Intelligent city sweeper operation monitoring management method and system

Abstract

The invention relates to an intelligent city sweeper operation monitoring management method and system. The method comprises the following steps: carrying out multi-source data acquisition processing on vehicle operation data of a cleaning vehicle to obtain a state fusion data set for representing operation behavior characteristics of the cleaning vehicle; according to a matching relationship between a preset standard operation template and the state fusion data set, performing hierarchical analysis processing on the operation behavior characteristics of the sweeping vehicle to obtain an operation behavior evaluation result; according to the operation behavior evaluation result, a matched monitoring feedback strategy is executed on the sweeping vehicle, an operation monitoring feedback information set is generated, and the operation monitoring feedback information set comprises operation abnormity alarm information, track deviation labeling information, resource allocation suggestion information and state diagnosis result information; the method is used for providing operation scheduling management basis for the sweeping vehicle for the preset monitoring platform. By adopting the method, fine identification and efficient management of the operation state of the sweeping vehicle can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of urban sanitation management, and in particular to a method and system for monitoring and managing the operation of an intelligent city sweeper. Background Art

[0002] In the field of urban sanitation management technology, it involves monitoring the operation of cleaning vehicles to achieve operation management and operation scheduling of cleaning vehicles.

[0003] Among the relevant sweeping vehicle operation monitoring methods, on the one hand, it is impossible to make effective feedback in a timely manner in complex scenarios such as operation trajectory deviation, equipment operation abnormality or operation interruption, which limits the refined management of cleaning operation quality and the improvement of resource allocation efficiency; on the other hand, there is a lack of hierarchical analysis of operation behavior characteristics and dynamic selection of feedback strategies, resulting in the feedback information generation being neither targeted nor structured, and the degree of intelligence in abnormal response and operation optimization is low, which makes it difficult to meet the current development needs of urban refined sanitation management. Summary of the Invention

[0004] Based on this, it is necessary to provide an intelligent city sweeper operation monitoring and management method, system, computer equipment and computer-readable storage medium to address the above technical problems, so as to achieve precise identification and efficient management of the operation status of the sweeper.

[0005] In a first aspect, the present application provides a method for monitoring and managing the operation of a smart city sweeper, comprising: Performing multi-source data collection and processing on the vehicle operation data of the cleaning vehicle to obtain a state fusion data set for characterizing the operation behavior characteristics of the cleaning vehicle, the state fusion data set including a vehicle operation state data set, a vehicle operation parameter set, and a geographic location information set; Based on the matching relationship between the preset standard operation template and the state fusion data set, the operation behavior characteristics of the cleaning vehicle are subjected to hierarchical analysis to obtain an operation behavior evaluation result, which includes the continuous operation section trajectory recognition result, the equipment action behavior sequence, and the operation abnormality indicator combination; Based on the operation behavior evaluation results, a matching monitoring feedback strategy is executed on the sweeping vehicle to generate an operation monitoring feedback information set. The operation monitoring feedback information set includes operation abnormality alarm information, trajectory deviation marking information, resource allocation suggestion information and status diagnosis result information, so as to provide a preset monitoring platform with an operation scheduling management basis for the sweeping vehicle.

[0006] In a second aspect, the present application also provides an intelligent city sweeper operation monitoring and management system, comprising: An acquisition module is used to perform multi-source data acquisition and processing on the vehicle operation data of the cleaning vehicle to obtain a state fusion data set for characterizing the operation behavior characteristics of the cleaning vehicle, wherein the state fusion data set includes a vehicle operation state data set, a vehicle operation parameter set, and a geographic location information set; An evaluation module is configured to perform hierarchical analysis on the operating behavior characteristics of the cleaning vehicle based on a matching relationship between a preset standard operating template and the state fusion dataset to obtain an operating behavior evaluation result, wherein the operating behavior evaluation result includes a continuous operating section trajectory recognition result, an equipment action behavior sequence, and a combination of operation abnormality indicators; A feedback module is used to execute a matching monitoring feedback strategy for the sweeping vehicle based on the operation behavior evaluation results, and generate an operation monitoring feedback information set. The operation monitoring feedback information set includes operation abnormality alarm information, trajectory deviation annotation information, resource allocation suggestion information and status diagnosis result information, so as to provide a preset monitoring platform with a basis for operation scheduling management of the sweeping vehicle.

[0007] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above steps when executing the computer program.

[0008] In a fourth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and the computer program implements the above steps when executed by a processor.

[0009] The above-mentioned smart city sweeper operation monitoring and management method, system, computer equipment and computer-readable storage medium, first, establish a unified state fusion data set based on multi-source collection and processing of vehicle operation data of the sweeping vehicle, providing a structured basis for subsequent operation behavior analysis; secondly, obtain the operation behavior evaluation result based on the matching relationship between the state fusion data set and the standard operation template, thereby realizing multi-dimensional extraction of the sweeping operation trajectory, equipment behavior and abnormal indicators, ensuring that the operation status identification has layered and diagnosable characteristics; thirdly, execute the matching monitoring feedback strategy on the operation behavior evaluation result, thereby generating a structured operation monitoring feedback information set, realizing structured feedback generation and management response to the operation status of the sweeping vehicle; based on this, by constructing a three-layer linkage mechanism of data fusion, behavior analysis and strategy feedback, the fine identification and efficient management of the operation status of the sweeping vehicle are realized, providing a reliable and adaptable operation scheduling management basis for the monitoring platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 1 is a flow chart of a method for monitoring and managing the operation of an intelligent city sweeper in one embodiment; Figure 2 This is a structural block diagram of an intelligent city sweeper operation monitoring and management system in one embodiment. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0013] In one embodiment, Figure 1 As shown, a method for monitoring and managing the operation of a smart city sweeper is provided. This embodiment uses the method applied to a server as an example. It is understood that the method can also be applied to a terminal, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps S101 to S103.

[0014] Step S101 , performing multi-source data acquisition and processing on the vehicle operation data of the cleaning vehicle to obtain a state fusion data set for characterizing the operation behavior characteristics of the cleaning vehicle, wherein the state fusion data set includes a vehicle operation state data set, a vehicle operation parameter set, and a geographic location information set.

[0015] Among them, sweeping vehicles refer to automated or semi-automated operating vehicles with urban road cleaning functions, which are used to perform tasks including road sweeping, garbage collection, water sprinkling and dust reduction, such as smart city sweepers with roller brushes, suction ports and water spray systems.

[0016] Among them, vehicle operation data refers to the collection of all raw data information related to the movement, operation and operation of the sweeping vehicle collected by various sensors, controllers and actuators during the operation process, which is used to comprehensively describe the dynamic state of the sweeping vehicle during the operation process.

[0017] Among them, the state fusion dataset refers to the dataset generated after unified processing of vehicle operation data from different data sources. It is used to systematically describe the operating behavior characteristics of cleaning vehicles. It includes the vehicle operation status dataset, vehicle operation parameter set and geographic location information set.

[0018] Among them, the vehicle operation status dataset represents a set of parameters that describe the physical operation status of the sweeping vehicle during the operation process. It is used to characterize the motion characteristics of the sweeping vehicle during the operation process, such as the vehicle's current gear, engine speed, acceleration and deceleration status, etc.

[0019] Among them, the vehicle operation parameter set represents a set of parameters related to equipment control during the operation of the cleaning vehicle, which is used to describe the operating status and operation settings of the operation components, such as nozzle opening, sweeping brush speed, suction port opening and closing status, etc.

[0020] Among them, the geographic location information set represents a set of parameters that describe the spatial position of the sweeping vehicle during the operation process, which is used to determine the geographic location of the vehicle operation and its matching relationship with the road network, such as the latitude and longitude coordinates collected by GPS or the current road segment code mapped by the map system.

[0021] For example, multi-source data collection and processing of vehicle operation data from cleaning vehicles involves: performing unified data structure modeling on the data streams output by the various basic operation sensors, operation status recording modules, and positioning modules on the cleaning vehicles, and aligning them using timestamps to form a data set with synchronized time series characteristics. In this process, the resulting vehicle operation status dataset can include parameters such as the speed, acceleration, engine speed, and braking frequency of the cleaning vehicle in various time periods, used to reflect whether the cleaning vehicle is currently in different states such as running, paused, or turning; the resulting vehicle operation parameter set can include status information of operating components such as brush disk speed, sprinkler pump power, garbage bin opening and closing status, and vacuum negative pressure, used to reflect whether the cleaning vehicle is in an effective cleaning operation state; and the resulting geographic location information set can be based on the location information collected by the GPS module and combined with preset map data to clearly define the spatial location of the cleaning vehicle's operation path. Based on this, after all data is collected and structured, a set of unified processing interfaces will be used to form a state fusion dataset, which serves as the basic data carrier for comprehensively expressing the cleaning vehicle's operating behavior.

