A space calculation-based environmental sanitation equipment positioning and state monitoring system

Abstract

The application discloses a kind of based on spatial computing's environmental sanitation equipment positioning and state monitoring system, it is related to environmental sanitation operation supervision technical field, including: data standardization module, for generating environmental sanitation equipment monitoring dataset;Space unit construction module, for dividing environmental sanitation operation space unit and generating space constraint index;Candidate unit generation module, for generating candidate operation space unit;Space sequence matching module, for determining equipment operation space matching sequence based on space constraint hidden Markov algorithm and Viterbi dynamic programming;State time sequence fusion module, for generating equipment space state fusion result;Effective operation discrimination module, for generating environmental sanitation equipment effective operation discrimination result;Abnormal monitoring output module, for generating environmental sanitation equipment positioning and state monitoring result.The application can improve environmental sanitation equipment space matching accuracy, effective operation discrimination reliability and abnormal supervision refinement degree.

Description

Technical Field

[0001] This invention relates to the field of sanitation operation supervision technology, and in particular to a sanitation equipment positioning and status monitoring system based on spatial computing. Background Technology

[0002] In recent years, with the development of refined urban sanitation management, vehicle-mounted positioning terminals, IoT sensing devices, digital maps, and operation scheduling platforms, the positioning and operational status monitoring of sanitation equipment has gradually become an important part of smart sanitation management. Current technologies typically collect GPS positioning data, equipment operating status data, and operational task data from sanitation equipment such as sweepers, water trucks, and garbage collection trucks. This data is then used to statistically analyze vehicle location, driving trajectory, operation time, and task completion. Combined with methods such as electronic fences, trajectory playback, and rule-based threshold judgments, the system monitors whether the equipment has entered the work area, whether it is operating along the prescribed route, and whether there are any instances of stopping, deviation, or missed sweeping.

[0003] However, existing technologies still suffer from insufficient spatial matching accuracy and inaccurate judgment of operational effectiveness in the positioning and status monitoring of sanitation equipment. On the one hand, sanitation operation scenarios involve complex road sections, work areas, collection points, and service grid boundaries. Positioning points are easily affected by drift, obstruction, and sampling intervals. Simply relying on the location of the point or electronic fence makes it difficult to accurately determine the actual work space unit corresponding to the equipment at each collection time. On the other hand, existing solutions often process positioning trajectory, equipment operating status, and work task constraints separately, lacking temporal fusion analysis of spatial boundaries, access connections, task range, and equipment operating status. This can easily lead to misjudging passing or stopping as valid operations, and makes it difficult to distinguish in a timely manner between deviation from operations, incomplete operations, and abnormal equipment status, affecting the accuracy and usability of sanitation operation supervision results. Summary of the Invention

[0004] One objective of this invention is to propose a spatial computing-based sanitation equipment positioning and status monitoring system. This invention fully utilizes spatial computing, spatially constrained hidden Markov algorithms, and state-time fusion technology, and describes in detail the implementation process of sanitation equipment operation space matching, effective operation identification, and abnormal status monitoring. It has the advantages of accurate spatial matching, reliable operation identification, and high degree of refined supervision.

[0005] According to an embodiment of the present invention, a sanitation equipment positioning and status monitoring system based on spatial computing includes: The data standardization module is used to acquire and standardize the monitoring data of sanitation equipment to generate a sanitation equipment monitoring dataset. The spatial unit construction module is used to divide sanitation operation spatial units based on the sanitation equipment monitoring dataset, and generate spatial constraint indexes according to spatial boundaries, access connections and task scope; The candidate unit generation module is used to perform spatial projection and boundary determination on the positioning points of sanitation equipment based on the spatial constraint index, and generate candidate operation spatial units corresponding to each collection time. The spatial sequence matching module is used to treat candidate operation space units as implicit states and sanitation equipment positioning points as observation states. It uses a spatially constrained hidden Markov algorithm to calculate the positioning observation cost and spatial transfer cost, and determines the equipment operation space matching sequence through Viterbi dynamic programming. The state-time fusion module is used to perform time-series correlation between the equipment operating status and the work task constraints corresponding to the equipment operation space matching sequence based on the sanitation equipment monitoring dataset, and generate the equipment space state fusion result. The effective operation discrimination module is used to determine the task matching status and effective operation status of sanitation equipment in each sanitation operation space unit based on the equipment space status fusion results and the matching object number, and generate the effective operation discrimination results of sanitation equipment. The anomaly monitoring output module is used to identify the deviation from the operation status, invalid operation status and abnormal status of sanitation equipment based on the effective operation judgment results of sanitation equipment, and generate the positioning and status monitoring results of sanitation equipment.

[0006] Optionally, the sanitation equipment monitoring associated data includes sanitation equipment positioning records, equipment operation status records, work task records, work space basic records, equipment attribute records, and historical monitoring records. The standardization processing includes unified equipment identification, unified coordinate system, aligned acquisition time, data format conversion, removal of abnormal records, completion of missing fields, merging of duplicate records, status code conversion, unified sampling frequency, and spatial object number marking.

[0007] Optionally, the spatial unit construction module includes: Extract basic records of the work space and work task records based on the sanitation equipment monitoring dataset; The road segments, work areas, collection and transportation points and service grids in the basic record of the work space are closed and organized according to the spatial boundaries to generate spatial objects to be divided. The spatial objects to be divided are subjected to coordinate correction, boundary overlap resolution, and object numbering and marking to generate sanitation operation spatial units; Generate passage connection records based on the road connectivity status, entrance and exit connection status, and operation passage direction between adjacent sanitation operation space units; Based on the task records, determine the equipment compatibility type, task coverage, and task time range for each sanitation operation space unit, and generate a task range record. The spatial constraint index is generated by associating sanitation operation space units, access connection records, and task scope records according to the spatial object number.

[0008] Optionally, the candidate unit generation module includes: Based on the sanitation equipment monitoring dataset, the sanitation equipment location records are extracted, and a sequence of sanitation equipment location points is generated according to the equipment number and collection time. Based on the spatial constraint index, the closed spatial range, object number, adjacent object number, and task range records of each sanitation operation spatial unit are obtained; The corresponding candidate search range is determined based on the positioning accuracy and data collection time of the sanitation equipment positioning points. The candidate search range is spatially intersected with the closed spatial range of the sanitation operation space unit to obtain the initial candidate space unit. Spatial projection is performed on the sanitation equipment location points and the initial candidate spatial units to determine the projection position, projection distance, and the object number to which the projection belongs; Based on the closed space range, the projection position is boundary determined, and the initial candidate spatial units located within the closed space range or within the boundary buffer range are identified as candidate operation spatial units; Candidate job space units are sorted according to the acquisition time to generate candidate job space units corresponding to each acquisition time.

