Low-efficiency commercial service land identification method and device based on multi-source data fusion

By preprocessing and spatializing power data and integrating it with POI data, it builds spatial coupling of functional business formats for commercial services, and solves the problem of low accuracy of land identification for inefficient commercial services, and achieves more accurate and real-time recognition effect.

CN119005514APending Publication Date: 2024-11-22CHENGDU PLANING & DESIGNING INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411089795.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The accuracy of land identification for inefficient commercial service industries in the existing technology is low, mainly due to the difficulty of obtaining data in traditional industries and the inaccurate classification of power data, which cannot accurately reflect the output efficiency of land for commercial service industries.

Method used

By acquiring power data for preprocessing and spatialization, combining POI data for multi-source data fusion, building spatial coupling of power data-commercial service land functional business format data, using standard units to select and analyze, identifying inefficient commercial service land.

Benefits of technology

The accuracy of identification of inefficient commercial service land has been improved, making the identification more real-time and accurate, adapted to urban characteristics, and effectively compensate for the lack of traditional data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005514A_ABST
    Figure CN119005514A_ABST
Patent Text Reader

Abstract

The invention discloses a low-efficiency commercial service land identification method based on multi-source data fusion, and relates to the technical field of low-efficiency commercial service land identification, and the method comprises the steps: obtaining the power consumption of a commercial land parcel through the spatialization of power grid data, carrying out the multi-source data fusion through POI data, analyzing the dominant function business state of the commercial service land parcel, and carrying out the recognition of the commercial service land parcel. And then analyzing the theoretical electricity consumption of the corresponding mixed function grid when each function industry is located in the same space grid, and determining the discrimination standard of the land for the low-efficiency commercial service industry, thereby providing a solution for the identification of the land for the low-efficiency commercial service industry, and being capable of effectively improving the identification accuracy of the land for the low-efficiency commercial service industry.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of inefficient commercial service land identification, and in particular to an inefficient commercial land identification method and device based on multi-source data fusion. Background Art

[0002] According to the "Guidelines for Classification of Land and Sea Use for National Land Space Survey, Planning and Use Control", commercial service land refers to land for commercial, business, finance, entertainment and sports facilities. Commercial service facility land is an important spatial carrier for urban public activities and industrial development. At present, the identification of inefficient commercial service land is mainly based on the dimension of economic output. Since traditional industry data such as total retail sales of consumer goods and corporate taxes are confidential and difficult to obtain, inefficient commercial service land is often unable to be obtained due to missing data. Identifying inefficient commercial service land is a basic and key step to improve its utilization efficiency. Therefore, turning to other new industry data and open source data to make up for the shortcomings of traditional industry data is inevitable for identifying inefficient commercial service land.

[0003] Electricity data has the characteristics of large data energy level, multiple data types, high value density and fast processing speed. It can realize self-iteration and real-time update of data through real-time monitoring of the power grid. With the development of the intelligent era, the power system has accumulated a large amount of "big data" of electricity consumption. At present, the State Grid can provide processed electricity consumption records of metering equipment on distribution transformers, and electricity consumption records of paid service providers engaged in commodity exchange or providing commercial, financial and service services. As a barometer of the economy, electricity consumption is also a direct reflection of the output efficiency of commercial service land. The current regulations on commercial service land and power load in commercial building design were formulated by the state many years ago and are reference standards for the configuration of power facilities. In actual applications, there are great differences between cities based on urban environment, seasonal climate, etc., which leads to low accuracy in identifying inefficient commercial service land, and it is necessary to comprehensively identify the actual electricity consumption of local cities. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for identifying inefficient commercial service land based on multi-source data fusion, introduce power data, link the actual power consumption of local urban commercial service land with the functional business format of the commercial service land, and construct a set of power data-commercial service land functional business format data spatial coupling, standard unit selection and analysis to identify inefficient commercial service land by comparing with the average usage value of typical functional business formats. This method provides a reference for exploring the usage rules of commercial service land and solves the technical problem of low accuracy in identifying inefficient commercial service land in the prior art.

[0005] The present invention is achieved through the following technical solutions:

[0006] On the one hand, the present invention provides a method for identifying inefficient commercial service land based on multi-source data fusion, comprising:

[0007] Acquiring power data, and preprocessing the power data to obtain preprocessed power data;

[0008] Based on the pre-processed power data, forward data collection and reverse data spatialization are carried out to realize power data spatialization, obtain power data spatialization results, and realize the transmission connection between grid data and plot data;

[0009] Acquire POI data corresponding to the building, and fuse the power data spatialization result with the POI data corresponding to the building to obtain a multi-source data fusion result;

[0010] Based on the multi-source data fusion results, the theoretical electricity consumption corresponding to each spatial grid is determined, and based on the theoretical electricity consumption corresponding to the spatial grid, the identification results of inefficient commercial service land corresponding to the spatial grid are determined.

[0011] In a possible implementation manner, acquiring power data and preprocessing the power data to obtain preprocessed power data includes:

[0012] Obtaining power data; wherein the power data includes annual total power distribution data, monthly power distribution data, and daily power distribution data of the distribution box;

[0013] Abnormal data and data that do not conform to the actual situation in the power data are eliminated to obtain the pre-processed power data.

[0014] In a possible implementation, based on the pre-processed power data, forward data collection and reverse data spatialization are performed to achieve power data spatialization, and the power data spatialization result is obtained, including:

[0015] Obtaining a research area input by a staff member through human-computer interaction, and dividing the research area into a plurality of spatial grids, each of which has the same size;

[0016] A unique grid code is assigned to each spatial grid using a preset code allocation rule;

[0017] Determine the standard spatial grid where the distribution box is located, and associate the distribution box and the power data corresponding to the distribution box with the grid code to achieve forward data collection and obtain a grid code-power data correspondence table;

[0018] Based on the grid code-power data correspondence table, the land parcel data in the study area are reversely spatialized to obtain the association between the land parcel and the spatial grid, realize the transmission of power data to the spatial grid and then to the land parcel, and obtain the power data spatialization result.