[0022] In step S102, based on the matching relationship between the preset standard operation template and the state fusion data set, the operation behavior characteristics of the cleaning vehicle are hierarchically analyzed to obtain the operation behavior evaluation results. The operation behavior evaluation results include the continuous operation section trajectory recognition results, the equipment action behavior sequence, and the operation abnormality indicator combination.

[0023] Among them, the standard operation template represents a set of reference operation behavior parameters and trajectory data structures pre-set according to established cleaning specifications or operation standards, which are used as the basis for subsequent cleaning behavior judgment and comparison. For example, it is stipulated that cleaning vehicles should maintain a driving speed of 5 to 10 km / h when operating on urban roads, keep the brush disc rotation and watering operations in the open state, and the trajectory should be close to the right edge of the road.

[0024] Among them, the operation behavior evaluation results represent a set of structured output information reflecting the compliance and abnormality of the cleaning behavior of the cleaning vehicle, which is used to provide a basis for the formulation of subsequent monitoring feedback and resource allocation strategies. For example, it can identify problems such as operation interruption behavior of a certain cleaning vehicle within a certain time period, incomplete coverage of the operation path, frequent start and stop of the equipment, etc., and generate corresponding evaluation labels and time period indexes.

[0025] Among them, the continuous operation section trajectory recognition result represents the set of trajectory segments traveled by the cleaning vehicle in a continuous operation state, which is used to judge the continuity and coverage of the cleaning task. For example, it is recognized that the trajectory of the cleaning vehicle between 10:00 and 10:25 shows continuous movement and the operating components are continuously turned on, so this time period is marked as a valid continuous operation trajectory.

[0026] The equipment action behavior sequence represents a set of time-series data that records and arranges the state changes of various operating components (such as the brush plate, sprinkler unit, and vacuum unit) on the cleaning vehicle during operation. This data is used to analyze the frequency of use, working hours, and compliance with standard operating procedures of each operating component. For example, the brush plate started and stopped six times between 09:00 and 09:10, indicating frequent operation.

[0027] Among them, the combination of operational abnormality indicators represents a set of feature items used to identify non-standard operational behaviors, that is, it is used to locate the specific manifestations of operational deviations, equipment abnormalities, or behavioral violations. For example, it includes quantifiable abnormality description indicators such as "cleaning interruptions more than 3 times", "single trajectory deviation exceeds 15 meters", and "the area of uncovered operation is greater than 20 square meters", to support subsequent alarm, labeling, resource adjustment and other operations.

[0028] For example, first, by analyzing the state fusion data set of the sweeping vehicle and combining it with the reference trajectory set by the standard operation template, the actual operation path of the sweeping vehicle is spatially compared and segmented to determine whether there are continuous and standardized operation segments during the operation process, thereby obtaining the continuous operation segment trajectory identification results; secondly, after identifying these operation segments with continuity characteristics, the operation behaviors within these operation segments are further analyzed, that is, the start and stop states and parameter change patterns of each operation component in each time period are extracted to construct a sequence structure describing the behavior of each operation component, and obtain the equipment action behavior sequence. Furthermore, by analyzing whether there are phenomena inconsistent with the standard operation logic in the equipment action behavior sequence, abnormal behaviors in different time periods are summarized and classified, thereby forming a quantifiable operation abnormality indicator combination. Finally, the above-identified continuous operation segment trajectory identification results, equipment action behavior sequence, and operation abnormality indicator combination are integrated to form a complete operation behavior evaluation result, providing a basis for subsequent monitoring and feedback strategies.

[0029] In step S103, a matching monitoring feedback strategy is implemented for the sweeping vehicle based on the operation behavior evaluation results to generate an operation monitoring feedback information set. The operation monitoring feedback information set includes operation abnormality alarm information, trajectory deviation marking information, resource allocation suggestion information, and status diagnosis result information, so as to provide a preset monitoring platform with a basis for operation scheduling management of sweeping vehicles.

[0030] Among them, the monitoring feedback strategy refers to a set of strategies used to classify and process the work behavior evaluation results and generate response information, which is matched with the work behavior evaluation results. It is used to guide how to perform information screening, level setting and response content construction for different types of work situations. For example, for mild anomalies that deviate from the trajectory but do not cause equipment malfunction, a strategy based on information prompts is adopted. For serious situations where abnormal equipment shutdown is accompanied by work interruption, a strategy based on automatic alarm and automatic scheduling is adopted.

[0031] Among them, the operation monitoring feedback information set represents a set of structured feedback information items generated after the execution of the monitoring feedback strategy, based on the operation anomalies, trajectory characteristics, equipment operation status and other information extracted from the operation behavior evaluation results. It is used for remote control, status presentation, abnormal response and subsequent scheduling of the sweeping vehicle. It includes operation anomaly alarm information, trajectory deviation annotation information, resource allocation suggestion information and status diagnosis result information.

[0032] Among them, the abnormal operation alarm information refers to warning information used to prompt or alert the cleaning vehicle that there is currently an obvious abnormal operation behavior. For example, when a cleaning vehicle does not turn on any operation component for 3 minutes during the cleaning process and is in a non-parking state, an "operation component not enabled alarm" message is generated.

[0033] Among them, the trajectory deviation marking information refers to the marking information used to prompt that the current trajectory of the cleaning vehicle has obviously deviated from the expected cleaning route. For example, it marks that the cleaning vehicle deviates from the standard cleaning route by 20 meters during the 12th to 15th minute of driving, and is accompanied by the start and end coordinates of the deviated section.

[0034] Among them, resource allocation suggestion information refers to suggestion information used to assist the monitoring platform in making resource rescheduling and reallocation decisions. For example, if the equipment status of the current cleaning vehicle is normal but it has been in a non-operating idle state for more than 30 minutes, it is recommended to transfer the cleaning vehicle to the area to be cleaned B to improve the operation coverage rate.

[0035] Among them, the status diagnosis result information represents diagnostic information used to assist in determining whether the operating component is in an abnormal state such as fatigue, misoperation or logical conflict. For example, if it is found that the start and stop frequency of a certain vacuum unit is abnormal during continuous operation, a diagnostic entry of the "device control logic may fail" or "control system response hysteresis" type is generated.

[0036] Among them, the monitoring platform refers to the background information management system or visual operation interface used to receive, display and process the data generated by each cleaning vehicle during the operation process. It is used for management personnel to view the operation status, behavior trajectory and equipment operation status of the cleaning vehicles in real time as a basis for the operation scheduling and management of the cleaning vehicles. For example, the operation management system deployed by the Urban Sanitation Management Center serves as a monitoring platform to realize the centralized scheduling, alarm response and status backtracking functions of all cleaning vehicles within the jurisdiction.

[0037] For example, after obtaining the operational behavior assessment results, key feature information useful for monitoring and judgment is extracted based on the trajectory identification results of the continuous operational sections, the equipment action behavior sequence, and the combination of abnormal operation indicators involved. This key feature information summarizes the typical performance of the sweeping vehicle during operation, such as path deviation, operation continuity, and equipment operational stability. Based on this, the currently extracted key feature information is matched and analyzed against multiple pre-defined monitoring feedback strategies to determine the monitoring feedback strategy that best matches the key feature information. Subsequently, based on the matched monitoring feedback strategy, the extracted key feature information is converted into structured information content to form the final operational monitoring feedback information set. This operational monitoring feedback information set has a clear classification structure and attribute tags for subsequent transmission to the monitoring platform to support abnormal status alarms, location annotation of trajectory deviations, generation of resource allocation suggestions, and preliminary diagnosis of equipment status, enabling the monitoring platform to provide timely and targeted handling and scheduling support based on the operational monitoring feedback information set.