[0009] Optionally, the spatial sequence matching module includes: A set of implicit states is established based on the candidate work space units corresponding to each collection time, and the sanitation equipment positioning points at the same collection time are determined as the observation states. The positioning observation cost of each candidate work space unit is calculated based on the projection distance, positioning accuracy and boundary determination results corresponding to the positioning points of sanitation equipment. Based on the adjacent object numbers, access connection records, and task range records in the spatial constraint index, calculate the spatial transfer cost of different candidate job spatial units between adjacent acquisition times. The location observation cost and spatial transfer cost are incorporated into the state cost matrix of the spatially constrained hidden Markov algorithm. According to the acquisition time sequence, the state cost matrix is ​​calculated by Viterbi dynamic programming to determine the candidate job space unit with the minimum cumulative cost at each acquisition time. The candidate workspace unit with the lowest cumulative cost is backtracked to generate a workspace matching sequence corresponding to the sanitation equipment location point sequence.

[0010] Optionally, the state-time fusion module includes: Based on the equipment workspace matching sequence, extract the equipment number, collection time, matching object number, projection position, and dwell time period; Based on the sanitation equipment monitoring dataset, the equipment operating status is matched according to the equipment number and collection time to generate a sequence of equipment operating status; Based on the sanitation equipment monitoring dataset, the operation task constraints are matched according to the equipment number, collection time, and matching object number to generate an operation task constraint sequence; The equipment workspace matching sequence, equipment operating status sequence, and work task constraint sequence are time-aligned according to the equipment number, collection time, and matching object number. The time-aligned records are continuously organized to generate device space state segments; Constraint matching is performed on equipment spatial state segments based on job task constraints to generate running state matching tags, spatial matching tags, and time matching tags; The device spatial state fragments, operating state matching tags, spatial matching tags, and time matching tags are associated to generate a device spatial state fusion result.

[0011] Optionally, the valid job determination module includes: Based on the device spatial state fusion results, extract the device number, matching object number, device spatial state fragment, device operating status, operating status matching tag, spatial matching tag and time matching tag; Based on the matching object number, the equipment spatial status segments are grouped according to the sanitation operation spatial unit to generate a set of spatial status segments; Based on spatial matching markers and temporal matching markers, task matching is determined for a set of spatial state fragments, and task matching status is generated. Based on the operation status matching tag and the equipment operation status, the set of spatial status segments is used to determine the validity of the operation and generate valid operation status; Anomalies are marked for sets of spatial state segments where the task matching status and the valid job status are inconsistent. Organize the equipment operating status, operating status matching flag, task matching status, effective operation status, and abnormal flag according to the equipment number, matching object number, and segment start and end time, and generate the effective operation judgment result of sanitation equipment.

[0012] Optionally, the anomaly monitoring output module includes: Based on the effective operation judgment results of sanitation equipment, extract the equipment number, matching object number, segment start and end time, task matching status, effective operation status, anomaly mark, equipment operation status and operation status matching mark; Determine the deviation status of sanitation equipment from its task operation based on the deviation from the anomaly markers. The invalid operation status of sanitation equipment is determined based on the in-place but not working anomaly and the effective operation status in the anomaly markers. The abnormal status of sanitation equipment is determined based on the equipment operating status and operating status matching tags. Based on the equipment number, the matching object number, and the start and end time of the segment, the deviation from the operation status, the invalid operation status, and the abnormal equipment status are correlated and organized to generate an equipment abnormality monitoring record; The time of occurrence of the anomaly, the corresponding spatial unit of the anomaly, and the type of the anomaly are determined based on the equipment anomaly monitoring records; The results of sanitation equipment location and status monitoring are generated by combining the time of anomaly occurrence, the corresponding spatial unit of the anomaly, the anomaly type, the deviation from the operation state, the invalid operation state, and the equipment anomaly state.

[0013] The beneficial effects of this invention are: This invention standardizes the monitoring data of sanitation equipment and divides sanitation operation space units based on basic operation space records. This allows different types of sanitation operation objects, such as road sections, operation areas, collection points, and service grids, to be expressed with unified spatial boundaries, object numbers, and access connections. Compared with methods that rely solely on location point landing areas or electronic fences, this invention can uniformly organize spatial boundaries, adjacent connections, and task ranges in complex operation scenarios. This provides a clearer spatial constraint basis for subsequent location matching and operation identification, reducing misjudgments of spatial attribution caused by boundary overlap, adjacent areas, or location drift.

[0014] This invention treats candidate operational space units as implicit states and sanitation equipment positioning points as observation states. It combines positioning observation costs, spatial transfer costs, and Viterbi dynamic programming to determine the equipment operational space matching sequence. This ensures that positioning points at individual acquisition moments are no longer judged in isolation, but are comprehensively matched based on spatial continuity, accessibility, and task range across different timeframes. Therefore, even with positioning point drift, occlusion, jumps, or unstable sampling intervals, this invention improves the accuracy and continuity of identifying actual operational space units for sanitation equipment, avoiding the direct identification of short-term offset points, boundary-near points, or abnormal jump points as the actual operational location of the equipment.

[0015] This invention further correlates the equipment operation space matching sequence with the equipment operating status and operation task constraints in a temporal sequence to generate a fusion result of the equipment space status, and on this basis, determines the task matching status and the effective operation status. By simultaneously considering whether the equipment is in the corresponding space, whether it is within the task time range, and whether the equipment operating status meets the operation requirements, it can effectively distinguish between different situations such as normal operation, operation deviating from the task, on-site but not operating, non-task dwelling, and abnormal equipment status, avoiding judging the completion of the operation solely based on the trajectory passing or the vehicle stopping, and improving the authenticity, traceability, and precision of the sanitation operation supervision results. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is an overall flowchart of a sanitation equipment positioning and status monitoring system based on spatial computing proposed in this invention; Figure 2 This is a schematic diagram of a candidate unit generation module for a spatial computing-based sanitation equipment positioning and status monitoring system proposed in this invention. Figure 3 This is a schematic diagram of the spatial sequence matching module of a sanitation equipment positioning and status monitoring system based on spatial computing proposed in this invention. Detailed Implementation

[0017] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0018] refer to Figures 1-3 A spatial computing-based sanitation equipment positioning and status monitoring system, comprising: The data standardization module is used to acquire and standardize the monitoring data of sanitation equipment to generate a sanitation equipment monitoring dataset. The spatial unit construction module is used to divide sanitation operation spatial units based on the sanitation equipment monitoring dataset, and generate spatial constraint indexes according to spatial boundaries, access connections and task scope; The candidate unit generation module is used to perform spatial projection and boundary determination on the positioning points of sanitation equipment based on the spatial constraint index, and generate candidate operation spatial units corresponding to each collection time. The spatial sequence matching module is used to treat candidate operation space units as implicit states and sanitation equipment positioning points as observation states. It uses a spatially constrained hidden Markov algorithm to calculate the positioning observation cost and spatial transfer cost, and determines the equipment operation space matching sequence through Viterbi dynamic programming. The state-time fusion module is used to perform time-series correlation between the equipment operating status and the work task constraints corresponding to the equipment operation space matching sequence based on the sanitation equipment monitoring dataset, and generate the equipment space state fusion result. The effective operation discrimination module is used to determine the task matching status and effective operation status of sanitation equipment in each sanitation operation space unit based on the equipment space status fusion results and the matching object number, and generate the effective operation discrimination results of sanitation equipment. The anomaly monitoring output module is used to identify the deviation from the operation status, invalid operation status and abnormal status of sanitation equipment based on the effective operation judgment results of sanitation equipment, and generate the positioning and status monitoring results of sanitation equipment.

