A Method for Monitoring and Utilization Evaluation of Urban Public Service Facilities

Abstract

This invention relates to a method for monitoring and evaluating the utilization rate of urban public service facilities, comprising: acquiring nighttime light satellite data, GIS data, POI data, and EVI data of the study area; extracting the spatial range of urban public service facilities based on the GIS data and POI data, and delineating an external buffer zone for the spatial range of urban public service facilities; calculating the time-series data of the difference in nighttime light intensity between the spatial range of urban public service facilities and the corresponding external buffer zone; analyzing the time-frequency characteristics of the difference time-series data using a three-level discrete wavelet transform based on the Haar function to obtain the residual sequence and high-frequency detail sequence of the nighttime light intensity difference time-series data; identifying outliers in the residual sequence and high-frequency detail sequence located outside a preset confidence interval, thereby achieving monitoring of abnormal use of urban public service facilities. This invention significantly reduces monitoring costs while improving monitoring accuracy and real-time performance, achieving efficient and automated monitoring of the utilization rate of urban public service facilities.

Description

Technical Field

[0001] This invention relates to the field of public service facility management, and in particular to a method for monitoring and evaluating the utilization rate of urban public service facilities. Background Technology

[0002] Urban public service facilities are key to achieving equitable access to services and enhancing residents' well-being. Accurately assessing the utilization rate of urban public service facilities is of great significance for improving the sophistication of urban governance and promoting sustainable development.

[0003] Currently, the assessment of the utilization rate of urban public service facilities mainly relies on data reported by local authorities or manual surveys, which not only results in time lags in data acquisition but also makes it difficult to guarantee objectivity.

[0004] Chinese invention patent CN119313227A discloses a method for evaluating the utilization efficiency of urban public service facilities based on high-resolution satellite data. This method uses high-resolution satellite data to realize the utilization rate of urban public service facilities. However, this method relies on a large number of high-resolution satellite images, which not only has high evaluation costs, but also makes it difficult to guarantee the real-time performance of the data.

[0005] Nighttime light satellites, capable of capturing real-time artificial light radiation on the Earth's surface at night, have become an important tool for monitoring socio-economic dynamics. Utilizing nighttime light satellite data to achieve real-time monitoring and accurate assessment of the utilization rate of urban public service facilities is of significant value for optimizing the management of these facilities. Summary of the Invention

[0006] To address the aforementioned problems, this invention provides a method for monitoring and evaluating the utilization rate of urban public service facilities based on nighttime light satellite data. Compared to monitoring methods using high-resolution satellite data, this invention significantly reduces monitoring costs while improving monitoring accuracy and real-time performance, achieving efficient and automated monitoring of the utilization rate of urban public service facilities.

[0007] The technical solution to achieve the purpose of this invention is as follows:

[0008] Firstly, a method for monitoring urban public service facilities is provided, the method comprising the following steps:

[0009] S1, acquire nighttime light satellite data, impermeable surface GIS data, points of interest (POI) data of urban public service facilities, and enhanced vegetation index (EVI) data of the study area;

[0010] S2, Based on GIS data and POI data, extract the spatial scope of urban public service facilities and delineate the outer buffer zone of the spatial scope of urban public service facilities;

[0011] S3, obtain the time series data of nighttime light intensity of the spatial range of urban public service facilities and the corresponding external buffer zone, and calculate the time series data of the difference in nighttime light intensity between the spatial range of urban public service facilities and the corresponding external buffer zone after desaturation using EVI data;

[0012] S4. The time-frequency characteristics of the difference time series data are analyzed by using the three-level discrete wavelet transform based on the Haar function to obtain the approximation coefficients and detail coefficients. The approximation coefficients and detail coefficients are then subjected to inverse wavelet transform to obtain the residual sequence and high-frequency detail sequence of the night light intensity difference time series data, respectively.

[0013] S5 identifies outliers in residual sequences and high-frequency detail sequences located outside a preset confidence interval, enabling the monitoring of abnormal use of urban public service facilities.

[0014] Secondly, a monitoring system for urban public service facilities is provided, the monitoring system comprising:

[0015] The data acquisition module is used to acquire nighttime light satellite data, impermeable surface GIS data, points of interest (POI) data of urban public service facilities, and enhanced vegetation index (EVI) data of the study area.