[0019] In a possible implementation, based on the grid code-power data correspondence table, reverse data spatialization is performed on the plot data in the study area, including:

[0020] Spatialize grid data and associate power data according to the grid code-power data correspondence table to achieve the location of power data on the spatial grid;

[0021] The grid boundary is used as the search path, and the circle with a radius of R is used as the convolution window to search the surrounding plots. If a plot is retrieved by a unique spatial grid, the association relationship between the plot and the power data corresponding to the spatial grid is directly established; if a plot is retrieved by multiple spatial grids at the same time, it is recorded in the spatial grid with the largest area coverage, thereby establishing the association relationship between the plot and the power data corresponding to the spatial grid, realizing the transmission of power data to the spatial grid and then to the plot, and obtaining the spatialization result of power data.

[0022] In a possible implementation, POI data corresponding to a building is obtained, and the power data spatialization result is fused with the POI data corresponding to the building to obtain a multi-source data fusion result, including:

[0023] Obtain the POI data corresponding to the building, and determine the electricity consumption function business type corresponding to each plot based on the POI data corresponding to the building;

[0024] According to the spatialization results of the power data and the power consumption function business type corresponding to each plot of land, the power consumption function business type corresponding to each spatial grid is determined to obtain the multi-source data fusion result.

[0025] In a possible implementation, based on the multi-source data fusion result, determining the theoretical power consumption corresponding to each spatial grid includes:

[0026] Based on the multi-source data fusion results, standard spatial grids are screened, in which the building area corresponding to the dominant functional business type of the grid accounts for a commercial service industry building area of ​​the corresponding spatial grid that exceeds a threshold;

[0027] Based on the standard space grid, determine the standard value of electricity consumption per unit building area corresponding to each functional business format;

[0028] According to the standard value of electricity consumption per unit building area and the results of multi-source data fusion, the theoretical electricity consumption corresponding to each spatial grid is determined.

[0029] In a possible implementation, based on the standard space grid, the standard value of electricity consumption per unit building area corresponding to each functional business format is determined, including:

[0030] Determine the dominant functional business format corresponding to the standard space grid, and obtain the target functional business format corresponding to the standard space grid;

[0031] According to the total building area of ​​the standard space grid and the results of multi-source data fusion, the standard value of electricity consumption per unit building area corresponding to the target functional business type is determined as follows:

[0032]

[0033] Where I represents the standard value of electricity consumption per unit building area corresponding to the target functional business format, λ Y represents the annual total power distribution data corresponding to the standard spatial grid, S w Represents the total amount of building area of ​​a standard space grid;

[0034] Traverse all functional business types and obtain the standard value of electricity consumption per unit building area corresponding to each functional business type.

[0035] In a possible implementation, the theoretical power consumption corresponding to each spatial grid is determined according to the standard value of power consumption per unit building area and the multi-source data fusion result, including:

[0036] According to the multi-source data fusion results, the building area corresponding to the i-th functional business type in the spatial grid is determined as A i ; Where i = 1, 2, ...., N, N represents the total number of functional business types;

[0037] According to the building area A corresponding to the i-th functional business type i And the standard value of electricity consumption per unit building area a i , determine the theoretical power consumption corresponding to the spatial grid as:

[0038]

[0039] Among them, λ SUM represents the theoretical power consumption of the hybrid functional grid;

[0040] Traverse all spatial grids to obtain the theoretical power consumption corresponding to each spatial grid.

[0041] In a possible implementation, determining the identification result of the inefficient commercial service land corresponding to the spatial grid according to the theoretical power consumption corresponding to the spatial grid includes:

[0042] Obtain the threshold value of inefficient commercial service land corresponding to the study area;

[0043] When the theoretical electricity consumption corresponding to the spatial grid is less than the threshold value of inefficient commercial service land, the spatial grid is determined to be inefficient commercial service land, and the inefficient commercial service land identification result is obtained.

[0044] On the other hand, the present invention provides an inefficient commercial service land identification device based on multi-source data fusion, comprising: a power data preprocessing module, a power data spatialization module, a multi-source data fusion module and an inefficient commercial service land identification module;

[0045] The power data preprocessing module is used to acquire power data and preprocess the power data to obtain preprocessed power data;

[0046] The power data spatialization module is used to perform forward data collection and reverse data spatialization based on the pre-processed power data to achieve power data spatialization and obtain power data spatialization results; wherein the power data spatialization results are used to characterize the association between the plot, the grid code and the power data;

[0047] The multi-source data fusion module is used to obtain the POI data corresponding to the building, and to fuse the power data spatialization result with the POI data corresponding to the building to obtain a multi-source data fusion result; wherein the multi-source data fusion result is used to characterize the association between functional formats, power data, buildings and grids;

[0048] The inefficient commercial service land identification module is used to determine the theoretical power consumption corresponding to each spatial grid based on the multi-source data fusion result, and determine the inefficient commercial service land identification result corresponding to the spatial grid according to the theoretical power consumption corresponding to the spatial grid.

[0049] The present invention provides a method for identifying inefficient commercial service land based on multi-source data fusion. The method spatializes the power grid data to obtain the power consumption of the commercial service land, performs multi-source data fusion through POI data, analyzes the dominant functional business types of the commercial service land, and then analyzes the theoretical power consumption of the mixed functional grid corresponding to each functional business type when it is located in the same spatial grid. The method establishes the discrimination standard of inefficient commercial service land, provides a solution for the identification of inefficient commercial service land, and can effectively improve the identification accuracy of inefficient commercial service land. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0051] Figure 1 A flowchart of a method for identifying inefficient commercial service land based on multi-source data fusion provided in an embodiment of the present invention.

[0052] Figure 2 A schematic diagram of the structure of an inefficient commercial service industry land identification device based on multi-source data fusion provided in an embodiment of the present invention.

[0053] Figure 3 A schematic diagram of the structure of an inefficient commercial service industry land identification device based on multi-source data fusion provided in an embodiment of the present invention.