[0019] In this embodiment, the monitoring data associated with sanitation equipment includes sanitation equipment location records, equipment operation status records, work task records, basic records of work space, equipment attribute records, and historical monitoring records. Standardization processing includes unified equipment identification, unified coordinate system, aligned collection time, data format conversion, removal of abnormal records, completion of missing fields, merging of duplicate records, status code conversion, unified sampling frequency, and spatial object number marking.

[0020] In this embodiment, the spatial unit construction module includes: Extract basic records of the work space and work task records based on the sanitation equipment monitoring dataset; The road segments, work areas, collection and transportation points and service grids in the basic record of the work space are closed and organized according to the spatial boundaries to generate spatial objects to be divided. The generation of the spatial objects to be divided is specifically as follows: Based on the basic records of the work space, obtain the road segment boundary lines, work area boundary surfaces, collection point location coordinates, and service grid boundary surfaces; perform a head-to-tail connection check on the road segment boundary lines, connecting road segment boundary lines with endpoint spacing less than 0.5m, and completing any broken road segment boundary lines according to the direction of adjacent boundaries to generate closed road segment boundaries; perform a boundary integrity check on the work area boundary surfaces, connecting unclosed boundary segments at their endpoints, and merging duplicate boundaries with an overlap length less than 1m to generate closed work area boundaries; generate collection point service boundaries based on the collection point location coordinates, with a service radius of 50m, and connect the collection point service boundaries to the nearest closed road segment boundary. The process involves: aligning and generating service boundaries for collection points corresponding to the closed boundaries of road segments; verifying grid numbers and filling in boundary breakpoints on the service grid boundary surfaces; merging boundaries with an overlap distance of less than 0.5m between adjacent service grid boundary surfaces to generate closed service grid boundaries; unifying the closed boundaries of road segments, work areas, collection points, and service grids into the same coordinate system; spatially overlaying and organizing the unified closed boundaries according to boundary inclusion, intersection, and adjacency states; merging duplicate areas formed after spatial overlay and organizing, segmenting intersecting areas, and marking isolated areas; and writing object numbers to each merged, segmented, and marked closed boundary to generate spatial objects to be divided, each with a closed spatial range and an object number. The spatial objects to be divided are subjected to coordinate correction, boundary overlap resolution, and object numbering and marking to generate sanitation operation spatial units; The generation of sanitation operation space units is specifically as follows: Based on the closed spatial range and object number of the space objects to be divided, the boundary continuity of the space objects to be divided is checked; boundary portions with a distance of less than 0.5m between adjacent boundaries are fitted together, boundary portions with a break distance of less than 0.3m are filled in, and boundary points with offsets in the closed spatial range are adjusted to the continuous direction of adjacent boundaries; boundary overlap resolution is performed on the space objects to be divided based on boundary inclusion, boundary intersection, and boundary adjacency states; when two space objects to be divided have a boundary inclusion state, the closed spatial range and object number of the included object are retained, and a corresponding mark is established between them and the containing object; when two space objects to be divided have a boundary intersection state, the space objects to be divided are segmented according to the intersecting boundary, so that... Each segmented part has an independent closed spatial range; when two spatial objects to be divided have a boundary adjacency, the closed spatial range of each adjacent object is retained, and the adjacent object number is recorded; duplicate areas after boundary overlap resolution are merged, intersecting areas are segmented, and isolated areas are retained and written with an isolation mark; the processed spatial objects to be divided are marked with object numbers according to the region order, object type, and generation order. The object number mark includes the region number, object type number, and spatial unit sequence number; the spatial objects to be divided after boundary continuity verification, boundary overlap resolution, and object number marking are determined as sanitation operation spatial units, and the closed spatial range, object number, object type, adjacent object number, and isolation mark of the sanitation operation spatial unit are recorded; Generate passage connection records based on the road connectivity status, entrance and exit connection status, and operation passage direction between adjacent sanitation operation space units; Based on the task records, determine the equipment compatibility type, task coverage, and task time range for each sanitation operation space unit, and generate a task range record. The generation of the task scope record is as follows: Based on the task record, obtain the task number, equipment number, equipment type, work area number, work route number, collection point number, and start and end times; match the work area number, work route number, and collection point number with the object number of the sanitation work space unit to determine the sanitation work space unit corresponding to the task; determine the equipment adaptation type based on the equipment type, where road sweepers are adapted to road segment sanitation work space units, water trucks are adapted to both road segment and work area sanitation work space units, and garbage collection trucks are adapted to collection point and service grid sanitation work space units; determine the task coverage area based on the work area number, work route number, and collection point number; determine the work time range based on the start and end times; and associate the task number, equipment number, equipment adaptation type, task coverage area, and work time range according to the object number to generate the task scope record. The spatial constraint index is generated by associating sanitation operation space units, access connection records, and task scope records according to the spatial object number.

