Intelligent environmental sanitation facility management method and system based on multi-source sensing data

Abstract

The invention relates to the technical field of environmental sanitation engineering, in particular to an intelligent environmental sanitation facility management method and system based on multi-source perception data, and the method comprises the steps: confirming a management region, carrying out the environmental sanitation facility extraction of the management region, obtaining a plurality of dustbins, mapping a plurality of dustbin models to a region base map, obtaining a digital base map, carrying out the region division of the digital base map, and obtaining a plurality of dustbin models; determining a multi-source sensing data set based on a plurality of target dustbins; determining environmental state scores based on the multi-source sensing data set; summarizing the environmental state scores to obtain a plurality of environmental state scores; determining a region center coordinate of an abnormal unit region and a plurality of adjacent regions; and determining management scheduling schemes based on the area center coordinates and the plurality of adjacent areas, and summarizing the management scheduling schemes to obtain a plurality of management scheduling schemes so as to complete intelligent management of the environmental sanitation facilities. The intelligent degree of environmental sanitation facility management can be improved.

Description

Technical Field

[0001] This invention relates to the field of sanitation engineering technology, and in particular to an intelligent management method and system for sanitation facilities based on multi-source sensing data. Background Technology

[0002] As urbanization continues, sanitation facilities such as trash cans, sweepers, and garbage compression stations play a vital role in the urban environment. However, their management and scheduling often rely on manual inspections and records, which are inefficient, slow to respond, and can easily lead to resource waste or untimely cleanup.

[0003] Currently, many cities have begun to explore the introduction of Internet of Things (IoT) technology and big data analytics to improve the intelligence level of sanitation facility management. Sensors and monitoring equipment are widely used for real-time monitoring of garbage bins, garbage trucks, sanitation facilities, etc., and can provide feedback information through sensing data (such as the overflow level of garbage bins, the running path of sweepers, etc.).

[0004] While the above methods can enable the management and control of sanitation facilities, most existing systems rely on a single data source, which cannot comprehensively and in real time reflect the operational status of facilities and environmental changes. This can easily lead to delayed or inaccurate decision-making. Traditional methods cannot dynamically adjust cleaning tasks and resource allocation when faced with changing urban environments and demands, resulting in waste of sanitation resources or low work efficiency. Therefore, how to improve the level of intelligence in sanitation facility management has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides an intelligent management method for sanitation facilities based on multi-source sensing data and a computer-readable storage medium, the main purpose of which is to improve the level of intelligence in sanitation facility management.

[0006] To achieve the above objectives, the present invention provides an intelligent management method for sanitation facilities based on multi-source sensing data, comprising:

[0007] Once the management area is identified, sanitation facilities are extracted from the management area, resulting in multiple trash cans;

[0008] A base map of the region was determined based on the management area;

[0009] Multiple trash cans were digitally modeled to obtain multiple trash can models;

[0010] Multiple trash can models are mapped onto the regional base map to obtain a digital base map;

[0011] The digital base map is divided into regions to obtain multiple candidate unit regions;

[0012] For each of the multiple candidate cell regions, perform the following operation:

[0013] Based on the candidate unit area and multiple trash cans, multiple target trash cans were identified;

[0014] A multi-source sensing dataset was identified based on multiple target trash cans;

[0015] An environmental status score was determined based on a multi-source sensing dataset.

[0016] The environmental status scores are aggregated to obtain multiple environmental status scores;

[0017] An abnormal region set was identified based on multiple environmental status scores and multiple candidate unit regions. The abnormal region set includes multiple abnormal unit regions.

[0018] For each of the multiple abnormal cell regions, perform the following operation:

[0019] The coordinates of the center of the abnormal unit region and multiple adjacent regions were identified.

[0020] A management and scheduling scheme was determined based on the regional center coordinates and multiple adjacent regions.

[0021] By summarizing the management and scheduling schemes, multiple management and scheduling schemes are obtained, thus completing the intelligent management of sanitation facilities.

[0022] Optionally, the process of dividing the digital base map into regions to obtain multiple candidate unit regions includes:

[0023] Roads are extracted from the digital base map to obtain a road distribution map;

[0024] The road distribution map is subjected to topological processing to obtain a road topology map, which includes multiple path nodes and multiple path lines.

[0025] Multiple road segments were identified based on multiple path nodes and multiple path lines in the road topology map;

[0026] Multiple interconnected, non-closed-loop road segments were identified based on multiple road sections;

[0027] Multiple connected, non-closed-loop road segments are combined to obtain multiple candidate unit areas.

[0028] Optionally, the identification of multiple road segments based on multiple path nodes and multiple path lines in the road topology map includes:

[0029] Perform the following operation on each of the multiple path nodes:

[0030] The number of connecting lines is determined based on the path nodes and multiple path lines;

[0031] Compare the number of connecting lines with a preset threshold. If the number of connecting lines is greater than the threshold, then the path node is used as the first type of split point.

[0032] If the number of connecting lines is less than or equal to the number threshold, then the path node is regarded as the first invalid split point;

[0033] By summing up the first type of split points and the first invalid split points respectively, we obtain multiple first type split points and multiple first invalid split points;

[0034] Multiple first-type segmentation points and multiple first-invalid segmentation points are removed from multiple path nodes to obtain multiple filtered segmentation points;

[0035] For each of the multiple filter split points, perform the following operation:

[0036] Based on the selection of dividing points and multiple path lines, multiple connected path lines were identified;

[0037] Perform the following operation on each of the multiple connected paths:

[0038] The road class code is determined based on the connected path lines;

[0039] By summing up the road class codes, multiple road class codes are obtained;

[0040] Determine whether multiple road level codes are consistent. If multiple road level codes are inconsistent, then the selected dividing point will be used as the second type of dividing point.

[0041] If multiple road level codes are the same, the filtering split point will be used as the second invalid split point;

[0042] By summing up the second type of split points and the second invalid split points respectively, we obtain multiple second type split points and multiple second invalid split points;

[0043] Multiple final segmentation points were identified based on multiple first-type segmentation points, multiple second-type segmentation points, multiple first-invalid segmentation points, and multiple second-invalid segmentation points.

[0044] Multiple path lines are further divided using multiple final split points to obtain multiple road segments.

[0045] Optionally, the step of combining multiple connected unclosed loop road segments to obtain multiple candidate unit regions includes:

[0046] For each of the multiple connected non-closed loop road segments, perform the following operation:

[0047] The road segment grade code is determined based on the connected non-closed loop road segments;

[0048] By summing up the road segment grade codes, multiple road segment grade codes are obtained;

[0049] Multiple connected, non-closed-loop road segments are sorted according to their corresponding road segment level codes to obtain a sequence to be processed, which includes multiple road segments to be processed.

[0050] Extract the first segment from multiple segments to be processed in the sequence to be processed. There are several road sections awaiting processing, among which... The initial value is 1;

[0051] The first One unprocessed road segment is used as the starting segment;

[0052] A candidate road segment set is identified based on the initial road segment and multiple connected non-closed loop road segments. The candidate road segment set includes multiple candidate road segments.

[0053] Feasibility results were determined based on multiple candidate road segments in the candidate road segment set, where the feasibility result is either feasible or infeasible.

[0054] If the feasibility result is not feasible, a second set of candidate road segments is identified based on the candidate road segment set and multiple connected non-closed loop road segments;

[0055] The second set of candidate road segments is used as the candidate road segment set, and the step of confirming the feasibility result based on multiple candidate road segments in the candidate road segment set is returned until the feasibility result is feasible.

[0056] If the feasibility result is feasible, the initial area is identified based on multiple candidate road segments;

[0057] The unit independence results were determined based on the initial region and multiple connected non-closed loop road segments. The unit independence results were: independent or not independent.

[0058] If the unit independence result is independent, the initial region is used as the candidate unit region and multiple candidate road segments are marked as used to obtain multiple marked road segments;

[0059] If the unit independence result is not independent, then the boundary road segment is identified based on the initial region and multiple connected unclosed loop road segments;

[0060] Using the boundary road segment as the starting road segment, return to the step of identifying the candidate road segment set based on the starting road segment and multiple connected non-closed loop road segments, until the unit independence result is independent;

[0061] make ,Will As Multiple marked road segments are removed from the sequence to be processed to obtain an updated sequence to be processed. This updated sequence is then used as the sequence to be processed. The process of extracting the first road segment from the multiple road segments to be processed in the sequence to be processed is then repeated. The steps for each pending road segment, until... By summing up the candidate unit regions, multiple candidate unit regions are obtained, among which... This represents the number of road segments to be processed out of multiple road segments in the sequence to be processed.

[0062] Optionally, the step of identifying a multi-source sensing dataset based on multiple target trash cans includes:

[0063] Perform the following operation on each of the multiple target trash cans:

[0064] Acquire data from overflow sensors, weight sensors, and temperature and humidity sensors;

[0065] The occupancy rate of the target trash can is collected using an overflow sensor to obtain the space occupancy rate;

[0066] The weight of the target trash can is collected using a weight sensor to obtain the real-time weight of the trash;

[0067] Temperature and humidity sensors are used to collect data on the target trash can, obtaining the humidity and temperature inside the can.