[0054] Figure 4 A schematic diagram of the power distribution range of a distribution box provided in an embodiment of the present invention.

[0055] Figure 5 A schematic diagram of the gridding of distribution box data provided by an embodiment of the present invention.

[0056] Figure 6 A schematic diagram of power data spatialization provided by an embodiment of the present invention.

[0057] Figure 7 A schematic diagram of a process for screening the proportion of functional business types in a spatial grid provided in an embodiment of the present invention.

[0058] Figure 8 A schematic diagram of standard values ​​for various commercial service industries in Chengdu provided in an embodiment of the present invention.

[0059] Marks and corresponding parts names in the attached drawings:

[0060] 201 - power data preprocessing module, 202 - power data spatialization module, 203 - multi-source data fusion module, 204 - low-efficiency commercial service land identification module, 301 - memory, 302 - processor, 303 - bus. DETAILED DESCRIPTION

[0061] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0062] Example 1

[0063] It is difficult to obtain key economic data in the existing methods for identifying inefficient commercial service land, and the cycle is based on one year, which makes it difficult to support more real-time spatial analysis. There is still a gap in the existing technology for combining power big data, POI (Point of Interest) data and commercial service land for spatial analysis. The present invention integrates power with POI data and spatial data for analysis, and measures the operating status of commercial service land in a more real-time manner, and identifies inefficient commercial service land more accurately and adapts to urban characteristics.

[0064] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying inefficient commercial service land based on multi-source data fusion, including:

[0065] S101, acquiring power data, and preprocessing the power data to obtain preprocessed power data;

[0066] Optionally, this embodiment adopts statistical data of commercial distribution boxes within the research scope in 2020, and the data information includes the grid code to which the distribution box belongs, the statistical period, industry category, number of users, electricity consumption, transformer capacity and average load rate.

[0067] Among them, grid coding is to divide the research scope into several 200m×200m grids, and encode each grid. Based on the grid corresponding to the spatial location of the distribution box, the distribution box is given a corresponding grid code to indicate the geographical location of the distribution box. The statistical period indicates the statistical period of power data, including the total power distribution data of the distribution box within one year, monthly power distribution data, and daily power distribution data.

[0068] Preprocessing can be divided into two parts: one is the cleaning of abnormal data, and the other is the cleaning of data that does not conform to the actual situation.

[0069] In a possible implementation manner, acquiring power data and preprocessing the power data to obtain preprocessed power data includes:

[0070] Obtaining power data; wherein the power data includes annual total power distribution data, monthly power distribution data, and daily power distribution data of the distribution box;

[0071] Abnormal data and data that do not conform to the actual situation in the power data are eliminated to obtain the pre-processed power data.

[0072] In this embodiment, abnormal data cleaning is for the original power data, eliminating data that does not support subsequent data analysis, including incomplete data in the three statistical periods of month, day, and time period for the same grid, and filling in irregular data.

[0073] Data cleaning that does not conform to the actual situation refers to the data after abnormal data cleaning, eliminating data that does not meet the construction standards or does not conform to the actual situation. Including electricity consumption data corresponding to grids with a land area of ​​less than 3,000 square meters, electricity consumption data corresponding to grids with a building area of ​​less than 3,000 square meters, and electricity data with an absolute power consumption of less than 1,000w.

[0074] S102, based on the pre-processed power data, forward data collection and reverse data spatialization are performed to achieve power data spatialization and obtain power data spatialization results; wherein the power data spatialization results are used to characterize the relationship between the plot, the grid code and the power data;

[0075] In a possible implementation, based on the pre-processed power data, forward data collection and reverse data spatialization are performed to achieve power data spatialization, and the power data spatialization result is obtained, including:

[0076] Obtaining a research area input by a staff member through human-computer interaction, and dividing the research area into a plurality of spatial grids, each of which has the same size;

[0077] A unique grid code is assigned to each spatial grid using a preset code allocation rule;

[0078] Determine the standard spatial grid where the distribution box is located, and associate the distribution box and the power data corresponding to the distribution box with the grid code to achieve forward data collection and obtain a grid code-power data correspondence table;

[0079] Based on the grid code-power data correspondence table, the land parcel data in the study area are reversely spatialized to obtain the association between the land parcel and the spatial grid, realize the transmission of power data to the spatial grid and then to the land parcel, and obtain the power data spatialization result.

[0080] In a possible implementation, based on the grid code-power data correspondence table, reverse data spatialization is performed on the plot data in the study area, including:

[0081] Spatialize grid data and associate power data according to the grid code-power data correspondence table to achieve the location of power data on the spatial grid;

[0082] The grid boundary is used as the search path, and a circle with a radius of R (such as 300m) is used as the convolution window to search the surrounding plots. If a plot is retrieved by a unique spatial grid, the association relationship between the plot and the power data corresponding to the spatial grid is directly established; if a plot is retrieved by multiple spatial grids at the same time, it is recorded in the spatial grid with the largest area coverage, thereby establishing the association relationship between the plot and the power data corresponding to the spatial grid, realizing the transmission of power data to the spatial grid and then to the plot, and obtaining the spatialization result of power data.

[0083] This example adopts the commercial electricity consumption stipulated in the "Notice of the Sichuan Provincial Price Bureau on Clarifying the Scope of Commercial Electricity Price Implementation" (2002.7.6), and the data statistical period is 2020, including annual distribution box total distribution data, monthly distribution data, daily distribution data, etc. Based on the dual considerations of data security and spatial location accessibility, the power department divides the study area into several 200m×200m grids, establishes the spatial correspondence between the distribution box and the grid unit, and summarizes the electricity consumption data of different statistical periods in the grid unit, unit: kw﹒h.

[0084] like Figures 4 to 6 As shown in the figure, the power department only provides statistical data of the distribution boxes that directly transmit and distribute electricity to each user through the transmission system for the sake of data security and spatial location accessibility. The power consumption information of all distribution boxes in the grid is counted as the power consumption information of the service range of the grid. The service radius of each distribution box is 300m, that is, the power consumption of each distribution box covers the total power consumption of all commercial users within the surrounding 300m. Therefore, the spatial location of this power data is divided into two steps: forward data collection and reverse data spatialization.

