Urban functional area identification method, system and device based on spatial co-location mode and storage medium

Abstract

The invention provides an urban functional area identification method, system and device based on a spatial co-location mode and a storage medium, and the method comprises the steps: firstly collecting POI data of a target area and a main annotation of a public map, setting a POI matched with the main annotation as a core POI, carrying out the block plot division of the target area according to road network data, and carrying out the recognition of the target area; the method comprises the following steps: re-classifying POIs according to urban functions, establishing a mapping relation between the POIs and the urban functions, mining a frequent spatial co-location mode of the POIs based on a spatial co-location mode, mining a spatial co-location mode combination of core POIs taking block plots as units according to the frequent spatial co-location mode of the POIs, and updating the mapping relation between the POIs and the urban functions. And finally, the city function of the block plot is identified. By dividing the importance of the POIs, the accuracy of urban functional area identification is improved, and the phenomenon that the types of the urban functional areas are misjudged due to the fact that the POIs are treated indiscriminately during identification is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of urban planning and management, and in particular to a method, system, device and storage medium for identifying urban functional areas based on a spatial co-location pattern. Background Art

[0002] Urban functional zones are important spatial carriers that carry various urban functions. Timely and accurate identification of urban functional zones and their spatial structures is of great significance for improving urban planning effects, improving urban order, and coordinating the relationship between people and land.

[0003] As an important geospatial data, POI (Point of Interest) has become an important data source for identifying urban functional areas because of its close relationship with urban functions and its high update frequency.

[0004] Research methods for identifying urban functional areas using POI data can be divided into two categories: the first category is based on the statistical information of the number of POIs in each category, that is, establishing the correlation between different POIs and various urban functions, dividing POI categories, and clarifying the main urban functions of each region based on the proportion of each type of POI in the POI area and the proportion of POI in the entire city. This type of method fully considers the role of the number scale of various types of POIs in the identification of urban functional areas, but ignores the urban functions reflected by the spatial combination of different POIs in the same area, and the spatial combination of different POIs is closely related to different regional functions. For example, for commercial areas, department stores, restaurants, and ATMs are more likely to be distributed together; while for cultural and educational areas, the combination of colleges and universities, scientific research institutes, and printing shops is more obvious. This defect will seriously affect the identification effect of urban functional areas. The second category is a method that takes into account the spatial combination characteristics of POIs, such as drawing on topic models, spatial context association models, etc., to establish spatial combination rules for various types of POIs, and identify the main functions of the region through the spatial combination and quantity scale of different POIs. This type of method makes up for the defect of ignoring spatial combination characteristics in the method based on POI quantity statistical information, but it treats each POI equally in the analysis process. In fact, the geographical landmarks represented by different POI individuals have obvious differences in their impact on urban functions, resulting in the identification results of the main functions of the region being inconsistent with the actual situation. Summary of the invention

[0005] Purpose of the invention: The purpose of the present invention is to provide a method, system, device and storage medium for identifying urban functional areas based on spatial co-location patterns with high recognition accuracy and avoiding misjudgment.

[0006] Technical solution: A method for identifying urban functional areas based on spatial co-location patterns, comprising the following steps:

[0007] (1) Collecting POI data of the target area, collecting non-linear feature annotations on public maps at a scale that can display the block plots in the target area, and marking the non-linear feature annotations as primary annotations;

[0008] (2) Retrieve and match the corresponding POIs using the main annotations, and set the matched POIs as core POIs;

[0009] (3) Collect and process the road network data of the target area, and use the road network data to divide the target area into several blocks;

[0010] (4) Reclassify POIs according to urban functions and establish a mapping relationship between POIs and urban functions;

[0011] (5) Mining frequent spatial co-location patterns of POIs based on spatial co-location patterns;

[0012] (6) Based on the frequent spatial co-location patterns of POIs, the spatial co-location pattern combinations of core POIs based on block plots are mined, and the mapping relationship between POIs and urban functions is updated;

[0013] (7) Identify the urban functions of the block plots based on the spatial co-location pattern combination of POIs and the mapping relationship between POIs and urban functions.