[0068] The video surveillance equipment was identified based on the target trash can;

[0069] The target trash can was captured using video surveillance equipment to obtain images of its surrounding environment.

[0070] The litter dispersion index is obtained by identifying litter dispersion in images of the surrounding environment.

[0071] Based on the target trash can, the collection timestamp is determined;

[0072] Obtain regional temperature and precipitation probability;

[0073] By integrating space occupancy rate, real-time waste weight, humidity inside the bin, temperature inside the bin, waste scattering index, collection timestamp, regional temperature and precipitation probability, multi-source sensing data is obtained.

[0074] By aggregating the multi-source sensing data, a multi-source sensing dataset is obtained.

[0075] Optionally, the step of identifying litter scattered in the surrounding environment images to obtain a litter scattered index includes:

[0076] The surrounding environment image is converted to grayscale to obtain a grayscale image;

[0077] Binarize the grayscale image to obtain a binary image;

[0078] Connectivity analysis of the binarized image revealed several suspected litter-scattered areas.

[0079] For each of the multiple suspected litter areas, perform the following operations:

[0080] The pixel area was determined based on the suspected area of ​​scattered garbage.

[0081] Sum the pixel areas to obtain multiple pixel areas;

[0082] The total scattered pixel area is determined based on the area of ​​multiple pixels, where the total scattered pixel area is the sum of the areas of multiple pixels;

[0083] Once the image pixel area is identified, the littering index is calculated based on the total scattered pixel area and the image pixel area.

[0084] Optionally, the step of determining the environmental state score based on the multi-source sensing dataset includes:

[0085] Perform the following operation on each multi-source sensing data point in the multi-source sensing dataset:

[0086] The overflow deviation index is calculated based on the space occupancy rate in multi-source sensing data and the preset overflow threshold.

[0087] The load index is calculated based on the real-time waste weight and the preset rated load from multi-source sensing data.

[0088] The environmental anomaly index is calculated based on the internal temperature, regional temperature, and internal humidity data from multi-source sensing data. The calculation formula is as follows:

[0089]

[0090] in, Indicates an environmental anomaly index. This represents the temperature inside the chamber from multi-source sensing data. This represents the regional temperature from multi-source sensing data. This represents the humidity inside the container from multi-source sensing data. This indicates the preset temperature influence index. This indicates the preset humidity impact index;

[0091] The anomaly degree of a single unit is determined based on the overflow deviation index, load index, environmental anomaly index, and litter dispersion index. The anomaly degree of a single unit is the sum of the overflow deviation index, load index, environmental anomaly index, and litter dispersion index.

[0092] Summarize the individual anomalies to obtain multiple individual anomalies;

[0093] The average outlier was determined based on multiple individual outliers, where the average outlier is the average of the multiple individual outliers.

[0094] Calculate facility status score based on average anomaly degree;

[0095] An environmental status score was determined based on facility status scores and multi-source sensing datasets.

[0096] Optionally, the determination of the environmental status score based on the facility status score and the multi-source sensing dataset includes:

[0097] Once the current time is determined, perform the following operation on each multi-source sensing data point in the multi-source sensing dataset:

[0098] The number of days for the collection interval is determined based on the current time and the collection timestamp in the multi-source sensing data.

[0099] The collection delay rate is calculated based on the collection interval days and the preset standard collection cycle.

[0100] Summarize the collection delay rates to obtain multiple collection delay rates;

[0101] An average delay rate was determined based on multiple collection delay rates, where the average delay rate is the average of the multiple collection delay rates;

[0102] The facility operation score is calculated based on the waste removal delay rate and the precipitation probability from multi-source sensing data, as shown in the following formula:

[0103]

[0104] in, Indicates facility operation score, This represents the average delay rate. Indicates the probability of precipitation;

[0105] The environmental status score is calculated based on the facility status score and the facility operation score.

[0106] Optionally, the step of determining the management and scheduling scheme based on the regional center coordinates and multiple adjacent regions includes:

[0107] Several vacant sanitation vehicles were identified;

[0108] For each of the multiple available sanitation vehicles, perform the following operations:

[0109] Obtain the real-time geographic location coordinates, current load, and rated load capacity of idle sanitation vehicles;

[0110] The real-time geographic location coordinates, current load, and rated load capacity are summarized to obtain the idle vehicle status data;

[0111] Summarize the idle vehicle status data to obtain multiple idle vehicle status data;

[0112] The target vehicle to be dispatched was identified based on the coordinates of the regional center and the status data of multiple idle vehicles.

[0113] The scope of the scheduling operation is determined based on multiple adjacent areas;

[0114] A management and dispatching plan is determined based on the target vehicles and the scope of dispatching operations.

[0115] To achieve the above objectives, the present invention also provides an intelligent management system for sanitation facilities based on multi-source sensing data, comprising:

[0116] The regional base map acquisition module is used to identify the management area, extract sanitation facilities in the management area to obtain multiple trash cans, and identify the regional base map based on the management area;

[0117] The status score acquisition module is used to digitally model multiple trash cans to obtain multiple trash can models, map the multiple trash can models to a regional base map to obtain a digital base map, divide the digital base map into regions to obtain multiple candidate unit regions, and perform the following operations on each candidate unit region: identify multiple target trash cans based on the candidate unit regions and multiple trash cans, identify a multi-source sensing dataset based on the multiple target trash cans, identify an environmental status score based on the multi-source sensing dataset, and summarize the environmental status scores to obtain multiple environmental status scores;

[0118] The abnormal region confirmation module is used to confirm an abnormal region set based on multiple environmental status scores and multiple candidate unit regions. The abnormal region set includes multiple abnormal unit regions. The following operation is performed on each of the multiple abnormal unit regions.

[0119] The scheduling scheme generation module is used to identify the regional center coordinates of the abnormal unit area and multiple adjacent areas, identify the management scheduling scheme based on the regional center coordinates and multiple adjacent areas, summarize the management scheduling schemes, obtain multiple management scheduling schemes, and complete the intelligent management of sanitation facilities.

[0120] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0121] Memory, storing at least one instruction; and

[0122] The processor executes the instructions stored in the memory to implement the above-described intelligent management method for sanitation facilities based on multi-source sensing data.

[0123] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned intelligent management method for sanitation facilities based on multi-source sensing data.

[0124] To address the problems described in the background art, this invention identifies a management area, extracts sanitation facilities within that area, and obtains multiple trash cans. This demonstrates that by clearly defining the management scope and accurately identifying target facilities, a foundational object library is established for subsequent digital management. Furthermore, a regional base map is generated based on the management area. This invention also acquires and constructs a standard geographic information layer for the management area, providing a digital platform for the spatial and visual management of sanitation facilities, thus improving the intelligence level of sanitation facility management. By digitally modeling multiple trash cans, multiple trash can models are obtained. This invention creates a corresponding three-dimensional digital model for each physical trash can, standardizing its data specifications and realizing the transformation from physical entities to digital twins. The transformation of the body maps multiple trash can models onto a regional base map, resulting in a digital base map. This embodiment of the invention generates a "single map" by precisely overlaying the facility digital model with geographic information, achieving intuitive and accurate visualization management of the entire sanitation facility distribution. The digital base map is then divided into regions, resulting in multiple candidate unit regions. This embodiment of the invention divides the entire region into logically clear and appropriately sized grid units based on management needs, providing structural support for a refined and district-level management model, and improving the intelligence level of sanitation facility management. For each candidate unit region, the following operation is performed: based on the candidate unit region and multiple trash cans, multiple target trash cans are identified. This embodiment of the invention, through... Each management unit automatically associates with specific facilities within its jurisdiction, clarifying the management objects and responsibilities of each unit. Based on multiple target trash cans, a multi-source sensing dataset is identified. This embodiment of the invention gathers real-time data (such as overflow level and temperature) from sensors of various facilities to form a dynamic dataset reflecting the sanitation status within the unit. Based on the multi-source sensing dataset, an environmental status score is determined. This embodiment of the invention utilizes a preset algorithm model to comprehensively analyze the sensing data, outputting a quantitative score to objectively assess the real-time sanitation health of each unit area, thus improving the intelligence level of sanitation facility management. By summarizing the environmental status scores, multiple environmental status scores are obtained. This embodiment of the invention forms a global environmental status score by aggregating the evaluation results of all units. This panoramic view of sanitation status allows management to conduct horizontal comparisons and overall situation assessments. Based on multiple environmental status scores and multiple candidate unit areas, an abnormal area set is identified. This abnormal area set includes multiple abnormal unit areas. As can be seen, this embodiment of the invention automatically filters out abnormal areas with excessively low scores that require priority intervention by setting threshold rules, achieving intelligent problem identification and early warning. For each of the multiple abnormal unit areas, the following operations are performed: the coordinates of the abnormal unit area's center and multiple adjacent areas are identified. This embodiment of the invention provides a geographical basis for formulating efficient and collaborative scheduling strategies by locating the core location of the abnormal area and analyzing its surrounding spatial relationships, thus improving the intelligence level of sanitation facility management.Based on the coordinates of the regional center and multiple adjacent areas, a management and scheduling plan is identified. It is evident that this embodiment of the invention intelligently generates optimized scheduling instructions, including personnel and vehicle routes, by comprehensively considering the problem's location, severity, and the availability of surrounding resources. By summarizing the management and scheduling plans, multiple management and scheduling schemes are obtained, thus completing the intelligent management of sanitation facilities. It is clear that this embodiment of the invention integrates and distributes the handling plans for all abnormal areas, forming a complete management closed loop from intelligent discovery and assessment to automatic generation and execution of optimized plans. This improves operational efficiency and response speed, and enhances the level of intelligence in sanitation facility management. Therefore, this invention can improve the level of intelligence in sanitation facility management. Attached Figure Description

[0125] Figure 1 This is a flowchart illustrating an intelligent management method for sanitation facilities based on multi-source sensing data, provided in an embodiment of the present invention.