[0021] In this embodiment, the candidate unit generation module includes: Based on the sanitation equipment monitoring dataset, the sanitation equipment location records are extracted, and a sequence of sanitation equipment location points is generated according to the equipment number and collection time. Based on the spatial constraint index, the closed spatial range, object number, adjacent object number, and task range records of each sanitation operation spatial unit are obtained; The corresponding candidate search range is determined based on the positioning accuracy and data collection time of the sanitation equipment positioning points. The determination of the candidate search range is as follows: Based on the sequence of sanitation equipment location points, the equipment number, collection time, positioning accuracy, and coordinate position of each sanitation equipment location point are read; the sanitation equipment location points are sorted by collection time according to the same equipment number to determine the collection time interval between the current sanitation equipment location point and adjacent sanitation equipment location points; the basic search range of the current sanitation equipment location point is determined based on the positioning accuracy. When the positioning accuracy is less than or equal to 3m, the basic search range is set to a range with a radius of 10m centered on the current sanitation equipment location point; when the positioning accuracy is greater than 3m and less than or equal to 10m... The basic search range is set to a radius of 20m centered on the current sanitation equipment location point. When the positioning accuracy is greater than 10m, the basic search range is set to a radius of 30m centered on the current sanitation equipment location point. The basic search range is adjusted based on the data collection time interval. When the data collection time interval is greater than 30 seconds, the basic search range is expanded by 5m for every additional 30 seconds. The adjusted basic search range is determined as the candidate search range corresponding to the current data collection time, and the candidate search range is associated with and recorded with the equipment number of the current sanitation equipment location point and the data collection time. The candidate search range is spatially intersected with the closed spatial range of the sanitation operation space unit to obtain the initial candidate space unit. The initial candidate spatial unit selection process is as follows: Based on the candidate retrieval range corresponding to the current acquisition time, sanitation operation spatial units that are geographically close to the candidate retrieval range are retrieved; the candidate retrieval range is superimposed and compared with the closed spatial range of each sanitation operation spatial unit to determine whether there is range inclusion, range overlap, or boundary intersection; sanitation operation spatial units whose current sanitation equipment positioning point is within the closed spatial range are directly identified as retained objects; sanitation operation spatial units whose candidate retrieval range overlaps with or intersects with the closed spatial range are marked as spatial units to be confirmed; spatial units to be confirmed are selected based on the geographical proximity between the current sanitation equipment positioning point and the closed spatial range of the spatial units to be confirmed; the selected sanitation operation spatial units are deduplicated according to their object numbers, and their object numbers, closed spatial ranges, adjacent object numbers, and corresponding acquisition times are recorded; the deduplicated sanitation operation spatial units are determined as the initial candidate spatial units corresponding to the current acquisition time. Spatial projection is performed on the sanitation equipment location points and the initial candidate spatial units to determine the projection position, projection distance, and the object number to which the projection belongs; Spatial projection specifically involves: obtaining the coordinate position of the sanitation equipment's location point based on the current acquisition time; reading the closed spatial range and object number of the initial candidate spatial unit; determining whether the sanitation equipment's location point is within the closed spatial range of the initial candidate spatial unit; when the sanitation equipment's location point is within the closed spatial range, determining the coordinate position of the sanitation equipment's location point as the projection position, marking the projection distance as zero, and determining the object number of the corresponding initial candidate spatial unit as the object number to which the projection belongs; when the sanitation equipment's location point is outside the closed spatial range, finding the boundary position within the closed spatial range that is closest to the sanitation equipment's location point, determining this boundary position as the projection position, determining the distance between the sanitation equipment's location point and the projection position as the projection distance, and determining the object number of the corresponding initial candidate spatial unit as the object number to which the projection belongs; performing spatial projection on multiple initial candidate spatial units at the same acquisition time to obtain the projection position, projection distance, and object number to which the projection belongs for each initial candidate spatial unit; Based on the closed space range, the projection position is boundary determined, and the initial candidate spatial units located within the closed space range or within the boundary buffer range are identified as candidate operation spatial units; Candidate job space units are sorted according to the acquisition time to generate candidate job space units corresponding to each acquisition time.

[0022] In this embodiment, the spatial sequence matching module includes: A set of implicit states is established based on the candidate work space units corresponding to each collection time, and the sanitation equipment positioning points at the same collection time are determined as the observation states. The implicit state set refers to the set of candidate work space units that the system believes sanitation equipment may actually be in at a certain data acquisition time. Due to drift, errors, and road obstruction of the sanitation equipment's positioning point, the system cannot directly determine which sanitation work space unit the equipment actually belongs to based on the location of the positioning point. Therefore, it is necessary to use multiple candidate work space units selected at the current data acquisition time as objects to be judged. These objects to be judged are the implicit state set. The observed state refers to the location point of the sanitation equipment that the system can directly acquire at a certain acquisition time. This location point includes the acquisition time, equipment number, and coordinate position, and is the data actually observed by the system. Since the observed state is only the location uploaded by the positioning equipment, it is not necessarily completely equivalent to the actual sanitation operation space unit where the equipment is located. Therefore, it is necessary to use the spatial constraint hidden Markov algorithm to match the observed state with the hidden state set. The positioning observation cost of each candidate work space unit is calculated based on the projection distance, positioning accuracy and boundary determination results corresponding to the positioning points of sanitation equipment. The calculation of the positioning observation cost is as follows: Read the projected distance, positioning accuracy, and boundary determination results between the sanitation equipment positioning point and each candidate workspace unit at the current acquisition time; quantify the projected distance in meters, and divide the projected distance by the positioning accuracy correction value at the current acquisition time to generate a distance cost, where the positioning accuracy correction value is obtained by adding 1 meter to the positioning accuracy; divide the positioning accuracy at the current acquisition time by the upper limit of positioning accuracy to generate an accuracy correction value, where the upper limit of positioning accuracy is 30 meters; generate a boundary cost based on the boundary determination results, where the boundary cost is calculated when the projected position is located within a candidate workspace unit. When the projected position is within the closed space of the operational space unit, the boundary cost is recorded as 0. When the projected position is within the boundary buffer range, the boundary cost is recorded as 0.5. When the projected position is outside the closed space and not within the boundary buffer range, the boundary cost is recorded as 1. The positioning observation cost relative to each candidate operational space unit is obtained by accumulating the cost according to the following proportions: 60% for distance cost, 20% for accuracy correction value, and 20% for boundary cost. The positioning observation cost is then rounded to two decimal places and associated with the corresponding acquisition time, object number, and object number to which the projection belongs. Based on the adjacent object numbers, access connection records, and task range records in the spatial constraint index, calculate the spatial transfer cost of different candidate job spatial units between adjacent acquisition times. The calculation of spatial transfer cost is as follows: Read the candidate job space units from the previous acquisition time and the candidate job space units from the current acquisition time to form candidate unit transfer pairs; obtain the adjacent object numbers of the previous candidate job space unit in the candidate unit transfer pair based on the spatial constraint index, and determine whether the object number of the current candidate job space unit belongs to that adjacent object number; when the object numbers of the two candidate job space units are the same, the transfer base value is recorded as 0; when the object number of the current candidate job space unit belongs to an adjacent object number, and the passage connection record shows that there is a passable connection between the two, the transfer base value is recorded as 0.3; when the object number of the current candidate job space unit belongs to an adjacent object number, but the passage connection record shows that the two have different passage directions, the transfer base value is recorded as 0.3. The base value for transfer is 0.6; when two candidate job space units are not adjacent object numbers but are within the same task range record, the base value for transfer is 0.8; when two candidate job space units are not adjacent object numbers and do not meet the requirement of being within the same task range record, the base value for transfer is 1; based on the task range record, it is determined whether the candidate unit transfer pair is within the corresponding job time range. For candidate unit transfer pairs that are within the job time range and meet the task coverage range, a task matching flag is written; for candidate unit transfer pairs that are not within the job time range or do not meet the task coverage range, a task deviation flag is written; a task correction value is generated based on the task matching flag and the task deviation flag; the base value for transfer and the task correction value are accumulated to generate the space transfer cost; The location observation cost and spatial transfer cost are incorporated into the state cost matrix of the spatially constrained hidden Markov algorithm. According to the acquisition time sequence, the state cost matrix is ​​calculated by Viterbi dynamic programming to determine the candidate job space unit with the minimum cumulative cost at each acquisition time. The Viterbi dynamic programming process is as follows: Candidate job space units in the state cost matrix are sequentially arranged according to acquisition time; the location observation cost of each candidate job space unit at the first acquisition time is used as the initial cumulative cost of the corresponding candidate job space unit and written into the cumulative cost record; starting from the second acquisition time, the location observation cost of each candidate job space unit at the current acquisition time, as well as the spatial transfer cost between the candidate job space unit and each candidate job space unit at the previous acquisition time, are read; the cumulative cost, corresponding spatial transfer cost, and location observation cost of each candidate job space unit at the previous acquisition time are accumulated respectively to obtain multiple sets of candidate cumulative costs corresponding to the current candidate job space unit; the set with the smallest value among the multiple sets of candidate cumulative costs is selected as the cumulative cost of the current candidate job space unit, and the candidate job space unit at the previous acquisition time corresponding to this set of candidate cumulative costs is recorded, generating a preceding unit marker; the cumulative cost calculation and preceding unit marker recording are repeated according to the acquisition time order until the state cost matrix calculation for all acquisition times is completed; the candidate job space unit with the smallest cumulative cost among the candidate job space units at the last acquisition time is selected as the starting point for path backtracking. The candidate workspace unit with the lowest cumulative cost is backtracked to generate a workspace matching sequence corresponding to the sanitation equipment location point sequence.