[0014] Specifically, step (5) includes:

[0015] (51) Define the POI spatial feature set F = {f1,f2,…,f n}, the spatial feature f in F i Corresponding to a type of POI;

[0016] (52) Define the spatial co-location pattern of POIs. The k-order spatial co-location pattern is a set of k POI types c = {f1, f2, …, f k},and

[0017] (53) Define row instances and table instances. For the spatial co-location pattern c in the target region R, row instance I = {o1, o2, …, o k} contains all spatial features in c, and the subset of I does not contain all spatial features in c, any instance o in I i With o j The Euclidean distance between them is less than the threshold of spatial proximity relationship; the set of all row instances constitutes the table instance RT(R,c) of the spatial co-location pattern c in the target region R;

[0018] (54) Take any instance o in the table instance RT(R,c) iIt is defined as a participating instance of the spatial co-location pattern c in the target region R, and the spatial feature f contained in the spatial co-location pattern c in the target region R is i The set of all different participating instances of is denoted as CP(R,fi,c);

[0019] (55) Given a frequent pattern d in the target region R, define the participation rate of the spatial feature fi contained in the frequent pattern d:

[0020]

[0021] Where: RPR(R,f i ,d) is the participation rate of fi, S i is the instance set of spatial features fi appearing in the target region R;

[0022] The participation index of frequent pattern d is defined as the minimum participation rate of all spatial features fi contained in frequent pattern d; if the participation index of frequent pattern d is greater than or equal to the set threshold, then frequent pattern d is a frequent spatial co-location pattern in the target region R.

[0023] Preferably, the spatial co-location pattern is a second-order spatial co-location pattern.

[0024] Preferably, the setting threshold of the participation index of the frequent pattern d is greater than or equal to 0.5.

[0025] Specifically, step (6) includes:

[0026] (61) according to the frequent spatial co-location patterns obtained in step (5), taking the block as a unit, extracting all frequent spatial co-location pattern instances containing the core POI;

[0027] (62) Define the mapping relationship between the frequent spatial co-location pattern of the core POI and the urban function, and update the mapping relationship between all POIs and urban functions in the frequent spatial co-location pattern, so that the mapping relationship between all POIs and urban functions in the same frequent spatial co-location pattern is consistent with that of the core POI.

[0028] Specifically, step (7) includes:

[0029] Based on the mapping relationship between POI and urban functions determined in step (6), the number of POIs carrying the mapping relationship of different urban functions is calculated based on the block plot as the unit, and the proportion of the number of POIs in the unit is calculated as RPF. i , if RPF i If it is greater than or equal to the set threshold, the city function of the unit is determined by RPF. i OK: When there is only 1 RPF in the unit iIf the frequent spatial co-location pattern is greater than or equal to the set threshold, the unit is marked as the urban functional area mapped by the core POI of the frequent spatial co-location pattern; when there are more than one RPF in the unit i For frequent spatial co-location patterns that are greater than or equal to a set threshold, the unit is marked as a mixed urban function area according to the urban functions mapped by the core POIs of the corresponding multiple frequent spatial co-location patterns;

[0030] If there is no RPF in the unit i Frequent spatial co-location patterns that are greater than or equal to the set threshold are used to mark the urban functions of the area based on the frequency density and type ratio of each POI in the unit.

[0031] Specifically, the frequency density and type ratio of each POI are calculated as follows:

[0032]

[0033] Where: i represents the POI type; n i is the number of POIs of the i-th type in the unit; N i is the total number of POIs of the i-th type; FP i is the frequency density of the ith type of POI in the total number of POIs of this type; CP i is the type ratio, which represents the ratio of the frequency density of the i-th type of POI to the frequency density of all types of POIs in the unit;

[0034] When the type ratio CP i When it is greater than or equal to the set threshold, the urban function labeling unit mapped by the POI of the i-th type is taken as the corresponding urban function area, otherwise the labeling unit is a mixed urban function area.

[0035] The present invention also provides an urban functional area identification system based on spatial co-location patterns, comprising:

[0036] Data collection module: used to collect POI data of the target area, collect non-linear feature annotations on the public map under the condition of a scale that can display the block plots in the target area, and mark the non-linear feature annotations as main annotations;

[0037] Core POI marking module: used to retrieve and match the corresponding POI using the main annotations, and set the matched POI as the core POI;

[0038] Area division module: used to collect and process the road network data of the target area, and use the road network data to divide the target area into several blocks;

[0039] Mapping establishment module: used to reclassify POIs according to urban functions and establish a mapping relationship between POIs and urban functions;

[0040] Frequent spatial co-location pattern mining module: used to mine frequent spatial co-location patterns of POIs based on spatial co-location patterns;

[0041] Mapping update module: used to mine the spatial co-location pattern combination of core POIs based on block plots according to the frequent spatial co-location patterns of POIs, and update the mapping relationship between POIs and urban functions;

[0042] Urban functional area identification module: used to identify the urban functions of block plots based on the spatial co-location pattern combination of POIs and the mapping relationship between POIs and urban functions.