[0126] Figure 2 This is a functional module diagram of an intelligent sanitation facility management system based on multi-source sensing data provided in an embodiment of the present invention;

[0127] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the intelligent management method for sanitation facilities based on multi-source sensing data, according to an embodiment of the present invention.

[0128] Explanation of reference numerals in the attached figures:

[0129] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0130] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0131] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0132] This application provides an intelligent management method for sanitation facilities based on multi-source sensing data. The executing entity of this intelligent management method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the intelligent management method for sanitation facilities based on multi-source sensing data can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0133] Reference Figure 1The diagram shown is a flowchart illustrating an intelligent management method for sanitation facilities based on multi-source sensing data according to an embodiment of the present invention. In this embodiment, the intelligent management method for sanitation facilities based on multi-source sensing data includes:

[0134] S1. Identify the management area, extract sanitation facilities from the management area, and obtain multiple trash cans.

[0135] For example, Xiao Zhang, a manager at a cleaning company, needs to manage sanitation facilities in a certain area of ​​the city. Xiao Zhang first identifies the management area, and then extracts the sanitation facilities within that area to obtain multiple sanitation facilities for subsequent management. The area in the city is the management area. Extracting sanitation facilities within the management area means: identifying all trash cans within the management area, including: identifying the location coordinates, capacity, and type of each trash can. The location coordinates refer to the coordinates of the trash can's location within the management area; the capacity refers to the trash can's capacity; and the type refers to the type of trash can (e.g., recyclable waste, non-recyclable waste). A trash can is a container used to store trash.

[0136] S2. Based on the management area, the area base map is identified, and multiple trash cans are digitally modeled to obtain multiple trash can models.

[0137] It should be explained that the "regional base map based on the management area" refers to: extracting the boundary and interior of the management area from the management area, and generating a two-dimensional planar map based on the boundary and interior of the management area. This two-dimensional planar map is the regional base map. The "digital modeling of multiple trash cans" refers to: performing 3D modeling based on the capacity and type of each trash can. The method for performing 3D modeling based on the capacity and type of each trash can is existing technology and will not be elaborated here. The trash can model refers to the three-dimensional model obtained after digitally modeling the sanitation facilities.

[0138] S3. Map multiple trash can models to the regional base map to obtain a digital base map. Divide the digital base map into regions to obtain multiple candidate unit regions.

[0139] It should be explained that mapping multiple trash can models to a regional base map means marking the corresponding multiple trash can models on a regional map, and the digital base map refers to a regional base map that contains multiple trash can models.

[0140] Specifically, the process of dividing the digital base map into regions to obtain multiple candidate unit regions includes:

[0141] Roads are extracted from the digital base map to obtain a road distribution map;

[0142] The road distribution map is subjected to topological processing to obtain a road topology map, which includes multiple path nodes and multiple path lines.

[0143] Multiple road segments were identified based on multiple path nodes and multiple path lines in the road topology map;

[0144] Multiple interconnected, non-closed-loop road segments were identified based on multiple road sections;

[0145] Multiple connected, non-closed-loop road segments are combined to obtain multiple candidate unit areas.

[0146] It should be explained that the road extraction from the digital base map refers to extracting all roads within the management area from the digital base map, thereby obtaining a road distribution map within the management area. This road distribution map is the road map itself. All roads within the management area include: expressways, arterial roads, secondary arterial roads, local roads, and pedestrian paths. Expressways refer to urban expressways, arterial roads to main roads, secondary arterial roads to secondary arterial roads, local roads to general urban roads, and pedestrian paths to pedestrian paths. The topology processing of the road distribution map refers to disconnecting all intersections of roads in the road distribution map, obtaining multiple disconnected roads. These disconnected roads are used as path lines, and a node is established at each intersection of roads, resulting in multiple nodes. Path nodes are nodes established at intersections of roads. The road topology map is the road distribution map after topology processing. The identification of multiple connected, non-closed-loop road segments based on multiple road segments refers to analyzing multiple road segments one by one, extracting all interconnected road segments that do not form closed loops, thereby obtaining multiple connected, non-closed-loop road segments. The interconnected road segments that do not form a closed loop are called connected unclosed loop road segments.

[0147] For example, using geographic coordinates: If a road distribution map contains a north-south road R1 with a starting point of (20°N, 20°E) and an ending point of (22°N, 20°E), and an east-west road R2 with a starting point of (21°N, 19°E) and an ending point of (21°N, 21°E), and roads R1 and R2 intersect at point P1 (21°N, 20°E), then after topological processing of the road distribution map, we obtain: 4 roads. Routes: Road R11, starting point: (20°N, 20°E), ending point: (21°N, 20°E); Road R12, starting point: (22°N, 20°E), ending point: (22°N, 20°E); Road R21, starting point: (21°N, 19°E), ending point: (21°N, 20°E); Road R22, starting point: (21°N, 20°E), ending point: (21°N, 21°E); 1 path node (21°N, 20°E).

[0148] Specifically, the identification of multiple road segments based on multiple path nodes and multiple path lines in the road topology map includes:

[0149] Perform the following operation on each of the multiple path nodes:

[0150] The number of connecting lines is determined based on the path nodes and multiple path lines;

[0151] Compare the number of connecting lines with a preset threshold. If the number of connecting lines is greater than the threshold, then the path node is used as the first type of split point.

[0152] If the number of connecting lines is less than or equal to the number threshold, then the path node is regarded as the first invalid split point;

[0153] By summing up the first type of split points and the first invalid split points respectively, we obtain multiple first type split points and multiple first invalid split points;

[0154] Multiple first-type segmentation points and multiple first-invalid segmentation points are removed from multiple path nodes to obtain multiple filtered segmentation points;

[0155] For each of the multiple filter split points, perform the following operation:

[0156] Based on the selection of dividing points and multiple path lines, multiple connected path lines were identified;

[0157] Perform the following operation on each of the multiple connected paths:

[0158] The road class code is determined based on the connected path lines;

[0159] By summing up the road class codes, multiple road class codes are obtained;

[0160] Determine whether multiple road level codes are consistent. If multiple road level codes are inconsistent, then the selected dividing point will be used as the second type of dividing point.

[0161] If multiple road level codes are the same, the filtering split point will be used as the second invalid split point;

[0162] By summing up the second type of split points and the second invalid split points respectively, we obtain multiple second type split points and multiple second invalid split points;

[0163] Multiple final segmentation points were identified based on multiple first-type segmentation points, multiple second-type segmentation points, multiple first-invalid segmentation points, and multiple second-invalid segmentation points.

[0164] Multiple path lines are further divided using multiple final split points to obtain multiple road segments.

[0165] It should be explained that determining the number of connecting lines based on path nodes and multiple path lines means counting the number of path lines intersecting with path nodes among multiple path lines. The number of path lines intersecting with path nodes is the number of connecting lines. The quantity threshold is a value set manually by the cleaning company's management personnel based on the complexity of the city's roads. Optionally, if the city's roads are complex and there are many roads, the quantity threshold is set to 3; if the city's roads are simple and there are few roads, the quantity threshold is set to 2. If the road level codes exceed 3, the city's roads are considered complex; if the city's road level codes are 3 or less, the city's roads are considered simple. The first type of segmentation point refers to a path node with a number of connecting lines greater than the quantity threshold, and the first invalid segmentation point refers to a path node with a number of connecting lines less than or equal to the quantity threshold.

[0166] For example, if multiple path nodes are: P2, P3, P4, P5, P6, P7, P8, P9, multiple first-type split points are: P5, P6, P7, and multiple first-invalid split points are: P3, P4, then after removing multiple first-type split points and multiple first-invalid split points from the multiple path nodes, multiple filtered split points are obtained: P2, P8, P9.

[0167] It should be understood that multiple connected path lines refer to all path lines that intersect at the filter split point. The road level code refers to the code of the road type corresponding to the path line. The road level code is determined as follows: if the path line corresponds to an expressway, the road level code is 1; if the path line corresponds to a main road, the road level code is 2; if the path line corresponds to a secondary road, the road level code is 3; if the path line corresponds to a side road, the road level code is 4; and if the path line corresponds to a pedestrian road, the road level code is 5. The second type of split point refers to filter split points with multiple inconsistent road level codes, and the second invalid split point refers to filter split points with multiple identical road level codes. The process of identifying multiple final segmentation points based on multiple first-type segmentation points, multiple second-type segmentation points, multiple first invalid segmentation points, and multiple second invalid segmentation points refers to using multiple first-type and multiple second-type segmentation points as multiple nodes for further segmentation of the path lines. These nodes are the final segmentation points. The process of further segmenting multiple path lines using these final segmentation points involves: first, identifying multiple intersection points between path lines; then, removing multiple final segmentation points from these intersection points to obtain multiple merged nodes; and finally, connecting the path lines intersecting these merged nodes to obtain the connected path lines. The multiple merged nodes are the intersection points of the path lines after removing the final segmentation points. The connected path lines are the road segments.