[0023] The path backtracking process is as follows: The candidate workspace unit with the lowest cumulative cost at the last acquisition time is used as the starting point for path backtracking. The preceding unit marker corresponding to this candidate workspace unit is read. Based on the preceding unit marker, the candidate workspace unit corresponding to the previous acquisition time is determined and written into the backtracking path. The preceding unit markers of each acquisition time are read sequentially in reverse order of acquisition time to determine the candidate workspace unit corresponding to each acquisition time. When backtracking reaches the first acquisition time, path backtracking stops, resulting in a reverse matching path. The reverse matching paths are sorted in forward order of acquisition time to generate an equipment workspace matching sequence. The equipment workspace matching sequence is mapped to the sanitation equipment positioning point sequence according to the equipment number and acquisition time, recording the matching object number, projection position, projection distance, positioning observation cost, spatial transfer cost, and cumulative cost corresponding to each acquisition time. Records with consecutively identical matching object numbers at adjacent acquisition times are merged into time periods to generate a dwell time period within the same sanitation workspace unit. The matching object number and dwell time period are written into the equipment workspace matching sequence.

[0024] In this embodiment, the state-time fusion module includes: Based on the equipment workspace matching sequence, extract the equipment number, collection time, matching object number, projection position, and dwell time period; Based on the sanitation equipment monitoring dataset, the equipment operating status is matched according to the equipment number and collection time to generate a sequence of equipment operating status; The generation of the equipment operation status sequence is as follows: Extract the corresponding equipment status records from the sanitation equipment monitoring dataset according to the same equipment number; align the equipment status records with the collection time in the equipment workspace matching sequence according to the collection time, and determine the driving status, stopping status, start / stop status of working components, speed status, load status, and abnormal alarm status corresponding to each collection time; when multiple equipment status records exist at the same collection time, retain the equipment status record with the collection time closest to the equipment workspace matching sequence; when a missing equipment status record is found at the same collection time, complete the status based on the equipment status records of adjacent collection times; organize the equipment operation status corresponding to each collection time according to the collection time order to generate the equipment operation status sequence. Based on the sanitation equipment monitoring dataset, the operation task constraints are matched according to the equipment number, collection time, and matching object number to generate an operation task constraint sequence; The generation of the task constraint sequence is as follows: Task records corresponding to equipment numbers are extracted from the sanitation equipment monitoring dataset. These task records include task number, task equipment type, task spatial range, task start and end time, and task execution status. The matching object number is matched with the task spatial range to determine the spatial constraint status corresponding to the current data collection time. The data collection time is matched with the task start and end time to determine the temporal constraint status corresponding to the current data collection time. Based on the equipment number, the corresponding equipment type is determined, and the corresponding equipment type is matched with the task equipment type to determine the equipment constraint status corresponding to the current data collection time. The spatial constraint status, temporal constraint status, equipment constraint status, and task execution status are arranged according to the data collection time order to generate the task constraint sequence. The equipment workspace matching sequence, equipment operating status sequence, and work task constraint sequence are time-aligned according to the equipment number, collection time, and matching object number. The time-aligned records are continuously organized to generate device space state segments; Based on task constraints, constraint matching is performed on equipment space state segments to generate operation status matching tags, spatial matching tags, and time matching tags. Specifically, the equipment number, matching object number, segment start and end time, and equipment operation status in the equipment space state segment are read; the equipment constraint status, spatial constraint status, time constraint status, and task execution status corresponding to the same equipment number in the task constraint sequence are read; the equipment operation status is matched with the task execution status, and an operation status matching tag is generated when the equipment is in the task execution state and the operation component is on or its speed status matches the corresponding operation status; the matching object number is matched with the spatial constraint status, and a spatial matching tag is generated when the matching object number belongs to the task space range; the segment start and end time is matched with the time constraint status, and a time matching tag is generated when the equipment space state segment is within the task start and end time range; the operation status matching tag, spatial matching tag, and time matching tag are written to the corresponding equipment space state segment according to the equipment number and segment start and end time. The device spatial state fragments, operating state matching tags, spatial matching tags, and time matching tags are associated to generate a device spatial state fusion result.