[0043] The present invention also provides a device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned urban functional area identification method when executing the computer program.

[0044] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned urban functional area identification method are implemented.

[0045] Beneficial effects: Compared with the prior art, the significant effects of the present invention are: the present invention quantitatively analyzes the differences between different types of POIs in identifying urban functional areas, mines the frequent spatial co-location patterns of POIs, marks the core POIs corresponding to the non-linear feature annotations, and identifies urban functional areas based on the frequent spatial co-location patterns of the core POIs, thereby improving the accuracy of identification and avoiding the misjudgment of the type of urban functional areas caused by indiscriminate treatment of POIs during identification. At the same time, the present invention uses road network data to divide block plots. Compared with the urban functional area identification and division method based on grid units, the identification results obtained are more consistent with the boundaries of the spatial layout of urban functional areas, which is conducive to better serving urban planning and development decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of the method of embodiment 1 of the present invention.

[0047] Figure 2 This is a POI distribution map of the target area in Example 2 of the present invention.

[0048] Figure 3 This is a comparison diagram before and after the target area is divided in Example 2 of the present invention.

[0049] Figure 4 This is a diagram showing the result of the urban functional area division according to Example 2 of the present invention. DETAILED DESCRIPTION

[0050] The present invention is further described below in conjunction with the accompanying drawings.

[0051] Example 1

[0052] See also Figure 1 As shown, this embodiment provides a method for identifying urban functional areas based on spatial co-location patterns, comprising the following steps:

[0053] (1) Collect POI data of the target area, collect non-linear feature annotations on public maps at a scale that can display the block plots in the target area, and mark the non-linear feature annotations as primary annotations.

[0054] In the present invention, the target area is the urban area to be studied, the non-linear feature annotation is the feature annotation other than the traffic roads, and each non-linear feature annotation can correspond to a POI.

[0055] (2) Use the main annotations to retrieve and match the corresponding POIs, and set the matched POIs as core POIs. In this way, POIs with clear functions can be screened out.

[0056] (3) Collect and process the road network data of the target area, and use the road network data to divide the target area into several blocks.

[0057] (4) Reclassify POIs according to urban functions and establish a mapping relationship between POIs and urban functions. The classification is based on the "Guidelines for Classification of Land and Sea Use for National Land Space Survey, Planning, and Use Control" issued by the Ministry of Natural Resources of China. The various land use classifications related to the city correspond to various urban functions, and the urban functional areas are divided into six types: residential areas, commercial areas, industrial and mining storage and logistics areas, public management and service areas, and green space ecological areas. The specific classification results are shown in Table 1 below.

[0058] Table 1

[0059]

[0060] (5) Mining frequent spatial co-location patterns of POIs based on spatial co-location patterns includes the following sub-steps:

[0061] (51) Define the POI spatial feature set F = {f1,f2,…,f n}, the POI spatial feature set F represents the set of different POI types in the space, and the spatial feature f in F i Corresponding to a type of POI;

[0062] (52) Define the spatial co-location pattern of POIs. The k-order spatial co-location pattern is a set of k POI types c = {f1, f2, …, f k},and Usually the 2nd-order spatial co-location pattern is selected;

[0063] (53) Define row instances and table instances. For the spatial co-location pattern c in the target region R, row instance I = {o1, o2, …, o k} contains all spatial features in c, and the subset of I does not contain all spatial features in c, any instance o in I i With o j The Euclidean distance between them is less than the threshold of spatial proximity, which can also be said that instance o i With o j Satisfy the core adjacency relationship; the set of all row instances constitutes the table instance RT(R,c) of the spatial co-location pattern c in the target region R;

[0064] (54) Take any instance o in the table instance RT(R,c) i It is defined as a participating instance of the spatial co-location pattern c in the target region R, and the spatial feature f contained in the spatial co-location pattern c in the target region R is i The set of all different participating instances of is denoted as CP(R,fi,c);