[0168] Specifically, the process of combining multiple connected, unclosed loop road segments to obtain multiple candidate unit regions includes:

[0169] For each of the multiple connected non-closed loop road segments, perform the following operation:

[0170] The road segment grade code is determined based on the connected non-closed loop road segments;

[0171] By summing up the road segment grade codes, multiple road segment grade codes are obtained;

[0172] Multiple connected, non-closed-loop road segments are sorted according to their corresponding road segment level codes to obtain a sequence to be processed, which includes multiple road segments to be processed.

[0173] Extract the first segment from multiple segments to be processed in the sequence to be processed. There are several road sections awaiting processing, among which... The initial value is 1;

[0174] The first One unprocessed road segment is used as the starting segment;

[0175] A candidate road segment set is identified based on the initial road segment and multiple connected non-closed loop road segments. The candidate road segment set includes multiple candidate road segments.

[0176] Feasibility results were determined based on multiple candidate road segments in the candidate road segment set, where the feasibility result is either feasible or infeasible.

[0177] If the feasibility result is not feasible, a second set of candidate road segments is identified based on the candidate road segment set and multiple connected non-closed loop road segments;

[0178] The second set of candidate road segments is used as the candidate road segment set, and the step of confirming the feasibility result based on multiple candidate road segments in the candidate road segment set is returned until the feasibility result is feasible.

[0179] If the feasibility result is feasible, the initial area is identified based on multiple candidate road segments;

[0180] The unit independence results were determined based on the initial region and multiple connected non-closed loop road segments. The unit independence results were: independent or not independent.

[0181] If the unit independence result is independent, the initial region is used as the candidate unit region and multiple candidate road segments are marked as used to obtain multiple marked road segments;

[0182] If the unit independence result is not independent, then the boundary road segment is identified based on the initial region and multiple connected unclosed loop road segments;

[0183] Using the boundary road segment as the starting road segment, return to the step of identifying the candidate road segment set based on the starting road segment and multiple connected non-closed loop road segments, until the unit independence result is independent;

[0184] make ,Will As Multiple marked road segments are removed from the sequence to be processed to obtain an updated sequence to be processed. This updated sequence is then used as the sequence to be processed. The process of extracting the first road segment from the multiple road segments to be processed in the sequence to be processed is then repeated. The steps for each pending road segment, until... By summing up the candidate unit regions, multiple candidate unit regions are obtained, among which... This represents the number of road segments to be processed out of multiple road segments in the sequence to be processed.

[0185] It should be understood that the method for determining the road segment level code based on connected non-closed loop road segments is the same as the method for determining the road level code based on connected path lines, and will not be repeated here. The road segment level code refers to the code of the road type corresponding to the connected non-closed loop road segments. The method for determining the road level code has been explained in the previous part of the embodiment and will not be repeated here.

[0186] It should be explained that sorting multiple connected non-closed-loop road segments according to their corresponding road segment level codes means: sorting the multiple connected non-closed-loop road segments in descending order of their corresponding road segment level codes; the sequence to be processed refers to the sequence obtained after sorting the multiple connected non-closed-loop road segments in descending order of their corresponding road segment level codes; and the road segment to be processed refers to the connected non-closed-loop road segments sorted in descending order of their road segment level numbers. For example, if the multiple non-closed-loop road segments and their corresponding road segment level numbers are (segment 1, 1), (segment 2, 4), (segment 3, 4), (segment 4, 3), (segment 5, 5), then the sequence to be processed after sorting the multiple connected non-closed-loop road segments according to their corresponding road segment level codes is: (segment 5, 5), (segment 2, 4), (segment 3, 4), (segment 4, 3), (segment 1, 1). Then, the second road segment to be processed extracted from the multiple road segments to be processed in the sequence is: (segment 2, 4).

[0187] Understandably, identifying the candidate road segment set based on the starting road segment and multiple connected unclosed loop road segments means: starting from the starting road segment, searching among multiple connected unclosed loop road segments for all connected unclosed loop road segments that are connected to the starting road segment and whose road segment level code is not higher than that of the starting road segment. The candidate road segment set is thus the set of all connected unclosed loop road segments that are connected to the starting road segment and whose road segment level code is not higher than that of the starting road segment. In short, a candidate road segment is a connected unclosed loop road segment that is connected to the starting road segment and whose road segment level code is not higher than that of the starting road segment.

[0188] It should be understood that the feasibility result confirmed based on multiple candidate road segments in the candidate road segment set refers to: judging whether multiple candidate road segments in the candidate road segment set can form a closed loop. If multiple candidate road segments in the candidate road segment set can form a closed loop, then feasibility is taken as a feasibility result. If multiple candidate road segments in the candidate road segment set cannot form a closed loop, then infeasibility is taken as a feasibility result. The feasibility result refers to the result obtained after judging whether multiple candidate road segments in the candidate road segment set can form a closed loop. Feasibility means that multiple candidate road segments in the candidate road segment set can form a closed loop, and infeasibility means that multiple candidate road segments in the candidate road segment set cannot form a closed loop.

[0189] It should be explained that the "confirmation of the initial region based on multiple candidate road segments" means connecting multiple candidate road segments to form a closed loop, and the interior of the closed loop is the initial region. The "confirmation of the unit independence result based on the initial region and multiple connected unclosed loop road segments" means determining whether there exists a connected unclosed loop road segment among the multiple connected unclosed loop road segments that satisfies the condition of being located within the initial region and having a road segment level code higher than the largest road segment level code in the initial region. If there is no connected unclosed loop road segment among the multiple connected unclosed loop road segments that satisfies the condition of being located within the initial region and having a road segment level code higher than the largest road segment level code in the initial region, then it will be considered an independent unit. If there is a connected unclosed loop road segment among the multiple connected unclosed loop road segments that satisfies the condition of being located within the initial region and having a road segment level code higher than the largest road segment level code in the initial region, then it will be considered an independent unit. If a connected unclosed loop segment has a road segment number higher than the highest road segment level code in the initial region, then it will be considered as not independent as a unit independence result. Unit independence refers to the result obtained after judging whether there is a connected unclosed loop segment located within the initial region with a road segment level code higher than the highest road segment level code in the initial region among multiple connected unclosed loop segments. Independence means that there is no connected unclosed loop segment located within the initial region with a road segment level code higher than the highest road segment level code in the initial region among multiple connected unclosed loop segments. Not independent means that there is a connected unclosed loop segment located within the initial region with a road segment level code higher than the highest road segment level code in the initial region among multiple connected unclosed loop segments. A candidate unit region is an initial region where the unit independence result is independent. Marking multiple candidate road segments as used means marking multiple candidate road segments as used road segments. A marked road segment is a candidate road segment after being marked as used. A boundary road segment refers to a connected unclosed loop segment located within the initial region among multiple connected unclosed loop segments with a road segment level code higher than the highest road segment level code in the initial region.

[0190] For example, if the sequence to be processed is: (segment 5, 5), (segment 2, 4), (segment 3, 4), (segment 4, 3), (segment 1, 1), and the multiple marked segments are: (segment 5, 5), (segment 2, 4), then the updated sequence to be processed after removing the multiple marked segments from the sequence to be processed is: (segment 3, 4), (segment 4, 3), (segment 1, 1).

[0191] It is understood that the determination of the second candidate road segment set based on the candidate road segment set and multiple connected unclosed loop road segments means: searching from multiple connected unclosed loop road segments to find one or more connected unclosed loop road segments that meet the following conditions: they are not located in the initial area formed by the candidate road segment set, their road segment level code is equal to the largest road segment level code in the candidate road segment set, and they are adjacent to the initial area formed by the candidate road segment set. The second candidate road segment set is a set composed of the candidate road segment set and the one or more connected unclosed loop road segments.

[0192] S4. Perform the following operation on each of the multiple candidate unit regions: identify multiple target trash cans based on the candidate unit regions and multiple trash cans.

[0193] It should be explained that the target trash can refers to the trash can located within the candidate unit area among multiple trash cans.

[0194] S5. Based on multiple target trash cans, identify a multi-source sensing dataset, identify an environmental status score based on the multi-source sensing dataset, summarize the environmental status scores, and obtain multiple environmental status scores.

[0195] Specifically, the multi-source sensing dataset identified based on multiple target trash cans includes:

[0196] Perform the following operation on each of the multiple target trash cans:

[0197] Acquire data from overflow sensors, weight sensors, and temperature and humidity sensors;

[0198] The occupancy rate of the target trash can is collected using an overflow sensor to obtain the space occupancy rate;

[0199] The weight of the target trash can is collected using a weight sensor to obtain the real-time weight of the trash;

[0200] Temperature and humidity sensors are used to collect data on the target trash can, obtaining the humidity and temperature inside the can.

[0201] The video surveillance equipment was identified based on the target trash can;

[0202] The target trash can was captured using video surveillance equipment to obtain images of its surrounding environment.