[0025] In this embodiment, the valid job determination module includes: Based on the device spatial state fusion results, extract the device number, matching object number, device spatial state fragment, device operating status, operating status matching tag, spatial matching tag and time matching tag; Based on the matching object number, the equipment spatial status segments are grouped according to the sanitation operation spatial unit to generate a set of spatial status segments; Based on spatial matching markers and temporal matching markers, task matching is determined for a set of spatial state fragments, and task matching status is generated. The generation of task matching status is specifically as follows: Read the device number, matching object number, segment start and end time, spatial matching flag, and time matching flag corresponding to each device spatial state segment in the spatial state segment set; determine the device spatial state segments marked as matching in both spatial and time matching as task matching segments; determine the device spatial state segments marked as mismatched in either spatial or time matching as task deviation segments; calculate the cumulative duration of the task matching segments and the total duration of the spatial state segment set according to the segment start and end times; when the cumulative duration of the task matching segments accounts for no less than 80% of the total duration of the spatial state segment set, mark the corresponding spatial state segment set as task matching; when the cumulative duration of the task matching segments accounts for less than 80%, mark the corresponding spatial state segment set as task mismatched; associate the task matching status with the device number, matching object number, and segment start and end time and record them. Based on the operation status matching tag and the equipment operation status, the set of spatial status segments is used to determine the validity of the operation and generate valid operation status; The generation of a valid job status is as follows: Read the device number, matching object number, segment start and end time, running status matching flag, and device running status corresponding to each device's spatial state segment in the spatial state segment set; determine the device spatial state segment with a matching running status flag and the operating component being in the "on" state in the device running status as a valid job segment; determine the device spatial state segment with a non-matching running status flag or the operating component being in the "off" state in the device running status as an invalid job segment; calculate the cumulative duration of the valid job segments and the total duration of the spatial state segment set according to the segment start and end times; when the cumulative duration of the valid job segments accounts for no less than 80% of the total duration of the spatial state segment set, mark the corresponding spatial state segment set as a valid job status; when the cumulative duration of the valid job segments accounts for less than 80%, mark the corresponding spatial state segment set as an invalid job status; associate and record the valid job status with the device number, matching object number, and segment start and end time. Anomalies are marked for sets of spatial state segments where the task matching status and the valid job status are inconsistent. The specific anomaly marking process is as follows: Read the task matching status and valid job status corresponding to the spatial state segment set; when the task matching status is "task matched" and the valid job status is "invalid job," mark the corresponding spatial state segment set as "in-place but not working anomaly"; when the task matching status is "task mismatched" and the valid job status is "valid job," mark the corresponding spatial state segment set as "deviation from task job anomaly"; when the task matching status is "task matched" and the valid job status is "valid job," mark the corresponding spatial state segment set as "normal job"; when the task matching status is "task mismatched" and the valid job status is "invalid job," mark the corresponding spatial state segment set as "non-task dwelling"; identify "in-place but not working anomaly" and "deviation from task job anomaly" as anomaly markers, and associate and record these anomaly markers with the equipment number, matching object number, and segment start and end time. Organize the equipment operating status, operating status matching flag, task matching status, effective operation status, and abnormal flag according to the equipment number, matching object number, and segment start and end time, and generate the effective operation judgment result of sanitation equipment.

[0026] In this embodiment, the anomaly monitoring output module includes: Based on the effective operation judgment results of sanitation equipment, extract the equipment number, matching object number, segment start and end time, task matching status, effective operation status, anomaly mark, equipment operation status and operation status matching mark; Determine the deviation status of sanitation equipment from its task operation based on the deviation from the anomaly markers. The invalid operation status of sanitation equipment is determined based on the in-place but not working anomaly and the effective operation status in the anomaly markers. The abnormal status of sanitation equipment is determined based on the equipment operating status and operating status matching tags. The determination of abnormal equipment status is as follows: Equipment space status segments whose operating status matches and is marked as mismatched are identified as candidate segments for abnormal operation; consecutive candidate segments for abnormal operation under the same equipment number are merged to generate continuous segments for abnormal operation; the continuous segments for abnormal operation are categorized based on the equipment's operating status; when the operating status match mark is consistently mismatched, it is marked as an abnormal operating status; when the equipment's operating status frequently switches between adjacent segments, it is marked as an abnormal status fluctuation; when the equipment's operating status is missing or interrupted within the segment's start and end time, it is marked as an abnormal status missing; the start and end times, matching object numbers, and status categorization results of the continuous segments for abnormal operation are correlated to generate the abnormal equipment status of the sanitation equipment. Based on the equipment number, the matching object number, and the start and end time of the segment, the deviation from the operation status, the invalid operation status, and the abnormal equipment status are correlated and organized to generate an equipment abnormality monitoring record; Based on equipment anomaly monitoring records, the anomaly occurrence time, corresponding spatial unit, and anomaly type are determined. Specifically, records with abnormal values ​​indicating deviation from the operating state, invalid operating state, or abnormal equipment state are identified as anomaly records. The anomaly occurrence time is determined based on the start and end times of the anomaly record segments, including the start and end times of the anomaly. The corresponding spatial unit is determined based on the matching object number of the anomaly record. When an anomaly record originates from a deviation from the operating state, the anomaly type is marked as a deviation from the operating state. When an anomaly record originates from an invalid operating state, the anomaly type is marked as an invalid operating state. When an anomaly record originates from an abnormal equipment state, the anomaly type is marked as an equipment state anomaly. When the anomaly types corresponding to the same equipment number, the same matching object number, and adjacent segment start and end times are consistent, the anomaly records are merged. The merged anomaly occurrence time, corresponding spatial unit, and anomaly type are then linked together. The results of sanitation equipment location and status monitoring are generated by combining the time of anomaly occurrence, the corresponding spatial unit of the anomaly, the anomaly type, the deviation from the operation state, the invalid operation state, and the equipment anomaly state.

[0027] Example 1: To verify the feasibility of this invention in practice, it was applied to a scenario of sanitation equipment positioning and status monitoring in a central urban area of ​​a city. This area includes main roads, secondary roads, branch roads, back streets and alleys, open squares, garbage collection points, and community service grids. The sanitation equipment monitored included road sweepers, water trucks, and garbage collection trucks, with a total of 56 vehicle-mounted positioning terminals, 56 equipment operation status acquisition terminals, and one set of operation scheduling and recording interfaces connected. The road spatial boundaries in this area are relatively complex, with some roads close to, intersecting with, or overlapping the service areas of community service grids and collection points. Among these, 37 collection points are less than 10 meters from the road boundaries. Some roads have tall buildings, trees obstructing the view, and narrow alleyways with turns, making it easy for vehicle-mounted positioning points to drift or experience short-term jumps. Traditional monitoring methods mainly rely on whether the location point enters the electronic fence, whether the vehicle stops, and whether the task route roughly covers the area to judge the operation status. When the vehicle passes near the boundary, makes a temporary U-turn, pulls over to avoid the side, or makes a short stop, it is easy to misjudge non-operational behavior as operation completion. When the vehicle enters the designated operation area but the operation components are not activated, it is also difficult to identify the non-operational status.

[0028] In this embodiment, the implementer accesses sanitation equipment location records, equipment operation status records, task records, work space basic records, equipment attribute records, and historical monitoring records. Equipment identification, coordinate system, acquisition time, status code, and spatial object number are uniformly processed to form a sanitation equipment monitoring dataset. Vehicle location records include equipment number, coordinate position, positioning accuracy, and acquisition time, with a positioning acquisition interval of 15 seconds. Approximately 5760 location records are generated per device per day. Equipment operation status records include vehicle driving status, parking status, start / stop status of operating components, speed status, and load status. Task records include task number, task equipment type, task spatial range, task start / end constraints, and task execution status, generating 84 road sweeping tasks, 46 watering tasks, and 112 garbage collection tasks per day. The spatial basic records contain approximately 320 road segment boundaries, 48 ​​work area boundaries, 126 collection point locations, and 36 service grid boundaries. Based on the above data, the system performs closed-loop processing of road segments, work areas, collection points, and service grids to generate sanitation operation spatial units. Each spatial unit is then assigned an object number, closed spatial range, adjacent object numbers, and access connection records. For cases where collection points are close to road boundaries, the system aligns the service range of the collection point with the boundary of the adjacent road segment. For cases where service grids intersect with road segment boundaries, the system uses boundary segmentation and object numbering to create a computable spatial constraint index for different types of spatial objects within the same coordinate system.