[0065] (55) Given a frequent pattern d in the target region R, define the participation rate of the spatial feature fi contained in the frequent pattern d:

[0066]

[0067] Where: RPR(R,f i ,d) is the participation rate of fi, S i is the instance set of spatial features fi appearing in the target region R;

[0068] The participation index of a frequent pattern d is defined as the minimum participation rate RPI(R,c) of all spatial features fi contained in the frequent pattern d:

[0069]

[0070] Given a participation index threshold min_cprev, if the participation index RPI(R,c) of frequent pattern d ≥ min_cprev, then frequent pattern d is a frequent spatial co-location pattern in the target region R. Generally speaking, min_cprev ≥ 0.5.

[0071] (6) Based on the frequent spatial co-location patterns obtained in step (5), all frequent spatial co-location pattern instances containing core POIs are extracted with block plots as units; the mapping relationship between the frequent spatial co-location patterns of core POIs and urban functions is defined, and the mapping relationship between all POIs and urban functions in the frequent spatial co-location patterns is updated, so that the mapping relationship between all POIs and urban functions in the same frequent spatial co-location pattern is consistent with that of its core POI.

[0072] (7) Identify the urban functions of the block plots based on the spatial co-location pattern combination of POIs and the mapping relationship between POIs and urban functions.

[0073] Based on the mapping relationship between POI and urban functions determined in step (6), the number of POIs carrying the mapping relationship of different urban functions is calculated based on the block plot as the unit, and the proportion of the number of POIs in the unit is calculated as RPF. i , if RPF i If it is greater than or equal to the set threshold, the city function of the unit is determined by RPF. i OK: When there is only 1 RPF in the unit i If the frequent spatial co-location pattern is greater than or equal to the set threshold, the unit is marked as the urban functional area mapped by the core POI of the frequent spatial co-location pattern; when there are more than one RPF in the unit i For frequent spatial co-location patterns that are greater than or equal to a set threshold, the unit is marked as a mixed urban function area according to the urban functions mapped by the core POIs of the corresponding multiple frequent spatial co-location patterns;

[0074] If there is no RPF in the unit i Frequent spatial co-location patterns that are greater than or equal to the set threshold are used to mark the urban functions of the area based on the frequency density and type ratio of each POI in the unit.

[0075] The frequency density and type ratio of each POI are calculated as follows:

[0076]

[0077] Where: i represents the POI type; n i is the number of POIs of the i-th type in the unit; N i is the total number of POIs of the i-th type; FP i is the frequency density of the ith type of POI in the total number of POIs of this type; CP i is the type ratio, which represents the ratio of the frequency density of the i-th type of POI to the frequency density of all types of POIs in the unit;

[0078] When the type ratio CP i When it is greater than or equal to the set threshold, the urban function labeling unit mapped by the POI of the i-th type is the corresponding urban function area, otherwise the labeling unit is a mixed urban function area. The set threshold is generally 0.5.

[0079] Example 2

[0080] This embodiment takes the main urban area of ​​a city as an example to specifically illustrate the urban functional area identification method based on the spatial co-location pattern described in Example 1:

[0081] (1) Taking the main urban area of ​​a city as the target area for implementing this method, the POI data and main annotations of the public map in the target area are collected.

[0082] (2) Use the main annotations to retrieve and match related POIs, and set the matched POIs as core POIs. Figure 2 As shown, a distribution map of core POIs and common POIs (POIs other than core POIs) is obtained.

[0083] (3) Collect and process the road network data of the target area, and use the road network data to divide the target area into several blocks. Figure 3 As shown, Figure 3 a is a road network map in a target area obtained through a public map, Figure 3 b is the block plot map constructed after fuzzy simplification of the road network data.

[0084] (4) Reclassify POIs according to city functions and establish a mapping relationship between POIs and city functions. The classification method described in step (4) of Example 1 is used to establish a mapping relationship between POIs and city functions.

[0085] (5) Mining frequent spatial co-location patterns of POIs based on spatial co-location patterns. In this embodiment, the distance threshold of the spatial proximity relationship is set to 800m, and the participation index threshold is set to 0.6. Using the above parameters and the method described in step (5) of Example 1, the frequent spatial co-location patterns of POIs in the target area are calculated and obtained.