[0016] The area delineation module is used to extract the spatial extent of urban public service facilities based on GIS data and POI data, and to delineate the outer buffer zone of the spatial extent of urban public service facilities.

[0017] The difference calculation module is used to obtain the time series data of night light intensity of the spatial range of urban public service facilities and the corresponding external buffer zone. After desaturation of the EVI data, the time series data of the difference in night light intensity between the spatial range of urban public service facilities and the corresponding external buffer zone are calculated.

[0018] The wavelet transform module is used to analyze the time-frequency characteristics of the difference time series data using a three-level discrete wavelet transform based on the Haar function, obtain the approximation coefficients and detail coefficients, and perform inverse wavelet transform on the approximation coefficients and detail coefficients to obtain the residual sequence and high-frequency detail sequence of the night light intensity difference time series data, respectively.

[0019] The anomaly monitoring module is used to identify outliers in residual sequences and high-frequency detail sequences that are outside a preset confidence interval, thereby enabling the monitoring of abnormal use of urban public service facilities.

[0020] Thirdly, an electronic device is provided, comprising:

[0021] Memory, used to store computer programs;

[0022] A processor is used to execute the computer program to implement the steps of the urban public service facility monitoring method as described above.

[0023] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the urban public service facility monitoring method described above.

[0024] Fifthly, a method for evaluating the utilization rate of urban public service facilities is provided, which includes the following steps:

[0025] Based on the monitoring results of the urban public service facilities monitoring method described above, the number of abnormal usage times and the number of normal usage times of urban public service facilities are calculated respectively, thereby obtaining the abnormal usage ratio and normal usage ratio of urban public service facilities, and realizing the utilization rate assessment of urban public service facilities.

[0026] Compared with existing technologies, the significant advantages of this invention are: It leverages the wide coverage, high spatial resolution, and strong real-time performance of nighttime light remote sensing satellites. Through multi-dimensional spatiotemporal feature fusion technology, it acquires the nighttime light intensity of urban public service facilities and their surrounding areas in real time, desaturates the nighttime light intensity, obtains multi-dimensional time-frequency information of nighttime light intensity using discrete wavelet transform, and uses preset thresholds to achieve dynamic monitoring of the utilization rate of urban public service facilities. Compared to traditional methods relying on local reporting or manual investigation, this invention overcomes the spatiotemporal limitations of data collection and ensures the objectivity of monitoring data. Compared to monitoring methods using high-resolution satellites, this invention significantly reduces monitoring costs while improving monitoring accuracy and real-time performance, achieving efficient and automated monitoring of the utilization rate of urban public service facilities. Attached Figure Description

[0027] Figure 1 This is a flowchart of the method of the present invention.

[0028] Figure 2 This is a diagram illustrating the research area in an embodiment of the present invention.

[0029] Figure 3 These are time-series data of the difference in nighttime light intensity according to an embodiment of the present invention.

[0030] Figure 4 This is a low-frequency trend sequence according to an embodiment of the present invention.

[0031] Figure 5 This is the residual sequence of nighttime light intensity in an embodiment of the present invention.

[0032] Figure 6 This corresponds to the embodiments of the present invention. High-frequency detail sequences.

[0033] Figure 7 This corresponds to the embodiments of the present invention. High-frequency detail sequences.

[0034] Figure 8 This corresponds to the embodiments of the present invention. High-frequency detail sequences.

[0035] Figure 9 This is the monitoring result of abnormal use of urban public service facilities according to an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, a clear and complete description will be provided below in conjunction with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the protection scope of the present invention.

[0037] Unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0038] like Figure 1 As shown, a method for monitoring and evaluating the utilization rate of urban public service facilities includes the following steps:

[0039] S1. Acquire nighttime satellite data, Global Impervious Surface (GIS) data, Point of Interest (POI) data for urban public service facilities, and Enhanced Vegetation Index (EVI) data for the study area.

[0040] S2. Based on GIS data and POI data, extract the spatial scope of urban public service facilities and delineate the external buffer zone of this spatial scope.

[0041] like Figure 2 As shown, the inner circle of the dashed line represents the spatial range of the public service facilities to be monitored in this embodiment of the invention, and the annular area between the inner and outer circles of the dashed line is the external buffer zone.

[0042] S3. Obtain time-series data of nighttime light intensity of urban public service facilities and their corresponding external buffer zones. After desaturation using EVI data, calculate time-series data of the difference in nighttime light intensity between the urban public service facilities and their corresponding external buffer zones.