[0085] Forward data collection is to add spatial location information to the power data collected by the distribution box. Since the specific spatial location of the distribution box is confidential, the power company will place the distribution box in the corresponding grid unit according to the principle of the closest distance based on the 200m*200m grid data provided, query and summarize the power meter data in the grid, and generate a "grid number-power data" correspondence table, thereby adding the corresponding grid unit number to the power data.

[0086] Reverse data spatialization is to spatially register the collected "grid number-power data" correspondence table to the plot. In ArcGIS, the grid data is first spatialized, and then the power data is associated based on the grid number to achieve the location of the power data on the spatial grid. Then, the grid boundary is used as the search path, and the circle with a radius of 300m is used as the convolution window to retrieve the surrounding plots. If a plot is retrieved by a unique grid, an association relationship with the power of the grid is directly established; if it is retrieved by multiple grids, the grid with the largest area coverage is recorded. Thus, the correspondence between the plot and the spatial grid is established. Through the transmission of power data to spatial grids to plots, the plot-scale spatial location of power data is achieved.

[0087] S103, obtaining POI data corresponding to the building, and fusing the spatialized power data result with the POI data corresponding to the building to obtain a multi-source data fusion result; wherein the multi-source data fusion result is used to characterize the association between functional formats, power data, buildings, and grids;

[0088] The present invention solves the problem of subdividing the existing commercial service land into middle categories. According to the "Guidelines for the Classification of Land and Sea Use for National Land Space Survey, Planning and Use Control", commercial service land includes four middle categories: commercial land, business and financial land, entertainment land, and other commercial service land. Among them, commercial land includes five small categories: retail commercial land, wholesale market land, catering land, hotel land, and public facility business outlets. According to Chengdu's current technical management regulations, the proportion of commercial service land subdivision types that can be mixed and compatible with each other is very high, and the existing functional business types cannot be determined through existing planning data. Under the major category of commercial service land, there are indeed differences in the unit land use between different types. Therefore, establishing a relationship between electricity consumption and functional business types is a necessary step to apply electricity data to commercial service land identification and improve accuracy.

[0089] Through sampling surveys, it is found that the industry information of electricity consumption data is inaccurate and cannot be used to analyze business formats. POI data is needed to supplement business formats. Typical buildings on commercial service land include large-plate markets, podium + point-type buildings, point-type office buildings or plate-type office buildings. POI data directly corresponds to the land, and the land format is confirmed according to the proportion of POIs in different business formats, ignoring the building area, which is prone to misclassification of business finance and commerce; on the other hand, the correlation between the building area and electricity consumption of different business formats is more intuitive and closer than the correlation between the electricity area and electricity consumption. Building base data includes accurate building outlines, as well as attributes such as element names, structures, and number of floors, which can accurately distinguish between podiums and point-type buildings. For this reason, the introduction of building base data further improves the accuracy of business format determination. For building data that lacks floor information and has a building base area greater than 3,000 square meters, the floor information is supplemented by querying Baidu Street View data.

[0090] In a possible implementation, POI data corresponding to a building is obtained, and the power data spatialization result is fused with the POI data corresponding to the building to obtain a multi-source data fusion result, including:

[0091] Obtain the POI data corresponding to the building, and determine the electricity consumption function business type corresponding to each plot based on the POI data corresponding to the building;

[0092] According to the spatialization results of the power data and the power consumption function business type corresponding to each plot of land, the power consumption function business type corresponding to each spatial grid is determined to obtain the multi-source data fusion result.

[0093] The functional business classification of power data itself cannot guide functional classification. In the early stage, typical areas were selected for field verification and analysis based on the functional business of power data itself, and it was found that there was a large error with the actual situation. According to communication with the competent department, the functional business part of commercial power data is modified according to the application registration. In actual operation, the functional information is often not updated in time due to frequent changes of tenants and owners. POI data is a point element in the Internet electronic map, which contains four attributes: name, address, coordinates, and category. POI data has the advantages of high accuracy, strong real-time performance, and wide coverage in identifying building functions, and can be used to analyze and judge the functional business of plots. Therefore, the integration and analysis of power data and functionally refined plot functions can achieve more real-time measurement of the operating status of commercial service land, and more accurate identification of inefficient commercial service land to adapt to urban characteristics.

[0094] After preliminary sampling verification, since the functional business forms of commercial electricity meters are self-declared by the account holders and will not be promptly revised and adjusted according to the changes in functional business forms, the industry attributes of commercial electricity data are less consistent with the actual situation. Therefore, this embodiment proposes to determine the main functional business forms of the grid by the "POI-building-land-grid" information transmission method. POI data has the advantages of high accuracy, strong real-time performance and wide coverage in identifying building functions, and can be used to analyze and judge the functional business forms of plots. There are three levels of POI data categories (major categories, medium categories and minor categories), of which there are 23 first-level categories, 267 second-level categories and 869 third-level categories. A corresponding information table of the business forms of POI sources and the categories in the "Guidelines for Classification of Land and Sea Use for National Land Space Survey, Planning and Use Control" can be established, and POI data of commercial service land types can be screened out according to the major category information to which POI belongs, and then a mapping relationship between the medium category information and the business forms can be established according to the medium category information to which POI belongs, and finally the POI data can be marked with the corresponding business form information.

[0095] Since the classification of electricity data is too complicated, this embodiment selects typical land for classification. This embodiment only considers the two most common types of land: commercial land and business and financial land. The electricity consumption characteristics of retail commercial land and wholesale market land in commercial land are also different, so retail business, wholesale market, and business and financial land are the focus of this study. Through typical data verification, the corresponding relationship between the "medium category" and "small category" classification of AutoNavi POI data and functional formats such as retail business, wholesale market, and business and finance is constructed.