[0038] In the above-mentioned smart city sweeper operation monitoring and management method, first, based on the multi-source collection and processing of the vehicle operation data of the sweeping vehicle, a unified state fusion data set is established to provide a structured basis for the subsequent operation behavior analysis; secondly, based on the matching relationship between the state fusion data set and the standard operation template, the operation behavior evaluation result is obtained, thereby realizing the multi-dimensional extraction of the sweeping operation trajectory, equipment behavior and abnormal indicators, ensuring that the operation status identification has the characteristics of stratification and diagnosability; thirdly, the matching monitoring feedback strategy is executed on the operation behavior evaluation result, thereby generating a structured operation monitoring feedback information set, realizing the structured feedback generation and management response of the operation status of the sweeping vehicle; based on this, by constructing a three-layer linkage mechanism of data fusion, behavior analysis and strategy feedback, the operation status of the sweeping vehicle can be finely identified and efficiently managed, providing the monitoring platform with a reliable and adaptable operation scheduling management basis.

[0039] In an exemplary embodiment, multi-source data collection and processing is performed on vehicle operation data of a cleaning vehicle to obtain a state fusion data set for characterizing the operating behavior characteristics of the cleaning vehicle, including steps S201 to S204.

[0040] In step S201, based on a preset periodic frame window, periodic bus data acquisition and processing is performed on the operation status detection unit of the cleaning vehicle to obtain a vehicle operation status data set. The vehicle operation status data set includes engine speed, vehicle speed, fuel consumption rate, shift status and parking status extracted based on the CAN bus frame structure.

[0041] Among them, the periodic frame window represents the time period division rule used to define the data acquisition frequency and time range, so as to sample the vehicle operation data according to a fixed period. For example, if 500 milliseconds is set as a frame window period, the vehicle operation data will be captured once every 500 milliseconds.

[0042] Among them, the operating status detection unit refers to a set of sensors and control modules installed on the cleaning vehicle for monitoring and collecting vehicle operating status data sets, for example, obtaining the current engine load status and transmission gear signal of the cleaning vehicle through the data interface in the vehicle controller.

[0043] The CAN bus frame structure represents a data frame format specification used to transmit a vehicle operating status data set in a vehicle control system, thereby ensuring that data is transmitted between control modules in the vehicle control system through a unified protocol.

[0044] For example, the operation status detection unit is periodically collected and processed via the CAN communication bus carried by the vehicle control system. That is, within each periodic frame window, the key field content carried in the current frame is extracted through the CAN bus frame structure parsing mechanism corresponding to the CAN communication bus, namely, the vehicle operation status data set; the vehicle operation status data set includes the engine speed reflecting the load and operation level of the power system, the vehicle speed data reflecting the current driving speed, the fuel consumption rate index used to evaluate fuel efficiency, the gear shift status signal representing the driving behavior and gear shift logic, and the parking mark indicating whether the vehicle is in a stationary state, etc.

[0045] In step S202, based on the vehicle operation status data set and in combination with the preset collaborative mechanism based on event triggering and periodic polling, data collection and processing are performed on the operation status unit of the cleaning vehicle to obtain a vehicle operation parameter set. The vehicle operation parameter set includes the opening and closing status of the scraper control valve, the working rhythm of the slide plate, the duration of the operation action, and the current fluctuation curve.

[0046] Among them, the collaborative mechanism based on event triggering and periodic polling represents a data acquisition control strategy that combines state change drive and timed sampling logic. It is used to respond immediately to key state changes while maintaining data integrity during regular time periods. For example, when the engine enters a high-speed state, the collection of the vehicle operating parameter set is immediately triggered, and the skateboard working rhythm status is polled regularly every 5 seconds.

[0047] Among them, the operation status unit represents a set of equipment interfaces and control modules used to detect and record the operation status of the operation components of the cleaning vehicle, such as a control interface used to record data such as whether the scraper is turned on, whether the slide is moving, and whether the operation duration exceeds the limit.

[0048] For example, according to the operating conditions provided by the vehicle operating status data set, the collection behavior of the operation status unit is coordinated and scheduled to obtain the vehicle operation parameter set of various key operation components of the cleaning vehicle during the operation process; in this process, a combination of event trigger mechanism and periodic polling mechanism is adopted, that is, when the vehicle reaches specific operating conditions, such as the engine speed enters the cleaning range and the vehicle speed is stable within the cleaning speed range, it will actively trigger the data collection of the specified operation component; and in other time periods, a timed polling method is adopted to ensure the timeliness and integrity of the information; through the above mechanism, it can effectively avoid the omission of information caused by too low collection frequency, and also suppress unnecessary data redundancy. Furthermore, during the collection process, the collected vehicle operation parameter set is mainly the core parameters related to the operation corresponding to the key operation components, such as the opening and closing state of the scraper control valve used to control the operation advancement, the working beat of the slide plate to control the operation rhythm, and the current fluctuation curve used to reflect the load.

[0049] In step S203 , the positioning unit of the cleaning vehicle is synchronized with the vehicle operation status data set and the vehicle operation parameter set to obtain a geographical location information set marked with the operation behavior fragment.

[0050] The positioning unit refers to a navigation or positioning module for obtaining the spatial position information of the cleaning vehicle in real time, such as a GPS module that regularly outputs the latitude and longitude of the cleaning vehicle.

[0051] Among them, the operation behavior segment represents a time segment with clear operation characteristics. For example, a behavior segment in which a sweeping vehicle runs at a sweeping speed at a certain location and keeps the operation components enabled for more than 30 seconds is defined as a valid operation behavior segment.

[0052] Exemplarily, the vehicle operation status data set and the vehicle operation parameter set are synchronized in time, and the positioning unit of the cleaning vehicle is coordinated accordingly to achieve effective correspondence between the operation behavior and the spatial position information, that is, with a unified time index as the intermediate benchmark, the key event points marked in the vehicle operation status data set and the vehicle operation parameter set are used as a reference, and the corresponding time window of the geographic location information output by the GPS module is calculated to segment the geographic location information. Each segment of geographic location information will be assigned a specific operation behavior fragment, thereby forming a structured geographic location information set, which not only contains spatial coordinate data, but also clearly marks the relevant data of the vehicle operation status data set and the relevant data of the vehicle operation parameter set corresponding to the coordinate.

[0053] In step S204 , the vehicle operation status data set, the vehicle operation parameter set, and the geographic location information set are integrated to obtain a state fusion data set.

[0054] Exemplarily, the vehicle operation status dataset, vehicle operation parameter set and geographic location information set are integrated and processed to form a unified data structure for describing the comprehensive behavioral performance of the cleaning vehicle in a specific operation scenario; wherein, with the same time series benchmark as the core, the relevant data of the vehicle operation status dataset, vehicle operation parameter set and geographic location information set in each operation behavior segment are vertically connected, and a data recording format with horizontal expansion capability is constructed, so that the dynamic state, operation details and location of the cleaning vehicle at any time can be integrated and analyzed; the final integrated output state fusion dataset not only has spatiotemporal continuity, but also reflects the coupling state of the process characteristics of the operation and the environmental characteristics.

[0055] In this embodiment, first, bus data collection and processing based on a periodic frame window is performed on the operation status detection unit to obtain a structured vehicle operation status data set, ensuring stable and continuous monitoring capabilities of the vehicle dynamic state; secondly, based on the collaborative mechanism of event triggering and periodic polling, combined with the vehicle operation status data set, data collection is performed on the operation status unit to obtain a vehicle operation parameter set, thereby achieving a detailed record of the operation action rhythm and execution status; thirdly, according to the timing characteristics of the vehicle operation status data set and the vehicle operation parameter set, the positioning unit is synchronized to construct a geographic location information set marked with operation behavior fragments, thereby achieving consistent mapping of operation behavior and spatial trajectory; thirdly, according to the time and space alignment characteristics of multiple types of data, the vehicle operation status data set, the vehicle operation parameter set and the geographic location information are fused to generate a state fusion data set that uniformly expresses the operation status of the cleaning vehicle. In an exemplary embodiment, based on the matching relationship between the preset standard operation template and the state fusion data set, the operation behavior characteristics of the cleaning vehicle are hierarchically analyzed to obtain the operation behavior evaluation result, including steps S301 to S304.

[0056] In step S301, the geographic location information set in the state fusion dataset is segment-matched with the expected trajectory path in the standard operation template to obtain a continuous operation segment trajectory recognition result. The continuous operation segment trajectory recognition result includes an operation segment that meets the preset spatiotemporal continuity constraint conditions.

[0057] Among them, the operating section that meets the preset spatiotemporal continuity constraints represents a set of operating sections that are continuous in both time and space dimensions and meet the cleaning operation judgment criteria. It is used to define the continuous sections in which the cleaning vehicle actually performs effective operations within a specific period of time. For example, when a cleaning vehicle continues to run at a stable speed on a certain street, the operating components remain turned on, and its trajectory points are continuously distributed close to the expected trajectory path for more than a preset time threshold, this section of the trajectory is marked as an operating section that meets the preset spatiotemporal continuity constraints.