[0043] S4. The time-frequency characteristics of the difference time series data are analyzed by using the three-level discrete wavelet transform (DWT) based on the Haar function to obtain the approximation coefficients and detail coefficients. The approximation coefficients and detail coefficients are then subjected to inverse wavelet transform to obtain the residual sequence and high-frequency detail sequence of the night light intensity difference time series data, respectively.

[0044] S5 identifies outliers in residual sequences and high-frequency detail sequences located outside a preset confidence interval, enabling the monitoring of abnormal use of urban public service facilities.

[0045] S6 calculates the annual utilization rate of urban public service facilities and enables dynamic monitoring of the effectiveness of public service facilities.

[0046] Step S1 specifically includes the following steps:

[0047] S11, clean the POI data, remove outliers, and summarize the data, retaining the urban public service facilities in the POI data;

[0048] S12 acquires nighttime light satellite data and performs image correction, georegistration, and mask extraction;

[0049] S13: Acquire GIS data and perform projection transformation, image registration, outlier removal, and mask extraction.

[0050] S14: Acquire EVI data, perform projection transformation, image registration, outlier removal, and mask extraction.

[0051] Step S2 specifically includes the following steps:

[0052] S21. Using the cleaned POI data and combined with map data, the spatial scope and external buffer zone of urban public service facilities are delineated.

[0053] S22, using GIS data, performs cropping of the impermeable surface of the public service facility space and the external buffer zone.

[0054] Step S3 specifically includes the following steps:

[0055] S31, cropping nighttime satellite data of the spatial extent of urban public service facilities to obtain raw time-series data of nighttime light intensity within the spatial extent of urban public service facilities. ,right Normalization was performed to obtain normalized nighttime light intensity time-series data. ,in The length of the observation window. Observation points for the spatial range of urban public service facilities The original nighttime luminescence intensity value, Observation points for the spatial extent of urban public service facilities after normalization The original night light intensity value; it should be noted that in this embodiment, the observation period is one year, but the actual number of observations obtained is about 240, so the observation length T=240 here.

[0056] S32, using EVI data to... Desaturation was performed to obtain time-series data on nighttime light intensity within the spatial area of ​​urban public service facilities after desaturation. ,in Observation points for the spatial range of urban public service facilities The desaturated night light intensity value, , The average enhanced vegetation index represents the spatial extent of urban public service facilities within the observation window.

[0057] S33, cropping nighttime satellite data from the outer buffer zone of urban public service facilities to obtain raw time-series data of nighttime light intensity from the outer buffer zone. ,right Normalization is performed to obtain the time-series data of nighttime light intensity in the normalized outer buffer. ,in Observation points for the outer buffer zone The original nighttime luminescence intensity value, For observation points in the normalized outer buffer zone The value of the nighttime luminescence intensity.

[0058] S34, using EVI data to... Desaturation, obtaining the time-series data of night light intensity from the outer buffer after desaturation. ,in For observation points in the outer buffer zone The desaturated night light intensity value, , The average enhanced vegetation index is defined within the buffer zones inside and outside the observation window.

[0059] S35, calculate the difference in desaturated nighttime light intensity between the spatial range of urban public service facilities and the corresponding external buffer zone, and obtain the time series data of the difference. ,in Observation points for the spatial scope of urban public service facilities and their corresponding external buffer zones The difference in desaturated night light intensity, .

[0060] like Figure 3 The figure shows the time-series data of the difference in night light intensity according to an embodiment of the present invention.

[0061] Step S4 specifically includes the following steps:

[0062] S41, using the first-level Haar scale sequence set For difference time series data Perform the first-level low-pass filtering to obtain the first-level approximation coefficient set. .in, For the normalized Haar scale sequence, , For the characteristic function, when The value is 1 if the condition is met, and 0 otherwise. ; For difference time series data and The inner product, .

[0063] S42, using the first-level Haar wavelet sequence set For difference time series data Perform the first-level high-pass filtering to obtain the first-level detail coefficient set. .in, For the first layer of normalized Haar wavelet sequence, , , All are indicator functions. For difference time series data and The inner product, .

[0064] S43, using the second-level Haar wavelet sequence set For difference time series data Perform a second-layer high-pass filter to obtain the second-layer detail coefficient set. .in, For the second-level normalized Haar wavelet sequence, , , All are indicator functions. For difference time series data and The inner product, .