[0203] The litter dispersion index is obtained by identifying litter dispersion in images of the surrounding environment.

[0204] Based on the target trash can, the collection timestamp is determined;

[0205] Obtain regional temperature and precipitation probability;

[0206] By integrating space occupancy rate, real-time waste weight, humidity inside the bin, temperature inside the bin, waste scattering index, collection timestamp, regional temperature and precipitation probability, multi-source sensing data is obtained.

[0207] By aggregating the multi-source sensing data, a multi-source sensing dataset is obtained.

[0208] It should be explained that the overflow sensor is a type of trash can overflow detector. Optionally, a First FST700-CSF07 trash overflow monitoring terminal can be used as the overflow sensor. The weight sensor is a type of weighing sensor. Optionally, an OMEGA stainless steel compression weighing sensor can be used as the weight sensor. The temperature and humidity sensor is a type of temperature and humidity sensor. Optionally, a Lifu LFH10A temperature and humidity transmitter can be used as the temperature and humidity sensor. The use of the overflow sensor to collect the occupancy rate of the target trash can refers to: using the overflow sensor to detect the proportion of trash stored in the target trash can to its total capacity. The method for using the overflow sensor to detect the proportion of trash stored in the target trash can to its total capacity is existing technology and will not be elaborated here. The proportion of trash stored in the target trash can to its total capacity is the space occupancy rate. The total capacity of the target trash can can be obtained from the technical manual provided by the target trash can manufacturer. The use of a weight sensor to collect weight data from the target trash can refers to measuring the weight of the trash stored in the target trash can using a weight sensor. The method for measuring the weight of the trash stored in the target trash can using a weight sensor is existing technology and will not be elaborated here. The weight of the trash stored in the target trash can is the real-time trash weight. The use of a temperature and humidity sensor to collect temperature and humidity data from the target trash can refers to measuring the temperature and humidity inside the target trash can using a temperature and humidity sensor. The method for measuring the temperature and humidity inside the target trash can using a temperature and humidity sensor is existing technology and will not be elaborated here. The humidity inside the trash can refers to the humidity inside the target trash can, and the temperature inside the trash can refers to the temperature inside the target trash can.

[0209] It is understood that the video surveillance equipment refers to a camera pre-installed near the target trash can. The phrase "using the video surveillance equipment to capture images of the target trash can's appearance" means capturing images of the environment surrounding the target trash can. The method for capturing these images is existing technology and will not be elaborated upon here. The surrounding environment image refers to an image of the environment around the target trash can. The area surrounding the target trash can refers to the interior of a circle with a radius of 1.5 meters, centered on the projection of the target trash can's center of gravity onto the ground. The collection timestamp refers to the timestamp of the most recent collection of the target trash can, and this timestamp can be obtained from the target trash can's operation log.

[0210] It should be understood that regional temperature refers to the temperature of the area where the target trash can is located, and precipitation probability refers to the probability of precipitation in the area where the target trash can is located. Both regional temperature and precipitation probability can be obtained from the meteorological bureau. The integration of space occupancy rate, real-time trash weight, internal humidity, internal temperature, trash scattering index, collection timestamp, regional temperature, and precipitation probability means combining these data into one source. Multi-source sensing data is the data obtained after integrating these data. The multi-source sensing dataset is a collection composed of multiple multi-source sensing data sets.

[0211] Specifically, the process of identifying litter scattered in surrounding environmental images to obtain a litter scattered index includes:

[0212] The surrounding environment image is converted to grayscale to obtain a grayscale image;

[0213] Binarize the grayscale image to obtain a binary image;

[0214] Connectivity analysis of the binarized image revealed several suspected litter-scattered areas.

[0215] For each of the multiple suspected litter areas, perform the following operations:

[0216] The pixel area was determined based on the suspected area of ​​scattered garbage.

[0217] Sum the pixel areas to obtain multiple pixel areas;

[0218] The total scattered pixel area is determined based on the area of ​​multiple pixels, where the total scattered pixel area is the sum of the areas of multiple pixels;

[0219] Once the image pixel area is determined, the garbage scattering index is calculated based on the total scattered pixel area and the image pixel area. The calculation formula is as follows:

[0220]

[0221] in, Indicates the litter dispersion index, Represents the total scattered pixel area. Represents the area of ​​image pixels. This is the preset scaling factor. This indicates the function that takes the smaller value.

[0222] It should be explained that the grayscale processing of the surrounding environment image refers to converting each pixel in the surrounding environment image to grayscale. The method for grayscale conversion of each pixel in the surrounding environment image is existing technology and will not be elaborated here. The grayscale image refers to the surrounding environment image after grayscale processing. The binarization processing of the grayscale image refers to binarizing each pixel in the grayscale image. The method for binarization of each pixel in the grayscale image is existing technology and will not be elaborated here. The binarized image refers to the grayscale image after binarization processing. The connected component analysis of the binarized image refers to analyzing the binarized image using a connected component analysis algorithm to obtain multiple connected regions. These connected regions are suspected areas of scattered garbage. The method for analyzing the binarized image using a connected component analysis algorithm to obtain multiple connected regions is existing technology and will not be elaborated here. Optionally, the Two-Pass algorithm can be used as the connected component analysis algorithm.

[0223] Understandably, pixel area refers to the total area of ​​all pixels within the suspected litter-strewn area, while image pixel area refers to the total area of ​​all pixels in the binarized image. The litter-strewn index reflects the amount of litter scattered around the target trash can; the higher the litter-strewn index, the more litter scattered around the target trash can. The scaling factor is a value manually set by the cleaning company's management based on the pedestrian traffic near the target trash can. Optionally, if the pedestrian traffic near the target trash can is high, the scaling factor is set to 1.5; if the pedestrian traffic near the target trash can is medium, the scaling factor is set to 1.3; and if the pedestrian traffic near the target trash can is low, the scaling factor is set to 1.1.

[0224] Specifically, the determination of the environmental state score based on the multi-source sensing dataset includes:

[0225] Perform the following operation on each multi-source sensing data point in the multi-source sensing dataset:

[0226] The overflow deviation index is calculated based on the space occupancy rate in the multi-source sensing data and the preset overflow threshold. The calculation formula is as follows:

[0227]

[0228] in, This indicates the overflow deviation index. This represents the space occupancy rate in multi-source sensing data. Indicates the overflow threshold. Indicates taking the larger function;

[0229] The load index is calculated based on the real-time waste weight from multi-source sensing data and the preset rated load capacity. The calculation formula is as follows:

[0230]

[0231] in, Indicates the load index. This represents the real-time weight of waste in the multi-source sensing data. Indicates the rated load capacity;

[0232] The environmental anomaly index is calculated based on the internal temperature, regional temperature, and internal humidity data from multi-source sensing data. The calculation formula is as follows:

[0233]

[0234] in, Indicates an environmental anomaly index. This represents the temperature inside the chamber from multi-source sensing data. This represents the regional temperature from multi-source sensing data. This represents the humidity inside the container from multi-source sensing data. This indicates the preset temperature influence index. This indicates the preset humidity impact index;

[0235] The anomaly degree of a single unit is determined based on the overflow deviation index, load index, environmental anomaly index, and litter dispersion index. The anomaly degree of a single unit is the sum of the overflow deviation index, load index, environmental anomaly index, and litter dispersion index.

[0236] Summarize the individual anomalies to obtain multiple individual anomalies;

[0237] The average outlier was determined based on multiple individual outliers, where the average outlier is the average of the multiple individual outliers.

[0238] The facility status score is calculated based on the average anomaly rate, using the following formula:

[0239]

[0240] in, Indicates the facility status score. Indicates the average anomaly degree;

[0241] An environmental status score was determined based on facility status scores and multi-source sensing datasets.

[0242] It should be explained that the overflow deviation index reflects the saturation level of the target trash can currently loaded with garbage. The larger the overflow deviation index, the greater the saturation level of the target trash can, indicating that the target trash can is loaded with a lot of garbage, has a high load pressure, and needs to be cleaned. The overflow threshold is a value set manually by the cleaning company's staff; optionally, the overflow threshold is 80. The load capacity index reflects the ratio of the weight of the garbage currently loaded in the target trash can to the structural design safety limit of the target trash can. When the load capacity index is close to 1, it indicates that the weight of the garbage in the target trash can is approaching the limit that the target trash can can withstand, and it needs to be prioritized for removal to prevent damage to the structure of the can. The rated load capacity is a value set manually by the cleaning company's management personnel based on the maximum weight of garbage that the target trash can can hold. For example, if the maximum weight of garbage that the target trash can can hold is 50 kg, then the rated load capacity is 50 kg, and the maximum weight of garbage that the target trash can can hold can be obtained from the product technical manual provided by the target trash can manufacturer. The structural design safety limit refers to the upper limit of the weight of garbage that will not damage the structure of the target trash can.