[0058] For example, with the expected trajectory path set in the standard operation template as a reference, combined with the spatiotemporal continuity characteristics in the geographic location information set, the location points corresponding to each time period are segmented and matched to achieve a structured comparison between the actual driving trajectory of the cleaning vehicle and the expected trajectory path; wherein, first, the geographic location information set is resampled and interpolated to ensure path continuity and point density balance; secondly, for the reference trajectory defined in the expected trajectory path, the distance, angle change rate and time continuity are used as constraints to determine whether the actual driving trajectory of the cleaning vehicle meets the preset operation segment standards. If the actual driving trajectory of the cleaning vehicle is continuously distributed in the matching area in the expected trajectory path within a specific time period and meets the continuous travel requirements in time, then the actual driving trajectory is divided into a valid operation segment and assigned a corresponding trajectory identifier and spatiotemporal index. Based on this, the final output of the continuous operation segment trajectory recognition result not only contains the trajectory path information, but also includes the corresponding operation start and end time, spatial range and continuity judgment basis.

[0059] In step S302, based on the operation sections that meet the preset spatiotemporal continuity constraints in the continuous operation section trajectory recognition results, the vehicle operation status dataset and the vehicle operation parameter set in the state fusion dataset are subjected to behavior sequence analysis to obtain the equipment action behavior sequence corresponding to each operation section.

[0060] Exemplarily, based on the identified continuous operation sections, the vehicle operation status data set and vehicle operation parameter set corresponding to the time range of the operation section in the state fusion data set are further subjected to behavior sequence analysis processing, that is, through the time window matching mechanism, the vehicle operation status data and vehicle operation parameters corresponding to each operation section are extracted, and thereby the equipment action behavior sequence reflecting the operation behavior of each operation section is constructed, wherein: the construction requirements of the equipment action behavior sequence not only cover the reading of static parameters such as the opening and closing status of the operation components, the operation frequency, and the action rhythm, but also include the judgment of the state change trend based on these parameters.

[0061] Step S303 , based on the operation index window indexed by the operation trajectory of the cleaning vehicle, abnormal index aggregation processing is performed on the equipment action behavior sequence corresponding to each operation section to obtain an abnormal operation index combination.

[0062] Among them, the operation index window represents the timing analysis window structure used to count and analyze the equipment action behavior sequence corresponding to each operation section. For example, multiple continuous operation sections are integrated into an operation index window with a specified time period as the unit. In each operation index window, the number of start and stop times of the operation component, the duration of the action, and other abnormal indicators are comprehensively calculated according to the equipment action behavior sequence of the corresponding continuous operation section, so as to comprehensively judge whether there is inconsistent operation component action or deviation in cleaning quality in the operation section.

[0063] For example, an operation index window is first constructed with the operating trajectory of the cleaning vehicle as the core reference. Based on the operation index window, multiple continuous operating segments are integrated and re-divided into several trajectory segments with time and space boundaries, thereby forming a corresponding relationship between the operation index window and the trajectory segment. Each operation index window is bound to the operating time interval and operating space range of a specific trajectory segment, forming a basic index structure for abnormal operation behavior analysis. Furthermore, in the abnormal indicator items provided by each operation index window, a comprehensive analysis of the equipment action behavior sequence of the corresponding continuous operating segment is performed based on the operating time interval and operating space range covered by each trajectory segment, and abnormal normal operation performance existing in multiple trajectory segments is identified. This identification process does not judge a single abnormal event, but uses aggregate analysis as the core logic, uniformly classifying the abnormal characteristics of multiple trajectory segments into the abnormal indicator items of the corresponding operation index window for analysis. Based on this, through this aggregation process, a combination of operation abnormality indicators covering all trajectory segments is finally obtained to reflect the typical abnormal patterns of the cleaning vehicle during operation.

[0064] In step S304, the continuous operation section trajectory recognition results, the equipment action behavior sequence, and the operation abnormality indicator combination are integrated and processed to obtain the operation behavior evaluation result.

[0065] Exemplarily, for example, the continuous operation section trajectory recognition results, equipment action behavior sequence and operation abnormality indicator combination are integrated and processed to form an operation behavior evaluation result for characterizing the overall operation behavior quality of the cleaning vehicle; wherein, with the same timing benchmark as the core, the continuous operation section trajectory recognition results, equipment action behavior sequence and operation abnormality indicator combination are vertically connected with the relevant data in each preset time period, and a data recording format with horizontal expansion capability is constructed, so that the trajectory characteristics, operation status characteristics and abnormal performance descriptions of the cleaning vehicle at any time can be integrated and analyzed to form an operation behavior evaluation result.

[0066] In this embodiment, first, the geographic location information set is segment-matched with the expected trajectory path in the standard operation template to identify the operation section that meets the preset spatiotemporal continuity constraints, thereby realizing effective spatial and temporal division of the operation behavior; secondly, the vehicle operation status data set and the vehicle operation parameter set are subjected to behavior sequence parsing according to the identified operation section, thereby extracting the equipment action behavior sequence corresponding to each operation section, thereby realizing temporal reconstruction of the operation process; thirdly, according to the operation indicator window indexed by the operation trajectory of the cleaning vehicle, the equipment action behavior sequence corresponding to each operation section is subjected to abnormal indicator aggregation processing to generate an operation abnormality indicator combination of abnormal characteristics with a structured representation; thirdly, the continuous operation section trajectory recognition results, the equipment action behavior sequence and the operation abnormality indicator combination are integrated to obtain the operation behavior evaluation result, thereby realizing multi-dimensional operation state recognition and analysis from trajectory, behavior to abnormality, and supporting accurate decision-making for subsequent feedback and scheduling control.

[0067] In an exemplary embodiment, based on an operation index window indexed by the operation trajectory of the cleaning vehicle, abnormal index aggregation processing is performed on the equipment action behavior sequence corresponding to each operation section to obtain an operation abnormality index combination, including steps S401 to S402.

[0068] In step S401, the operation index window indexed by the operation trajectory of the cleaning vehicle is subjected to trajectory segment indexing processing to obtain a trajectory segment index set corresponding to the corresponding operation index window. The trajectory segment index set is mapped to the operation time interval and operation space range corresponding to the corresponding trajectory segment.

[0069] The trajectory segment index set represents a set of trajectory segments obtained by dividing the continuous path according to preset time intervals and spatial intervals based on the operation trajectory of the cleaning vehicle.

[0070] Among them, the operation time interval represents the time range in which the cleaning vehicle performs the operation operation on each trajectory segment in the trajectory segment index set; the operation space range represents the geographical space area covered by the cleaning vehicle when performing the operation operation on each trajectory segment in the trajectory segment index set.

[0071] For example, the operation trajectory of the cleaning vehicle is used as the core index to construct an operation index window for subsequent analysis, and the operation index window is subjected to trajectory segmentation index processing to achieve a refined division of trajectory data under different operation states, wherein: based on the operation index window, multiple continuous operation segments are integrated, and then re-divided into several trajectory segments with time and space boundaries according to the preset time interval and spatial distribution characteristics, so that each trajectory segment corresponds to a clear operation time interval and operation space range. In this process, first, based on the timestamps recorded in the trajectory after the integration of multiple continuous operation segments, the trajectory is divided into multiple trajectory segments at the set time interval. At the same time, combined with the spatial distribution characteristics of the coordinate points in the trajectory, such as the spatial distribution density, curvature change degree and position extension, the spatial continuity of the divided multiple trajectory segments is tested to ensure that each trajectory segment has stable geographical extension and operation continuity. Based on this, by incorporating both time and space factors into the segmentation index standard, a trajectory segment index set that can cover the entire operation process is established; as a multidimensional index structure, this trajectory segment index set not only provides accurate spatiotemporal anchor points for subsequent equipment actions and anomaly analysis, but also provides a structured division basis for the staged evaluation of the operation status.

[0072] In step S402, based on the operation time intervals and operation space ranges corresponding to the trajectory segment index set, combined with the joint analysis of the abnormal indicator items of the cleaning vehicle in each operation indicator window, the abnormal indicator aggregation processing is performed on the equipment action behavior sequence corresponding to each operation section to obtain the operation abnormality indicator combination.

