A method for identifying the layout and value density of "three-dimensional space" of urban agglomeration and metropolitan area based on the "land-industry-person" composite perspective

Abstract

A method for identifying the layout and value density of "three-life spaces" in urban agglomerations and metropolitan areas based on a "land-industry-people" composite perspective is proposed. Building upon spatial use classification, this method considers the coupling of human activities with space and identifies composite spaces by combining land use space with the distribution of employed and residential populations. Due to the complexity of the geographical environment, the diversity of evaluation units at the macro scale, and regional differences, the final classification results of the evaluation units include five composite functional spaces in addition to three single-function types: living-production composite space, production-living composite space, ecology-living composite space, ecology-production composite space, and three-life composite space. This method is more accurate and practical than traditional three-life space analysis and provides precise judgment on the density of activity spaces.

Description

Technical Field

[0001] This invention belongs to the field of urban planning and design technology, and specifically relates to a method for identifying the layout and value density of "three-life spaces" in urban agglomerations and metropolitan areas from a composite perspective of "land-industry-people". Background Technology

[0002] "Three-dimensional space" refers to three different types of space: production space, living space, and ecological space. These three types of space together constitute the main elements of urban space. They are independent of each other but also interconnected, exhibiting symbiotic integration and constraint effects.

[0003] Production space mainly refers to the land space used for production and business activities, such as industrial production, logistics warehousing, and commercial business services; living space mainly refers to the land space used for people to live, consume, relax, and entertain, including residential land, public management and service land, and commercial land; ecological space refers to the environmental space required for the survival and reproduction of species in a macroscopically stable state, such as forests, grasslands, wetlands, rivers, and lakes, which are important components for ensuring urban ecological security and improving the quality of life of residents.

[0004] The optimization goal of the "three-dimensional space" is to achieve intensive and efficient production space, livable and moderate living space, and beautiful and pristine ecological space. This requires a scientific and rational layout and overall planning of these three types of spaces in urban planning to promote the high integration and sustainable development of regional ecological protection, economic development, and social construction.

[0005] In urban planning, identifying the layout of the three spaces (life, environment, and ecology) is fundamental to optimizing them. Existing technologies already include some methods for identifying these three spaces.

[0006] For example, Chinese patent application CN202110567216.6 discloses a method for urban three-life space identification and pattern analysis based on multi-source data. This method includes determining a classification system for urban three-life spaces and constructing calculation indicators; acquiring remote sensing image data, POI quantity data, and AOI area data, and performing data processing and indicator calculation; classifying and identifying the three-life spaces based on the processed data, training and generating a three-life space classification model; predicting the three-life types of other spatial units within the entire study area based on the trained model; and conducting three-life space pattern analysis on the study area. This method utilizes multi-source data and employs a random forest method, resulting in more accurate, faster, and more reliable identification. However, this method only uses remote sensing image data, POI quantity data, and AOI for analysis and extraction, without reflecting population activity, which may lead to misjudgments or omissions.

[0007] Chinese patent application CN202310035093.0 discloses a method for identifying the three-life space based on qualitative and quantitative functional evaluation. This method divides the three-life space into three single spaces (production, living, and ecology) and four composite spaces (production-living, production-ecology, living-ecology, and production-living-ecology). The method identifies and classifies the three-life space through four steps: calculating qualitative functional evaluation values, calculating quantitative functional evaluation values, calculating qualitative-quantitative functional evaluation values, and calculating the first-to-last index, and then determining the type of the three-life space. It uses coupling coordination degree to correct imbalanced space types. This method provides a theoretical basis for research on the optimization of national land spatial structure and layout, guides the optimization of national land spatial structure and layout, improves the rationality and scientific nature of resource allocation in national land spatial planning, and promotes the optimized development of national land spatial pattern, thus having practical significance and good application prospects. However, this method only uses 37 types determined by the second-level classification system of the Second National Land Survey for analysis and extraction, and does not reflect population activity, which may lead to misjudgments or omissions.