[0096] Spatial morphological data include building base data and commercial service land plot data from the third national land survey. Building base data comes from the 1:500 topographic map of Chengdu in 2018, and is manually supplemented for the 2019 and 2020 regions based on satellite impacts and on-site surveys. The data includes attributes such as building use, building quality, number of floors, and completion time. Commercial service land plot data comes from the results of the third national land (territorial) survey in 2020.

[0097] Typical buildings in commercial service land include large-scale market, cluster + point-type buildings, point-type office buildings or panel-type office buildings. The main use functions of large-scale market and point-type office buildings or panel-type office buildings can be determined through POI; for cluster + point-type buildings, this embodiment further introduces building base data, and uses POI + building form to comprehensively determine the use function. The building base data includes accurate building outlines, element names, structures, number of floors and other attributes, which can accurately distinguish between podiums and point-type buildings. In this way, the association between the building volume and the functional business format determined by the POI data is established.

[0098] The building and land use data are linked through the step-by-step transmission of "building to plot - plot to grid". The functional business type and corresponding building area of ​​the building are determined through POI, and the functional business type and total building area of ​​the covered building are summarized with the plot as the statistical unit. The functional business types of various buildings in the associated plots and their total building areas are summarized with the grid as the statistical unit, and finally the functional business type and total building area of ​​the electricity consumption data corresponding to the grid are determined.

[0099] like Figure 7 As shown, this embodiment provides a flow chart for screening the proportion of functional business types in a spatial grid, and the method can be used to obtain and determine the electricity-consuming functional business type corresponding to each plot.

[0100] S104. Based on the multi-source data fusion result, determine the theoretical power consumption corresponding to each spatial grid, and determine the identification result of the inefficient commercial service land corresponding to the spatial grid according to the theoretical power consumption corresponding to the spatial grid.

[0101] In a possible implementation, based on the multi-source data fusion result, determining the theoretical power consumption corresponding to each spatial grid includes:

[0102] Based on the multi-source data fusion result, standard spatial grids are screened, in which the building area corresponding to the dominant functional business type of the grid accounts for a commercial building area of ​​the corresponding spatial grid exceeding a threshold;

[0103] Based on the standard space grid, determine the standard value of electricity consumption per unit building area corresponding to each functional business format;

[0104] According to the standard value of electricity consumption per unit building area and the results of multi-source data fusion, the theoretical electricity consumption corresponding to each spatial grid is determined.

[0105] In a possible implementation, based on the standard space grid, the standard value of electricity consumption per unit building area corresponding to each functional business format is determined, including:

[0106] Determine the dominant functional business format corresponding to the standard space grid, and obtain the target functional business format corresponding to the standard space grid;

[0107] According to the total building area of ​​the standard space grid and the results of multi-source data fusion, the standard value of electricity consumption per unit building area corresponding to the target functional business type is determined as follows:

[0108]

[0109] Where I represents the standard value of electricity consumption per unit building area corresponding to the target functional business format, λ Y represents the annual total power distribution data corresponding to the standard spatial grid, S w Represents the total amount of building area of ​​a standard space grid;

[0110] Traverse all functional business types and obtain the standard value of electricity consumption per unit building area corresponding to each functional business type.

[0111] In order to study the electricity consumption standards of different functional formats, it is necessary to select grids with relatively pure functional formats for the calculation of electricity consumption standards for each functional format, and select grids where the building area of ​​the dominant functional format of the grid exceeds the threshold of the total commercial building area of ​​the grid as the object of electricity consumption standard calculation. The threshold is set at 70%.

[0112] Optionally, the annual electricity consumption can be used as the basis, and the top 10% and bottom 10% of the data can be eliminated. The remaining data can be used for standard calculations, and the following formula can be used to calculate the electricity consumption standards for various functional business formats.

[0113] In commercial service land, the electricity demand and standards of buildings with different functions are different. According to the "Urban Electricity Planning Specifications GB / T50293-2014", the power load forecasting method in the detailed urban planning stage, the general load (uniformly distributed load) should adopt the unit construction land load index method. When the unit construction land load density method is used for load forecasting, the unit construction land load index of commercial service facility land is stipulated to be 400-1200kw / hm2. When the unit building area load density index method is used, the "Urban Electricity Planning Specifications GB / T50293-2014" stipulates the planned unit building area load index. Buildings on commercial service land belong to public buildings, and their electricity load index is 40-150w / m2, with a relatively large range of values. In addition, with regard to the prediction of unit building area electricity load index, provinces and cities across the country have made relevant refinements and adjustments based on the actual situation on the basis of the electricity planning specifications. Shanghai has further clarified that the office and financial index in public buildings is 100w / m 2 , commercial is 120w / m 2 ; Shaanxi Province has set the office and financial building index at 90w / m 2 , commercial buildings: 100w / m 2 ; Ningbo City has specified that commercial service buildings should be 80-100w / m 2 . According to the above-mentioned local electricity load standards, urban power planning specifications and building load survey forms, it can be seen that the data per unit of construction land fluctuates greatly. The electricity load index per unit of building area is used as the standard, and should be adjusted according to different business offices and commercial services. In 2020, Chengdu requires that measures be taken to reduce energy consumption and improve energy efficiency while ensuring the function of the building and the quality of the indoor environment. Electricity consumption has gradually decreased with the implementation of energy-saving regulations. The results of the "2020 Shanghai Public Building Energy Consumption Analysis Report" show that the electricity consumption of shopping mall buildings, office buildings, and tourist hotel buildings in 2019-2020 were 140, 81.5, and 95.8 kWh / m 2 The average power load per unit building area is 32.0, 18.6, and 21.9w / m 2 ,From this we can see that the average electricity load of commercial buildings with different functions is quite different from the standard.

[0114] Therefore, the embodiment of the present invention separately obtains the standard value of electricity consumption per unit building area corresponding to each functional business format, which can effectively improve the recognition accuracy of inefficient commercial service land.

[0115] In a possible implementation, the theoretical power consumption corresponding to each spatial grid is determined according to the standard value of power consumption per unit building area and the multi-source data fusion result, including:

[0116] According to the multi-source data fusion results, the building area corresponding to the i-th functional business type in the spatial grid is determined as A i ; Wherein, i=1,2,....,N, N represents the total number of functional business types; in this embodiment, N is 3.