[0073] For example, first, the equipment action behavior sequence corresponding to each operating section is extracted according to the trajectory segment index set. In the spatiotemporal constraint framework composed of the operating time interval and operating space range of each trajectory segment in the operating index window, the corresponding equipment action behavior sequence is parsed according to the preset abnormality judgment rules to identify whether there are behavioral characteristics such as operation delays, frequent starts and stops, inconsistent action durations, or abnormal fluctuations. For the same abnormal events that appear in multiple trajectory segments, they can be standardized and clustered according to factors such as their type, severity, duration, and changes in associated parameters to form abnormal indicator items that are uniformly described in the operating index window. Subsequently, all abnormal indicator items in the same operating index window are statistically merged to obtain a representative operating abnormality indicator combination. Based on this, the final generated operating abnormality indicator combination has a compact structure and clear classification, which can fully reflect the distribution and nature of abnormal behaviors during the cleaning operation.

[0074] In this embodiment, first, the operation index window indexed by the operation trajectory of the cleaning vehicle is subjected to trajectory segmentation index processing to obtain a trajectory segment index set corresponding to the corresponding operation index window, thereby dividing the continuous operation path into trajectory segments with clear operation time intervals and operation space ranges, ensuring that the subsequent behavior analysis has clear time and space boundaries; secondly, according to the various operation time intervals and various operation space ranges corresponding to the trajectory segment index set, combined with the abnormal indicator items of the operation index window, the equipment action behavior sequence is subjected to abnormal indicator aggregation processing to obtain an operation abnormality indicator combination, thereby realizing the classification expression and centralized output of abnormal behavior; based on this, the spatiotemporal attribution and indicator integration of abnormal states during the operation of the cleaning vehicle can be realized, providing structured support for the precise positioning of abnormal identification and monitoring response.

[0075] In an exemplary embodiment, according to the operation behavior evaluation result, a matching monitoring feedback strategy is executed on the cleaning vehicle to generate an operation monitoring feedback information set, including steps S501 to S502.

[0076] Step S501: Perform monitoring feature extraction on the continuous operation section trajectory recognition results, equipment action behavior sequence, and operation abnormality indicator combination in the operation behavior evaluation results to obtain a monitoring feature set, which includes path deviation features, operation stability features, and operation stability features.

[0077] Among them, the monitoring feature set represents a set of multi-dimensional structured feature items extracted from the operation behavior evaluation results, which is used to uniformly express the key monitoring feature combinations such as path deviation characteristics, operation stability characteristics, and operation stability characteristics of the sweeping vehicle during the operation process.

[0078] Among them, the path deviation feature represents a characteristic item that reflects the degree of spatial deviation of the actual operating trajectory of the sweeping vehicle relative to the expected operating path. It is used to identify whether the sweeping vehicle has problems such as inconsistent operating trajectory, insufficient cleaning coverage, or derailment. For example, if the average deviation distance of the actual trajectory of a certain section of road exceeds the set tolerance range, it can be recorded as a high-deviation level path feature.

[0079] Among them, the operational stability feature refers to a feature item that reflects whether the operating behaviors of various operational components of the sweeping vehicle during the operation process are continuous, coordinated, and have a reasonable rhythm. It is used to reflect whether there are frequent starts and stops, inconsistent operation durations, or interruptions in the operation process. For example, if an operating component stops without warning multiple times on a certain road section and fails to maintain the operating action, it can be recorded as a low operational stability feature.

[0080] Among them, the operational stability characteristics represent characteristic items that reflect the fluctuations in the states of the operating components and the concentration of abnormal events during the overall operation of the sweeping vehicle, and are used to determine whether there is system-level instability or a trend of loss of control at the equipment level during the operation process; for example, if the suction control current fluctuates frequently and is accompanied by operation interruptions during a certain cleaning cycle, it can be recorded as a high-volatility operational characteristic.

[0081] For example, first, the path offset analysis is performed on the trajectory recognition results of the continuous operation section, and the path offset characteristics reflecting the accuracy of the cleaning vehicle path execution are extracted by calculating the distance distribution, offset direction and duration between the actual trajectory and the expected operation path; secondly, according to the temporal structure of the equipment action behavior sequence, the stability of the operation of each operation component, the integrity of the continuous operation and the regularity of the operation rhythm are indexed to generate operation stability characteristics reflecting the consistency and coherence of the operation process of each operation component; thirdly, various non-standard behaviors recorded in the operation abnormality indicator combination are merged and counted, and according to the type, frequency and distribution of abnormal events, operation stability characteristics reflecting the state fluctuations of the operation components and the concentration of abnormal events are generated.

[0082] In step S502, a preset monitoring feedback strategy set is matched with the monitoring feature set to obtain a monitoring feedback strategy that matches the monitoring feature set. According to the monitoring feedback strategy, the monitoring feature set is structured to generate a job monitoring feedback information set.

[0083] Among them, the monitoring feedback strategy set represents a set of response rule systems pre-configured for matching various monitoring feature combinations, that is, the appropriate feedback content structure and response method are selected according to the monitoring feature combination of the monitoring feature set. For example, when the path deviation feature is high and the operation stability feature is low, a combined feedback strategy including trajectory correction suggestions and operation interruption warnings is generated by matching.

[0084] For example, in a monitoring feature set, based on the attribute values, indicator levels, and corresponding warning thresholds of various monitoring features, the adaptability of each monitoring feature in the monitoring feedback strategy set is determined, and the monitoring feedback strategy that best matches the current monitoring features is selected, wherein: strategy matching is judged using rule-driven logic, that is, based on the attribute values, indicator levels, and corresponding warning thresholds of various monitoring features, the monitoring feedback strategy corresponding to the corresponding rule-driven logic is triggered. For example, if the path deviation feature is abnormal, a sub-strategy based on trajectory deviation warning is triggered; if the operation stability feature is abnormal, a sub-strategy based on continuous operation prompt is triggered; if the operation stability feature is abnormal, a sub-strategy based on operation status diagnosis is triggered. The monitoring feedback strategy that matches the monitoring feature set is obtained from each sub-strategy. After the monitoring feedback strategy is determined, the relevant content in the monitoring feature set is data mapped and structured according to the feedback item structure and display template specified in the monitoring feedback strategy. A job monitoring feedback information entry including multiple fields such as feedback type, positioning information, impact range, and recommended disposal method is generated and included in the job monitoring feedback information set.

[0085] In this embodiment, first, monitoring feature extraction is performed on the operation behavior evaluation results, thereby converting the multi-source evaluation content into a monitoring feature set with structured attributes, which is convenient for subsequent standardized identification and strategy docking; secondly, based on the matching relationship between the monitoring feature set and the preset monitoring feedback strategy set, the monitoring feedback strategy is determined and the monitoring feature set is processed for structured feedback generation, thereby forming an operation monitoring feedback information set with clear classification and response direction; based on this, a closed-loop transformation from evaluation results to feedback information is achieved, with dynamic monitoring capabilities driven by behavior characteristics to support the precise execution of operation scheduling and operation and maintenance decisions.

[0086] In an exemplary embodiment, according to the monitoring feature set, a strategy matching process is performed on a preset monitoring feedback strategy set to obtain a monitoring feedback strategy that matches the monitoring feature set, including steps S601 to S603.

[0087] Step S601 : performing feature normalization processing on the path deviation feature, the operation stability feature, and the operation stability feature in the monitoring feature set to obtain a unified feature vector for strategy selection.

[0088] For example, in order to achieve effective docking between the monitoring feature set and the monitoring feedback strategy, it is necessary to perform feature normalization processing on the various monitoring features in the monitoring feature set so that monitoring features of different dimensions and types can be uniformly represented as feature vectors under the same structure. In the specific processing process, first, the original feature values of the path offset feature, operation stability feature and operation stability feature are extracted, and these values are converted into relative measurement forms based on the preset standardized interval, threshold interval or percentile range so that they are in the same dimension and comparable range. For example, the actual offset distance is mapped to the interval [0,1], the frequency of equipment start and stop is converted into a standardized stability index, and the frequency of abnormal events is expressed as normalized fluctuation intensity. Finally, all processed feature values are arranged and combined according to the three dimensions of path, operation and operation to form a multi-dimensional unified feature vector for strategy selection.

[0089] In step S602 , condition matching calculations are performed on each strategy in the monitoring feedback strategy set at the path level, the operation level, and the operation level according to the unified feature vector to obtain a candidate monitoring feedback strategy set.

[0090] The candidate monitoring feedback strategy set represents a set of candidate monitoring feedback strategies that are screened out after conditional matching calculation is performed on all preset monitoring feedback strategies and that meet the main matching requirements of the current monitoring feature set.