[0029] In this scenario, when a road sweeper continuously operates along a main urban road towards adjacent side roads, the vehicle's positioning accuracy remains between 3m and 6m in open sections, increasing to 12m to 18m in sections with dense high-rise buildings. Some positioning points are offset to the edge of the adjacent service grid due to obstruction by buildings on both sides of the road. Traditional electronic fence methods would divide the continuous operation trajectory into main road segments, service grid segments, and side road segments in this section, resulting in spatial affiliation jumps. Instead of directly determining whether the vehicle has entered the service grid based on the location where the positioning point falls, the system first determines the candidate retrieval range based on positioning accuracy and data acquisition time. Then, it performs spatial intersection judgment between the candidate retrieval range and the closed spatial range of the sanitation operation space unit to filter out candidate operation space units such as road segments, adjacent side roads, and adjacent service grids. Subsequently, the system projects the positioning point onto each initial candidate space unit, determines the projection position, projection distance, and the object number to which the projection belongs, and retains candidate operation space units within the closed spatial range or the boundary buffer range through boundary judgment. During spatial sequence matching, the system treats candidate work space units as implicit states and positioning points as observation states. It calculates the positioning observation cost by combining projection distance, positioning accuracy, and boundary judgment results, and calculates the spatial transfer cost based on adjacent object numbers, access connection records, and task range records. Viterbi dynamic programming selects the candidate unit path with the minimum cumulative cost according to the acquisition time sequence, ultimately forming the equipment work space matching sequence, allowing short-term offset points to be corrected based on the spatial continuity before and after.

[0030] Therefore, this invention can achieve unified analysis of the location, task constraints, and operating status of sanitation equipment in complex urban sanitation operation environments, solving the problems of coarse spatial judgment, disconnect between trajectory and task, and insufficient identification of effective operations in traditional electronic fence methods, and improving the precision of sanitation equipment positioning supervision and operation status monitoring.

[0031] Table 1. Performance Comparison of Methods for Positioning and Monitoring Operation Status of Sanitation Equipment

[0032] As shown in Table 1, the matching accuracy of the work space unit using traditional electronic fence and trajectory rule methods is 88.9%, while that of the method in this invention is 94.7%. Both methods can determine the spatial affiliation of sanitation equipment based on vehicle positioning data and work space boundaries. However, the traditional method mainly relies on whether the positioning point falls within the electronic fence range. When the vehicle is at the road boundary, the edge of the collection point service area, or the intersection area of ​​the service grid, it is easily affected by positioning drift and boundary proximity. This invention uses candidate work space unit screening, spatial projection, boundary determination, and spatial constraint hidden Markov algorithm for continuous matching. Therefore, while retaining the positioning point observation information, it can use the spatial continuity and traffic connection status of the previous and subsequent collection times to correct some short-term offset points, making the work space unit matching results more stable.

[0033] Regarding the misjudgment rate near the boundary, the traditional method has a misjudgment rate of 10.6%, while the method of this invention has a rate of 5.8%. In terms of the number of trajectory spatial affiliation jumps, the traditional method has 214 jumps, while the method of this invention has 126 jumps. These indicators demonstrate that the present invention is superior to the traditional method in handling complex spatial boundaries. Traditional methods tend to misclassify positioning points as adjacent spatial objects when vehicles approach road edges, make temporary avoidances, make U-turns, or pass near collection points, causing discontinuities in trajectory segments. The present invention simultaneously records the closed spatial range, adjacent object numbers, and traffic connection records when constructing sanitation operation spatial units, and calculates the positioning observation cost and spatial transfer cost during spatial sequence matching, thus reducing spatial jumps that do not conform to traffic connections and task ranges.

[0034] In terms of the accuracy rates of task matching status recognition and effective operation status recognition, traditional methods achieve 87.6% and 85.4% respectively, while the method of this invention achieves 93.1% and 91.2% respectively. Traditional methods typically use whether a vehicle enters the task area, stops, or travels along a route as the basis for operation judgment, which can meet general regulatory needs. However, they are insufficient in recognizing situations such as vehicles entering the task area without activating operating components, operating briefly outside the task area, or being near the collection point but not actually collecting goods. This invention temporally correlates the equipment operation space matching sequence, equipment operating status, and task constraints, generating operating status matching tags, spatial matching tags, and temporal matching tags. Therefore, it can jointly determine the effectiveness of the operation from three aspects: space, time, and equipment operating status.

[0035] The recall rate for identifying non-operational tasks in place increased from 80.8% using traditional methods to 88.6% using the method of this invention; the recall rate for identifying deviations from the intended operation increased from 82.3% to 89.1%; and the accuracy rate for identifying abnormal equipment status increased from 86.2% to 90.5%. These indicators demonstrate that the present invention provides a more detailed identification of abnormal operation statuses. This is because the present invention combines the judgment of task matching status and effective operation status during the effective operation determination stage. This allows it to distinguish between different states such as task matching without effective operation, task mismatch but with operational behavior, non-task dwell, and normal operation, avoiding the lumping of all abnormal situations into trajectory deviation or task incompleteness.

[0036] The above are merely preferred embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A spatial computing-based sanitation equipment positioning and status monitoring system, characterized in that, include: The data standardization module is used to acquire and standardize the monitoring data of sanitation equipment to generate a sanitation equipment monitoring dataset. The spatial unit construction module is used to divide sanitation operation spatial units based on the sanitation equipment monitoring dataset, and generate spatial constraint indexes according to spatial boundaries, access connections and task scope; The candidate unit generation module is used to perform spatial projection and boundary determination on the positioning points of sanitation equipment based on the spatial constraint index, and generate candidate operation spatial units corresponding to each collection time. The spatial sequence matching module is used to treat candidate operation space units as implicit states and sanitation equipment positioning points as observation states. It uses a spatially constrained hidden Markov algorithm to calculate the positioning observation cost and spatial transfer cost, and determines the equipment operation space matching sequence through Viterbi dynamic programming. The state-time fusion module is used to perform time-series correlation between the equipment operating status and the work task constraints corresponding to the equipment operation space matching sequence based on the sanitation equipment monitoring dataset, and generate the equipment space state fusion result. The effective operation discrimination module is used to determine the task matching status and effective operation status of sanitation equipment in each sanitation operation space unit based on the equipment space status fusion results and the matching object number, and generate the effective operation discrimination results of sanitation equipment. The anomaly monitoring output module is used to identify the deviation from the operation status, invalid operation status and abnormal status of sanitation equipment based on the effective operation judgment results of sanitation equipment, and generate the positioning and status monitoring results of sanitation equipment.