[0065] S44, using the third-level Haar wavelet sequence set For difference time series data Perform a third-layer high-pass filter to obtain the set of third-layer detail coefficients. .in, For the third-level normalized Haar wavelet sequence, , , All are indicator functions. For difference time series data and The inner product, .

[0066] S45, detail factor , and Set to zero for approximation coefficients Perform three upsampling operations and use a low-pass reconstruction filter Reconstruct and obtain difference time series data Low-frequency trend sequence Calculate the residual sequence of night light intensity ,in For the reconstructed observation points The low-frequency value of the night light intensity For observation point The residual value of the night light intensity; such as Figure 4 The image shows a low-frequency trend sequence according to an embodiment of the present invention, such as... Figure 5 The image shows the residual sequence of nighttime light intensity in an embodiment of the present invention.

[0067] S46, set of approximation coefficients Set to zero, respectively for , and Perform upsampling three times, twice, and once respectively, and use a high-pass reconstruction filter. Reconstruct and obtain difference time series data High-frequency detail sequence , , ,in , , They are respectively the corresponding , and Reconstructed observation points The high-frequency value of the nighttime luminescence intensity. For example... Figures 6 to 8 The figures shown are corresponding to embodiments of the present invention. , and High-frequency detail sequences.

[0068] Step S5 specifically includes the following steps:

[0069] S51, for residual sequences and high-frequency detail sequences , , If the residual or high-frequency value of the night light intensity at a certain observation point is less than the lower limit of the confidence interval, then the residual or high-frequency value of the night light intensity at that observation point is considered to be abnormally small; if the residual or high-frequency value of the night light intensity at a certain observation point is greater than the upper limit of the confidence interval, then the residual or high-frequency value of the night light intensity at that observation point is considered to be abnormally large; otherwise, the residual or high-frequency value of the night light intensity at that observation point is considered to be normal.

[0070] S52, if more than half of the residual nighttime light intensity and high-frequency values ​​at a certain observation point are identified as abnormally low, then the urban public service facilities at that observation point are considered underutilized; if more than half of the residual nighttime light intensity and high-frequency values ​​at a certain observation point are identified as abnormally high, then the urban public service facilities at that observation point are considered overloaded; otherwise, the urban public service facilities at that observation point are considered to be in normal use. Figure 9 The image shows the monitoring results of abnormal use of urban public service facilities according to an embodiment of the present invention, where "▲" indicates overloaded use and "▼" indicates unused use.

[0071] In step S51, a sliding window is selected. Calculate the approximation coefficients respectively. and detail coefficient Confidence interval within the window ,in, for or or or The mean within the sliding window, for or or or The standard deviation within the sliding window.

[0072] Step S6 specifically includes the following steps:

[0073] S51, Based on the aforementioned monitoring results, the number of observation points for underutilization of public service facilities is U=5, the number of observation points for overloaded use is O=5, and the number of observation points for normal use is N=TUO=240-5-5=230.

[0074] S52, Calculate the annual underutilization rate of public service facilities Normal usage rate Overload usage rate