[0008] Chinese patent application CN202310564712.5 discloses a method for training a refined urban land use type identification model, comprising: dividing a land parcel area into several grids arranged in a square grid; using the land parcel area as a land use identification window; using the central grid of the land use identification window as the land parcel to be identified; using the grids adjacent to the central grid as adjacent land parcels; acquiring feature data for each grid, including point of interest type, land type, population density category, and whether it is located in the central urban area; selecting a land parcel with a known land type as the central land parcel of the land use identification window; using the adjacent land parcels of the central land parcel as samples; using the feature data of the samples as a feature set to construct a sample feature dataset; using the sample feature dataset as model input and the sample label dataset as model output to train the model and obtain an urban land use type identification model. However, this method does not address the case of complex spaces.

[0009] Chinese patent application CN 201910366300.4 discloses a spatial optimization method for "three-life" based on external ecological function positioning. Specifically, it involves a spatial optimization method for "three-life" based on external ecological function positioning, including (1) simulation of the spatial quantity structure of "three-life"; the spatial quantity structure of "three-life" is constructed according to the requirements of national key ecological function zones with the goal of maximizing ecosystem service value, and is obtained through a grey linear programming model; (2) spatial pattern configuration of "three-life"; an MLP-CA model is constructed by combining multilayer neural networks and cellular automata; the model includes two main modules, namely a training module and a simulation module; in the training module, the trained network is used to automatically obtain internal conversion rules, and external conversion rules are superimposed, and then these conversion rules are input into the simulation module to complete the spatial simulation operation process of "three-life". This scheme highlights the spatial optimization of "three-life" under ecological function positioning and realizes the synchronization of spatial quantity simulation and pattern configuration of "three-life", but it does not involve the case of composite space.

[0010] Existing three-dimensional space identification methods have problems such as not reflecting population activities and not considering composite spaces, which make it impossible to comprehensively and accurately identify urban land use types, resulting in misjudgments or omissions. Summary of the Invention

[0011] To address the problems existing in the prior art, this invention, based on functional space identification, further incorporates population big data and proposes a method that, in addition to spatial utilization classification, considers the coupling between human activities and space. By combining land use space with the distribution of employed and resident populations, composite spaces are identified. Due to the complexity of the geographical environment, the diversity of evaluation units at the macro scale, and regional differences, the final classification results of the evaluation units include not only three single-function types but also five composite functional spaces: living-production composite space, production-living composite space, ecological-living composite space, ecological-production composite space, and three-life composite space.

[0012] This invention provides a method for identifying the layout and value density of "three-life spaces" in urban agglomerations and metropolitan areas from a composite perspective of "land-industry-people," comprising the following steps:

[0013] Collect relevant data within the area to be identified, including remote sensing image data, POI data, AOI data, and LBS data, and construct a database;

[0014] The area to be identified is divided into a grid of a set size;

[0015] Based on the remote sensing image data, the proportion of construction land area in each grid of the area to be identified is calculated, and grids with a construction land area proportion of more than 20% are identified as construction land grids, and the rest are identified as ecological grids.

[0016] Based on the AOI data, the area ratio of production space and living space in the construction land grid is identified, and the grid with a production or living space area ratio of more than 70% is regarded as production space or living space; the remaining grids are composite grids, and the type with the dominant area ratio is regarded as the dominant space, namely, production-living composite space or living-production composite space.

[0017] For the construction land grids not identified by AOI, based on the POI data, the production or living space weight of each grid is calculated, and the grid is determined to be a production space or a living space.

[0018] Based on LBS data, further functional identification is performed on ecological grids and production or living spaces obtained from POI data.

[0019] Furthermore, in the remote sensing image data, urban and rural settlements and industrial and transportation construction land are classified as construction land, while the rest are classified as ecological space land.

[0020] Furthermore, in the AOI data, industrial parks, office buildings, and government agencies are classified as production space land, while the rest are classified as living space land.

[0021] Furthermore, based on the AHP method, the POI data is assigned weights for living and / or production factors according to each secondary category, and a weighted summation is performed for each grid to obtain the cumulative proportion of living and / or production scores for each grid. The dominant function and type of the grid are then determined based on this cumulative proportion of living and / or production scores. For each grid unit, the above calculation method can be expressed by the following formula:

[0022] ,

[0023] in, The cumulative percentage of life score, The cumulative percentage of production score is represented by T, where T is the grid cell, P is the score for living space function type in POI data, and L is the score for production space function type in POI data.

[0024] Furthermore, the cumulative percentage of the calculated living scores for each grid was analyzed. ,if If the percentage is greater than 50%, the grid cell is considered a living space cell; this is based on the calculated cumulative percentage of production scores for each grid cell. ,if If the percentage is greater than 50%, then the grid cell is a production space cell.