[0117] According to the building area A corresponding to the i-th functional business type i And the standard value of electricity consumption per unit building area a i , determine the theoretical power consumption corresponding to the spatial grid as:

[0118]

[0119] Among them, λ SUM represents the theoretical power consumption of the hybrid functional grid;

[0120] Traverse all spatial grids to obtain the theoretical power consumption corresponding to each spatial grid.

[0121] In a possible implementation, determining the identification result of the inefficient commercial service land corresponding to the spatial grid according to the theoretical power consumption corresponding to the spatial grid includes:

[0122] Obtain the threshold value of inefficient commercial service land corresponding to the study area;

[0123] When the theoretical electricity consumption corresponding to the spatial grid is less than the threshold value of inefficient commercial service property land, the spatial grid is determined to be inefficient commercial service land, and the inefficient commercial land identification result is obtained.

[0124] Assuming that the research area is Chengdu, this embodiment provides a method such as Figure 8 The standard values ​​of various types of commercial buildings in Chengdu shown are combined with the electricity load indicators per unit building area of ​​Chengdu’s actual commercial categories and the relevant vacancy rate requirements for low-efficiency land to determine the standard values ​​of various types of commercial inefficient land (i.e., the thresholds for the subdivision types of inefficient commercial service industry land).

[0125] The present invention obtains the electricity consumption of commercial plots through the spatialization of data from the State Grid, obtains the dominant function of the commercial plots through POI data analysis, obtains the actual electricity consumption of the dominant function through standard units, and thereby establishes the discrimination standard for inefficient commercial service land, providing a solution for the identification of inefficient commercial service land.

[0126] The data provided by the State Grid is grid data after rasterization of distribution transformer data. First, the problem of linking commercial service land with power data is solved. Secondly, the main functions of the land are determined by calculating POI data and spatial form. Thirdly, the standard value of electricity consumption for commercial service land is obtained by selecting the main functional standard unit. Finally, the standard of 30% lower than the standard value is used as the standard for inefficient land to identify inefficient commercial service land.

[0127] Optionally, in order to better understand the technical solution of the embodiment of the present invention for those skilled in the art, an example of merging POI data may include:

[0128] 1. Determine the business type and proportion of the building based on POI.

[0129] Establish the corresponding relationship between building base and POI through spatial superposition;

[0130] Typical buildings in commercial service land include large-scale market, podium + point-type buildings, point-type office buildings or plate-type office buildings. For large-scale market and point-type office buildings or plate-type office buildings, the proportion of various business types in the building base is calculated according to the business types corresponding to POI; the business type with the largest number of POIs is determined as its dominant business type. When calculating the construction volume of the subsequent plot, the building area is the building base × the number of podium floors, and the business type is the dominant business type.

[0131] For the podium + point-type buildings, in the building base processing, the group of buildings and the point-type buildings are separated into two objects, and the functions are determined by using the comprehensive use of POI + building form.

[0132] The business format of a group of houses is determined by the proportion of the number of various POIs within the group of houses. The one with the highest proportion is confirmed as the dominant business format. When the subsequent construction volume of the plot is calculated, the building area is the base of the podium × the number of podium floors, and the business format is the dominant business format.

[0133] For point-type buildings, the one with the highest proportion is identified as the dominant business type according to the proportion of the number of various POIs within the scope of the point-type building. When the construction volume of the subsequent plot is calculated, the building area is the base area of ​​the point-type building × (number of point-type building floors - corresponding number of podium floors), and the business type is the dominant business type.

[0134] In order to solve the problem that POIs and buildings do not completely overlap in space, a retrieval tolerance of 10m is set between the two.

[0135] 2. Revise the building types based on the third survey of commercial service industry plots.

[0136] The data of the third national land survey (hereinafter referred to as the "third survey") clearly defines the current status of the land use nature of each plot, which can assist in correcting the building type. Only the building bases with non-empty dominant types and located on the commercial plots in the "third survey" are selected for subsequent calculations.

[0137] 3. Establish a corresponding relationship between commercial building formats and the third survey of commercial service industry plots.

[0138] The business type ratio and corresponding building area of ​​the plot are the sum of all the buildings that overlap in its space. The business type of the base of a single building is determined according to the proportion of the number of POIs, which is then multiplied by the number of floors to convert into the building area of ​​the business type. The distribution of the building area of ​​different business types in the entire plot is finally determined according to the proportion of the building area.

[0139] Specific calculation formula:

[0140] Among them, Ab i represents the building area of ​​the i-th business type of the current plot, n represents the number of building bases of the i-th business type of the current plot, Al ij represents the j-th building base land area of ​​the current plot i-type business format, F j Indicates the number of base floors of the j-th building in the current plot.

[0141] 4. Calculate the business proportion and corresponding building area of ​​each grid.

[0142] The third survey of commercial service industry plots and grid power statistical points have a many-to-one or one-to-one relationship. The business type ratio and corresponding building area of ​​each plot in the grid are summarized. Finally, the business type composition of each grid is obtained, which forms a multi-dimensional fusion result with the above-mentioned power data spatialization results.

[0143] Business structure of the plot = Building 1 + Building 2 + Building 3 + ... Building N

[0144] Grid business structure = plot 1 + plot 2 + plot 3 + ... plot N

[0145] In terms of the association between building and land use data, the data is transferred step by step from "building to plot, plot to grid", that is, the business type and corresponding building area of ​​the building are determined through POI, and the business type and total building area of ​​the covered building are summarized with the plot as the statistical unit. The various building business types and the total building area of ​​the associated plot are summarized with the grid as the statistical unit, and finally the business type and total building area of ​​the electricity consumption data corresponding to the grid are determined.

[0146] 5. Determine the standard electricity consumption for different functional business types in local urban commercial service land.

[0147] The standard electricity consumption for different functional business types is clarified through screening and calculation at the grid unit level.