[0075] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0076] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device, equipment, and storage medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0077] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0078] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of monitoring urban public service facilities, characterized by, Includes the following steps: S1, acquire nighttime light satellite data, impermeable surface GIS data, points of interest (POI) data of urban public service facilities, and enhanced vegetation index (EVI) data of the study area; S2, Based on the impermeable surface GIS data and the urban public service facility POI data, extract the spatial range of the urban public service facilities and construct an external buffer zone located outside the spatial range; S3, extract the time series data of night light intensity of the spatial range of the urban public service facilities and its external buffer zone respectively, and perform desaturation processing on the time series data of night light intensity of the spatial range of the urban public service facilities and its external buffer zone based on the EVI data, and calculate the time series data of desaturated night light intensity difference between the spatial range of the urban public service facilities and the external buffer zone. S4, perform a three-level discrete wavelet transform based on the Haar function on the difference time series data, obtain an approximate coefficient set through low-pass filtering, and obtain a first-level detail coefficient set, a second-level detail coefficient set, and a third-level detail coefficient set through first-level high-pass filtering, second-level high-pass filtering, and third-level high-pass filtering, respectively. S5, set the first layer detail coefficient set, the second layer detail coefficient set and the third layer detail coefficient set to zero, upsample the approximation coefficient set and reconstruct it using a low-pass reconstruction filter to obtain the low-frequency trend sequence of the difference time series data, and obtain the night light intensity residual sequence based on the difference between the difference time series data and the low-frequency trend sequence. S6, set the approximation coefficient set to zero, upsample the first layer detail coefficient set, the second layer detail coefficient set and the third layer detail coefficient set respectively, and reconstruct them using a high-pass reconstruction filter to obtain the first layer high-frequency detail sequence, the second layer high-frequency detail sequence and the third layer high-frequency detail sequence of the difference time series data respectively; S7. Based on the night light intensity residual sequence and the first layer high-frequency detail sequence, the second layer high-frequency detail sequence and the third layer high-frequency detail sequence, identify outliers located outside the preset information interval to realize the monitoring of abnormal use of urban public service facilities. Step S4 specifically includes: S41, for difference time series data Using the first-level Haar scale sequence set Perform low-pass filtering to obtain a set of approximate coefficients. ,in, For the normalized Haar scale sequence, , For the characteristic function, when The value is 1 if it is true, and 0 otherwise. ; S42, for difference time series data Using the first-level Haar wavelet sequence set respectively Second-level Haar wavelet sequence set and the third layer of the Haar wavelet sequence set Perform high-pass filtering to obtain the first-layer detail coefficient set. Second layer detail coefficient set and the third level of detail coefficient set ,in, , ; , ; , ; , , ; , , , , , All of them are indicator functions.

2. The method for monitoring urban public service facilities according to claim 1, characterized in that: Step S3 includes: S31, crop the nighttime satellite data corresponding to the spatial range of urban public service facilities to obtain the original time-series data of nighttime light intensity within the spatial range of urban public service facilities. ,right Normalization was performed to obtain normalized nighttime light intensity time-series data. ,in The length of the observation window. Observation points for the spatial range of urban public service facilities The original nighttime luminescence intensity value, Observation points for the spatial extent of urban public service facilities after normalization The value of the night light intensity; S32, using EVI data to... Desaturation processing was performed to obtain time-series data of nighttime light intensity within the spatial range of urban public service facilities after desaturation. ,in Observation points for the spatial range of urban public service facilities The desaturated night light intensity value, , The average enhanced vegetation index of the spatial extent of urban public service facilities within the observation window; S33, crop the nighttime satellite data corresponding to the external buffer zone of urban public service facilities to obtain the raw nighttime light intensity time series data of the external buffer zone. ,right Normalization is performed to obtain the time-series data of nighttime light intensity in the normalized outer buffer. ,in Observation points for the outer buffer zone The original nighttime luminescence intensity value, For observation points in the normalized outer buffer zone The value of the night light intensity; S34, using EVI data to... Perform desaturation processing to obtain the time-series data of nighttime light intensity in the outer buffer after desaturation. ,in Observation points for the outer buffer zone The desaturated night light intensity value, , The average enhanced vegetation index is defined within the buffer zones inside and outside the observation window. S35, based on the time-series data of nighttime light intensity of urban public service facilities spatial range after desaturation. Time series data of nighttime light intensity from the desaturated outer buffer Calculate the time series data of the desaturated nighttime light intensity difference between the spatial extent of urban public service facilities and the external buffer zone. ,in Observation points for the spatial scope of urban public service facilities and their corresponding external buffer zones The difference in desaturated night light intensity, .

3. The method for monitoring urban public service facilities according to claim 1, characterized in that: Step S5 specifically includes: S51, for the first level detail coefficient set Second layer detail coefficient set and the third level of detail coefficient set Set to zero for the set of approximation coefficients. Upsampling is performed and reconstructed using a low-pass reconstruction filter to obtain the difference time series data. Low-frequency trend sequence ,in, For the reconstructed observation points The low-frequency value of the night light intensity was obtained using a low-pass reconstruction filter. ; S52, based on the difference time series data With the low-frequency trend sequence Calculate the residual sequence of night light intensity ,in For observation point The residual value of the night light intensity.

4. The method for monitoring urban public service facilities according to claim 1, characterized in that: Step S6 specifically includes: For the set of approximation coefficients Set to zero, respectively for the first level detail coefficient set Second layer detail coefficient set and the third level of detail coefficient set Upsampling is performed, and then a high-pass reconstruction filter is used for reconstruction to obtain the difference time series data. First layer high-frequency detail sequence Second-layer high-frequency detail sequence and the third layer high-frequency detail sequence ,in, , , They are respectively the corresponding , and Reconstructed observation points The high-frequency value of the night light intensity was obtained using a high-pass reconstruction filter. .