[0025] Furthermore, based on LBS big data, the number of employed and / or resident populations in each grid of the area to be identified is counted; grids with significant, moderate, and insignificant activity of employed and / or resident populations are identified.

[0026] Calculate the ratio of employed population to resident population for each grid within the area to be identified. If the ratio of employed population to resident population is higher than the average ratio for the entire area, the grid is considered to have a production attribute; otherwise, it is considered to have a living attribute. Further determine whether there are significant production and / or living activities in the grid, and whether the activity type is consistent with the production and / or living attribute. If they are consistent, the original classification is maintained; if they are inconsistent, it is a composite space.

[0027] The ecological, production, and living attributes of each grid identified based on remote sensing image data, AOI, and / or POI are overlaid with the spatial attributes identified based on LBS big data to obtain the final functional identification results of each grid.

[0028] Furthermore, based on data on intercity commuting of the population and intercity headquarters branches of enterprises, the value density of each grid in the area to be identified is determined; wherein, the higher the number of intercity commuting of the population and intercity headquarters branches of enterprises in a grid, the higher the value of the living or production function attributes under the development of the metropolitan area and urban agglomeration it provides services.

[0029] The layout recognition method for the three-dimensional space provided by this invention achieves the following technical effects compared to the prior art:

[0030] 1. Incorporating the impact of human activities on spatial characteristics enhances scientific rigor. This invention utilizes remote sensing imagery, AOI, POI, population, and industrial and commercial enterprise data to form a relatively complete database. By analyzing land use, spatial functions, and the nature of population activities, it achieves precise spatial positioning; it quantifies composite land use functions and land use spatial descriptions, and graphically represents spatial locations.

[0031] 2. To improve the precision of grid spatial identification and measurement, this invention uses a 500m grid as the basic spatial unit for research, which improves the precision compared to using districts, counties, towns, etc.

[0032] 3. The spatial density identification of activities related to life, production, and ecology is performed. Since it is based on the cumulative analysis of multi-source data and the statistics of multiple elements and the number of active population, the method described in this invention is more accurate and practical than the existing spatial analysis of life, production, and ecology, and can accurately identify the spatial density of activities.

[0033] 4. To assess the value of the three-dimensional functional space in promoting and supporting the development of metropolitan areas and urban clusters, since the method described in this invention takes into account cross-city commuting and cross-city headquarters branches of enterprises, the functional value provided by the grid in the development of metropolitan areas and urban clusters can be measured. Attached Figure Description

[0034] To gain a more complete understanding of the invention, reference will now be made to the following description taken in conjunction with the accompanying drawings, wherein:

[0035] Figure 1 This is a schematic diagram of the technical route for the method of identifying the spatial layout of urban agglomerations and metropolitan areas based on the composite perspective of "land-industry-people" as described in this invention.

[0036] Figure 2 This is a schematic diagram of the technology path for land use spatial identification based on AOI and POI data;

[0037] Figure 3 This is a schematic diagram of the three-life space identification technology path based on population spatiotemporal data;

[0038] Figure 4 This is a schematic diagram illustrating the identification results of the three-life space of a certain metropolitan area based on the method described in this invention;

[0039] Figure 5 This is a schematic diagram illustrating the identification results of a three-dimensional composite space in a certain urban agglomeration based on the method described in this invention. Detailed Implementation

[0040] To clearly illustrate the purpose, technical details, and effective applications of this invention, and to facilitate understanding and implementation by those skilled in the art, a further detailed description will be provided below in conjunction with the embodiments and accompanying drawings. Obviously, the embodiments described herein are for illustrative and explanatory purposes only and are not intended to limit the scope of the invention.

[0041] This invention provides a method for identifying the layout and value density of "three-life spaces" in urban agglomerations and metropolitan areas from a composite perspective of "land-industry-people," as shown in the attached figures of the specification. Figure 1 As shown, it includes the following steps:

[0042] Step S01: Collect relevant data within the area to be identified, including remote sensing image data, POI data, AOI data, population data, and industrial and commercial enterprise data, and construct a database.

[0043] Collect relevant data for the area to be identified, including remote sensing image data, points of interest (POI) data, areas of interest (AOI) data, population data, and business data.