2. The sanitation equipment positioning and status monitoring system based on spatial computing according to claim 1, characterized in that, The sanitation equipment monitoring data includes sanitation equipment location records, equipment operation status records, work task records, work space basic records, equipment attribute records, and historical monitoring records. The standardization process includes unified equipment identification, unified coordinate system, data acquisition time alignment, data format conversion, abnormal record removal, missing field completion, duplicate record merging, status code conversion, unified sampling frequency, and spatial object number marking.

3. The sanitation equipment positioning and status monitoring system based on spatial computing according to claim 1, characterized in that, The spatial unit construction module includes: Extract basic records of the work space and work task records based on the sanitation equipment monitoring dataset; The road segments, work areas, collection and transportation points and service grids in the basic record of the work space are closed and organized according to the spatial boundaries to generate spatial objects to be divided. The spatial objects to be divided are subjected to coordinate correction, boundary overlap resolution, and object numbering and marking to generate sanitation operation spatial units; Generate passage connection records based on the road connectivity status, entrance and exit connection status, and operation passage direction between adjacent sanitation operation space units; Based on the task records, determine the equipment compatibility type, task coverage, and task time range for each sanitation operation space unit, and generate a task range record. The spatial constraint index is generated by associating sanitation operation space units, access connection records, and task scope records according to the spatial object number.

4. The sanitation equipment positioning and status monitoring system based on spatial computing according to claim 1, characterized in that, The candidate unit generation module includes: Based on the sanitation equipment monitoring dataset, the sanitation equipment location records are extracted, and a sequence of sanitation equipment location points is generated according to the equipment number and collection time. Based on the spatial constraint index, the closed spatial range, object number, adjacent object number, and task range records of each sanitation operation spatial unit are obtained; The corresponding candidate search range is determined based on the positioning accuracy and data collection time of the sanitation equipment positioning points. The candidate search range is spatially intersected with the closed spatial range of the sanitation operation space unit to obtain the initial candidate space unit. Spatial projection is performed on the sanitation equipment location points and the initial candidate spatial units to determine the projection position, projection distance, and the object number to which the projection belongs; Based on the closed space range, the projection position is boundary determined, and the initial candidate spatial units located within the closed space range or within the boundary buffer range are identified as candidate operation spatial units; Candidate job space units are sorted according to the acquisition time to generate candidate job space units corresponding to each acquisition time.

5. The sanitation equipment positioning and status monitoring system based on spatial computing according to claim 1, characterized in that, The spatial sequence matching module includes: A set of implicit states is established based on the candidate work space units corresponding to each collection time, and the sanitation equipment positioning points at the same collection time are determined as the observation states. The positioning observation cost of each candidate work space unit is calculated based on the projection distance, positioning accuracy and boundary determination results corresponding to the positioning points of sanitation equipment. Based on the adjacent object numbers, access connection records, and task range records in the spatial constraint index, calculate the spatial transfer cost of different candidate job spatial units between adjacent acquisition times. The location observation cost and spatial transfer cost are written into the state cost matrix of the spatially constrained hidden Markov algorithm. According to the acquisition time sequence, the state cost matrix is ​​calculated by Viterbi dynamic programming to determine the candidate job space unit with the minimum cumulative cost at each acquisition time. The candidate workspace unit with the lowest cumulative cost is backtracked to generate a workspace matching sequence corresponding to the sanitation equipment location point sequence.

6. The sanitation equipment positioning and status monitoring system based on spatial computing according to claim 1, characterized in that, The state-time fusion module includes: Based on the equipment workspace matching sequence, extract the equipment number, collection time, matching object number, projection position, and dwell time period; Based on the sanitation equipment monitoring dataset, the equipment operating status is matched according to the equipment number and collection time to generate a sequence of equipment operating status; Based on the sanitation equipment monitoring dataset, the operation task constraints are matched according to the equipment number, collection time, and matching object number to generate an operation task constraint sequence. The equipment workspace matching sequence, equipment operating status sequence, and work task constraint sequence are time-aligned according to the equipment number, collection time, and matching object number. The time-aligned records are continuously organized to generate device space state segments; Constraint matching is performed on equipment spatial state segments based on job task constraints to generate running state matching tags, spatial matching tags, and time matching tags; The device spatial state fragments, operating state matching tags, spatial matching tags, and time matching tags are associated to generate a device spatial state fusion result.

7. The sanitation equipment positioning and status monitoring system based on spatial computing according to claim 1, characterized in that, The valid job determination module includes: Based on the device spatial state fusion results, extract the device number, matching object number, device spatial state fragment, device operating status, operating status matching tag, spatial matching tag and time matching tag; Based on the matching object number, the equipment spatial status segments are grouped according to the sanitation operation spatial unit to generate a set of spatial status segments; Based on spatial matching markers and temporal matching markers, task matching is determined for a set of spatial state fragments, and task matching status is generated. Based on the operation status matching tag and the equipment operation status, the set of spatial status segments is used to determine the validity of the operation and generate valid operation status; Anomalies are marked for sets of spatial state segments where the task matching status and the valid job status are inconsistent. Organize the equipment operating status, operating status matching flag, task matching status, effective operation status, and abnormal flag according to the equipment number, matching object number, and segment start and end time, and generate the effective operation judgment result of sanitation equipment.

8. The sanitation equipment positioning and status monitoring system based on spatial computing according to claim 1, characterized in that, The anomaly monitoring output module includes: Based on the effective operation judgment results of sanitation equipment, extract the equipment number, matching object number, segment start and end time, task matching status, effective operation status, anomaly mark, equipment operation status and operation status matching mark; Determine the deviation status of sanitation equipment from its task operation based on the deviation from the anomaly markers. The invalid operation status of sanitation equipment is determined based on the in-place but not working anomaly and the effective operation status in the anomaly markers. The abnormal status of sanitation equipment is determined based on the equipment operating status and operating status matching tags. Based on the equipment number, the matching object number, and the start and end time of the segment, the deviation from the operation status, the invalid operation status, and the abnormal equipment status are correlated and organized to generate an equipment abnormality monitoring record; The time of occurrence of the anomaly, the corresponding spatial unit of the anomaly, and the type of the anomaly are determined based on the equipment anomaly monitoring records; The results of sanitation equipment location and status monitoring are generated by combining the time of anomaly occurrence, the corresponding spatial unit of the anomaly, the anomaly type, the deviation from the operation state, the invalid operation state, and the equipment anomaly state.

Images