[0148] The screening of standard units is considered based on the fact that the dominant business building area accounts for more than the threshold of the total grid commercial building area and the potential unit accounts for more than the threshold of the overall unit. When the threshold is too high, the number of pure business grids that can be used for calculation will be very small, which is easy to cause overall standard distortion due to data errors; conversely, when the threshold is too low, the business mixing degree of the grid data involved in the calculation will be high, resulting in insufficient directionality of the grid data involved in the calculation.

[0149] After screening out the standard units, the average land area within the standard units is used as the standard value for the corresponding business format.

[0150] The specific formula is:

[0151]

[0152] Among them, S i represents the standard electricity consumption per unit building area of ​​the i-th business format, p represents the number of standard units within the research scope, and N it Ab represents the annual electricity consumption of the tth standard unit of the i-th business format, it Represents the building area of ​​the tth standard unit of the i-th business format.

[0153] For pure retail, commercial and financial, and wholesale market grids, statistics on various types of electricity consumption are collected. Based on annual electricity consumption, the top and bottom 10% of the data are removed, and the remaining data is used to calculate the standard. The following formula is used to statistically analyze the grid's electricity consumption:

[0154]

[0155] Among them, SE k represents the standard power consumption of the current grid k, m represents the number of business types contained in the current grid k, Ab ik Represents the building area of ​​the i-th business type in the current grid k.

[0156] 6. Identify inefficient commercial service land use standards.

[0157] The vacancy rate refers to the ratio of the controlled housing area to the total housing area at a certain moment. According to international practice, the vacancy rate between 5% and 10% is a reasonable zone; the vacancy rate between 10% and 20% is a vacancy danger zone; and the vacancy rate above 20% is a serious backlog zone. According to the "Chengdu Commercial Real Estate Market Report in the First Half of 2020", the office vacancy rate in Chengdu is 21.6%, which is lower than in previous years; the vacancy rate in the retail market is 8.0%. Affected by special factors, the vacancy rate has only risen to a three-year high, but it is still within a reasonable range. In the present invention, the standard for identifying the inefficiency of commercial buildings is a vacancy rate of more than 40%.

[0158] The standard value of electricity consumption is obtained as follows:

[0159] L k =SE k ×(1-Q)

[0160] Among them, L k Indicates the standard value of electricity consumption per unit building area of ​​the current grid K classification inefficient land, SE k represents the current standard electricity consumption of grid k, and Q represents the vacancy rate.

[0161] 7. Screening of inefficient land.

[0162] Inefficient land and inefficient units are screened according to the annual average electricity consumption being less than or equal to the inefficiency standard value.

[0163] Example 2

[0164] like Figure 2 As shown, the present invention provides an inefficient commercial service land identification device based on multi-source data fusion, comprising: a power data preprocessing module 201, a power data spatialization module 202, a multi-source data fusion module 203 and an inefficient commercial service land identification module 204;

[0165] The power data preprocessing module 201 is used to acquire power data and preprocess the power data to obtain preprocessed power data;

[0166] The power data spatialization module 202 is used to perform forward data collection and reverse data spatialization based on the pre-processed power data to achieve power data spatialization and obtain power data spatialization results; wherein the power data spatialization results are used to characterize the relationship between the plot, the grid code and the power data;

[0167] The multi-source data fusion module 203 is used to obtain POI data corresponding to the building, and to fuse the power data spatialization result with the POI data corresponding to the building to obtain a multi-source data fusion result; wherein the multi-source data fusion result is used to characterize the association between functional formats, power data, buildings and grids;

[0168] The inefficient commercial service land identification module 204 is used to determine the theoretical power consumption corresponding to each spatial grid based on the multi-source data fusion result, and determine the inefficient commercial service land identification result corresponding to the spatial grid according to the theoretical power consumption corresponding to the spatial grid.

[0169] The inefficient commercial service land identification device based on multi-source data fusion provided in this embodiment can execute the method and technical solution described in Example 1. Its principles and beneficial effects are similar and will not be repeated here.

[0170] Example 3

[0171] like Figure 3 As shown, an embodiment of the present invention provides an inefficient commercial service land identification device based on multi-source data fusion, which may include a memory 301 and a processor 302, and the memory 301 and the processor 302 are interconnected via a bus 303.

[0172] The memory 301 stores computer-executable instructions.

[0173] The processor 302 executes the computer execution instructions stored in the memory, so that the processor executes the method for identifying inefficient commercial service land by fusion of multi-source data as described in Example 1.

[0174] For example, the memory may include, but is not limited to, random access memory (RAM), read only memory (ROM), flash memory, first input first output (FIFO) and / or first in last out (FILO), etc. Specifically, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). At the same time, the processor may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state.

[0175] Example 4

[0176] This embodiment provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, they are used to implement a method for identifying inefficient commercial service land using multi-source data fusion as described in Example 1.

[0177] Example 5

[0178] This embodiment provides a computer program product, including a computer program, which, when executed by a processor, implements a method for identifying inefficient commercial service land by fusion of multi-source data as described in Example 1.

[0179] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying inefficient commercial service land based on multi-source data fusion, characterized in that: include: Acquiring power data, and preprocessing the power data to obtain preprocessed power data; Based on the pre-processed power data, forward data collection and reverse data spatialization are carried out to realize power data spatialization and obtain power data spatialization results; Acquire POI data corresponding to the building, and fuse the power data spatialization result with the POI data corresponding to the building to obtain a multi-source data fusion result; Based on the multi-source data fusion results, the theoretical electricity consumption corresponding to each spatial grid is determined, and based on the theoretical electricity consumption corresponding to the spatial grid, the identification results of inefficient commercial service land corresponding to the spatial grid are determined.

2. The method for identifying inefficient commercial service land based on multi-source data fusion according to claim 1 is characterized in that: Acquiring power data and preprocessing the power data to obtain preprocessed power data includes: Obtaining power data; wherein the power data includes annual total power distribution data, monthly power distribution data, and daily power distribution data of the distribution box; Abnormal data and data that do not conform to the actual situation in the power data are eliminated to obtain the pre-processed power data.