[0091] Exemplarily, each monitoring feedback strategy in the candidate monitoring feedback strategy set is configured with a multi-layer logic rule, that is, for the eigenvalues on each dimension in the unified feature vector, a matching calculation is performed with the threshold range, logic condition or scoring function defined in the multi-layer logic rule configured for each monitoring feedback strategy to determine whether the eigenvalues of each dimension meet the response requirements of the strategy. For example, at the path level, the path deviation conditions are compared for the eigenvalues of the path dimension, at the job level, the continuity and frequency comparison is performed for the eigenvalues of the job dimension, and at the operation level, the fluctuation levels of the eigenvalues of the operation dimension are analyzed. If the multi-layer logic rules of a monitoring feedback strategy match the unified feature vector in all or major key dimensions, the monitoring feedback strategy is included in the candidate monitoring feedback strategy set. Based on this, the candidate monitoring feedback strategy set finally constructed represents the monitoring feedback strategy with response adaptability under the current monitoring feature scenario, and is the preliminary strategy screening result before performing the preferred sorting.

[0092] In step S603, based on a preset joint evaluation function combining strategy matching frequency and indicator sensitivity, the candidate monitoring feedback strategy set is sorted by confidence to obtain the target monitoring feedback strategy with the highest confidence score, and the target monitoring feedback strategy is used as the monitoring feedback strategy that matches the monitoring feature set.

[0093] Among them, the joint evaluation function combining strategy matching frequency and indicator sensitivity represents a scoring function that prioritizes the candidate monitoring feedback strategy set by comprehensively considering strategy matching frequency and indicator sensitivity, and is used to evaluate the overall adaptation strength between each monitoring feedback strategy in the candidate monitoring feedback strategy set and the monitoring feature set.

[0094] Among them, the strategy matching frequency indicates the statistical frequency of a monitoring feedback strategy meeting the triggering conditions in its own historical modeling data. It is used to reflect the frequency of activation of the monitoring feedback strategy during actual or simulated operation. For example, if a monitoring feedback strategy was effectively triggered 5,000 times in past training samples and the total number of samples is 20,000, then its strategy matching frequency is 0.25, indicating that the monitoring feedback strategy is adaptable in 25% of scenarios.

[0095] Among them, indicator sensitivity represents the degree of dependence or influence weight of a monitoring feedback strategy on the changes of each input indicator in its internal judgment logic. It is used to measure the response intensity of the monitoring feedback strategy to different indicators during the construction process and determine which indicators have a dominant role in the output of the monitoring feedback strategy. For example, in a certain monitoring feedback strategy, the weight of the path deviation feature is 0.7, and the weight of the operation stability feature is 0.3. Then, the monitoring feedback strategy has a higher indicator sensitivity to the path deviation feature and relies more on the path deviation feature to make response judgments.

[0096] Exemplarily, based on a joint evaluation function combining strategy matching frequency and indicator sensitivity, the values of the two dimensions of strategy matching frequency and indicator sensitivity corresponding to each monitoring feedback strategy in the candidate monitoring feedback strategy set are fused and calculated to form a confidence score for sorting, thereby screening out the target monitoring feedback strategy that best suits the current application scenario from the candidate monitoring feedback strategy set based on the confidence score. First, in the candidate monitoring feedback strategy set, the data label information established in the model building phase for each monitoring feedback strategy is called to extract its strategy matching frequency. This value represents the frequency with which the monitoring feedback strategy is triggered in historical training data or rule application, reflecting the breadth of applicability of the strategy. Subsequently, the internal response weight of each monitoring feedback strategy to each monitoring indicator is extracted, namely, the indicator sensitivity. This value represents the degree of dependence of the monitoring feedback strategy on each input factor in the structure, reflecting the dominant characteristic variable of the strategy decision logic.

[0097] Furthermore, the joint evaluation function combines the strategy matching frequency and indicator sensitivity of the same monitoring feedback strategy into a confidence score for the corresponding monitoring feedback strategy through a preset data fusion method. The preset data fusion method can represent linear weighting, piecewise function mapping, or a weighted normalization model. After each monitoring feedback strategy in the candidate monitoring feedback strategy set is scored, all monitoring feedback strategies are sorted from high to low according to their confidence scores, and the monitoring feedback strategy with the highest confidence score is selected as the target monitoring feedback strategy that best suits the current application scenario.

[0098] In this embodiment, first, the path deviation characteristics, operation stability characteristics and operation stability characteristics are normalized to construct a unified feature vector, ensuring that various monitoring characteristics are comparable and can be used for standardized strategy evaluation; secondly, the various strategies are conditionally matched according to the unified feature vector to screen out a set of candidate monitoring feedback strategies that meet multi-dimensional condition constraints, ensuring that the strategy screening has logical coverage and structural matching; thirdly, the candidate monitoring feedback strategy set is sorted according to a joint evaluation function constructed by combining the strategy matching frequency and the indicator sensitivity, thereby determining the target monitoring feedback strategy with the best confidence score; based on this, a multi-strategy screening and optimization mechanism driven by standardized features is implemented to ensure that the monitoring feedback strategy has adaptability and response accuracy, thereby improving the reliability and practicality of the monitoring response.

[0099] In an exemplary embodiment, according to the monitoring feedback strategy, feedback information structuring processing is performed on the monitoring feature set to generate a job monitoring feedback information set, including steps S701 to S703.

[0100] Step S701 : performing rule parsing processing on the rule set in the monitoring feedback strategy to obtain a feedback rule structure including a path deviation response rule, an operation anomaly identification rule, and an operation status suggestion rule.

[0101] Among them, the rule set in the monitoring feedback strategy represents a combination of several judgment conditions and processing instructions that constitute the internal response logic of a monitoring feedback strategy, which is used to define what type of feedback operation should be performed when a certain operating state or monitoring feature occurs; for example, a certain monitoring feedback strategy contains three independent rules for judging whether the trajectory deviation exceeds the limit, whether the equipment start and stop is abnormal, and whether the operating current fluctuation is serious, which constitutes the rule set of the monitoring feedback strategy.

[0102] Among them, the feedback rule structure represents the structured expression form after parsing, classifying and standardizing each rule in the rule set according to functional categories and logical levels, which is used to provide a unified input template and execution path for subsequent feature matching and feedback content generation; for example, the feedback rule structure divides the original rules into three categories: path deviation response rules, job anomaly identification rules, and operation status recommendation rules. Each type of rule contains corresponding response conditions and processing fields.

[0103] The path deviation response rule represents a subset of rules within the feedback rule structure specifically designed to handle vehicle trajectory deviations from the expected operating path. These rules determine whether the trajectory deviation exceeds the permissible range and decide whether to generate feedback related to the deviation. For example, if the vehicle's deviation distance continuously exceeds a set threshold of more than 10 meters for more than 30 seconds, the response condition in the path deviation response rule is met.

[0104] Among them, the operation abnormality identification rule represents a subset of rules in the feedback rule structure used to identify abnormal operation behaviors during the cleaning operation, that is, it is used to identify behaviors such as operation interruption, frequent start and stop, and discontinuous cleaning and generate operation abnormality alarm information. For example, when the brush stops unexpectedly three times in a row during the operation, the response conditions in the operation abnormality identification rule are met.

[0105] Among them, the operating status recommendation rule represents a subset of rules in the feedback rule structure used to monitor the operating stability of the sweeping vehicle system and provide advisory feedback, that is, it is used to identify operating fluctuations of operating components, load abnormalities and other conditions and provide auxiliary diagnosis or deployment suggestions. For example, if the operating current fluctuation frequency of the suction unit increases abnormally, the response condition in the operating status recommendation rule is met.

[0106] For example, the rule set in the monitoring feedback strategy is parsed, that is, according to the preset parsing process, the response conditions, trigger logic, output format and other information in the rule set are disassembled, classified and marked to extract the feedback rule structure that can be used to guide subsequent information classification and content generation. Furthermore, the rule set is divided into three types of basic rules, namely path deviation response rules, operation anomaly identification rules and operation status recommendation rules, among which: the path deviation response rules mainly include the threshold conditions for trajectory deviation judgment and the processing instructions for the deviation range, the operation anomaly identification rules mainly include the identification criteria for features such as continuous operation interruption and equipment start-stop anomalies and the corresponding feedback level settings, and the operation status recommendation rules mainly include the auxiliary judgments and optimization suggestions required by the system under specific operation conditions. Based on this, these basic rules are uniformly converted into a standardized feedback rule structure after parsing, with clear response conditions, execution logic and corresponding output field identifiers.

