triggering the secondary skeleton construction; according to the secondary skeleton construction, the secondary commercial agglomeration area is identified through the density clustering algorithm to form a detailed boundary, traverse all grid cells, calculate the core point attributes of each cell, further identify the core node, merge the identified core points and neighboring cells to form a detailed boundary area, and perform boundary repair and optimization at the same time, and pass the results to the self-correction module for dynamic adjustment;

[0109] The self-correction module repairs the boundary breaks caused by data loss through spatial adjacency connectivity constraints based on the business district boundary provided by the boundary generation module, performs dynamic correction and optimization to ensure the accuracy and timeliness of the business district boundary. The self-correction module is responsible for monitoring the changing trend of the pedestrian flow line and the update of commercial facilities in real time, making elastic adjustments to the boundary, establishing an anomaly warning mechanism, and triggering manual review and regional reconstruction when necessary. At the same time, it feeds back the adjustment results to the boundary generation module to achieve the closed-loop operation of the entire system.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for identifying business district boundaries based on spatial data, characterized by: include, Collect business district data, divide POI data into spatial grids, construct feature matrix, adjust feature weights through time dimension correction factors, and identify the initial boundary range of the business district; The constructing of the feature matrix includes dividing the collected POI data into spatial grids, and generating a feature vector for each grid unit, including business density, functional complementarity, and spatial accessibility; The business density is the percentage of any type of POI; The functional complementarity is the spatial proximity of POIs of different business formats; The spatial accessibility is the shortest path distance based on the road network, that is, walking distance rather than straight-line distance; Combining the feature vectors into a matrix as input data for business district identification; Based on the feature matrix, core nodes are selected to build the basic skeleton structure of the business district. The density clustering algorithm is used to fill in the detailed boundaries in the skeleton structure, and the boundaries are repaired and optimized. The weight of each grid unit is dynamically adjusted to ensure that the weight of the core commercial cluster area increases: ； in, For the The weight value of the grid cell, and are adjustment factors, respectively controlling the impact of business density and functional complementarity. For the The number of POIs of a certain type in a grid cell, is the total number of POIs in the area, For the The business type correlation of each grid unit, For the The functional integrity score of each grid cell; The weights of all grid cells are combined into a dynamic weight matrix and the time series of historical passenger flow data are extracted to analyze the passenger flow change patterns in different time periods; According to the changing rules of passenger flow, a time correction factor is assigned to each grid unit, and the weight value in the feature matrix is ​​adjusted; Feed the corrected weight values ​​back to the dynamic weight matrix for dynamic optimization in the time dimension, continuously optimize, and identify the initial boundary range of the core commercial agglomeration area; The weight value in the time correction factor adjustment feature matrix is ​​adjusted using a dual-dimensional mechanism to set a time limit, with the first dimension being the time attenuation factor and the second dimension being the time enhancement factor, and the two being linearly superimposed to generate a final correction value; A time decay factor is used for historical data, that is, an exponential decay model is used to process the collected historical data. The weight decay amplitude is adjusted for each additional time period of historical data. For the collected non-historical data, a time enhancement factor is used, that is, a multiple enhancement model is used for processing. If the current time is within the time limit, the first weight is dynamically assigned; if the current time is a statutory holiday, the second weight is dynamically assigned; Based on the dynamic weight matrix, the grid cells with weight values ​​higher than the threshold are selected as core nodes, specifically: An improved hierarchical clustering algorithm is used to cluster core nodes according to spatial proximity and weight similarity to form the basic skeleton structure of the business district, which is composed of the core business district area and the main connection paths. Each time a hierarchical clustering is completed, the silhouette coefficient of the current clustering result is calculated. When the coefficient is less than the coefficient threshold, the number of clusters is automatically increased by 20% and recalculated; Under the constraints of the skeleton structure, the secondary commercial agglomeration area is identified through the density clustering algorithm, the detailed boundary is formed, all grid cells are traversed, and the core point attributes of each cell are calculated: ； in, To determine the grid unit Is it a core point? for The set of neighborhood grid cells of is the weight value of the neighborhood grid cell, for and The spatial distance is the distance attenuation coefficient, is the core point determination threshold, , is the mean of the dynamic weight matrix, is the standard deviation of the dynamic weight matrix; Merge the identified core points and neighborhood units to form a detailed boundary area; Set flexible boundary adjustments, dynamically revise the boundaries of business districts according to the changing trends of pedestrian flow lines and the update of commercial facilities, establish an abnormal early warning mechanism, and adopt corresponding boundary adjustment strategies; The boundary elastic adjustment includes real-time monitoring of the changing trend of the flow of people and the updating of commercial facilities, making boundary elastic adjustments, and calculating the boundary adjustment range: ； in, is the boundary adjustment amplitude, is the elastic coefficient, is the change of human flow line, For commercial facility renewal, and They are the historical maximum values ​​for pedestrian flow lines and commercial facilities respectively; Dynamically modify the boundaries of the business district according to the adjustment range to ensure that the boundary shape is consistent with actual business activities. Specifically, When the first correction threshold < When the value is less than or equal to the second correction threshold, only the coordinates of the boundary points are adjusted, and the maximum offset distance does not exceed 5% of the original boundary; When the second correction threshold < ≤ the third correction threshold, press Direction adjustment boundary, amplitude ; when >When the third correction threshold is reached, the early warning mode is triggered, the automatic correction is frozen, the manual review is triggered, and the regional reconstruction is started; Establish an abnormal warning mechanism. When the third correction threshold is less than When the value is less than or equal to the fourth correction threshold, the region is reconstructed, the skeleton structure is kept unchanged, the density clustering algorithm is re-executed to identify the secondary commercial agglomeration area, the detailed boundary is formed, and manual review and correction are performed; when >When the fourth correction threshold is reached, the original skeleton structure is cancelled, triggering the re-identification of the initial boundary range of the core commercial cluster area.