[0044] Specifically, the remote sensing image data includes 25 secondary land categories, as shown in the table below.

[0045]

[0046] The POI data selected by this invention comprises 13 secondary categories with distinct functional characteristics, including catering, public facilities, companies and enterprises, transportation and warehousing, education and culture, finance and insurance, residential services, scientific and technological services, wholesale and retail, commercial facilities and services, health and social security, sports and leisure, and accommodation.

[0047] The AOI data has six secondary categories, including residential areas, industrial parks, office buildings, government agencies, general hospitals, and educational and training venues.

[0048] The population data includes specific attributes such as the number of residents, the number of working people, the number of origin-destination (OD) points, and population commuting within the area to be identified.

[0049] The specific attributes of the industrial and commercial enterprise data include the enterprise's latitude and longitude, enterprise type, and headquarters and branches.

[0050] Step S02: Identify the construction land space and non-construction land space in the area to be identified.

[0051] Specifically, it includes the following steps:

[0052] Step S201: Establish a grid within the area to be identified.

[0053] For example, a 500m × 500m grid can be established within the area to be identified.

[0054] Step S202: Reclassify the 25 secondary land use categories in the remote sensing image data according to construction land and ecological space land. Urban and rural residential areas and industrial and transportation construction land are classified as construction land, while the rest are classified as ecological space land. See the table below for details.

[0055]

[0056] Step S203: Calculate the proportion of construction land area in each grid based on remote sensing image data, and extract the grids in the 500m × 500m grid where the proportion of construction land area exceeds 20% as construction land space.

[0057] Thus, the area to be identified is divided into a construction land grid and a non-construction land grid (ecological grid).

[0058] Step S03: Determine the production and living attributes of the construction land space obtained in step S02.

[0059] Specifically, see Figure 2 After identifying the construction land and non-construction land spaces in the area to be identified based on the China Land Use / Land Cover Remote Sensing Monitoring Database (LUCC), the production and living attributes of the identified construction land spaces are further identified based on AOI and POI data. Specifically, this includes the following steps:

[0060] Step S301: Reclassify the AOI data into production space and living space, calculate the proportion of AOI in the construction land space, and determine the production space and living space of the construction land space.

[0061] The AOI data has six secondary categories; these six secondary categories are then reclassified into production and daily life categories, as shown in the table below.

[0062]

[0063] First, determine whether the total area of ​​the reclassified AOI data type within the grid exceeds 70%. If it does, the composite case is disregarded. That is, the grid is classified as either production or living space. For example, if the combined area of ​​an industrial park and office buildings within the grid exceeds 70% of the total construction land area, the grid is directly classified as production space.

[0064] Secondly, in other cases, the type with the largest area proportion dominates as the dominant space. Based on the AOI data type proportion results after reclassification, we can determine whether the proportion of residential or production attributes is higher, and then determine the nature of the grid, i.e., a production-residential composite space or a residential-production composite space.

[0065] Since the coverage of AOI data within the area to be identified is not high, this step can only complete the attribute judgment for part of the grid construction so far.

[0066] Step S302: Reclassify POI data into production and living categories. For construction grids not identified by AOIs, count the number of POIs of each type and determine the dominant function and type of spatial units to achieve functional space identification of the three-life space. The POI data contains 13 secondary categories; these 13 secondary categories are reclassified into production and living categories, primarily based on the production and living weight allocation according to the POI functional attributes, as detailed in the table below:

[0067]

[0068] Based on the AHP method, weights are assigned to the "three functions" elements of each secondary category of the POI data. The standardized "three functions" elements are then weighted and synthesized to obtain the scores of each "living and production function" within a 500m × 500m grid space unit. Based on the cumulative proportion of living and production scores within the space unit, the dominant function and type of the space unit are determined, thereby realizing the functional space identification of the three functions space.

[0069] The above calculation method can be expressed by the following formula:

[0070]

[0071] in, The score represents the percentage of the living space score, T represents the spatial unit, P represents the dominant score of the living space function type, and L represents the dominant score of the production space function type.

[0072] The score percentage of each grid cell is calculated based on the above formula. If the result is greater than 50%, then the grid cell is a living space cell.

[0073]

[0074] in, The score represents the percentage of production items, T represents spatial units, P represents the dominant score for living space function type, and L represents the dominant score for production space function type.