[0086] (6) Based on the frequent spatial co-location patterns obtained in step (5), all frequent spatial co-location pattern instances containing core POIs are extracted with block plots as units; the mapping relationship between the frequent spatial co-location patterns of core POIs and urban functions is defined, and the mapping relationship between all POIs and urban functions in the frequent spatial co-location patterns is updated, so that the mapping relationship between all POIs and urban functions in the same frequent spatial co-location pattern is consistent with that of its core POI.

[0087] (7) According to the spatial co-location pattern combination of POIs and the mapping relationship between POIs and urban functions, the urban functions of the block plots are identified, and the urban function zone division result of the target area of ​​this embodiment is obtained by using the method described in step (7) of Example 1. Please refer to Figure 4 As shown in the figure, the target area is finally divided into commercial area, residential area, industrial storage area, public cultural and educational service area, green ecological area, mixed functional area, area to be developed and water area. The urban functional area division result has clear boundaries and clear functions, which avoids the error in urban functional area identification caused by taking the same treatment for all POIs and improves the accuracy of urban functional area identification and division.

[0088] Example 3

[0089] This embodiment provides an urban functional area identification system corresponding to the urban functional area identification method based on spatial co-location pattern provided in Embodiment 1, including:

[0090] Data collection module: used to collect POI data of the target area, collect non-linear feature annotations on the public map under the condition of a scale that can display the block plots in the target area, and mark the non-linear feature annotations as main annotations;

[0091] Core POI marking module: used to retrieve and match the corresponding POI using the main annotations, and set the matched POI as the core POI;

[0092] Area division module: used to collect and process the road network data of the target area, and use the road network data to divide the target area into several blocks;

[0093] Mapping establishment module: used to reclassify POIs according to urban functions and establish a mapping relationship between POIs and urban functions;

[0094] Frequent spatial co-location pattern mining module: used to mine frequent spatial co-location patterns of POIs based on spatial co-location patterns;

[0095] Mapping update module: used to mine the spatial co-location pattern combination of core POIs based on block plots according to the frequent spatial co-location patterns of POIs, and update the mapping relationship between POIs and urban functions;

[0096] Urban functional area identification module: used to identify the urban functions of block plots based on the spatial co-location pattern combination of POIs and the mapping relationship between POIs and urban functions.

[0097] This embodiment also provides a device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the urban functional area identification method of embodiment 1 are implemented.

[0098] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the urban functional area identification method of embodiment 1 are implemented.

Claims

1. A method for identifying urban functional areas based on spatial co-location patterns, characterized in that: The following steps are involved: (1) Collecting POI data of the target area, collecting non-linear feature annotations on public maps at a scale that can display the block plots in the target area, and marking the non-linear feature annotations as primary annotations; (2) Retrieve and match the corresponding POIs using the main annotations, and set the matched POIs as core POIs; (3) Collect and process the road network data of the target area, and use the road network data to divide the target area into several blocks; (4) Reclassify POIs according to urban functions and establish a mapping relationship between POIs and urban functions; (5) Mining frequent spatial co-location patterns of POIs based on spatial co-location patterns; (6) Based on the frequent spatial co-location patterns of POIs, the spatial co-location pattern combinations of core POIs based on block plots are mined, and the mapping relationship between POIs and urban functions is updated; (7) Identify the urban functions of the block plots based on the spatial co-location pattern combination of POIs and the mapping relationship between POIs and urban functions.

2. The method for identifying urban functional areas according to claim 1, characterized in that: The step (5) comprises: (51) Define the POI spatial feature set F = {f1,f2,…,f n }, the spatial feature f in F i Corresponding to a type of POI; (52) Define the spatial co-location pattern of POIs. The k-order spatial co-location pattern is a set of k POI types c = {f1, f2, …, f k },and (53) Define row instances and table instances. For the spatial co-location pattern c in the target region R, row instance I = {o1, o2, …, o k } contains all spatial features in c, and the subset of I does not contain all spatial features in c, any instance o in I i With o j The Euclidean distance between them is less than the threshold of spatial proximity relationship; the set of all row instances constitutes the table instance RT(R,c) of the spatial co-location pattern c in the target region R; (54) Take any instance o in the table instance RT(R,c) i It is defined as a participating instance of the spatial co-location pattern c in the target region R, and the spatial feature f contained in the spatial co-location pattern c in the target region R is i The set of all different participating instances of is denoted as CP(R,fi,c); (55) Given a frequent pattern d in the target region R, define the participation rate of the spatial feature fi contained in the frequent pattern d: Where: RPR(R,f i ,d) is the participation rate of fi, S i is the instance set of spatial features fi appearing in the target region R; The participation index of frequent pattern d is defined as the minimum participation rate of all spatial features fi contained in frequent pattern d; if the participation index of frequent pattern d is greater than or equal to the set threshold, then frequent pattern d is a frequent spatial co-location pattern in the target region R.