2. The method for identifying business district boundaries based on spatial data according to claim 1, characterized in that: The business district data includes POI data and basic data; The POI data is the point of interest data of commercial facilities; the basic data includes: the category attributes of the POI include the business type and scale level, the spatial location includes longitude and latitude, business hours, passenger flow, surrounding road network density, and historical data; The construction of the feature matrix includes dividing the collected POI data into spatial grids, generating a feature vector for each grid unit, including business density, functional complementarity and spatial accessibility, and combining the feature vectors into a matrix as input data for business district identification.

3. The method for identifying business district boundaries based on spatial data according to claim 2, characterized in that: The basic skeleton structure of building a business district includes selecting grid cells with weight values ​​higher than a threshold as core nodes based on a dynamic weight matrix, specifically: An improved hierarchical clustering algorithm is used to cluster core nodes according to spatial proximity and weight similarity to form the basic skeleton structure of the business district, which is composed of the core business district area and the main connection paths. Each time a hierarchical clustering is completed, the silhouette coefficient of the current clustering result is calculated. When the coefficient is less than the coefficient threshold, the number of clusters is automatically increased by the specified amplitude and recalculated; Under the constraints of the skeleton structure, the radiation distance of the core nodes is set. When it is detected that the distance between two core nodes exceeds the radiation distance, an independent sub-business district is automatically generated with the middle point of the two core nodes as the dividing line, triggering the construction of the secondary skeleton; Based on the secondary skeleton construction, the secondary commercial agglomeration area is identified through the density clustering algorithm to form a detailed boundary, traverse all grid cells, calculate the core point attributes of each cell, further identify the core nodes, merge the identified core points and neighboring cells to form a detailed boundary area; At the same time, for the connection paths connecting the core nodes, the actual travel time is obtained by obtaining GIS. When the actual time is greater than twice the theoretical time, a virtual node is inserted to refine the detail boundary; Integrate the core business district area formed by the basic skeleton structure and the secondary business area formed by the secondary skeleton into an initial business district scope, and further repair and optimize the boundaries.

4. The method for identifying business district boundaries based on spatial data according to claim 3, characterized in that: The boundary repair and optimization includes repairing boundary breaks caused by missing data through spatial adjacency connectivity constraints; The adjacency connectivity constraint is that each boundary area must be directly adjacent to at least two core nodes; When the boundary area is connected to only one core node, the connection path is completed through the path search algorithm; Detect broken boundaries, mark all isolated areas that do not meet the adjacent connectivity constraints, generate a minimum spanning tree based on the road network data, and complete the missing connections between core nodes; A buffer zone is set for the patched boundary generation, and a patch record database is established to record the parameters and effect evaluation indicators of each patching operation.

5. A system using a method for identifying business district boundaries based on spatial data as claimed in any one of claims 1 to 4, characterized in that: It includes data adjustment module, boundary generation module and self-correction module; The data adjustment module collects and processes raw data and adjusts feature weights according to the time dimension correction factor; The boundary generation module constructs the basic skeleton structure of the business district based on the feature matrix and uses a density clustering algorithm to fill and repair the boundary; The self-correction module dynamically corrects and optimizes the business district boundary provided by the boundary generation module, performs boundary elastic adjustment, establishes an abnormal warning mechanism, and triggers manual review and area reconstruction.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of a method for identifying business district boundaries based on spatial data as described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for identifying business district boundaries based on spatial data as described in any one of claims 1 to 4 are implemented.

Images