[0075] The score percentage of each grid cell is calculated based on the above formula. If the result is greater than 50%, then the grid cell is a production space cell.

[0076] For the remaining cases, if there is no POI element, that is, the denominator of the grid cell in the above calculation formula is zero, then it is determined whether the grid cell is located in a continuous urban area. If so, it is a production space; otherwise, it is considered a living space.

[0077] At this point, the residential / production attributes of the construction grid of the area to be identified have been determined.

[0078] Step S04: Based on LBS (Location Based Services) big data, further functional identification is performed on the obtained living, production, and ecological spaces.

[0079] Specifically, see Figure 3 This includes the following steps:

[0080] Step S401: Based on LBS (Location Based Services) big data, count the number of employed and resident people in each cell of the 500m × 500m grid in the area to be identified.

[0081] The total number of employed people and the number of residents within the area to be identified are counted. The average ratio of employed people to residents within the area to be identified is obtained by dividing the total number of employed people by the number of residents.

[0082] After analysis, the top 10% of the high-density grids for employed and residential populations were classified as having significant activity; the bottom 10% of the high-density grids for employed and residential populations (mainly grids with fewer than 10 people, usually caused by base station drift) were classified as having insignificant activity and were removed; the rest were classified as having moderate activity.

[0083] Step S402: Calculate the ratio of employed population to residential population for each grid within the area to be identified. If the ratio of employed population to residential population is higher than the average ratio within the entire area, the grid is considered to have production attributes; otherwise, it is considered to have living attributes.

[0084] Step S403: Based on step S402, further determine whether there are significant production or living activities in the grid, and whether the activity type is consistent with the spatial classification. If they are consistent, maintain the original classification; if they are inconsistent, it is a composite space.

[0085] Step S404: Overlay the ecological, production, and living attributes of each grid identified in step S03 with the spatial attributes identified based on LBS big data to obtain the final functional identification.

[0086] For example, for grids already identified as residential based on Points of Interest (POIs) during construction, overlaying LBS big data-identified spatial attributes may yield either residential space or residential-production space. Residential-production space refers to grids whose primary function is residential, but which also provide workspaces and job opportunities; these typically take the form of office buildings + residences or office buildings + commercial areas.

[0087] For grids already identified as production areas based on Points of Interest (POIs) during construction, overlaying spatial attributes identified by LBS big data can potentially create production spaces or production-living spaces. Production-living spaces, where the grid's function is primarily production-oriented but also provides residential space, typically take the form of factory buildings + dormitories or office buildings + apartments.

[0088] For ecological grids, overlaying spatial attributes identified by LBS big data can yield ecological spaces (grids where production and living activities are not significant), ecological-living spaces, ecological-production spaces, or ecological-production-living composite spaces (grids where both production and living activities are significant). Ecological-living, ecological-production, or ecological-production-living composite spaces mean that these grids are primarily ecological in function but also provide work / residence spaces. These typically take the form of rural housing + farmland, forest land / village / township factories, or agricultural, forestry, animal husbandry, and fishery spaces + farmland, forest land, meadows, etc.

[0089] As shown in the attached diagram of the instruction manual. Figure 4 , 5 As shown in the attached diagram of the instruction manual. Figure 4 This is a schematic diagram of the functional space identification results according to the method of the present invention; Figure 5 This is a schematic diagram of the composite functional space identification results according to the method of the present invention. It can be seen that the method described in this invention incorporates the influence of human activities on spatial characteristics, improving its scientific rigor. This invention uses remote sensing imagery, AOI, POI, population, and industrial and commercial enterprise data to form a relatively complete database. Through analysis of land use, spatial functions, and population activity characteristics, it achieves precise spatial positioning; it quantifies composite land use functions and land use spatial descriptions, and graphically represents spatial locations. Step S05: Based on data on intercity commuting of populations in metropolitan areas and urban clusters, and intercity headquarters and branch data of enterprises, the value density of each composite control grid in the region is identified.