[0243] Understandably, the Environmental Anomaly Index reflects the degree of difference between the temperature and humidity inside and outside the target trash can. A higher Environmental Anomaly Index indicates a greater difference between the temperature and humidity inside and outside the target trash can, suggesting abnormal fermentation or temperature rise within the trash can, requiring prompt removal and treatment. The Temperature Impact Index (which can be set to 20) serves as a baseline value for the temperature difference (the absolute difference between the temperature inside the trash can and the regional temperature), used to normalize significant biological fermentation (generating heat) or abnormal temperature rise. The Humidity Impact Index (which can be set to 200) acts as a scaling factor for humidity, normalizing the percentage-based humidity inside the trash can while balancing the contribution weights of humidity and temperature, reflecting that temperature changes have a higher weight than humidity changes. The Facility Status Score reflects the overall operational health of all target trash cans within the candidate unit area. A higher Facility Status Score indicates a better overall operational health of all target trash cans within the candidate unit area, suggesting continued operation without the need for removal and treatment.

[0244] Specifically, the environmental status score determined based on facility status score and multi-source sensing dataset includes:

[0245] Once the current time is determined, perform the following operation on each multi-source sensing data point in the multi-source sensing dataset:

[0246] The number of days for the collection interval is determined based on the current time and the collection timestamp in the multi-source sensing data.

[0247] The collection delay rate is calculated based on the collection interval days and the preset standard collection cycle, using the following formula:

[0248]

[0249] in, This indicates the rate of delay in waste collection. Indicates the number of days between cleaning and collection. Indicates the standard waste collection cycle;

[0250] Summarize the collection delay rates to obtain multiple collection delay rates;

[0251] An average delay rate was determined based on multiple collection delay rates, where the average delay rate is the average of the multiple collection delay rates;

[0252] The facility operation score is calculated based on the waste removal delay rate and the precipitation probability from multi-source sensing data, as shown in the following formula:

[0253]

[0254] in, Indicates facility operation score, This represents the average delay rate. Indicates the probability of precipitation;

[0255] The environmental status score is calculated based on the facility status score and facility operation score, using the following formula:

[0256]

[0257] in, This indicates the environmental condition score.

[0258] It should be explained that "current time" refers to the current time, and "collection interval days" refers to the number of days between the current time and the collection timestamp in the multi-source sensing data. For example, if the current time is 10:30 AM on December 26th, and the collection timestamp in the multi-source sensing data is 10:30 AM on December 25th, then the collection interval days are 1 day. If the current time is 10:30 AM on December 26th, and the collection timestamp in the multi-source sensing data is 4:30 AM on December 26th, then the collection interval days are 0.25 days. The standard collection cycle is a duration manually set by the cleaning company's management personnel based on the pedestrian traffic near the target trash can. Optionally, if the pedestrian traffic near the target trash can is high, the standard collection cycle is set to 6 hours; if the pedestrian traffic near the target trash can is medium, the standard collection cycle is set to 12 hours; and if the pedestrian traffic near the target trash can is low, the standard collection cycle is set to 24 hours. The collection delay rate reflects the severity of the deviation between the actual collection cycle and the standard collection cycle of the target garbage bin. A higher collection delay rate indicates a greater degree of deviation and a risk of overflow. The facility operation score reflects the timeliness of overall collection operations within a unit area, taking into account external environmental disturbances (primarily precipitation probability). A higher facility operation score indicates stronger timeliness of overall collection operations within the unit area. The environmental condition score reflects the overall cleanliness level of the environment within the unit area. A higher environmental condition score indicates a higher overall cleanliness level, suggesting that the sanitation facilities within the unit area are in good condition and that collection operations are timely and efficient.

[0259] S6. Based on multiple environmental status scores and multiple candidate unit regions, an abnormal region set is identified. The abnormal region set includes multiple abnormal unit regions. For each of the multiple abnormal unit regions, the following operation is performed: the regional center coordinates of the abnormal unit region and multiple adjacent regions are identified.

[0260] It should be explained that the identification of the abnormal region set based on multiple environmental status scores and multiple candidate unit regions means: comparing each environmental status score with a preset status score threshold to obtain all environmental status scores below the threshold; then extracting the candidate unit regions corresponding to all environmental status scores below the threshold from the multiple candidate unit regions. The abnormal region set is the collection of candidate unit regions corresponding to all environmental status scores below the threshold, and these candidate unit regions are the abnormal unit regions. The region center coordinates refer to the coordinates of the center of the smallest circumcircle of the abnormal unit region within the management area. Adjacent regions refer to candidate unit regions adjacent to the abnormal unit regions. The status score threshold is a value manually set by the cleaning company staff based on the average environmental status scores of multiple unit regions where multiple normally operating target trash cans are located historically. For example, if the average environmental status scores of multiple unit regions where multiple normally operating target trash cans are located historically is 85, then the status score threshold is 85.

[0261] S7. Based on the regional center coordinates and multiple adjacent areas, a management and scheduling plan is identified, and the management and scheduling plans are summarized to obtain multiple management and scheduling plans, thus completing the intelligent management of sanitation facilities.

[0262] Specifically, the process of determining the management and scheduling scheme based on the regional center coordinates and multiple adjacent regions includes:

[0263] Several vacant sanitation vehicles were identified;

[0264] For each of the multiple available sanitation vehicles, perform the following operations:

[0265] Obtain the real-time geographic location coordinates, current load, and rated load capacity of idle sanitation vehicles;

[0266] The real-time geographic location coordinates, current load, and rated load capacity are summarized to obtain the idle vehicle status data;

[0267] Summarize the idle vehicle status data to obtain multiple idle vehicle status data;

[0268] The target vehicle to be dispatched was identified based on the coordinates of the regional center and the status data of multiple idle vehicles.

[0269] The scope of the scheduling operation is determined based on multiple adjacent areas;

[0270] A management and dispatching plan is determined based on the target vehicles and the scope of dispatching operations.

[0271] It should be explained that "idle sanitation vehicles" refers to garbage collection vehicles that are idle in the management area; "real-time geographic location coordinates" refers to the coordinates of the idle sanitation vehicles in the management area; "current load" refers to the weight of garbage in the idle sanitation vehicles; and "rated load capacity" refers to the maximum allowable load of the idle sanitation vehicles. The maximum allowable load of the idle sanitation vehicles can be obtained from the vehicle technical manual provided by the manufacturer of the idle sanitation vehicles. "Summarizing the real-time geographic location coordinates, current load, and rated load capacity" means integrating the real-time geographic location coordinates, current load, and rated load capacity. "Idle vehicle status data" refers to the data obtained after summarizing the real-time geographic location coordinates, current load, and rated load capacity.

[0272] It should be understood that identifying the target dispatch vehicle based on the regional center coordinates and multiple idle vehicle status data means: calculating the distances between multiple real-time geographical coordinates in the multiple idle vehicle status data and the regional center coordinates to obtain multiple vehicle distances, and selecting the idle sanitation vehicle corresponding to the smallest vehicle distance as the target dispatch vehicle. Confirming the dispatch operation range based on multiple adjacent areas means: obtaining the environmental status score of each adjacent area in multiple adjacent areas of the abnormal unit area, merging adjacent areas with environmental status scores less than the status score threshold with the abnormal unit area to obtain the dispatch operation range. Determining the management and dispatch scheme based on the target dispatch vehicle and the dispatch operation range means: first, identifying multiple target garbage bins within the dispatch operation range, and then determining the collection order according to the distance between the target dispatch vehicle and the multiple target garbage bins from closest to farthest, thus obtaining the final management and dispatch scheme. The collection order is the management and dispatch scheme.

[0273] For example, once multiple management and scheduling schemes are obtained, Xiao Zhang can distribute these schemes to the corresponding garbage trucks, thereby achieving the management of sanitation facilities.

[0274] To address the problems described in the background art, this invention identifies a management area, extracts sanitation facilities within that area, and obtains multiple trash cans. This demonstrates that by clearly defining the management scope and accurately identifying target facilities, a foundational object library is established for subsequent digital management. Furthermore, a regional base map is generated based on the management area. This invention also acquires and constructs a standard geographic information layer for the management area, providing a digital platform for the spatial and visual management of sanitation facilities, thus improving the intelligence level of sanitation facility management. By digitally modeling multiple trash cans, multiple trash can models are obtained. This invention creates a corresponding three-dimensional digital model for each physical trash can, standardizing its data specifications and realizing the transformation from physical entities to digital twins. The transformation of the body maps multiple trash can models onto a regional base map, resulting in a digital base map. This embodiment of the invention generates a "single map" by precisely overlaying the facility digital model with geographic information, achieving intuitive and accurate visualization management of the entire sanitation facility distribution. The digital base map is then divided into regions, resulting in multiple candidate unit regions. This embodiment of the invention divides the entire region into logically clear and appropriately sized grid units based on management needs, providing structural support for a refined and district-level management model, and improving the intelligence level of sanitation facility management. For each candidate unit region, the following operation is performed: based on the candidate unit region and multiple trash cans, multiple target trash cans are identified. This embodiment of the invention, through... Each management unit automatically associates with specific facilities within its jurisdiction, clarifying the management objects and responsibilities of each unit. Based on multiple target trash cans, a multi-source sensing dataset is identified. This embodiment of the invention gathers real-time data (such as overflow level and temperature) from sensors of various facilities to form a dynamic dataset reflecting the sanitation status within the unit. Based on the multi-source sensing dataset, an environmental status score is determined. This embodiment of the invention utilizes a preset algorithm model to comprehensively analyze the sensing data, outputting a quantitative score to objectively assess the real-time sanitation health of each unit area, thus improving the intelligence level of sanitation facility management. By summarizing the environmental status scores, multiple environmental status scores are obtained. This embodiment of the invention forms a global environmental status score by aggregating the evaluation results of all units. This panoramic view of sanitation status allows management to conduct horizontal comparisons and overall situation assessments. Based on multiple environmental status scores and multiple candidate unit areas, an abnormal area set is identified. This abnormal area set includes multiple abnormal unit areas. As can be seen, this embodiment of the invention automatically filters out abnormal areas with excessively low scores that require priority intervention by setting threshold rules, achieving intelligent problem identification and early warning. For each of the multiple abnormal unit areas, the following operations are performed: the coordinates of the abnormal unit area's center and multiple adjacent areas are identified. This embodiment of the invention provides a geographical basis for formulating efficient and collaborative scheduling strategies by locating the core location of the abnormal area and analyzing its surrounding spatial relationships, thus improving the intelligence level of sanitation facility management.Based on the coordinates of the regional center and multiple adjacent areas, a management and scheduling plan is identified. It is evident that this embodiment of the invention intelligently generates optimized scheduling instructions, including personnel and vehicle routes, by comprehensively considering the problem's location, severity, and the availability of surrounding resources. By summarizing the management and scheduling plans, multiple management and scheduling schemes are obtained, thus completing the intelligent management of sanitation facilities. It is clear that this embodiment of the invention integrates and distributes the handling plans for all abnormal areas, forming a complete management closed loop from intelligent discovery and assessment to automatic generation and execution of optimized plans. This improves operational efficiency and response speed, and enhances the level of intelligence in sanitation facility management. Therefore, this invention can improve the level of intelligence in sanitation facility management.