[0107] In step S702, based on the matching monitoring feature set and the response conditions in the feedback rule structure, the monitoring feature set is classified and mapped to obtain each type of feedback field corresponding to the operation abnormality alarm information, trajectory deviation annotation information, resource allocation suggestion information, and status diagnosis result information. Exemplarily, the monitoring feature set is matched with the response conditions in the feedback rule structure to perform classification mapping on the monitoring feature set, thereby accurately attributing the monitoring feature set to the corresponding feedback data category and generating the corresponding feedback field, ensuring that the feedback field has the closure of content logic and structural integrity, wherein the feedback data category includes different data categories belonging to operation abnormality alarm information, trajectory deviation annotation information, resource allocation suggestion information, and status diagnosis result information. Among them, each type of monitoring feature in each monitoring feature set is traversed and compared with the response conditions of various basic rules integrated in the feedback rule structure. If the feature value of a certain monitoring feature meets the corresponding response condition, the monitoring feature is classified into the feedback data category corresponding to the corresponding basic rule and the corresponding feedback field is generated.

[0108] For example, under the path deviation response rule, if the offset exceeds the set threshold, trajectory deviation annotation information is generated; under the operation abnormality identification rule, if the operation stability characteristics indicate high-frequency interruptions, operation abnormality alarm information is generated; under the operation status recommendation rule, if the operation fluctuation index is greater than the preset threshold, status diagnosis result information and resource allocation recommendation information are generated.

[0109] Step S703 : combining the vehicle number, timestamp, and information category identifier, performing identification integration processing on each type of feedback field to obtain an operation monitoring feedback information set.

[0110] Among them, the vehicle number, timestamp and information category identifier represent the three basic field components used to identify the record source, occurrence time and feedback data category of the feedback field, that is, to ensure that each feedback field has unique identifiability, time traceability and classification management attributes. For example, the various feedback fields that have been classified and mapped are further structurally identified and integrated to form a standard and unified job monitoring feedback information set, that is, the unique number information of the cleaning vehicle, the corresponding timestamp data, and the feedback data category to which the feedback field belongs are embedded in each feedback field, thereby constructing the context boundary of the feedback field. In this embodiment, first, the rule set in the monitoring feedback strategy is parsed and processed to extract a feedback rule structure with functional classification and structural standardization, ensuring that the feedback logic is executable and has a clear input basis; secondly, the monitoring feature set is classified and mapped according to the response conditions in the feedback rule structure, thereby generating multiple types of feedback fields with clear structure and content, ensuring that the feedback information has an accurate source and readability; thirdly, the feedback field is identified and integrated according to the vehicle number, timestamp and information category identification, thereby forming an operation monitoring feedback information set with source identification and platform compatibility, realizing a structural closed loop from rule logic drive to feedback information generation, and improving the traceability, parsability and response efficiency of feedback information in the monitoring platform.

[0111] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0112] Based on the same inventive concept, the present application also provides an intelligent city sweeper operation monitoring and management system for implementing the aforementioned intelligent city sweeper operation monitoring and management method. The solution provided by this system is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following intelligent city sweeper operation monitoring and management system embodiments can be found in the aforementioned limitations of the intelligent city sweeper operation monitoring and management method and will not be further elaborated here.

[0113] In an exemplary embodiment, Figure 2 As shown, a smart city sweeper operation monitoring and management system is provided, including: a collection module 201, an evaluation module 202 and a feedback module 203, wherein: The acquisition module 201 is used to collect and process multi-source data of the vehicle operation data of the cleaning vehicle to obtain a state fusion data set for characterizing the operation behavior characteristics of the cleaning vehicle. The state fusion data set includes a vehicle operation state data set, a vehicle operation parameter set, and a geographic location information set; Evaluation module 202 is used to perform hierarchical analysis on the operating behavior characteristics of the cleaning vehicle based on the matching relationship between the preset standard operation template and the state fusion data set to obtain the operating behavior evaluation results. The operating behavior evaluation results include the continuous operation section trajectory recognition results, the equipment action behavior sequence, and the combination of operation abnormality indicators; Feedback module 203 is used to execute a matching monitoring feedback strategy for the sweeping vehicle based on the operation behavior evaluation results, and generate an operation monitoring feedback information set. The operation monitoring feedback information set includes operation abnormality alarm information, trajectory deviation annotation information, resource allocation suggestion information and status diagnosis result information, so as to provide a preset monitoring platform with a basis for operation scheduling management of sweeping vehicles.

[0114] In an exemplary embodiment, the acquisition module 201 is also used to: perform periodic bus data acquisition and processing on the operation status detection unit of the cleaning vehicle based on a preset periodic frame window to obtain a vehicle operation status data set, the vehicle operation status data set includes engine speed, vehicle speed, fuel consumption rate, gear shift status and parking status extracted based on the CAN bus frame structure; according to the vehicle operation status data set, combined with a preset collaborative mechanism based on event triggering and periodic polling, perform data acquisition and processing on the operation status unit of the cleaning vehicle to obtain a vehicle operation parameter set, the vehicle operation parameter set includes the opening and closing status of the scraper control valve, the working rhythm of the slide plate, the duration of the operation action and the current fluctuation curve; combine the vehicle operation status data set and the vehicle operation parameter set to perform time synchronization processing on the positioning unit of the cleaning vehicle to obtain a geographic location information set marked with operation behavior fragments; integrate the vehicle operation status data set, the vehicle operation parameter set and the geographic location information set to obtain a state fusion data set.

[0115] In an exemplary embodiment, the evaluation module 202 is also used to: perform segment matching processing on the geographic location information set in the state fusion dataset and the expected trajectory path in the standard operation template to obtain a continuous operation segment trajectory recognition result, and the continuous operation segment trajectory recognition result includes an operation segment that meets the preset time and space continuity constraint conditions; based on the operation segment that meets the preset time and space continuity constraint conditions in the continuous operation segment trajectory recognition result, perform behavior sequence parsing processing on the vehicle operation state dataset and the vehicle operation parameter set in the state fusion dataset to obtain the equipment action behavior sequence corresponding to each operation segment; based on the operation indicator window indexed by the operation trajectory of the cleaning vehicle, perform abnormal indicator aggregation processing on the equipment action behavior sequence corresponding to each operation segment to obtain an operation abnormality indicator combination; integrate the continuous operation segment trajectory recognition result, the equipment action behavior sequence and the operation abnormality indicator combination to obtain an operation behavior evaluation result.

[0116] In an exemplary embodiment, the evaluation module 202 is also used to: perform trajectory segmentation index processing on the operation index window indexed by the operation trajectory of the cleaning vehicle to obtain a trajectory segment index set corresponding to the corresponding operation index window, and the trajectory segment index set is mapped to the operation time interval and operation space range corresponding to the corresponding trajectory segment; according to each operation time interval and each operation space range corresponding to the trajectory segment index set, combined with the joint analysis of the abnormal indicator items of the cleaning vehicle in each operation index window, the equipment action behavior sequence corresponding to each operation section is aggregated to obtain an operation abnormality indicator combination.

[0117] In an exemplary embodiment, the feedback module 203 is also used to: perform monitoring feature extraction processing on the continuous operation section trajectory recognition results, equipment action behavior sequences and operation abnormality indicator combinations in the operation behavior evaluation results to obtain a monitoring feature set, the monitoring feature set includes path offset features, operation stability features and operation stability features; based on the monitoring feature set, perform strategy matching processing on the preset monitoring feedback strategy set to obtain a monitoring feedback strategy that matches the monitoring feature set; based on the monitoring feedback strategy, perform feedback information structured processing on the monitoring feature set to generate an operation monitoring feedback information set.

[0118] In an exemplary embodiment, the feedback module 203 is also used to: perform feature normalization processing on the path deviation features, operation stability features and operation stability features in the monitoring feature set to obtain a unified feature vector for strategy selection; based on the unified feature vector, perform condition matching calculation processing on each strategy in the monitoring feedback strategy set at the path level, operation level and operation level to obtain a candidate monitoring feedback strategy set; based on a preset joint evaluation function combining strategy matching frequency and indicator sensitivity, perform confidence sorting processing on the candidate monitoring feedback strategy set to obtain the target monitoring feedback strategy with the highest confidence score, and use the target monitoring feedback strategy as the monitoring feedback strategy that matches the monitoring feature set.