3. The method for identifying inefficient commercial service land based on multi-source data fusion according to claim 2 is characterized in that: Based on the pre-processed power data, forward data collection and reverse data spatialization are carried out to achieve power data spatialization and obtain power data spatialization results, including: Obtaining a research area input by a staff member through human-computer interaction, and dividing the research area into a plurality of spatial grids, each of which has the same size; A unique grid code is assigned to each spatial grid using a preset code allocation rule; Determine the standard spatial grid where the distribution box is located, and associate the distribution box and the power data corresponding to the distribution box with the grid code to achieve forward data collection and obtain a grid code-power data correspondence table; Based on the grid code-power data correspondence table, the land parcel data in the study area are reversely spatialized to obtain the association between the land parcel and the spatial grid, realize the transmission of power data to the spatial grid and then to the land parcel, and obtain the power data spatialization result.

4. The method for identifying inefficient commercial service land based on multi-source data fusion according to claim 3 is characterized in that: Based on the grid code-power data correspondence table, reverse data spatialization is performed on the plot data in the study area, including: Spatialize grid data and associate power data according to the grid code-power data correspondence table to achieve the location of power data on the spatial grid; The grid boundary is used as the search path, and the circle with a radius of R is used as the convolution window to search the surrounding plots. If a plot is retrieved by a unique spatial grid, the association relationship between the plot and the power data corresponding to the spatial grid is directly established; if a plot is retrieved by multiple spatial grids at the same time, it is recorded in the spatial grid with the largest area coverage, thereby establishing the association relationship between the plot and the power data corresponding to the spatial grid, realizing the transmission of power data to the spatial grid and then to the plot, and obtaining the spatialization result of power data.

5. The method for identifying inefficient commercial service land based on multi-source data fusion according to claim 4 is characterized in that: The POI data corresponding to the building is obtained, and the spatialization result of the power data is fused with the POI data corresponding to the building to obtain a multi-source data fusion result, including: Obtain the POI data corresponding to the building, and determine the electricity consumption function business type corresponding to each plot based on the POI data corresponding to the building; According to the spatialization results of the power data and the power consumption function business type corresponding to each plot of land, the power consumption function business type corresponding to each spatial grid is determined to obtain the multi-source data fusion result.

6. The method for identifying inefficient commercial service land based on multi-source data fusion according to claim 5 is characterized in that: Based on the multi-source data fusion result, the theoretical power consumption corresponding to each spatial grid is determined, including: Based on the multi-source data fusion result, standard spatial grids are screened, in which the building area corresponding to the dominant functional business type of the grid accounts for a commercial building area of ​​the corresponding spatial grid exceeding a threshold; Based on the standard space grid, determine the standard value of electricity consumption per unit building area corresponding to each functional business format; According to the standard value of electricity consumption per unit building area and the results of multi-source data fusion, the theoretical electricity consumption corresponding to each spatial grid is determined.

7. The method for identifying inefficient commercial service land based on multi-source data fusion according to claim 6 is characterized in that: Based on the standard space grid, determine the standard value of electricity consumption per unit building area corresponding to each functional business format, including: Determine the dominant functional business format corresponding to the standard space grid, and obtain the target functional business format corresponding to the standard space grid; According to the total building area of ​​the standard space grid and the results of multi-source data fusion, the standard value of electricity consumption per unit building area corresponding to the target functional business type is determined as follows: Where I represents the standard value of electricity consumption per unit building area corresponding to the target functional business format, λ Y represents the annual total power distribution data corresponding to the standard spatial grid, S w Represents the total amount of building area of ​​a standard space grid; Traverse all functional business types and obtain the standard value of electricity consumption per unit building area corresponding to each functional business type.

8. The method for identifying inefficient commercial service land based on multi-source data fusion according to claim 7 is characterized in that: According to the standard value of electricity consumption per unit building area and the results of multi-source data fusion, the theoretical electricity consumption corresponding to each spatial grid is determined, including: According to the multi-source data fusion results, the building area corresponding to the i-th functional business type in the spatial grid is determined as A i ; Where i = 1, 2, ...., N, N represents the total number of functional business types; According to the building area A corresponding to the i-th functional business type i And the standard value of electricity consumption per unit building area a i , determine the theoretical power consumption corresponding to the spatial grid as: Among them, λ SUM represents the theoretical power consumption of the hybrid functional grid; Traverse all spatial grids to obtain the theoretical power consumption corresponding to each spatial grid.

9. The method for identifying inefficient commercial service land based on multi-source data fusion according to any one of claims 1 to 8, characterized in that: According to the theoretical electricity consumption corresponding to the spatial grid, the identification results of inefficient commercial service land corresponding to the spatial grid are determined, including: Obtain the threshold value of inefficient commercial service land corresponding to the study area; When the theoretical electricity consumption corresponding to the spatial grid is less than the threshold value of inefficient commercial service land, the spatial grid is determined to be inefficient commercial service land, and the inefficient commercial service land identification result is obtained.

10. A device for identifying inefficient commercial service land based on multi-source data fusion, characterized in that: include: Power data preprocessing module, power data spatialization module, multi-source data fusion module and inefficient commercial service land identification module; The power data preprocessing module is used to acquire power data and preprocess the power data to obtain preprocessed power data; The power data spatialization module is used to perform forward data collection and reverse data spatialization based on the pre-processed power data to achieve power data spatialization and obtain power data spatialization results; wherein the power data spatialization results are used to characterize the association between the plot, the grid code and the power data; The multi-source data fusion module is used to obtain the POI data corresponding to the building, and to fuse the power data spatialization result with the POI data corresponding to the building to obtain a multi-source data fusion result; wherein the multi-source data fusion result is used to characterize the association between functional formats, power data, buildings and grids; The inefficient commercial service land identification module is used to determine the theoretical power consumption corresponding to each spatial grid based on the multi-source data fusion result, and determine the inefficient commercial service land identification result corresponding to the spatial grid according to the theoretical power consumption corresponding to the spatial grid.