[0275] like Figure 2 The diagram shown is a functional block diagram of an intelligent sanitation facility management system based on multi-source sensing data provided in an embodiment of the present invention.

[0276] The intelligent sanitation facility management system 100 based on multi-source sensing data described in this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent sanitation facility management system 100 based on multi-source sensing data may include a regional base map acquisition module 101, a status scoring acquisition module 102, an abnormal area confirmation module 103, and a scheduling scheme generation module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0277] The area base map acquisition module 101 is used to identify the management area, extract sanitation facilities in the management area to obtain multiple trash cans, and identify the area base map based on the management area.

[0278] The state score acquisition module 102 is used to digitally model multiple trash cans to obtain multiple trash can models, map the multiple trash can models to a regional base map to obtain a digital base map, divide the digital base map into regions to obtain multiple candidate unit regions, and perform the following operations on each candidate unit region: identify multiple target trash cans based on the candidate unit regions and multiple trash cans, identify a multi-source sensing dataset based on the multiple target trash cans, identify an environmental state score based on the multi-source sensing dataset, and summarize the environmental state scores to obtain multiple environmental state scores;

[0279] The abnormal region confirmation module 103 is used to confirm an abnormal region set based on multiple environmental state scores and multiple candidate unit regions. The abnormal region set includes multiple abnormal unit regions. The following operation is performed on each of the multiple abnormal unit regions.

[0280] The scheduling scheme generation module 104 is used to identify the regional center coordinates of the abnormal unit area and multiple adjacent areas, identify the management scheduling scheme based on the regional center coordinates and multiple adjacent areas, summarize the management scheduling schemes, obtain multiple management scheduling schemes, and complete the intelligent management of sanitation facilities.

[0281] In detail, the modules in the intelligent sanitation facility management system 100 based on multi-source sensing data described in this embodiment of the invention employ the same methods as described above. Figure 1 The method uses the same technical means as the intelligent management method for sanitation facilities based on multi-source sensing data described in the article, and can produce the same technical effect, so it will not be elaborated here.

[0282] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing an intelligent management method for sanitation facilities based on multi-source sensing data, according to an embodiment of the present invention.

[0283] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a method program for intelligent management of sanitation facilities based on multi-source sensing data.

[0284] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as the portable hard drive of the electronic device 1. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a smart management method program for sanitation facilities based on multi-source sensing data, but also to temporarily store data that has been output or will be output.

[0285] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., intelligent management method program for sanitation facilities based on multi-source sensing data) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0286] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0287] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0288] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0289] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0290] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0291] The intelligent management method program for sanitation facilities based on multi-source sensing data, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0292] Once the management area is identified, sanitation facilities are extracted from the management area, resulting in multiple trash cans;

[0293] A base map of the region was determined based on the management area;

[0294] Multiple trash cans were digitally modeled to obtain multiple trash can models;

[0295] Multiple trash can models are mapped onto the regional base map to obtain a digital base map;

[0296] The digital base map is divided into regions to obtain multiple candidate unit regions;

[0297] For each of the multiple candidate cell regions, perform the following operation:

[0298] Based on the candidate unit area and multiple trash cans, multiple target trash cans were identified;

[0299] A multi-source sensing dataset was identified based on multiple target trash cans;

[0300] An environmental status score was determined based on a multi-source sensing dataset.

[0301] The environmental status scores are aggregated to obtain multiple environmental status scores;

[0302] An abnormal region set was identified based on multiple environmental status scores and multiple candidate unit regions. The abnormal region set includes multiple abnormal unit regions.

[0303] For each of the multiple abnormal cell regions, perform the following operation:

[0304] The coordinates of the center of the abnormal unit region and multiple adjacent regions were identified.

[0305] A management and scheduling scheme was determined based on the regional center coordinates and multiple adjacent regions.

[0306] By summarizing the management and scheduling schemes, multiple management and scheduling schemes are obtained, thus completing the intelligent management of sanitation facilities.

[0307] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0308] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0309] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0310] Once the management area is identified, sanitation facilities are extracted from the management area, resulting in multiple trash cans;

[0311] A base map of the region was determined based on the management area;

[0312] Multiple trash cans were digitally modeled to obtain multiple trash can models;

[0313] Multiple trash can models are mapped onto the regional base map to obtain a digital base map;

[0314] The digital base map is divided into regions to obtain multiple candidate unit regions;

[0315] For each of the multiple candidate cell regions, perform the following operation:

[0316] Based on the candidate unit area and multiple trash cans, multiple target trash cans were identified;

[0317] A multi-source sensing dataset was identified based on multiple target trash cans;

[0318] An environmental status score was determined based on a multi-source sensing dataset.

[0319] The environmental status scores are aggregated to obtain multiple environmental status scores;

[0320] An abnormal region set was identified based on multiple environmental status scores and multiple candidate unit regions. The abnormal region set includes multiple abnormal unit regions.

[0321] For each of the multiple abnormal cell regions, perform the following operation:

[0322] The coordinates of the center of the abnormal unit region and multiple adjacent regions were identified.

[0323] A management and scheduling scheme was determined based on the regional center coordinates and multiple adjacent regions.

[0324] By summarizing the management and scheduling schemes, multiple management and scheduling schemes are obtained, thus completing the intelligent management of sanitation facilities.

[0325] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0326] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0327] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0328] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0329] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for intelligent management of sanitation facilities based on multi-source sensing data, characterized in that, The method includes: Once the management area is identified, sanitation facilities are extracted from the management area, resulting in multiple trash cans; A base map of the region was determined based on the management area; Multiple trash cans were digitally modeled to obtain multiple trash can models; Multiple trash can models are mapped onto the regional base map to obtain a digital base map; The digital base map is divided into regions to obtain multiple candidate unit regions; For each of the multiple candidate cell regions, perform the following operation: Based on the candidate unit area and multiple trash cans, multiple target trash cans were identified; A multi-source sensing dataset was identified based on multiple target trash cans; An environmental status score was determined based on a multi-source sensing dataset. The environmental status scores are aggregated to obtain multiple environmental status scores; An abnormal region set was identified based on multiple environmental status scores and multiple candidate unit regions. The abnormal region set includes multiple abnormal unit regions. For each of the multiple abnormal cell regions, perform the following operation: The coordinates of the center of the abnormal unit region and multiple adjacent regions were identified. A management and scheduling scheme was determined based on the regional center coordinates and multiple adjacent regions. By summarizing the management and scheduling schemes, multiple management and scheduling schemes are obtained, thus completing the intelligent management of sanitation facilities.

2. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 1, characterized in that, The process of dividing the digital base map into regions yields multiple candidate unit regions, including: Roads are extracted from the digital base map to obtain a road distribution map; The road distribution map is subjected to topological processing to obtain a road topology map, which includes multiple path nodes and multiple path lines. Multiple road segments were identified based on multiple path nodes and multiple path lines in the road topology map; Multiple interconnected, non-closed-loop road segments were identified based on multiple road sections; Multiple connected, non-closed-loop road segments are combined to obtain multiple candidate unit areas.

3. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 2, characterized in that, The multiple road segments identified based on multiple path nodes and multiple path lines in the road topology map include: Perform the following operation on each of the multiple path nodes: The number of connecting lines is determined based on the path nodes and multiple path lines; Compare the number of connecting lines with a preset threshold. If the number of connecting lines is greater than the threshold, then the path node is used as the first type of split point. If the number of connecting lines is less than or equal to the number threshold, then the path node is regarded as the first invalid split point; By summing up the first type of split points and the first invalid split points respectively, we obtain multiple first type split points and multiple first invalid split points; Multiple first-type segmentation points and multiple first-invalid segmentation points are removed from multiple path nodes to obtain multiple filtered segmentation points; For each of the multiple filter split points, perform the following operation: Based on the selection of dividing points and multiple path lines, multiple connected path lines were identified; Perform the following operation on each of the multiple connected paths: The road class code is determined based on the connected path lines; By summing up the road class codes, multiple road class codes are obtained; Determine whether multiple road level codes are consistent. If multiple road level codes are inconsistent, then the selected dividing point will be used as the second type of dividing point. If multiple road level codes are the same, the filtering split point will be used as the second invalid split point; By summing up the second type of split points and the second invalid split points respectively, we obtain multiple second type split points and multiple second invalid split points; Multiple final segmentation points were identified based on multiple first-type segmentation points, multiple second-type segmentation points, multiple first-invalid segmentation points, and multiple second-invalid segmentation points. Multiple path lines are further divided using multiple final split points to obtain multiple road segments.

4. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 3, characterized in that, The process of combining multiple connected, non-closed-loop road segments to obtain multiple candidate unit regions includes: For each of the multiple connected non-closed loop road segments, perform the following operation: The road segment grade code is determined based on the connected non-closed loop road segments; By summing up the road segment grade codes, multiple road segment grade codes are obtained; Multiple connected, non-closed-loop road segments are sorted according to their corresponding road segment level codes to obtain a sequence to be processed, which includes multiple road segments to be processed. Extract the first segment from multiple segments to be processed in the sequence to be processed. There are several road sections awaiting processing, among which... The initial value is 1; The first One unprocessed road segment is used as the starting segment; A candidate road segment set is identified based on the initial road segment and multiple connected non-closed loop road segments. The candidate road segment set includes multiple candidate road segments. Feasibility results were determined based on multiple candidate road segments in the candidate road segment set, where the feasibility result is either feasible or infeasible. If the feasibility result is not feasible, a second set of candidate road segments is identified based on the candidate road segment set and multiple connected non-closed loop road segments; The second set of candidate road segments is used as the candidate road segment set, and the step of confirming the feasibility result based on multiple candidate road segments in the candidate road segment set is returned until the feasibility result is feasible. If the feasibility result is feasible, the initial area is identified based on multiple candidate road segments; The unit independence results were determined based on the initial region and multiple connected non-closed loop road segments. The unit independence results were: independent or not independent. If the unit independence result is independent, the initial region is used as the candidate unit region and multiple candidate road segments are marked as used to obtain multiple marked road segments; If the unit independence result is not independent, then the boundary road segment is identified based on the initial region and multiple connected unclosed loop road segments; Using the boundary road segment as the starting road segment, return to the step of identifying the candidate road segment set based on the starting road segment and multiple connected non-closed loop road segments, until the unit independence result is independent; make ,Will As Multiple marked road segments are removed from the sequence to be processed to obtain an updated sequence to be processed. This updated sequence is then used as the sequence to be processed. The process of extracting the first road segment from the multiple road segments to be processed in the sequence to be processed is then repeated. The steps for each pending road segment, until... By summing up the candidate unit regions, multiple candidate unit regions are obtained, among which... This represents the number of road segments to be processed out of multiple road segments in the sequence to be processed.

5. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 4, characterized in that, The multi-source sensing dataset identified based on multiple target trash cans includes: Perform the following operation on each of the multiple target trash cans: Acquire data from overflow sensors, weight sensors, and temperature and humidity sensors; The occupancy rate of the target trash can is collected using an overflow sensor to obtain the space occupancy rate; The weight of the target trash can is collected using a weight sensor to obtain the real-time weight of the trash; Temperature and humidity sensors are used to collect data on the target trash can, obtaining the humidity and temperature inside the can. The video surveillance equipment was identified based on the target trash can; The target trash can was captured using video surveillance equipment to obtain images of its surrounding environment. The litter dispersion index is obtained by identifying litter dispersion in images of the surrounding environment. The collection timestamp is determined based on the target trash can; Obtain regional temperature and precipitation probability; By integrating space occupancy rate, real-time waste weight, humidity inside the bin, temperature inside the bin, waste scattering index, collection timestamp, regional temperature and precipitation probability, multi-source sensing data is obtained. By aggregating the multi-source sensing data, a multi-source sensing dataset is obtained.

6. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 5, characterized in that, The process of identifying litter scattered in surrounding environmental images to obtain a litter scattered index includes: The surrounding environment image is converted to grayscale to obtain a grayscale image; Binarize the grayscale image to obtain a binary image; Connectivity analysis of the binarized image revealed several suspected litter-scattered areas. For each of the multiple suspected litter areas, perform the following operations: The pixel area was determined based on the suspected area of ​​scattered garbage. Sum the pixel areas to get multiple pixel areas; The total scattered pixel area is determined based on the area of ​​multiple pixels, where the total scattered pixel area is the sum of the areas of multiple pixels; Once the image pixel area is identified, the littering index is calculated based on the total scattered pixel area and the image pixel area.

7. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 6, characterized in that, The environmental state score determined based on the multi-source sensing dataset includes: Perform the following operation on each multi-source sensing data point in the multi-source sensing dataset: The overflow deviation index is calculated based on the space occupancy rate in multi-source sensing data and the preset overflow threshold. The load index is calculated based on the real-time waste weight and the preset rated load from multi-source sensing data. The environmental anomaly index is calculated based on the internal temperature, regional temperature, and internal humidity data from multi-source sensing data. The calculation formula is as follows: in, Indicates an environmental anomaly index. This represents the temperature inside the chamber from multi-source sensing data. This represents the regional temperature from multi-source sensing data. This represents the humidity inside the container from multi-source sensing data. This indicates the preset temperature influence index. This indicates the preset humidity impact index; The anomaly degree of a single unit is determined based on the overflow deviation index, load index, environmental anomaly index, and litter dispersion index. The anomaly degree of a single unit is the sum of the overflow deviation index, load index, environmental anomaly index, and litter dispersion index. Summarize the individual anomalies to obtain multiple individual anomalies; The average outlier was determined based on multiple individual outliers, where the average outlier is the average of the multiple individual outliers. Calculate facility status score based on average anomaly degree; An environmental status score was determined based on facility status scores and multi-source sensing datasets.

8. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 7, characterized in that, The environmental status score determined based on facility status score and multi-source sensing dataset includes: Once the current time is determined, perform the following operation on each multi-source sensing data point in the multi-source sensing dataset: The number of days for the collection interval is determined based on the current time and the collection timestamp in the multi-source sensing data. The collection delay rate is calculated based on the collection interval days and the preset standard collection cycle. Summarize the collection delay rates to obtain multiple collection delay rates; An average delay rate was determined based on multiple collection delay rates, where the average delay rate is the average of the multiple collection delay rates; The facility operation score is calculated based on the waste removal delay rate and the precipitation probability from multi-source sensing data, as shown in the following formula: in, Indicates facility operation score, This represents the average delay rate. Indicates the probability of precipitation; The environmental status score is calculated based on the facility status score and the facility operation score.

9. The intelligent management method for sanitation facilities based on multi-source sensing data as described in claim 8, characterized in that, The management and scheduling scheme determined based on the regional center coordinates and multiple adjacent regions includes: Several vacant sanitation vehicles were identified; For each of the multiple available sanitation vehicles, perform the following operations: Obtain the real-time geographic location coordinates, current load, and rated load capacity of idle sanitation vehicles; The real-time geographic location coordinates, current load, and rated load capacity are summarized to obtain the idle vehicle status data; Summarize the idle vehicle status data to obtain multiple idle vehicle status data; The target vehicle to be dispatched was identified based on the coordinates of the regional center and the status data of multiple idle vehicles. The scope of the scheduling operation is determined based on multiple adjacent areas; A management and dispatching plan is determined based on the target vehicles and the scope of dispatching operations.

10. An intelligent management system for sanitation facilities based on multi-source sensing data, characterized in that, The system includes: The regional base map acquisition module is used to identify the management area, extract sanitation facilities in the management area to obtain multiple trash cans, and identify the regional base map based on the management area; The status score acquisition module is used to digitally model multiple trash cans to obtain multiple trash can models, map the multiple trash can models to a regional base map to obtain a digital base map, divide the digital base map into regions to obtain multiple candidate unit regions, and perform the following operations on each candidate unit region: identify multiple target trash cans based on the candidate unit regions and multiple trash cans, identify a multi-source sensing dataset based on the multiple target trash cans, identify an environmental status score based on the multi-source sensing dataset, and summarize the environmental status scores to obtain multiple environmental status scores; The abnormal region confirmation module is used to confirm an abnormal region set based on multiple environmental status scores and multiple candidate unit regions. The abnormal region set includes multiple abnormal unit regions. The following operation is performed on each of the multiple abnormal unit regions. The scheduling scheme generation module is used to identify the regional center coordinates of the abnormal unit area and multiple adjacent areas, identify the management scheduling scheme based on the regional center coordinates and multiple adjacent areas, summarize the management scheduling schemes, obtain multiple management scheduling schemes, and complete the intelligent management of sanitation facilities.

Images