5. The method for monitoring urban public service facilities according to claim 1, characterized in that: Step S7 includes: S71, Select a sliding window, and apply the results based on the night light intensity residual sequence. and the first layer of high-frequency detail sequence Second-layer high-frequency detail sequence and the third layer high-frequency detail sequence A preset information interval is established within the sliding window, and the preset information interval is... ,in for or or or The mean within the sliding window, for or or or Standard deviation within the sliding window; S72, based on the preset information interval, the residual sequence of night light intensity and the first layer of high-frequency detail sequence Second-layer high-frequency detail sequence and the third layer high-frequency detail sequence Anomaly detection is performed as follows: when the residual value or high-frequency value of nighttime light intensity at a certain observation point is less than the lower limit of the preset information interval, it is determined to be an abnormally small value; when the residual value or high-frequency value of nighttime light intensity at a certain observation point is greater than the upper limit of the preset information interval, it is determined to be an abnormally large value; the rest are determined to be normal values. S73. When more than half of the residual values ​​and high-frequency values ​​of night light intensity corresponding to a certain observation point are judged to be abnormally small, it is determined that the urban public service facilities are underutilized at that moment; when more than half of the residual values ​​of night light intensity and the high-frequency values ​​of the first, second and third layers corresponding to a certain observation point are judged to be abnormally large, it is determined that the urban public service facilities are overloaded at that moment; the rest are judged to be in normal use of urban public service facilities.

6. A monitoring system employing the urban public service facility monitoring method as described in any one of claims 1 to 5, characterized in that, include: The data acquisition module is used to acquire nighttime light satellite data, impermeable surface GIS data, points of interest (POI) data of urban public service facilities, and enhanced vegetation index (EVI) data of the study area. The region extraction module is used to extract the spatial range of urban public service facilities based on the impermeable surface GIS data and the POI data of urban public service facilities, and to construct an external buffer zone located outside the spatial range. The difference time series construction module is used to extract the night light intensity time series data of the spatial range of the urban public service facilities and its external buffer zone respectively, and perform desaturation processing on the night light intensity time series data of the spatial range of the urban public service facilities and its external buffer zone based on the EVI data, and calculate the desaturated night light intensity difference time series data between the spatial range of the urban public service facilities and the external buffer zone. The wavelet transform module is used to perform a three-level discrete wavelet transform based on the Haar function on the difference time series data. It obtains an approximate coefficient set through low-pass filtering, and obtains a first-level detail coefficient set, a second-level detail coefficient set, and a third-level detail coefficient set through first-level high-pass filtering, second-level high-pass filtering, and third-level high-pass filtering, respectively. The sequence reconstruction module is used to set the first layer detail coefficient set, the second layer detail coefficient set, and the third layer detail coefficient set to zero, upsample and reconstruct the approximation coefficient set to obtain the low-frequency trend sequence of the difference time series data, and obtain the night light intensity residual sequence based on the difference between the difference time series data and the low-frequency trend sequence; and to set the approximation coefficient set to zero, upsample and reconstruct the first layer detail coefficient set, the second layer detail coefficient set, and the third layer detail coefficient set to obtain the first layer high-frequency detail sequence, the second layer high-frequency detail sequence, and the third layer high-frequency detail sequence of the difference time series data respectively. An anomaly monitoring module is used to identify outliers located outside a preset information interval based on the night light intensity residual sequence and the first layer high-frequency detail sequence, the second layer high-frequency detail sequence and the third layer high-frequency detail sequence, so as to realize the monitoring of abnormal use of urban public service facilities.

7. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the steps of the urban public service facility monitoring method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the urban public service facility monitoring method as described in any one of claims 1 to 5.

9. A method for evaluating the utilization rate of urban public service facilities, characterized in that, Includes the following steps: Based on the monitoring results of the urban public service facility monitoring method as described in any one of claims 1 to 5, the number of observation points for underutilization, overutilization, and normal use of urban public service facilities are counted respectively, and the corresponding underutilization ratio, overutilization ratio, and normal use ratio are calculated to achieve the assessment of the utilization rate of urban public service facilities.

Images