[0119] In an exemplary embodiment, the feedback module 203 is also used to: perform rule parsing processing on the rule set in the monitoring feedback strategy to obtain a feedback rule structure including path deviation response rules, operation abnormality identification rules and operation status recommendation rules; perform classification mapping processing on the monitoring feature set according to the response conditions in the matching monitoring feature set and the feedback rule structure to obtain each type of feedback field corresponding to the operation abnormality alarm information, trajectory deviation annotation information, resource allocation recommendation information and status diagnosis result information; combine the vehicle number, timestamp and information category identification to identify and integrate each type of feedback field to obtain the operation monitoring feedback information set.

[0120] Each module in the aforementioned intelligent city sweeper operation monitoring and management system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device in hardware form, or stored in a computer device's memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0121] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in any of the above embodiments when executing the computer program.

[0122] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above embodiments are implemented.

[0123] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0124] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0125] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for monitoring and managing the operation of an intelligent city sweeper, characterized in that: The method comprises: Performing multi-source data collection and processing on the vehicle operation data of the cleaning vehicle to obtain a state fusion data set for characterizing the operation behavior characteristics of the cleaning vehicle, the state fusion data set including a vehicle operation state data set, a vehicle operation parameter set, and a geographic location information set; Based on the matching relationship between the preset standard operation template and the state fusion data set, the operation behavior characteristics of the cleaning vehicle are subjected to hierarchical analysis to obtain an operation behavior evaluation result, which includes the continuous operation section trajectory recognition result, the equipment action behavior sequence, and the operation abnormality indicator combination; Based on the operation behavior evaluation results, a matching monitoring feedback strategy is executed on the sweeping vehicle to generate an operation monitoring feedback information set. The operation monitoring feedback information set includes operation abnormality alarm information, trajectory deviation marking information, resource allocation suggestion information and status diagnosis result information, so as to provide a preset monitoring platform with an operation scheduling management basis for the sweeping vehicle.

2. The method according to claim 1, characterized in that The multi-source data collection and processing of the vehicle operation data of the sweeping vehicle is performed to obtain a state fusion data set for characterizing the operating behavior characteristics of the sweeping vehicle, including: Based on a preset periodic frame window, a running state detection unit of the cleaning vehicle is subjected to periodic bus data acquisition and processing to obtain a vehicle running state data set, wherein the vehicle running state data set includes engine speed, vehicle speed, fuel consumption rate, shift state, and parking state extracted based on a CAN bus frame structure; Based on the vehicle operation status data set, combined with a preset collaborative mechanism based on event triggering and periodic polling, data collection and processing are performed on the operation status unit of the cleaning vehicle to obtain a vehicle operation parameter set, wherein the vehicle operation parameter set includes the opening and closing state of the scraper control valve, the working rhythm of the slide plate, the duration of the operation action, and the current fluctuation curve; Combining the vehicle operation status data set with the vehicle operation parameter set, performing time-series synchronization processing on the positioning unit of the cleaning vehicle to obtain a geographical location information set marked with operation behavior segments; The vehicle operation status data set, the vehicle operation parameter set, and the geographic location information set are integrated to obtain a status fusion data set.

3. The method according to claim 1, characterized in that The operation behavior characteristics of the cleaning vehicle are subjected to hierarchical analysis based on the matching relationship between the preset standard operation template and the state fusion data set to obtain an operation behavior evaluation result, including: Performing segment matching processing on the geographic location information set in the state fusion data set and the expected trajectory path in the standard operation template to obtain a continuous operation segment trajectory recognition result, wherein the continuous operation segment trajectory recognition result includes an operation segment that meets a preset spatiotemporal continuity constraint condition; According to the operation sections satisfying the preset spatiotemporal continuity constraint conditions in the continuous operation section trajectory recognition results, the vehicle operation state dataset and the vehicle operation parameter set in the state fusion dataset are subjected to behavior sequence analysis to obtain the equipment action behavior sequence corresponding to each operation section; According to the operation index window indexed by the operation trajectory of the cleaning vehicle, abnormal index aggregation processing is performed on the equipment action behavior sequence corresponding to each operation section to obtain an abnormal operation index combination; The continuous operation section trajectory recognition result, the equipment action behavior sequence and the operation abnormality indicator combination are integrated and processed to obtain the operation behavior evaluation result.

4. The method according to claim 3, characterized in that According to the operation index window indexed by the operation trajectory of the cleaning vehicle, abnormal index aggregation processing is performed on the equipment action behavior sequence corresponding to each operation section to obtain an abnormal operation index combination, including: Performing a trajectory segment indexing process on an operation index window indexed by the operation trajectory of the cleaning vehicle to obtain a trajectory segment index set corresponding to the corresponding operation index window, wherein the trajectory segment index set is mapped to an operation time interval and an operation space range corresponding to each trajectory segment; According to the various operation time intervals and various operation space ranges corresponding to the trajectory segment index set, combined with the joint analysis of the abnormal indicator items of the cleaning vehicle in each operation indicator window, the equipment action behavior sequence corresponding to each operation section is subjected to abnormal indicator aggregation processing to obtain an abnormal operation indicator combination.

5. The method according to claim 1, characterized in that The method of executing a matching monitoring feedback strategy on the cleaning vehicle according to the operation behavior evaluation result to generate an operation monitoring feedback information set includes: Performing monitoring feature extraction processing on the continuous operation section trajectory recognition results, the equipment action behavior sequence, and the operation abnormality indicator combination in the operation behavior assessment results to obtain a monitoring feature set, the monitoring feature set including a path deviation feature, an operation stability feature, and an operation stability feature; According to the monitoring feature set, the preset monitoring feedback strategy set is matched to obtain a monitoring feedback strategy that matches the monitoring feature set. According to the monitoring feedback strategy, the monitoring feature set is structured to generate a job monitoring feedback information set.

6. The method according to claim 5, characterized in that The step of performing strategy matching processing on a preset monitoring feedback strategy set according to the monitoring feature set to obtain a monitoring feedback strategy that matches the monitoring feature set includes: performing feature normalization processing on the path deviation feature, the operation stability feature, and the operation stability feature in the monitoring feature set to obtain a unified feature vector for strategy selection; According to the unified feature vector, each strategy in the monitoring feedback strategy set is subjected to condition matching calculation processing at the path level, the operation level, and the operation level to obtain a candidate monitoring feedback strategy set; Based on a preset joint evaluation function combining strategy matching frequency and indicator sensitivity, the candidate monitoring feedback strategy set is sorted by confidence to obtain the target monitoring feedback strategy with the highest confidence score, and the target monitoring feedback strategy is used as the monitoring feedback strategy that matches the monitoring feature set.

7. The method according to claim 5, characterized in that The step of performing feedback information structuring processing on the monitoring feature set according to the monitoring feedback strategy to generate a job monitoring feedback information set includes: Performing rule parsing on the rule set in the monitoring feedback strategy to obtain a feedback rule structure including a path deviation response rule, an operation anomaly identification rule, and an operation status suggestion rule; According to the matching of the monitoring feature set with the response conditions in the feedback rule structure, the monitoring feature set is classified and mapped to obtain each type of feedback field corresponding to the operation abnormality alarm information, trajectory deviation annotation information, resource allocation suggestion information, and status diagnosis result information; Combined with the vehicle number, timestamp and information category identifier, each type of feedback field is identified and integrated to obtain the operation monitoring feedback information set.

8. An intelligent city sweeper operation monitoring and management system, characterized in that: The system comprises: An acquisition module is used to perform multi-source data acquisition and processing on the vehicle operation data of the cleaning vehicle to obtain a state fusion data set for characterizing the operation behavior characteristics of the cleaning vehicle, wherein the state fusion data set includes a vehicle operation state data set, a vehicle operation parameter set, and a geographic location information set; An evaluation module is configured to perform hierarchical analysis on the operating behavior characteristics of the cleaning vehicle based on a matching relationship between a preset standard operating template and the state fusion dataset to obtain an operating behavior evaluation result, wherein the operating behavior evaluation result includes a continuous operating section trajectory recognition result, an equipment action behavior sequence, and a combination of operation abnormality indicators; A feedback module is used to execute a matching monitoring feedback strategy for the sweeping vehicle based on the operation behavior evaluation results, and generate an operation monitoring feedback information set. The operation monitoring feedback information set includes operation abnormality alarm information, trajectory deviation annotation information, resource allocation suggestion information and status diagnosis result information, so as to provide a preset monitoring platform with a basis for operation scheduling management of the sweeping vehicle.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images