[0090] In cells with living space attributes, such as living space, living-production space, and production-living space, the number of people residing in this grid among commuters crossing city boundaries is counted. In cells with production space attributes, such as production space, living-production space, and production-living space, the number of people working in this grid among commuters crossing city boundaries is counted, as well as the number of headquarters and branch enterprises established across the metropolitan area within this type of grid. Based on the number of residents, working populations, and corporate headquarters and branches, the value of the grid's living and production function attributes in the metropolitan area and urban agglomeration is measured. That is, the higher the number of commuters crossing city boundaries residing in a grid, the higher its value of living function attributes under the development of the service metropolitan area and urban agglomeration. Similarly, the higher the number of commuters crossing city boundaries working in a grid, and the higher the number of cross-city headquarters / city branches under other metropolitan areas or urban agglomerations, the higher its value of production function attributes under the development of the service metropolitan area and urban agglomeration. For example, consider two production space units, T1 and T2, within Dongguan City: In T1, enterprises mainly establish branches within Dongguan City, and their employees mainly reside within Dongguan City; while in T2, enterprises mainly establish branches in Shenzhen and Huizhou, and their employees mainly reside within Shenzhen City. Therefore, it is believed that T2 provides a higher value for its work functions under the development of metropolitan areas and urban clusters.

[0091] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the description of the embodiments above. Therefore, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the system claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. A method for identifying the layout and value density of "three-life spaces" in urban agglomerations and metropolitan areas from a composite perspective of "land-industry-people," comprising the following steps: Collect relevant data within the area to be identified, including remote sensing image data, POI data, AOI data, and LBS data, and construct a database; The area to be identified is divided into a grid of a set size; Based on the remote sensing image data, the proportion of construction land area in each grid of the area to be identified is calculated, and grids with a construction land area proportion of more than 20% are identified as construction land grids, and the rest are identified as ecological grids. Based on the AOI data, the area ratio of production space and living space in the construction land grid is identified, and the grid with a production or living space area ratio of more than 70% is regarded as production space or living space; the remaining grids are composite grids, and the type with the dominant area ratio is regarded as the dominant space, namely, production-living composite space or living-production composite space. For the construction land grids not identified by AOI, based on the POI data, the production or living space weight of each grid is calculated, and the grid is determined to be a production space or a living space. Based on LBS data, further functional identification is performed on ecological grids and production or living spaces obtained from POI data.

2. The method according to claim 1, characterized in that: In the remote sensing image data, urban and rural settlements and industrial and transportation construction land are classified as construction land, while the rest are classified as ecological space land.

3. The method according to claim 1, characterized in that: In the AOI data, industrial parks, office buildings, and government agencies are classified as production space land, while the rest are classified as living space land.

4. The method according to claim 1, characterized in that: Based on the AHP method, the POI data is weighted according to each secondary category, assigning weights to living and / or production factors. Weighted summation is then performed on each grid to obtain the cumulative percentage of living and / or production scores for each grid. This cumulative percentage of living and / or production scores is used to determine the dominant function and type of the grid. For each grid unit, the above calculation method can be expressed by the following formula: ， ； in, The cumulative percentage of life score, The cumulative percentage of production score is represented by T, where T is the grid cell, P is the score for living space function type in POI data, and L is the score for production space function type in POI data.

5. The method according to claim 4, characterized in that: The cumulative percentage of the life score for each grid was calculated. ,if If the percentage is greater than 50%, the grid cell is considered a living space cell; this is based on the calculated cumulative percentage of production scores for each grid cell. ,if If the percentage is greater than 50%, then the grid cell is a production space cell.

6. The method according to claim 1, characterized in that: Based on LBS big data, the number of employed and / or resident populations in each grid of the area to be identified is counted; grids with significant, moderate, and insignificant activity of employed and / or resident populations are identified. Calculate the ratio of employed population to resident population for each grid within the area to be identified. If the ratio of employed population to resident population is higher than the average ratio for the entire area, the grid is considered to have a production attribute; otherwise, it is considered to have a living attribute. Further determine whether there are significant production and / or living activities in the grid, and whether the activity type is consistent with the production and / or living attribute. If they are consistent, the original classification is maintained; if they are inconsistent, it is a composite space. The ecological, production, and living attributes of each grid identified based on remote sensing image data, AOI, and / or POI are overlaid with the spatial attributes identified based on LBS big data to obtain the final functional identification results of each grid.

7. The method according to claim 1, characterized in that: Based on data on intercity commuting of the population and intercity headquarters branches of enterprises, the value density of each grid in the area to be identified is determined. The higher the number of intercity commuting of the population and intercity headquarters branches of enterprises in a grid, the higher the value of the living or production function attributes of the metropolitan area or urban agglomeration it provides services for.

Images