3. The method for identifying urban functional areas according to claim 1, characterized in that: The spatial co-location pattern is a second-order spatial co-location pattern.

4. The method for identifying urban functional areas according to claim 2, characterized in that: The set threshold of the participation index of the frequent pattern d is greater than or equal to 0.

5.

5. The method for identifying urban functional areas according to claim 1, characterized in that: The step (6) comprises: (61) according to the frequent spatial co-location patterns obtained in step (5), taking the block as a unit, extracting all frequent spatial co-location pattern instances containing the core POI; (62) Define the mapping relationship between the frequent spatial co-location pattern of the core POI and the urban function, and update the mapping relationship between all POIs and urban functions in the frequent spatial co-location pattern, so that the mapping relationship between all POIs and urban functions in the same frequent spatial co-location pattern is consistent with that of the core POI.

6. The method for identifying urban functional areas according to claim 1, characterized in that: The step (7) comprises: Based on the mapping relationship between POI and urban functions determined in step (6), the number of POIs carrying the mapping relationship of different urban functions is calculated based on the block plot as the unit, and the proportion of the number of POIs in the unit is calculated as RPF. i , if RPF i If it is greater than or equal to the set threshold, the city function of the unit is determined by RPF. i OK: When there is only 1 RPF in the unit i If the frequent spatial co-location pattern is greater than or equal to the set threshold, the unit is marked as the urban functional area mapped by the core POI of the frequent spatial co-location pattern; when there are more than one RPF in the unit i For frequent spatial co-location patterns that are greater than or equal to a set threshold, the unit is marked as a mixed urban function area according to the urban functions mapped by the core POIs of the corresponding multiple frequent spatial co-location patterns; If there is no RPF in the unit i Frequent spatial co-location patterns that are greater than or equal to the set threshold are used to mark the urban functions of the area based on the frequency density and type ratio of each POI in the unit.

7. The method for identifying urban functional areas according to claim 6, characterized in that: In step (7), based on the frequency density and type ratio of each POI in the unit, the urban functions of the marked area include: Calculate the frequency density and type ratio of each POI: Where: i represents the POI type; n i is the number of POIs of the i-th type in the unit; N i is the total number of POIs of the i-th type; FP i is the frequency density of the i-th type of POI in the total number of POIs of this type; CP i is the type ratio, which represents the ratio of the frequency density of the i-th type of POI to the frequency density of all types of POIs in the unit; When the type ratio CP i When it is greater than or equal to the set threshold, the urban function labeling unit mapped by the POI of the i-th type is taken as the corresponding urban function area, otherwise the labeling unit is a mixed urban function area.

8. A system for identifying urban functional areas based on spatial co-location patterns, characterized in that: include: Data collection module: used to collect POI data of the target area, collect non-linear feature annotations on the public map under the condition of a scale that can display the block plots in the target area, and mark the non-linear feature annotations as main annotations; Core POI marking module: used to retrieve and match the corresponding POI using the main annotations, and set the matched POI as the core POI; Area division module: used to collect and process the road network data of the target area, and use the road network data to divide the target area into several blocks; Mapping establishment module: used to reclassify POIs according to city functions and establish a mapping relationship between POIs and city functions; Frequent spatial co-location pattern mining module: used to mine frequent spatial co-location patterns of POIs based on spatial co-location patterns; Mapping update module: used to mine the spatial co-location pattern combination of core POIs based on block plots according to the frequent spatial co-location patterns of POIs, and update the mapping relationship between POIs and urban functions; Urban functional area identification module: used to identify the urban functions of block plots based on the spatial co-location pattern combination of POIs and the mapping relationship between POIs and urban functions.

9. A device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. 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 the method according to any one of claims 1 to 7 are implemented.

Images